Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 56
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Generating IFC-compliant models and structural graphs of truss bridges from dense point clouds

  • Justo, Andrés
  • Lamas, Daniel
  • Sánchez-Rodríguez, Ana
  • Soilán, Mario
  • Riveiro, Belén
[EN] The IFC schema has been evolving towards the infrastructure domain. Furthermore, the use of laser scanning technologies as means to digitalize and monitor infrastructures has also significantly increased. This work presents an automated modelling approach for truss bridges that utilizes laser scanning data as its source for geometrical information. The methodology takes a partially instance-segmented point cloud of a truss bridge and generates both an IFC-compliant information model of the truss and the corresponding structural graph. This process uses bounding boxes and their collisions to overcome the missing data from the partial segmentation to create the truss model, as well as to identify the nodes that connect the different truss members. The methodology was tested on a use case made of 272 members and obtained the truss model and structural graph files., This project has received funding from the European Union s Horizon 2020 research and innovation programme under grant agreement No. 769255. This work has been partially supported by the Spanish Ministry of Science and Innovation through the PONT3 project Ref. PID2021-124236OB-C33. This work has been partially supported by the University of Vigo through the human resources grant: Axudas para a contratacion ¿ de personal investigador predoutoral en formacion da Universidade De Vigo 2021 (PREUVIGO-21) and by the Spanish Ministry of Science and Innovation through the grant FJC2020046370- I and the grant RYC2021 033560-I.
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Introduction of deep learning in thermographic monitoring of cultural heritage and improvement by automatic thermogram pre-processing algorithms

  • Garrido González, Iván
  • Erazo Aux, Jorge
  • Lagüela López, Susana
  • Sfarra, Stefano
  • Ibarra Castanedo, Clemente
  • Pivarčiová, Elena
  • Gargiulo, Gianfranco
  • Maldague, Xavier
  • Arias Sánchez, Pedro
The monitoring of heritage objects is necessary due to their continuous deterioration over time. Therefore, the joint use of the most up-to-date inspection techniques with the most innovative data processing algorithms plays an important role to apply the required prevention and conservation tasks in each case study. InfraRed Thermography (IRT) is one of the most used Non-Destructive Testing (NDT) techniques in the cultural heritage field due to its advantages in the analysis of delicate objects (i.e., undisturbed, non-contact and fast inspection of large surfaces) and its continuous evolution in both the acquisition and the processing of the data acquired. Despite the good qualitative and quantitative results obtained so far, the lack of automation in the IRT data interpretation predominates, with few automatic analyses that are limited to specific conditions and the technology of the thermographic camera. Deep Learning (DL) is a data processor with a versatile solution for highly automated analysis. Then, this paper introduces the latest state-of-the-art DL model for instance segmentation, Mask Region-Convolution Neural Network (Mask R-CNN), for the automatic detection and segmentation of the position and area of different surface and subsurface defects, respectively, in two different artistic objects belonging to the same family: Marquetry. For that, active IRT experiments are applied to each marquetry. The thermal image sequences acquired are used as input dataset in the Mask R-CNN learning process. Previously, two automatic thermal image pre-processing algorithms based on thermal fundamentals are applied to the acquired data in order to improve the contrast between defective and sound areas. Good detection and segmentation results are obtained regarding state-of-the-art IRT data processing algorithms, which experience difficulty in identifying the deepest defects in the tests. In addition, the performance of the Mask R-CNN is improved by the prior application of the proposed pre-processing algorithms., Ministerio de Ciencia, Innovación y Universidades (España) | Ref. FPU16/03950, Universidad de Salamanca | Ref. Cátedra Iberdrola VIII Centenario
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Automatic detection of moistures in different construction materials from thermographic images

  • Garrido González, Iván
  • Lagüela López, Susana
  • Sfarra, Stefano
  • Madruga, F. J.
  • Arias Sánchez, Pedro
Moisture is a pathology that damages all type of construction materials, from materials of building envelopes to materials of bridges. Its presence can negatively affect the users’ conditions of indoor comfort. Furthermore, heating and cooling energy demand can be increased by the presence of moist materials. Infrared thermography (IRT) is a common technique in the scientific field to detect moisture areas, because of its non-destructive, non-contact nature. In addition, IRT allows an earlier moisture detection compared to the analysis using visible images. In order to optimize thermographic inspections, this paper presents one of the first methodologies for the automatic detection of moisture areas affecting the surface of construction materials. The methodology is based on the application of visible image processing techniques adapted to thermographic images through the consideration of an image conversion format, a thermal criterion and a thermal and a geometric filter. The precision, recall and F-score parameters obtained are around 83.5%, 73.5% and 72.5%, respectively, considering the false positives/negatives through a series of 12 tests made in different construction materials and ambient conditions, comparing the preliminary results with existing methodologies., Ministerio de Economía y Competitividad | Ref. FPU16/03950, Ministerio de Economía y Competitividad | Ref. TEC2016-76021-C2-2-R, Universidad de Salamanca. Cátedra Iberdrola VIII Centenario
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Development of thermal principles for the automation of the thermographic monitoring of cultural heritage

  • Garrido González, Iván
  • Sfarra, Stefano
  • Arias Sánchez, Pedro
  • Lagüela López, Susana
The continuous deterioration of elements, with high patrimonial value over time, can only be mitigated or annulled through the application of techniques that facilitate the preventative detection of the possible agents of deterioration. InfraRed Thermography (IRT) is one of the most used techniques for this task. However, there are few IRT methodologies, which can automatically monitor the cultural heritage field, and are vitally important in eliminating the subjectivity in interpreting and accelerating the analysis process. In this work, a study is performed on a tessellatum layer of a mosaic to automatically: (i) Detect the first appearance of the thermal footprint of internal water, (ii) delimit the contours of the thermal footprint of internal water from its first appearance, and (iii) classify between harmful and non-harmful internal water. The study is based on the analysis of the temperature distribution of each thermal image. Five thermal images sequences are acquired during the simulation of different real situations, obtaining a set of promising results for the optimization of the thermographic inspection process, while discussing the following recommended steps to be taken in the study for future researches., España. Ministerio de Educación I Ref. FPU16/03950, Iberdrola I Ref. Cátedra Iberdrola VIII Centenario - Universidad de Salamanca
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

UAV payload with collision mitigation for contact inspection

  • González De Santos, Luis Miguel
  • Martínez Sánchez, Joaquín
  • González Jorge, Higinio
  • Navarro Medina, Fermín
  • Arias Sánchez, Pedro
This document presents a payload designed to perform semi-autonomous collision-mitigation inspection tasks on UAVs. This system features no external aid positioning the UAV such as the motion capture systems or the Global Navigation Satellite System (GNSS), which makes these inspections possible in the GNSS-denied areas. The payload is composed of two distance measuring units that calculate the range and angle between the UAV and the structure. The payload controller uses this information to calculate the pitch and yaw signal to control approach and contact. A hybrid automaton has been implemented, which represents the corresponding UAV states during the approach and the contact with different control strategies for each one. For this study, an ultrasonic contact sensor was used as an inspection sensor, but the system can work with any other contact sensor. This sensor measures the thickness of the metal sheets when is in contact with it. Various tests have been performed on the system with accurate results, demonstrating that the system can maintain stable contact with a vertical structure., Ministerio de Economía, Industria y Competitividad | Ref. TIN2016-77158-C4-2-R, Ministerio de Economía, Industria y Competitividad | Ref. RTC-2016-5257-7
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Mathematical morphology directly applied to point cloud data

  • Balado Frías, Jesús
  • Van Oosterom, Peter
  • Díaz Vilariño, Lucía
  • Meijers, Martijn
Many of the point cloud processing techniques have their origin in image processing. But mathematical morphology, despite being one of the most used image processing techniques, has not yet been clearly adapted to point clouds. The aim of this work is to design the basic operations of mathematical morphology applicable to 3D point cloud data, without the need to transform point clouds to 2D or 3D images and avoiding the associated problems of resolution loss and orientation restrictions. The object shapes in images, based on pixel values, are assumed to be the existence or absence of points, therefore, morphological dilation and erosion operations are focused on the addition and removal of points according to the structuring element. The structuring element, in turn, is defined as a point cloud with characteristics of shape, size, orientation, point density, and one reference point. The designed method has been tested on point clouds artificially generated, acquired from real case studies, and the Stanford bunny model. The results show a robust behaviour against point density variations and consistent with image processing equivalent. The proposed method is easy and fast to implement, although theselection of a correct structuring element requires previous knowledge about the problem and the input point cloud. Besides, the proposed method solves well-known point cloud processing problems such as object detection, segmentation, and gap filling., Xunta de Galicia | Ref. ED481B-2019-061, Xunta de Galicia | Ref. ED481D 2019/020, Xunta de Galicia | Ref. ED431C 2016-038, Ministerio de Ciencia, Innovacion y Universidades | Ref. RTI2018-095893-BC21, Ministerio de Ciencia, Innovaci´on y Universidades | Ref. PID2019-105221RB-C43
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Introduction of active thermography and automatic defect segmentation in the thermographic inspection of specimens of ceramic tiling for building façades

