Pasar al contenido principal

INTEGRACION DE INFORMACION MULTISENSORIAL Y APRENDIZAJE AUTOMATICO PARA LA DETECCION, CARACTERIZACION Y RECONOCIMIENTO PRECISO DE ESTRUCTURAS NATURALES EN CAMPOS DE CULTIVO

AGL2014-52465-C4-3-R

•
Nombre agencia financiadora Ministerio de Economía y Competitividad
Acrónimo agencia financiadora MINECO
Programa Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Convocatoria Proyectos I+D+i Retos de Investigación
Año convocatoria 2014
Plan Estatal 2013-2016 Plan Estatal de Investigación Científica y Técnica y de Innovación
Unidad de gestión Secretaría de Estado de Educación, Formación Profesional y Universidades
Centro beneficiario AGENCIA ESTATAL CONSEJO SUPERIOR DE INVESTIGACIONES CIENTIFICAS (CSIC)
Identificador persistente http://dx.doi.org/10.13039/501100003329

Resultados relacionados

Resultados totales (Incluyendo duplicados): 9
Encontrada(s) 1 página(s)

RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Plataforma de inspección para la obtención de mapas 2D y 3D de un cultivo

  • Bengochea-Guevara, José M.
  • Andújar, Dionisio
  • Conesa-Muñoz, Jesús
  • Ribeiro, Ángela
[Resumen] El concepto de Gestión Integrada de Plagas (GIP) ha surgido en los últimos años con el fin de lograr un manejo sostenible de los cultivos reduciendo, entre otras cosas, la cantidad de agroquímicos empleados y con ello el impacto medioambiental. Un elemento clave es la monitorización o inspección continua de los cultivos para asegurar la detección temprana de plagas. En este artículo se presenta una plataforma móvil terrestre capaz de inspeccionar dos tipos de escenarios: los cultivos anuales (maíz, cereales, etc) y los cultivos plurianuales (árboles frutales, viñedos, etc)., Este trabajo está siendo financiado en su totalidad por el proyecto del Plan Estatal “Integración de información multisensorial y aprendizaje automático para la detección, caracterización y reconocimiento preciso de estructuras naturales en campos de cultivo” (AGL2014-52465-C4-3-R), https://doi.org/10.17979/spudc.9788497498081
Repositori Obert UdL
Publicación Artículo científico (JournalArticle)

A LiDAR-Based System to Assess Poplar Biomass

  • Andújar, Dionisio
  • Escolà i Agustí, Alexandre
  • Rosell Polo, Joan Ramon
  • Sanz Cortiella, Ricardo
  • Rueda-Ayala, Victor
  • Fernandez Quintanilla, C.
  • Ribeiro, Angela
  • Dorado, José
This study evaluated the capabilities of a LiDAR-based system to characterize poplar trees for biomass production. The precision of the system was assessed by analyzing the relationship between the distance records and biophysical parameters. The terrestrial laser scanner (TLS) system consisted of a 2D time-of-flight LiDAR sensor, a gimbal to dynamically stabilize the sensor and a RTK-GPS to georeference its location and, subsequently, the sensor data. The sensor and its stabilizer were fixed facing downwards, on a metal frame designed for this purpose. Then, it was mounted on an all-terrain vehicle to perform 2D scans in planes perpendicular to the travel direction. Distances between the sensor and the surrounding objects had a high spatial resolution, providing high density 3D point clouds. Results on the reliability of the LiDAR system to estimate plant height showed a significant relationship between the sensor readings and actual poplar height and biomass data. In addition, tree biomass and tree volume were properly estimated in the point cloud. Regression analysis showed significant estimates of 0.79 and 0.89 for biomass and volume, respectively. These results reveal the potential of the LiDAR sensor to estimate both, plant height and plant biomass. This sensor's capability, added to its relative low cost, fast reaction, and the high number of readings per second consolidate the ideal system for estimating the productivity of biomass in energy crops. http://link.springer.com/article/10.1007%2Fs10343-016-0369-1, This research was funded by the CICyT (Commision Interministerial de Ciencia y Tecnología, Spain), under Agreement No. AGL2011-25243 and AGL2014-52465-C4.
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Merge Fuzzy Visual Servoing and GPS-Based Planning to Obtain a Proper Navigation Behavior for a Small Crop-Inspection Robot

  • Bengochea-Guevara, José M.
  • Conesa-Muñoz, Jesús
  • Andújar, Dionisio
  • Ribeiro Seijas, Ángela
The authors wish to thank Pedro Hernáiz and his team (ICA-CSIC) for their invaluable help in the field trials. The authors wish to acknowledge the invaluable technical support of Damian Rodriguez. Author Contributions: The work was developed as a collaboration among all authors. J.M. Bengochea-Guevara and A Ribeiro designed the study. J.M. Bengochea-Guevara carried out the system integration and programming. D. Andújar posed the field experiments. J. Conesa-Muñoz mainly contributed to the development of the planner and provided support in the field tests with D. Andújar. A. Ribeiro directed the research, collaborating in the testing and the discussion of the results. The manuscript was mainly drafted by J.M. Bengochea-Guevara and A. Ribeiro and was revised and corrected by all co-authors. All authors have read and approved the final manuscript., The concept of precision agriculture, which proposes farming management adapted to crop variability, has emerged in recent years. To effectively implement precision agriculture, data must be gathered from the field in an automated manner at minimal cost. In this study, a small autonomous field inspection vehicle was developed to minimise the impact of the scouting on the crop and soil compaction. The proposed approach integrates a camera with a GPS receiver to obtain a set of basic behaviours required of an autonomous mobile robot to inspect a crop field with full coverage. A path planner considered the field contour and the crop type to determine the best inspection route. An image-processing method capable of extracting the central crop row under uncontrolled lighting conditions in real time from images acquired with a reflex camera positioned on the front of the robot was developed. Two fuzzy controllers were also designed and developed to achieve vision-guided navigation. A method for detecting the end of a crop row using camera-acquired images was developed. In addition, manoeuvres necessary for the robot to