  • Garrido González, Iván
  • Barreira, Eva
  • Almeida, Ricardo M.S.F.
  • Lagüela López, Susana
Financiado para publicación en acceso aberto: Universidade de Vigo/CISUG, InfraRed Thermography (IRT) has proven to be a valuable diagnostic tool due to its real-time, remote, and non-destructive operation yielding accurate detection of the position of defect areas in building façade ceramic tiling. Ceramic tiles coating building façades are widely used throughout the world because of their technical and aesthetic characteristics. However, the detachment of ceramic tiles and the water infiltration in deep layers are still common problems. So, this paper proposes active infrared thermography as a thermographic acquisition mode, in contrast to the common use of passive thermography, and segmentation of defect areas and automation in the thermal image processing as added values never before proposed in the ceramic tiling thermographic inspection. For that, specimens of ceramic tiling for building façades were tested under different laboratory conditions, with inserted corks (simulating detachments), and by injecting water into holes drilled in the back surfaces (simulating water infiltration), as defects. Good results have been obtained in all the tests, both in dry and wet conditions in the specimens and for surfaces with homogeneous and heterogeneous surface properties, serving the introduction of this workflow for a first and fast inspection in ceramic tiling building façades. Future research will work with the fine-tuning phase of the methodology by applying it to real case studies., Ministerio de Educación, Cultura y Deporte | Ref. FPU16/03950, Fundação para a Ciência e a Tecnologia | Ref. UIDB/04708/2020
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

3D point cloud data processing and infrastructure information models: methods and findings from safeway project

  • Soilán Rodríguez, Mario
  • Justo Dominguez, Andrés
  • Sánchez Rodríguez, Ana
  • Lamas Novoa, Daniel
  • Riveiro Rodríguez, Belén
Monitoring and digitalization are key to improve the resilience of the infrastructure network in the context of assessing its disaster management cycle. SAFEWAY is a project funded by the H2020 framework that aims to assess infrastructure resilience integrating multiscale information attending to all modes of disaster management cycle. This work presents the methodologies developed in the project for road and rail infrastructure monitoring and modelling, using remotely sensed data from Mobile Mapping Systems (MMS). First, 3D point clouds of both road and rail infrastructure are heuristically processed, obtaining geometric and semantic information from the most relevant assets, as well as the alignment, which is a key entity for generating information models. Such models are computed following the specifications of the Industry Foundation Classes (IFC) 4.1 schema, considering its current limitations and future potential for linear infrastructure modelling. Finally, the information is centralized in a core software platform where a user interface has been developed to aid visualization and interpretation of the resulting data., Agencia Estatal de Investigación | Ref. RTI2018-095893-B-C21, Agencia Estatal de Investigación | Ref. FJC2018-035550-I
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Fully automated methodology for the delineation of railway lanes and the generation of IFC alignment models using 3D point cloud data

  • Soilán Rodríguez, Mario
  • Novoa Martínez, Andrea
  • Sánchez Rodríguez, Ana
  • Justo Dominguez, Andrés
  • Riveiro Rodríguez, Belén
This work presents a fully automated methodology that, in a first step, is able to reliably extract and delineate the position and geometry of the rails from three-dimensional (3D) point cloud data of railway infrastructure by sequentially applying heuristic-based point cloud processing steps, namely railway track segmentation, rough rail estimation, and rail extraction. Then, that information is used to generate the alignment of the surveyed railway lane following the requirements of the Industry Foundation Classes (IFC) Alignment standard. Finally, the proposed method exports an IFC-compliant file that describes the position of the rails with respect to the railway lane alignment. This method has been applied to a 90-km long railway lane, and validated on two one-kilometer subsections of the case study data, obtaining an average rail delineation error of less than 3 cm. Furthermore, the track gauge was measured using the rail alignment data, obtaining errors of a similar magnitude., Ministerio de Ciencia e Innovación | Ref. FJC2018-035550-I, Agencia Estatal de Investigación | Ref. RTI2018-095893-B-C21
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Pointnet for the automatic classification of aerial point clouds

  • Soilán Rodríguez, Mario
  • Lindenbergh, R.
  • Riveiro Rodríguez, Belén
  • Sánchez Rodríguez, Ana
During the last couple of years, there has been an increased interest to develop new deep learning networks specifically for processing 3D point cloud data. In that context, this work intends to expand the applicability of one of these networks, PointNet, from the semantic segmentation of indoor scenes, to outdoor point clouds acquired with Airborne Laser Scanning (ALS) systems. Our goal is to of assist the classification of future iterations of a national wide dataset such as the Actueel Hoogtebestand Nederland (AHN), using a classification model trained with a previous iteration. First, a simple application such as ground classification is proposed in order to prove the capabilities of the proposed deep learning architecture to perform an efficient point-wise classification with aerial point clouds. Then, two different models based on PointNet are defined to classify the most relevant elements in the case study data: Ground, vegetation and buildings. While the model for ground classification performs with a F-score metric above 96%, motivating the second part of the work, the overall accuracy of the remaining models is around 87%, showing consistency across different versions of AHN but with improvable false positive and false negative rates. Therefore, this work concludes that the proposed classification of future AHN iterations is feasible but needs more experimentation, Ministerio de Economía y Competitividad | Ref. BES-2014-067736
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

IRT and GPR techniques for moisture detection and characterisation in buildings

  • Garrido González, Iván
  • Solla Carracelas, Maria Mercedes
  • Lagüela López, Susana
  • Fernández, Norberto
The integrity, comfort, and energy demand of a building can be negatively affected by the presence of moisture in its walls. Therefore, it is essential to identify and characterise this building pathology with the most appropriate technologies to perform the required prevention and maintenance tasks. This paper proposes the joint application of InfraRed Thermography (IRT) and Ground-Penetrating Radar (GPR) for the detection and classification of moisture in interior walls of a building according to its severity level. The IRT method is based on the study of the temperature distribution of the thermal images acquired without an application of artificial thermal excitation for the detection of superficial moisture (less than 15 mm deep in plaster with passive IRT). Additionally, in order to characterise the level of moisture severity, the Evaporative Thermal Index (ETI) was obtained for each of the moisture areas. As for GPR, with measuring capacity from 10 mm up to 30 cm depth with a 2300 MHz antenna, several algorithms were developed based on the amplitude and spectrum of the received signals for the detection and classification of moisture through the inner layers of the wall. In this work, the complementarity of both methods has proven to be an effective approach to investigate both superficial and internal moisture and their severity. Specifically, IRT allowed estimating superficial water movement, whereas GPR allowed detecting points of internal water accumulation. Thus, through the combination of both techniques, it was possible to provide an interpretation of the water displacement from the exterior surface to the interior surface of the wall, and to give a relative depth of water inside the wall. Therefore, it was concluded that more information and greater reliability can be gained by using complementary IRT-GPR, showing the benefits of combining both techniques in the building sector., AEI/FEDER, UE | Ref. TEC2016-76021-C2-2-R, Ministerio de Educación, Cultura y Deporte | Ref. FPU16/03950, Agencia Estatal de Investigación | Ref. RTI2018-095893-B-C21, Universidad de Salamanca. Cátedra Iberdrola VIII Centenario
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Thermographic methodologies used in infrastructure inspection: A review Post-processing procedures

  • Garrido González, Iván
  • Lagüela López, Susana
  • Otero Alonso, Roi
  • Arias Sánchez, Pedro
The different thermal behaviour between defects and unaltered zones allows the detection and thermal characterisation of superficial, and subsuperficial defects, which must be considered when maintaining a structure in optimal conditions. InfraRed Thermography is among the most appropriate Non-Destructive techniques to measure these thermal behaviours, represented on temperature maps of the infrastructure analysed by thermal images, regardless the size of the structure. In addition, InfraRed Thermography is also used for the thermal characterisation of structures for such important purposes as the energy study of buildings. Proof of the importance of InfraRed Thermography in infrastructure inspections are the continuous developments of new thermal image processing algorithms, where the post-processing stage is widely used to improve the inspection performance. In this work, an exhaustive review is performed regarding the most recent and important practical thermographic procedures for infrastructure applications, focusing on the post-acquisition stage, due to the lack of an in-depth analysis regarding the most recent and used algorithms. Specifically, the theory of these thermal image processing techniques is described, classifying them according to the corresponding theoretical post-acquisition approach used: qualitative and/or quantitative analysis. In addition, a discussion based on the advantages and disadvantages of each thermal data processing technique is performed, as well as a description of the latest IRT works related to each. Ending with a series of conclusions, this review paper confirms the maturity of InfraRed Thermography to face the greatest challenges in infrastructure inspection, although it also mentions the limitations to overcome and the future trends to follow., España. Ministerio de Economía y Competitividad | Ref. FPU16/03950, Cátedra Iberdrola VIII Centenario – Universidad de Salamanca
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Point cloud approach for modelling the lost volume of the Fillaboa Bridge cutwater

  • Balado Frías, Jesús
  • Sánchez Rodríguez, Ana
The digitization of heritage is being rapidly realised in many parts of the world, thanks to LiDAR technology. In addition to the simple digital preservation of heritage, 3D acquisition makes it possible to monitor the structural condition and assess possible damage. This paper presents a method for modelling the lost volume of a heritage bridge. The selected case study is the Fillaboa bridge in Salvaterra de Miño, Spain, which has two cutwaters with the same cutting angle, one of which is damaged and has a stone loss. The bridge was acquired with a Terrestrial Laser Scanner. The method consists of the following processes. First, the walls of the whole cutwater are segmented and aligned by the Iterative Closest Point algorithm over the damaged cutwater. Second, the distance between the two point clouds is calculated, and the damaged area is delimited in both point clouds. And third, the alpha-shape algorithm is applied to model the point cloud of the damaged area on a polygon. By searching for the optimal alpha radius, the polygon that best fits the damaged volume is generated. The proposed method also allows digital reconstruction of the damaged area, although it is sensitive to acquisition problems, which require manual interventions in the processing. The accuracy of the method is mainly dependent on the acquired point cloud registration (with an RMS error of 60mm) and the ICP registration error (31mm). Its use is limited to the existence of two geometries that allow superposition: one in good condition and one damaged to compare., Xunta de Galicia | Ref. ED481B-2019-061, Xunta de Galicia | Ref. ED431C 2020/01
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

HBIM application in historic timber atructures: a systematic review

  • Santos, David
  • Sousa, Hélder S.
  • Cabaleiro Núñez, Manuel
  • Branco, Jorge M.
Despite the recent significant increase on the use of Building Information Modelling (BIM) in the cultural heritage field, its application on heritage timber structures aiming at their conservation and assessment has not yet been fully established. Comparing with other construction materials, timber presents singular features that must be addressed in order to carry out a proper condition assessment. For this reason, this review summarizes existing works on historical timber structures using Historical BIM (HBIM), focusing not only on various geometric surveying and 3D modelling methods, but also on nongeometric information included in the model which are especially related with conservation, testing, and monitoring. In addition, this work illustrates the effectiveness increase given by a structural analysis, as to assess structural heath, after being implemented within a HBIM-based framework. To that aim, a global framework is proposed where the development and implementation level of different analysis stages are described., Xunta de Galicia | Ref. ED431C 2020/01, Fundação para a Ciência e a Tecnologia | Ref. UIDB/04029/2020
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

3D Point cloud to BIM: semi-automated framework to define IFC alignment entities from MLS-acquired LiDAR data of highway roads

  • Soilán Rodríguez, Mario
  • Justo Dominguez, Andrés
  • Sánchez Rodríguez, Ana
  • Riveiro Rodríguez, Belén
Building information modeling (BIM) is a process that has shown great potential in the building industry, but it has not reached the same level of maturity for transportation infrastructure. There is a standardization need for information exchange and management processes in the infrastructure that integrates BIM and Geographic Information Systems (GIS). Currently, the Industry Foundation Classes standard has harmonized different infrastructures under the Industry Foundation Classes (IFC) 4.3 release. Furthermore, the usage of remote sensing technologies such as laser scanning for infrastructure monitoring is becoming more common. This paper presents a semi-automated framework that takes as input a raw point cloud from a mobile mapping system, and outputs an IFC-compliant file that models the alignment and the centreline of each road lane in a highway road. The point cloud processing methodology is validated for two of its key steps, namely road marking processing and alignment and road line extraction, and a UML diagram is designed for the definition of the alignment entity from the point cloud data., Ministerio de Ciencia, Innovación y Universidades | Ref. RTI2018-095893-B-C21, Ministerio de Ciencia e Innovación y Universidades | Ref. FJC2018-035550-I
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

New algorithm for the merging of geometric entities towards the correct generation of semantic gbXML models

  • Otero Alonso, Roi
  • Lagüela López, Susana
  • Arias Sánchez, Pedro
This paper presents an algorithm developed to solve a duplicity problem found during the development of a software system for BIM generation. The chosen schema for the BIM is gbXML. The Manhattan World Assumption is adopted because the objective of the system is to obtain simplified and regularized 3D models of the indoor environment to perform a thermal analysis. At the moment of writing the gbXML, some duplicity and errors were found in the polygons of both sides of walls that divide adjacent rooms. The algorithm presented in this paper was developed to detect and solve these errors. Also, this paper includes the testing and validation of the algorithm. The test is based on the application of the algorithm to six different scenarios of study: four of them are artificial scenarios developed to test the different issues detected and two of them are real cases.
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Automated inspection of railway tunnels’ power line using LiDAR point clouds

  • Sánchez Rodríguez, Ana
  • Soilán Rodríguez, Mario
  • Cabaleiro Núñez, Manuel
  • Arias Sánchez, Pedro
Transport networks need periodic inspections to increase their safety and improve their management. In the last few years, LiDAR (light detection and ranging) technology has become a tool for helping to create a precise database of almost any type of infrastructure. Mobile laser scanning (MLS) systems use a laser beam to collect dense three dimensional (3D) point clouds, which include geometric and radiometric data of the environment in which they are placed. In the context of this paper, a methodology for automatically inspecting the clearance gauge and the deflection of the aerial contact line in railway tunnels is presented. The main objective is to compare results and verify their compliance with the Spanish norm. The 3D data are provided by a LYNX Mobile Mapper System (MMS). First, the area is surveyed and then the obtained (3D) point cloud is classified into contact wire, suspension wire, and remaining points. Finally, the inspection of the railway’s power line is performed. The validation of the proposed methodology has been carried out in three different tunnel point clouds, obtaining both qualitative and quantitative results for points’ classification, together with the results of the measures performed., Universidade de Vigo
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Thermographic methodologies used in infrastructure inspection: A review data acquisition procedures

  • Garrido González, Iván
  • Lagüela López, Susana
  • Otero Alonso, Roi
  • Arias Sánchez, Pedro
InfraRed Thermography (IRT) is one of the best tools for the thermal characterization of the materials of structures and for the detection and thermal characterization of the most typical defects in the infrastructure field. An exhaustive review of the most recent thermographic acquisition (data collection) procedures in infrastructure inspection is presented here, comparing the existing variety of experimental thermographic configurations for infrastructure inspection. Furthermore, a discussion searching similarities and differences between data collection procedures, together with a series of objective and critical conclusions, are described, University of Salamanca | Ref. Cátedra Iberdrola VIII Centenario, Ministerio de Economía y Competitividad | Ref. FPU16/03950
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Mobile indoor mapping technologies: a review

  • Otero Alonso, Roi
  • Lagüela López, Susana
  • Garrido González, Iván
  • Arias Sánchez, Pedro
Last developments in terrestrial surveying technologies, regarding both hardware and software, provide the possibility for their application to new interesting uses. Among them, this article focuses on indoor mapping and surveying with mobile devices. The use of these devices implies an improvement in the flexibility of the data acquisition in comparison to the static equivalent. This article analyses and compares the different options for mobile indoor mapping currently in the market, focusing on interesting characteristics for construction and architectural studies, such as physical configuration, weight, sensor type, colouring possibilities and operating time. The aim of this paper is to show the reader the state of the art of the technology, helping to fill the gap of information which exists in this field of technology and to help on the selection of the best option depending on the requirements., Universidad de Salamanca. Cátedra Iberdrola VIII Centenario
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Realistic correction of sky-coloured points in Mobile Laser Scanning point clouds

  • Gonzalez Rodriguez, Maria Elena
  • Balado Frías, Jesús
  • Arias Sánchez, Pedro
  • Lorenzo Cimadevila, Henrique Remixio
Financiado para publicación en acceso aberto: Universidade de Vigo/CISUG, The enrichment of the point clouds with colour images improves the visualisation of the data as well as the segmentation and recognition processes. Coloured point clouds are becoming increasingly common, however, the colour they display is not always as expected. Errors in the colouring of point clouds acquired with Mobile Laser Scanning are due to perspective in the camera image, different resolution or poor calibration between the LiDAR sensor and the image sensor. The consequences of these errors are noticeable in elements captured in images, but not in point clouds, such as the sky. This paper focuses on the correction of the sky-coloured points, without resorting to the images that were initially used to colour the whole point cloud. The proposed method consists of three stages. First the region of interest where the erroneously coloured points are accumulated, is selected. Second, the sky-coloured points are detected by calculating the colour distance in the Lab colour space to a sample of the sky-colour. And third, the colour of the sky-coloured detected points is restored from the colour of the nearby points. The method is tested in ten real case studies with their corresponding point clouds from urban and rural areas. In two case studies, sky-coloured points were assigned manually and the remaining eight case studies, the sky-coloured points are derived from the acquisition errors. The algorithm for sky-coloured points detection obtained an average F1-score of 94.7%. The results show a correct reassignment of colour, texture, and patterns, while improving the point cloud visualisation., Xunta de Galicia | Ref. ED481B-2019-061, Xunta de Galicia | Ref. ED431C 2020/01, Agencia Estatal de Investigación | Ref. PID2019-105221RB-C43, Agencia Estatal de Investigación | Ref. PID2019-108816RB-I00
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Point cloud semantic segmentation of complex railway environments using deep learning

  • Grandio Gonzalez, Javier
  • Riveiro Rodríguez, Belén
  • Soilán Rodríguez, Mario
  • Arias Sánchez, Pedro
Safety of transportation networks is of utmost importance for our society. With the emergency of digitalization, the railway sector is accelerating the automation in inventory and inspection procedures. Mobile mapping systems allow capturing three-dimensional point clouds of the infrastructure in short periods of time. In this paper, a deep learning methodology for semantic segmentation of railway infrastructures is presented. The methodology segments both linear and punctual elements from railway infrastructure, and it is tested in four scenarios: i) 90 km-long railway; ii) 2 km-long low-quality point clouds; iii) 400 m-long high-quality point clouds; iv) 1.4 km-long railway recoded with aerial mapping system. The longest one is used for training and testing, obtaining mean accuracy greater than 90%. The other scenarios are used only for testing, and qualitative results are discussed, proving that the method can be applied to new scenarios that significantly differ in terms of data quality and resolution., Agencia Estatal de Investigación | Ref. PID2019-108816RB-I00, Ministerio de Universidades | Ref. FPU20/01024, Universidade de Vigo/CISUG
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

First approach to UAV-based contact inspection: a smart payload for navigation in the neighbourhood of structures

  • González De Santos, Luis Miguel
  • Martínez Sánchez, Joaquín
  • González Jorge, Higinio
  • Novo Gómez, Ana
  • Arias Sánchez, Pedro
Many inspection tasks of structures are already carried out by unmanned aerial vehicles (UAV). Most of these inspections consist of using payloads for close range remote sensing purposes (i.e. digital cameras, thermal or LiDAR sensors). In all these inspection tasks the UAV system does not need to be close to the structure and typically the GPS coverage is good to perform mission navigation. In this paper, a smart payload developed for navigation in the neighbourhood of structures is presented. With this payload the UAV system is able to control the distance to a structure and the angle formed by the UAV and the structure in the horizontal plane. This payload has been calibrated in order to determine the calibration curve and measure the accuracy of the payload. The system has been tested in an indoor environment (GPS-denied). Good position and angular results has been obtained, Universidade de Vigo | Ref. 00Vl 131H 641.02, European Union’s Horizon 2020 | Ref. 769255
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Automatic gbXML modeling from LiDAR data for energy studies

  • Otero Alonso, Roi
  • Frías Nores, Ernesto
  • Lagüela López, Susana
  • Arias Sánchez, Pedro
This paper proposes an efficient and simplified procedure for the 3D modelling of buildings, based on the semi-automatic processing of point clouds acquired with mobile LiDAR scanners. The procedure is designed with the aim at generating BIM, in gbXML format, from the point clouds. In this way, the main application of the procedure is the performance of energy analysis, towards the increase of the energy efficiency in the construction sector, and its consequent contribution to the mitigation of the climate change. Thus, the main contribution of the methodology proposed is its easiness of use and its level of automation, which allow its utilization by users who are experts in the use of energy in buildings but non-experts on 3D modelling. The software provides a solution for the 3D modelling of complex point clouds of various millions of points in times of execution less than 10 minutes. The system is evaluated through its application to three different real-world scenarios and compared with manual modelling. Moreover, the results are used for an example of an energy application, proving their performance against manually elaborated models., Xunta de Galicia | Ref. IN852A 2018/59, Xunta de Galicia | Ref. I948131H646011
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Automatic detection of surface damage in round brick chimneys by finite plane modelling from terrestrial laser scanning point clouds. Case study of Bragança Dukes’ Palace, Guimarães, Portugal

  • Balado Frías, Jesús
  • Díaz Vilariño, Lucía
  • Azenha, Miguel
  • Lourenço, Paulo B.
Chimneys are architectural elements of difficult access and analysis in heritage buildings. This paper presents a method for automatic modelling of round brick chimneys and analysing their inclination, straightness and surface. The method uses as input data point clouds acquired with a Terrestrial Laser Scanner. Four chimneys have been surveyed on the north face of Bragança Dukes’ Palace in Guimarães, Portugal. The method consists of two main processes. First, the point cloud of each chimney is segmented into circumferential sections and adjusted to cylinders by applying Maximum Likelihood Sample Consensus. From the set of centroids, the inclination and the straightness of the chimney is estimated. Second, the point cloud chimney is segmented longitudinally and adjusted to finite planes. The distance estimation between the input point cloud and the modelled planes allows detecting the lack of bricks or mortar erosions. The proposed method allows estimating characteristics in chimneys even if the chimneys have not been completely acquired., Xunta de Galicia | Ref. ED481D 2019/020, Xunta de Galicia | Ref. ED481B 2019/061, Xunta de Galicia | Ref. ED431C 2016- 038, Agencia Estatal de Investigación | Ref. RTI2018-095893-B-C21, Fundação para a Ciência e a Tecnologia | Ref. UIDB/04029/2020
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Point clouds to direct indoor pedestrian pathfinding

  • Balado Frías, Jesús
  • Díaz Vilariño, Lucía
  • Arias Sánchez, Pedro
  • Frías Nores, Ernesto
Increase in building complexity can cause difficulties orienting people, especially people with reduced mobility. This work presents a methodology to enable the direct use of indoor point clouds as navigable models for pathfinding. Input point cloud is classified in horizontal and vertical elements according to inclination of each point respect to n neighbour points. Points belonging to the main floor are detected by histogram application. Other floors at different heights and stairs are detected by analysing the proximity to the detected main floor. Then, point cloud regions classified as floor are rasterized to delimit navigable surface and occlusions are corrected by applying morphological operations assuming planarity and taking into account the existence of obstacles. Finally, point cloud of navigable floor is downsampled and structured in a grid. Remaining points are nodes to create navigable indoor graph. The methodology has been tested in two real case studies provided by the ISPRS benchmark on indoor modelling. A pathfinding algorithm is applied to generate routes and to verify the usability of generated graphs. Generated models and routes are coherent with selected motor skills because routes avoid obstacles and can cross areas of non-acquired data. The proposed methodology allows to use point clouds directly as navigation graphs, without an intermediate phase of generating parametric model of surfaces, Universidade de Vigo | Ref. 00VI 131H 641.02, Xunta de Galicia | Ref. ED481B 2016/079-0, Xunta de Galicia | Ref. ED431C 2016-038, Ministerio de Economía, Industria y Competitividad | Ref. TIN2016-77158-C4-2-R, Ministerio de Economía, Industria y Competitividad | Ref. RTC-2016-5257-7
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Transfer learning for indoor object classification: from images to point clouds

  • Balado Frías, Jesús
  • Díaz Vilariño, Lucía
  • Verbree, Edward
  • Arias Sánchez, Pedro
Indoor furniture is of great relevance to building occupants in everyday life. Furniture occupies space in the building, gives comfort, establishes order in rooms and locates services and activities. Furniture is not always static; the rooms can be reorganized according to the needs. Keeping the building models up to date with the current furniture is key to work with indoor environments. Laser scanning technology can acquire indoor environments in a fast and precise way, and recent artificial intelligence techniques can classify correctly the objects that contain. The objective of this work is to study how to minimize the use of point cloud samples in Neural Network training, tedious to label, and replace them with images obtained from online sources. For this, point clouds are converted to images by means of rotations and projections. The conversion of a 3D vector data to a 2D raster allows the use of Convolutional Neural Networks, the achievement of several images for each acquired point cloud object and the combination with images obtained from online sources, such as Google Images. The images have been distributed among the validation and testing training sets following different percentages. The results show that, although point cloud images cannot be completely dispensed within the training set, only 10% of these achieve high accuracy in the classification, Xunta de Galicia | Ref. ED481B-2019-061, Xunta de Galicia | Ref. ED481D 2019/020, Xunta de Galicia | Ref. ED431C 2016-038, Agencia Estatal de Investigación | Ref. RTI2018-095893-B-C21
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Barrier and guardrail extraction and classification from point clouds

  • Vidal, M.
  • Díaz Vilariño, Lucía
  • Arias Sánchez, Pedro
  • Balado Frías, Jesús
In the recent years, the modelling of infrastructures has been receiving increasingly attention due to the importance of transport infrastructures for global economy, traffic safety and for the generation of high definition maps, essential to autonomous vehicles. This paper presents a simple method for the segmentation and classification of concrete barriers and guardrails in road surroundings. First steps of the method are aimed to delimit the region of the point cloud outside the driving lanes in which barriers and guardrails are installed. The purpose is to significantly reduce the size of point clouds in order to improve further processing. Then, barrier segmentation and classification are designed as parameter-dependent processes because the geometric features of roads and barriers and guardrails are mostly regulated by norms and standards. Results show a good performance in terms of classification in comparison of other state of the art methods. Better results were obtained for guardrails than for concrete barriers. The method has been tested in a set of point clouds acquired with a Mobile Laser Scanner from conventional roads and highways., Xunta de Galicia | Ref. ED481B-2019-061, Xunta de Galicia | Ref. ED481D 2019/020, Ministerio de Ciencia Innovación y Universidades (España) Ref. RTI2018-095893-B-C21, European Commission
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Automatic detection and characterization of ground occlusions in urban point clouds from mobile laser scanning data

  • Balado Frías, Jesús
  • González Rodríguez, Maria Elena
  • Verbree, E.
  • Díaz Vilariño, Lucía
  • Lorenzo Cimadevila, Henrique Remixio
Occlusions accompany serious problems that reduce the applicability of numerous algorithms. The aim of this work is to detect and characterize urban ground gaps based on occluding object. The point clouds for input have been acquired with Mobile Laser Scanning and have been previously segmented into ground, buildings and objects, which have been classified. The method generates various raster images according to segmented point cloud elements, and detects gaps within the ground based on their connectivity and the application of the hit-or-miss transform. The method has been tested in four real case studies in the cities of Vigo and Paris, and an accuracy of 99.6% has been obtained in occlusion detection and labelling. Cars caused 80.6% of the occlusions. Each car occluded an average ground area of 11.9 m2. The proposed method facilitates knowing the percentage of occluded ground, and if this would be reduced in successive multi-temporal acquisitions based on mobility characteristics of each object class., Xunta de Galicia | Ref. ED481B-2019-061, Xunta de Galicia | Ref. ED481D 2019/020, Agencia Estatal de Investigación | Ref. RTI2018-095893-B-C21, Agencia Estatal de Investigación | Ref. PID2019-05221RB-C43
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Review of laser scanning technologies and their applications for road and railway infrastructure monitoring

  • Soilán Rodríguez, Mario
  • Sánchez Rodríguez, Ana
  • Del Rio Barral, Pablo
  • Perez Collazo, Carlos
  • Arias Sánchez, Pedro
  • Riveiro Rodríguez, Belén
Improving the resilience of infrastructures is key to reduce their risk vulnerability and mitigate impact from hazards at different levels (e.g., from increasing extreme events, driven by climate change); or from human-made events such as: accidents, vandalism or terrorist actions. One of the most relevant aspects of resilience is preparation. This is directly related to: (i) the risk prediction capability; (ii) the infrastructure monitoring; and (iii) the systems contributing to anticipate, prevent and prepare the infrastructure for potential damage. This work focuses on those methods and technologies that contribute to more efficient and automated infrastructure monitoring. Therefore, a review that summarizes the state of the art of LiDAR (Light Detection And Ranging)-based data processing is presented, giving a special emphasis to road and railway infrastructure. The most relevant applications related to monitoring and inventory transport infrastructures are discussed. Furthermore, different commercial LiDAR-based terrestrial systems are described and compared to offer a broad scope of the available sensors and tools to remote monitoring infrastructures based on terrestrial systems., Agencia Estatal de Investigación | Ref. RTI2018-095893-B-C21
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Automatic processing of aerial LiDAR data to detect vegetation continuity in the surroundings of roads

  • Novo Gómez, Ana
  • Fariñas Álvarez, Noelia
  • Martínez Sánchez, Joaquín
  • González Jorge, Higinio
  • Lorenzo Cimadevila, Henrique Remixio
The optimization of forest management in the surroundings of roads is a necessary task in term of wildfire prevention and the mitigation of their effects. One of the reasons why a forest fire spreads is the presence of contiguous flammable material, both horizontally and vertically and, thus, vegetation management becomes essential in preventive actions. This work presents a methodology to detect the continuity of vegetation based on aerial Light Detection and Ranging (LiDAR) point clouds, in combination with point cloud processing techniques. Horizontal continuity is determined by calculating Cover Canopy Fraction (CCF). The results obtained show 50% of shrubs presence and 33% of trees presence in the selected case of study, with an error of 5.71%. Regarding vertical continuity, a forest structure composed of a single stratum represents 81% of the zone. In addition, the vegetation located in areas around the roads were mapped, taking into consideration the distances established in the applicable law. Analyses show that risky areas range from a total of 0.12 ha in a 2 m buffer and 0.48 ha in a 10 m buffer, representing a 2.4% and 9.5% of the total study area, respectively., TOPACIO | Ref. IN852A 2018/37, European Union’s Horizon 2020 | Ref. 769255
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Pavement crack detection and clustering via region-growing algorithm from 3D MLS point clouds

  • Del Rio Barral, Pablo
  • Soilán Rodríguez, Mario
  • Gonzalez Collazo, Silvia María
  • Arias Sánchez, Pedro
Road condition monitoring plays a critical role in transportation infrastructure maintenance and traffic safety assurance. This research introduces a methodology to detect cracks on pavement point clouds acquired with Mobile Laser Scanning systems, which offer more versatility and comprehensive information about the road environment than other specific surveying systems (i.e., profilometers, 3D cameras). The methodology comprises the following steps: (1) Road segmentation; (2) the detection of candidate crack points in individual scanning lines of the point cloud, based on point elevation; (3) crack point clustering via a region-growing algorithm; and (4) crack geometrical attributes extraction. Both the profile evaluation and the region-growing clustering algorithms have been developed from scratch to detect cracks directly from 3D point clouds instead of using raster data or Geo-Referenced Feature images, offering a quick and effective pre-rating tool for pavement condition assessment. Crack detection is validated with data from damaged roads in Portugal., Ministerio de Ciencia e Innovación | Ref. PID2019-105221RB-C43, Ministerio de Ciencia e Innovación | Ref. FJC2018-035550-I
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Scan-to-BIM for the infrastructure domain: generation of IFC-complaint models of road infrastructure assets and semantics using 3D point cloud data

  • Justo Dominguez, Andrés
  • Soilán Rodríguez, Mario
  • Sánchez Rodríguez, Ana
  • Riveiro Rodríguez, Belén
The development of the IFC 4.3 candidate standard sets the pathway for interoperability amongst different infrastructures that have been harmonized under the buildingSMART project proposals. Furthermore, the use of laser scanning as a tool for the monitoring of infrastructures has also been rising. This paper showcases a combination of BIM and remote sensing for infrastructure in a road scenario. A semi-automatic approach is presented for the IFC 4.1 compliant modelling of traffic signs and guardrails, along with the inclusion of some semantics via property sets. The input data for the IFC modelling procedure is obtained from the automatic processing of a 3D point cloud, that extracts road alignment, traffic signs, and guardrails, and from standardized dimensions for certain assets. The point cloud processing is validated for the guardrail identification and the IFC modelling is described alongside an UML, exemplifying the possibility of modelling the as-is state of the road infrastructure., Ministerio de Ciencia, Innovación y Universidades | Ref. RTI2018-095893-B-C21, Ministerio de Ciencia e Innovación | Ref. FJC2018-035550-I, Universidade de Vigo/CISUG
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Semantic segmentation of point clouds with PointNet and KPConv architectures applied to railway tunnels

  • Soilán Rodríguez, Mario
  • Novoa Martínez, Andrea
  • Sánchez Rodríguez, Ana
  • Riveiro Rodríguez, Belén
  • Arias Sánchez, Pedro
Transport infrastructure monitoring has lately attracted increasing attention due to the rise in extreme natural hazards posed by climate change. Mobile Mapping Systems gather information regarding the state of the assets, which allows for more efficient decision-making. These systems provide information in the form of three-dimensional point clouds. Point cloud analysis through deep learning has emerged as a focal research area due to its wide application in areas such as autonomous driving. This paper aims to apply the pioneering PointNet, and the current state-of-the-art KPConv architectures to perform scene segmentation of railway tunnels, in order to validate their employability over heuristic classification methods. The approach is to perform a multi-class classification that classifies the most relevant components of tunnels: ground, lining, wiring and rails. Both architectures are trained from scratch with heuristically classified point clouds of two different railway tunnels. Results show that, while both architectures are suitable for the proposed classification task, KPConv outperforms PointNet with F1-scores over 97% for ground, lining and wiring classes, and over 90% for rails. In addition, KPConv is tested using transfer learning, which gives F1-scores slightly lower than for the model training from scratch but shows better generalization capabilities.
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Novel approach to automatic traffic sign inventory based on mobile mapping system data and deep learning

  • Balado Frías, Jesús
  • Gonzalez Rodriguez, Maria Elena
  • Arias Sánchez, Pedro
  • Castro, David
Traffic signs are a key element in driver safety. Governments invest a great amount of resources in maintaining the traffic signs in good condition, for which a correct inventory is necessary. This work presents a novel method for mapping traffic signs based on data acquired with MMS (Mobile Mapping System): images and point clouds. On the one hand, images are faster to process and artificial intelligence techniques, specifically Convolutional Neural Networks, are more optimized than in point clouds. On the other hand, point clouds allow a more exact positioning than the exclusive use of images. The false positive rate per image is only 0.004. First, traffic signs are detected in the images obtained by the 360° camera of the MMS through RetinaNet and they are classified by their corresponding InceptionV3 network. The signs are then positioned in the georeferenced point cloud by means of a projection according to the pinhole model from the images. Finally, duplicate geolocalized signs detected in multiple images are filtered. The method has been tested in two real case studies with 214 images, where 89.7% of the signals have been correctly detected, of which 92.5% have been correctly classified and 97.5% have been located with an error of less than 0.5 m. This sequence, which combines images to detection–classification, and point clouds to geo-referencing, in this order, optimizes processing time and allows this method to be included in a company’s production process. The method is conducted automatically and takes advantage of the strengths of each data type., Xunta de Galicia | Ref. ED481B-2019-061, Xunta de Galicia | Ref. ED481D 2019/020, Xunta de Galicia | Ref. ED431C 2016-038
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Generation and enrichment of pedestrian maps with vertical shadows in urban environments from mobile laser scanning data

  • Balado Frías, Jesús
  • Díaz Vilariño, Lucía
  • Frías Nores, Ernesto
  • González Rodríguez, Maria Elena
Cities are becoming more pedestrian-friendly, reducing traffic and promoting physical activity and walking. However, prolonged exposure to the sun can cause sunburn and skin problems, so minimizing exposure to the sun while travelling is especially relevant at certain latitudes and in the summer months. This paper proposes a method for modelling urban contours and generating pedestrian maps with the location of shaded areas and accessibility barriers. The proposed method uses as input data a point cloud of an urban environment acquired with Mobile Laser Scanning. First, the input point cloud is segmented in ground points, obstacle points, and points causing shadows. Then, the three segmented point clouds are rasterized and the corresponded images are combined to obtain the navigable ground and the shaded areas. Finally, from the navigable ground, a navigation map is generated for pedestrians. To check the usefulness of this navigation map, a pathfinding algorithm is applied. The results show a correct generation of the navigable ground, and routes prioritizing the trajectory by shadow areas. Depending on the weighting between sun and shaded areas, the routes obtained show differences in distance travelled and sun exposure. The proposed method is sensitive to the existence of obstacles and noise in the point clouds., Xunta de Galicia | Ref. ED481B-2019-061, Xunta de Galicia | Ref. ED481D 2019/020, Xunta de Galicia | Ref. ED431C 2016- 038, Agencia Estatal de Investigación | Ref. RTI2018-095893-B-C21, Agencia Estatal de Investigación | Ref. PID2019- 105221RB-C43
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Comparison between geostatistical interpolation and numerical weather model predictions for meteorological conditions mapping

  • López Gómez, Javier
  • Troncoso Pastoriza, Francisco Manuel
  • Granada Álvarez, Enrique
  • Eguía Oller, Pablo
Mapping of meteorological conditions surrounding road infrastructures is a critical tool to identify high-risk spots related to harsh weather. However, local or regional data are not always available, and researchers and authorities must rely on coarser observations or predictions. Thus, choosing a suitable method for downscaling global data to local levels becomes essential to obtain accurate information. This work presents a deep analysis of the performance of two of these methods, commonly used in meteorology science: Universal Kriging geostatistical interpolation and Weather Research and Forecasting numerical weather prediction outputs. Estimations from both techniques are compared on 11 locations in central continental Portugal during January 2019, using measured data from a weather station network as the ground truth. Results show the different performance characteristics of both algorithms based on the nature of the specific variable interpolated, highlighting potential correlations to obtain the most accurate data for each case. Hence, this work provides a solid foundation for the selection of the most appropriate tool for mapping of weather conditions at the local level over linear transport infrastructures., Universidade de Vigo | Ref. 00VI 131H 641.02, Xunta de Galicia | Ref. IN852A 2018/37
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Payload for contact inspection tasks with UAV systems

  • González De Santos, Luis Miguel
  • Martínez Sánchez, Joaquín
  • González Jorge, Higinio
  • Ribeiro, M.
  • Sousa, J.B. de
  • Arias Sánchez, Pedro
This paper presents a payload designed to perform semi-autonomous contact inspection tasks without any type of positioning system external to the UAV, such as a global navigation satellite system (GNSS) or motion capture system, making possible inspection in challenging GNSS- denied sites. This payload includes two LiDAR sensors which measure the distance between the UAV and the target structure and their inner orientation angle. The system uses this information to control the approaching of the UAV to the structure and the contact between both, actuating over the pitch and yaw signals. This control is performed using a hybrid automaton with different states that represent all the possible UAV status during the inspection tasks. It uses different control strategies in each state. An ultrasonic gauge has been used as the inspection sensor of the payload to measure the thickness of a metallic sheet. The sensor requires a stable contact in order to collect reliable measurements. Several tests have been performed on the system, reaching accurate results which show it is able to maintain a stable contact with the target structure., Universidade de Vigo | Ref. 00Vl 131H 641.02, Ministerio de Economia, Industria y Competitividad, Gobierno de España | Ref. TIN2016-77158-C4-2-R, Ministerio de Economia, Industria y Competitividad, Gobierno de España | Ref. RTC-2016-5257-7, IACOBUS Program, European Union’s Horizon 2020 | Ref. 769255
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Point clouds for direct pedestrian pathfinding in urban environments

  • Balado Frías, Jesús
  • Díaz Vilariño, Lucía
  • Arias Sánchez, Pedro
  • Lorenzo Cimadevila, Henrique Remixio
Pathfinding applications for the citizen in urban environments are usually designed from the perspective of a driver, not being effective for pedestrians. In addition, urban scenes have multiple elements that interfere with pedestrian routes and navigable space. In this paper, a methodology for the direct use of point clouds for pathfinding in urban environments is presented, solving the main limitations for this purpose: (a) the excessive number of points is reduced for transformation into nodes on the final graph, (b) urban static elements acting as permanent obstacles, such as furniture and trees, are delimited and differentiated from dynamic elements such as pedestrians, (c) occlusions on ground elements are corrected to enable a complete graph modelling, and (d) navigable space is delimited from free unobstructed space according to two motor skills (pedestrians without reduced mobility and wheelchairs). The methodology is tested into three different streets sampled as point clouds by mobile laser scanning (MLS) systems: an intersection of several streets with ground composed of sidewalks at different heights; an avenue with wide sidewalks, trees and cars parked on one side; and a street with a single-lane road and narrow sidewalks. By applying Dijkstra pathfinding algorithm to the resulting graphs, the correct viability of the generated routes has been verified based on a visual analysis of the generated routes on the point cloud and on the knowledge of the urban study area. The methodology enables the automatic generation of graphs representing the navigable urban space, on which safe and real routes for different motor skills can be calculated., Universidade de Vigo, Xunta de Galicia | Ref. ED481B 2016/079-0, Xunta de Galicia | Ref. ED431C 2016/038, Ministerio de Economía, Industria y Competitividad. TIN2016-77158-C4-2-R, RTC-2016-5257-7
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Comparison of heuristic and deep learning-based methods for ground classification from aerial point clouds

  • Soilán Rodríguez, Mario
  • Riveiro Rodríguez, Belén
  • Balado Frías, Jesús
  • Arias Sánchez, Pedro
The automatic definition of the ground from 3D point clouds has been a common process for the last two decades, with many different approaches and applications that can be found in a vast literature. This paper presents a comparison of three different methodological concepts for ground classification, in order to establish the advantages and drawbacks of each method. First, a heuristic method, based on previous knowledge of the geometry and context of the 3D data. Secondly, a Deep Convolutional Network based on SegNet that classifies 2D images generated from the 3D point cloud. Finally, the third method applies a Deep Learning classification based on PointNet, which takes 3D points directly as inputs. To validate each method and compare them, public and labelled point clouds frothe m the Actueel Hoogtebestand Nederland dataset are employed. Furthermore, the three methods are validated against the ISPRS 3D Semantic Labeling Contest benchmark. The results obtained show that the deep learning based approaches outperform the heuristic method, with F-scores above 96%. The best results were obtained using a shallower version of SegNet, with F-score above 97%., Ministerio de Economía y Competitividad | Ref. BES-2014-067736, Xunta de Galicia | Ref. ED431C2016-038
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Analytical model for the fatigue analysis of steel joints by clamps according to the lever length

  • Cabaleiro Núñez, Manuel
  • Comesaña Piñeiro, Rafael
  • González Gaya, Cristina
  • Caamaño Martinez, Jose Carlos
Among the most commonly used materials in the construction of structures in the last two centuries are iron and steel. Clamp joints are a suitable type of joint when it is necessary to rehabilitate or modify a historical steel structure for new uses, reinforcing or modifying it with new beams, without the need to drill or weld on the original structure. The clamps allow beams to be joined with a flange (such as I-beams) without the need for any prior operation on the beams and allow the manufacture of completely removable and reconfigurable structures. Developing and analysing this type of fully removable and reconfigurable structure is necessary. To date, no studies have been carried out on the fatigue behaviour of steel joints by clamps, especially taking into account their main geometric characteristics, such as the size of the clamp levers. In this work, an analytical model is proposed that allows for the analysis of the number of cycles and the fatigue limit of clamp joints as a function of the size of the clamp levers. In addition, various fatigue tests are performed with different clamp sizes. The experimental results are compared with those obtained with the proposed methodology. Finally, the relationships between the lever length and the fatigue behaviour of the clamp joints have been determined. It is concluded that an increase in the size of the front lever is associated to a decrease in the fatigue limit. On the contrary, if the size of the rear lever is increased, the fatigue limit of the joint increases. In general, according to the obtained results, the resistance of the joint can be reduced to approximately one third when it is subjected to fatigue loads., Ministerio de Ciencia, Innovación | Ref. RTI2018-095893-B-C21, European Commission | Ref. H2020, n. 769255
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Visibility analysis for the occlusion detection and characterisation in street point clouds acquired with Mobile Laser Scanning

  • Barros-Ribademar, Jose
  • Balado Frías, Jesús
  • Arias Sánchez, Pedro
  • Gonzalez Collazo, Silvia María
Although multi-temporal acquisitions are a widely accepted way to reduce occlusions in point clouds, occlusion analysis continues to be a visual analysis. The objective of this work is the design of an automatic method for the detection and characterization of street point cloud occlusions acquired with Mobile Laser Scanning (MLS). The proposed method consists of four main phases: alignment of the point cloud, rasterization, generation of occluded point clouds and visibility analysis. The proposed method was tested with point clouds of TerraMobil-ita/iQmulus dataset. The result shows a correct detection of 98.71% of the occlusions on ground and 83.37% on fac¸ades. All detected occlusions were correctly characterized. In the case studies, cars generated the largest amount of occluded area on the ground, with an occluded area per object of 15.36 m2. The main source of occlusions on fac¸ades was the building geometry and windows., Xunta de Galicia | Ref. ED481B-2019-061, Xunta de Galicia | Ref. ED431C 2020/01, Agencia Estatal de Investigación | Ref. PID2019-105221RB-C43
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Automatic point cloud semantic segmentation of complex railway environments

  • Lamas Novoa, Daniel
  • Soilán Rodríguez, Mario
  • Grandio Gonzalez, Javier
  • Riveiro Rodríguez, Belén
The growing development of data digitalisation methods has increased their demand and applications in the transportation infrastructure field. Currently, mobile mapping systems (MMSs) are one of the most popular technologies for the acquisition of infrastructure data, with three-dimensional (3D) point clouds as their main product. In this work, a heuristic-based workflow for semantic segmentation of complex railway environments is presented, in which their most relevant elements are classified, namely, rails, masts, wiring, droppers, traffic lights, and signals. This method takes advantage of existing methodologies in the field for point cloud processing and segmentation, taking into account the geometry and spatial context of each classified element in the railway environment. This method is applied to a 90-kilometre-long railway lane and validated against a manual reference on random sections of the case study data. The results are presented and discussed at the object level, differentiating the type of the element. The indicators F1 scores obtained for each element are superior to 85%, being higher than 99% in rails, the most significant element of the infrastructure. These metrics showcase the quality of the algorithm, which proves that this method is efficient for the classification of long and variable railway sections, and for the assisted labelling of point cloud data for future applications based on training supervised learning models., Agencia Estatal de Investigación | Ref. RTI2018-095893-B-C21, Agencia Estatal de Investigación | Ref. FJC2018-035550-I
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Generating IFC-compliant models and structural graphs of truss bridges from dense point clouds

  • Justo Dominguez, Andrés
  • Lamas Novoa, Daniel
  • Sánchez Rodríguez, Ana
  • Soilán Rodríguez, Mario
  • Riveiro Rodríguez, Belén
The IFC schema has been evolving towards the infrastructure domain. Furthermore, the use of laser scanning technologies as means to digitalize and monitor infrastructures has also significantly increased. This work presents an automated modelling approach for truss bridges that utilizes laser scanning data as its source for geometrical information. The methodology takes a partially instance-segmented point cloud of a truss bridge and generates both an IFC-compliant information model of the truss and the corresponding structural graph. This process uses bounding boxes and their collisions to overcome the missing data from the partial segmentation to create the truss model, as well as to identify the nodes that connect the different truss members. The methodology was tested on a use case made of 272 members and obtained the truss model and structural graph files., Agencia Estatal de Investigación | Ref. FJC2020–046370-I, Agencia Estatal de Investigación | Ref. PID2021-124236OB-C33, Agencia Estatal de Investigación | Ref. FJC2020–046370-I, Universidade de Vigo/CISUG
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Canopy detection over roads using mobile lidar data

  • Novo Gómez, Ana
  • González Jorge, Higinio
  • Martínez Sánchez, Joaquín
  • Lorenzo Cimadevila, Henrique Remixio
A high percentage of forest fires take place around roads. These infrastructures provide an escape route for the population in case of fire. Optimization of forest management in the surroundings of roads is a necessary task in terms of wildfires prevention and mitigation of their effects. Therefore, it is essential to avoid the horizontal continuity of vegetation across roads. A methodology for the measurement of canopy area over roads is developed and based on mobile LiDAR (Light Detection and Ranging) point clouds. The acquisition of LiDAR data is done by Lynx Mobile Mapper System from the University of Vigo. The methodology is automated using LiDAR data processing (M-estimator Sample Consensus and near neighbour algorithms) and image processing techniques (rasterization and binarization). The developed algorithms are tested on a study area, the DP-3606 road (Spain). Results are compared with ground truth data of the canopy projected on the road. The best obtained results present a mean geometric error of 2.82% for 0.25 m resolution and 104.02% for 2 m resolution. Furthermore, the higher the pixel size, the greater the error was obtained with a linear correlation value of 0.99., Diputación de Pontevedra | Ref. 17/410.1720.789.02
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Road environment semantic segmentation with deep learning from MLS point cloud data

  • Balado Frías, Jesús
  • Martínez Sánchez, Joaquín
  • Arias Sánchez, Pedro
  • Novo Gómez, Ana
In the near future, the communication between autonomous cars will produce a network of sensors that will allow us to know the state of the roads in real time. Lidar technology, upon which most autonomous cars are based, allows the acquisition of 3D geometric information of the environment. The objective of this work is to use point clouds acquired by Mobile Laser Scanning (MLS) to segment the main elements of road environment (road surface, ditches, guardrails, fences, embankments, and borders) through the use of PointNet. Previously, the point cloud was automatically divided into sections in order for semantic segmentation to be scalable to different case studies, regardless of their shape or length. An overall accuracy of 92.5% has been obtained, but with large variations between classes. Elements with a greater number of points have been segmented more effectively than the other elements. In comparison with other point-by-point extraction and ANN-based classification techniques, the same success rates have been obtained for road surfaces and fences, and better results have been obtained for guardrails. Semantic segmentation with PointNet is suitable when segmenting the scene as a whole, however, if certain classes have more interest, there are other alternatives that do not need a high training cost., Universidade de Vigo | Ref. 00VI 131H 641.02, Xunta de Galicia | Ref. ED481B 2016/079-0, Xunta de Galicia | Ref. ED431C 2016-038
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Model calibration methodology to assess the actual lighting conditions of a road infrastructure

  • Ogando Martínez, Ana
  • Troncoso Pastoriza, Francisco Manuel
  • Eguía Oller, Pablo
  • Granada Álvarez, Enrique
  • Erkoreka, Aitor
Street lighting plays an important role in the comfort and safety of drivers and pedestrians, so the control and management of the lighting systems operation and consumption is an essential service for a city. In this document, a methodology is presented to calibrate lighting models in order to assess the lighting performance through simulation techniques. The objective of this calibration is to identify the maintenance factor of the street lamps, determine the real average luminance coefficient of the road pavement and adapt the reflection properties of the road material. The method is applied in three stages and is based on the use of Radiance and GenOpt software suits for the modeling, simulation, and calibration of lighting scenes. The proposed methodology achieves errors as low as 13% for the calculation of illuminance and luminance, evincing its potential to assess the actual lighting conditions of a road., Ministerio de Ciencia, Innovación y Universidades | Ref. FPU17/01834
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

From BIM to scan planning and optimization for construction control

  • Frías Nores, Ernesto
  • Díaz Vilariño, Lucía
  • Balado Frías, Jesús
  • Lorenzo Cimadevila, Henrique Remixio
Scan planning of buildings under construction is a key issue for an efficient assessment of work progress. This work presents an automatic method aimed to determinate the optimal scan positions and the optimal route based on the use of Building Information Models (BIM) and considering data completeness as stopping criteria. The method is considered for a Terrestrial Laser Scanner mounted on a mobile robot following a stop & go procedure. The method starts by extracting floor plans from the BIM model according to the planned construction status, and including geometry and semantics of the building elements considered for construction control. The navigable space is defined from a binary map considering a security distance to building elements. After a grid-based and a triangulation-based distribution are implemented for generating scan position candidates, a visibility analysis is carried out to determine the optimal number and position of scans. The optimal route to visit all scan positions is addressed by using a probabilistic ant colony optimization algorithm. The method has been tested in simulated and real buildings under very dissimilar conditions and structural construction elements. The two approaches for generating scan position candidates are evaluated and results show the triangulation-based distribution as the more efficient approach in terms of processing and acquisition time, especially for large-scale buildings., Ministerio de Economía, Industria y Competitividad | Ref. TIN2016-77158, Ministerio de Economía, Industria y Competitividad | Ref. RTC-2016-5257-7, Xunta de Galicia | Ref. ED481B 216/079-0
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Point clouds to direct indoor pedestrian pathfinding

  • Balado Frías, Jesús
  • Díaz Vilariño, Lucía
  • Arias Sánchez, Pedro
  • Frías Nores, Ernesto
Increase in building complexity can cause difficulties orienting people, especially people with reduced mobility. This work presents a methodology to enable the direct use of indoor point clouds as navigable models for pathfinding. Input point cloud is classified in horizontal and vertical elements according to inclination of each point respect to n neighbour points. Points belonging to the main floor are detected by histogram application. Other floors at different heights and stairs are detected by analysing the proximity to the detected main floor. Then, point cloud regions classified as floor are rasterized to delimit navigable surface and occlusions are corrected by applying morphological operations assuming planarity and taking into account the existence of obstacles. Finally, point cloud of navigable floor is downsampled and structured in a grid. Remaining points are nodes to create navigable indoor graph. The methodology has been tested in two real case studies provided by the ISPRS benchmark on indoor modelling. A pathfinding algorithm is applied to generate routes and to verify the usability of generated graphs. Generated models and routes are coherent with selected motor skills because routes avoid obstacles and can cross areas of non-acquired data. The proposed methodology allows to use point clouds directly as navigation graphs, without an intermediate phase of generating parametric model of surfaces.
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Active UAV payload based on horizontal propellers for contact inspections tasks

  • González De Santos, Luis Miguel
  • Martínez Sánchez, Joaquín
  • González Jorge, Higinio
  • Arias Sánchez, Pedro
Increase in building complexity can cause difficulties orienting people, especially people with reduced mobility. This work presents a methodology to enable the direct use of indoor point clouds as navigable models for pathfinding. Input point cloud is classified in horizontal and vertical elements according to inclination of each point respect to n neighbour points. Points belonging to the main floor are detected by histogram application. Other floors at different heights and stairs are detected by analysing the proximity to the detected main floor. Then, point cloud regions classified as floor are rasterized to delimit navigable surface and occlusions are corrected by applying morphological operations assuming planarity and taking into account the existence of obstacles. Finally, point cloud of navigable floor is downsampled and structured in a grid. Remaining points are nodes to create navigable indoor graph. The methodology has been tested in two real case studies provided by the ISPRS benchmark on indoor modelling. A pathfinding algorithm is applied to generate routes and to verify the usability of generated graphs. Generated models and routes are coherent with selected motor skills because routes avoid obstacles and can cross areas of non-acquired The present work presents a UAV payload designed to perform semi-autonomous contact inspection tasks in vertical structures. The presented system includes on-board positioning capabilities to calculate the distance and angle between the structure and the UAV. In this way, the system is able to navigate in the neighbourhood of the structure, that may be considered a GPS-denied area. The payload includes two horizontal propellers aimed to push the system against the structure gently. The distance and angle acquired by the payload controller are a basis to calculate the control signals for payload engines and UAV heading. Such control signals are needed to perform the contact. Also, the proposed system has been compared to a previous design based on the UAV pitch signal control, highlighting the advantages of the new prototype. The series of tests that have been performed on the system demonstrate that the developed payload maintains a more stable and reliable contact with the structure.
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Point cloud room segmentation based on indoor spaces and 3D mathematical morphology

  • Frías Nores, Ernesto
  • Balado Frías, Jesús
  • Díaz Vilariño, Lucía
  • Lorenzo Cimadevila, Henrique Remixio
Room segmentation is a matter of ongoing interesting for indoor navigation and reconstruction in robotics and AEC. While in robotics field, the problem room segmentation has been typically addressed on 2D floorplan, interest in enrichment 3D models providing more detailed representation of indoors has been growing in the AEC. Point clouds make available more realistic and update but room segmentation from point clouds is still a challenging topic. This work presents a method to carried out point cloud segmentation into rooms based on 3D mathematical morphological operations. First, the input point cloud is voxelized and indoor empty voxels are extracted by CropHull algorithm. Then, a morphological erosion is performed on the 3D image of indoor empty voxels in order to break connectivity between voxels belonging to adjacent rooms. Remaining voxels after erosion are clustered by a 3D connected components algorithm so that each room is individualized. Room morphology is retrieved by individual 3D morphological dilation on clustered voxels. Finally, unlabelled occupied voxels are classified according proximity to labelled empty voxels after dilation operation. The method was tested in two real cases and segmentation performance was evaluated with encouraging results., Xunta de Galicia | Ref. ED481B-2019-061, Xunta de Galicia | Ref. ED481D 2019/020, Agencia Estatal de Investigación | Ref. RTI2018-095893-B-C21, Agencia Estatal de Investigación | Ref. PID2019-105221RB-C43
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Transfer Learning in urban object classification: online images to recognize point clouds

Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Automatic detection of forest-road distances to improve clearing operations in road management

  • Novo Gómez, Ana
  • González Jorge, Higinio
  • Martínez Sánchez, Joaquín
  • González De Santos, Luis Miguel
  • Lorenzo Cimadevila, Henrique Remixio
There is a complex relation between roads and fires. Several major wildfires were ignited near to roads (Morrison 2007) and how they progressed is an important role to understand the importance to forest management in this environment. Nowadays, a sustainable forest management is necessary both for environment and politics. One of the reasons of road management is that these infrastructures provide an effective firewall in case of forest fires and an escape route for the population. Forest management optimization in road surroundings would improve wildfires prevention and mitigate their effects. One of the main indicators of road safety is the distance between road and vegetation.The aim of this work is to develop a methodology to determine what areas do not obey current laws about safety distances between forest and roads. The acquisition of LiDAR data is done by Lynx Mobile Mapper System from University of Vigo. The methodology is automated using LiDAR data processing. The developed algorithms are based in height and length segmentation of the road. The objective is classifying vegetation groups by height and calculate the distance to the edges of road. The vegetation is divided in groups of height of 5, 10, 15 and 30 m. The minimum distance calculation is 2 m, for the vegetation of 5 m height and a maximum of 60 m for vegetation 30 m height. The height of vegetation has a directly relation with the distance separation with the road., Universidade de Vigo | Ref. 00VI 131H 641.02
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Use of a numerical weather prediction model as a meteorological source for building thermal simulations

  • López Gómez, Javier
  • Troncoso Pastoriza, Francisco
  • Arce Fariña, Elena
  • Eguía, Pablo
  • Granada, Enrique
This version of the article has been accepted for publication, after peer review, but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1016/j.scs.2020.102403, [Abstract]: Thermal simulations are a commonly used tool for energy efficiency analysis of buildings. Regional meteorological station networks are a prime source of weather data inputs, required for building thermal simulations. However, local measurements from weather stations are not always available, and when available, access to data may be expensive. This paper analysed a novel use of a numerical weather prediction mesoscale model, the Global Forecast System (GFS) sflux model, as a source of input data for transient thermal simulations. Two interpolation techniques (nearest neighbour and universal kriging) were used to generate local weather datasets from GFS outputs at 27 locations spread over an area of 29,574 km2 in Galicia (northwest Spain). The performance of the GFS estimations was tested against weather measurements obtained from a government weather agency. A representative building with the most common features was selected for running thermal simulations in the TRNSYS environment, focused on heating demands, with estimated weather data as the input. The results highlighted that GFS-interpolated datasets consistently performed better than using measured data from the nearest weather station. GFS was found to be an appropriate weather source for building simulations and was able to provide good-quality, free and global-scale local weather inputs., Xunta de Galicia; TOPACIO IN852A 2018/37, Universidade de Vigo; 00VI 131H 641.02, Xunta de Galicia; TOPACIO IN852A 2018/37, This investigation article was partially supported by the University of Vigo through the grant Convocatoria de Axudas á Investigación 2018: Axudas Predoutorais UVigo 2018 (grant number 00VI 131H 641.02). This investigation article was also partially supported by the Galician Government by means of the Xunta de Galicia CONECTA PEME 2018 (Project: TOPACIO IN852A 2018/37). This paper was carried out in the framework of the GIS-Based Infrastructure Management System for Optimized Response to Extreme Events of Terrestrial Transport Networks (SAFEWAY) project, which has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 769255. Neither the Innovation and Networks Executive Agency (INEA) nor the European Commission is in any way responsible for any use that may be made of the information it contains
GREDOS. Repositorio Institucional de la Universidad de Salamanca
Publicación Artículo científico (JournalArticle)

Introduction of the combination of thermal fundamentals and Deep Learning for the automatic thermographic inspection of thermal bridges and water-related problems in infrastructures

  • Garrido González, Iván
  • Lagüela López, Susana
  • Fang, Qiang
  • Arias Castanedo, Pedro
[EN] Infrastructure inspection is fundamental to keep its service performance at the highest level. For that, special attention should be paid to the most severe defects in order to be able to subsequently mitigate or even eliminate them. Therefore, this paper introduces the combination of an automatic thermogram pre-processing algorithm and a Deep Learning (DL) model, Mask R-CNN, applied to thermal images acquired from different infrastructures (buildings, heritage sites and civil infrastructures) with water-related problems and thermal bridges. The pre-processing algorithm developed is based on thermal fundamentals. As an output, the thermal contrast between defect and defect-free areas is increased in each image. Then, Mask R-CNN is trained using the pre-processing algorithm outputs as input dataset to automatically detect, segment and classify each defect area. The training process of Mask R-CNN is improved by the prior application of the proposed pre-processing algorithm in terms of time. This shows the capacity of thermal fundamentals to improve the performance of the DL models for their application to the InfraRed Thermography (IRT) field. In addition, DL models are introduced for the first time in the thermographic inspection of water-related problems and thermal bridges when inspecting an infrastructure.
GREDOS. Repositorio Institucional de la Universidad de Salamanca
Publicación Artículo científico (JournalArticle)

Introduction of active thermography and automatic defect segmentation in the thermographic inspection of specimens of ceramic tiling for building façades

  • Garrido González, Iván
  • Barreira, Eva
  • M. S. F. Almeida, Ricardo
  • Lagüela López, Susana
[EN] InfraRed Thermography (IRT) has proven to be a valuable diagnostic tool due to its real-time, remote, and non-destructive operation yielding accurate detection of the position of defect areas in building façade ceramic tiling. Ceramic tiles coating building façades are widely used throughout the world because of their technical and aesthetic characteristics. However, the detachment of ceramic tiles and the water infiltration in deep layers are still common problems. So, this paper proposes active infrared thermography as a thermographic acquisition mode, in contrast to the common use of passive thermography, and segmentation of defect areas and automation in the thermal image processing as added values never before proposed in the ceramic tiling thermographic inspection. For that, specimens of ceramic tiling for building façades were tested under different laboratory conditions, with inserted corks (simulating detachments), and by injecting water into holes drilled in the back surfaces (simulating water infiltration), as defects. Good results have been obtained in all the tests, both in dry and wet conditions in the specimens and for surfaces with homogeneous and heterogeneous surface properties, serving the introduction of this workflow for a first and fast inspection in ceramic tiling building façades. Future research will work with the fine-tuning phase of the methodology by applying it to real case studies.
GREDOS. Repositorio Institucional de la Universidad de Salamanca
Publicación Artículo científico (JournalArticle)

Semi-automatic roof modelling from indoor laser-acquired data

  • Otero, Roi
  • Sánchez Aparicio, María
  • Lagüela López, Susana
  • Arias, Pedro
[EN] Roof modelling provides useful information for energy analysis, but the methodologies traditionally applied are based on data acquired through aerial vehicles. This requirement makes necessary two data acquisition campaigns: one from indoors and another from outdoors. However, most energy studies can be performed using regularized and simplified models where most of the information of the exhaustive acquisitions is not used. Therefore, this paper proposes a semi-automatic procedure for the 3D modelling of roofs using indoor point clouds, reducing the acquisition campaigns to the indoors campaign. The methodology is based on the hypothesis that surfaces have no thickness, which makes the algorithm especially useful in industrial environments where there are no false ceilings and therefore, the contribution of the roof in the energy behaviour of the building is more important. The methodology is tested on six different scenarios, obtaining their regularized models with relative errors lower than 2% in ideal conditions.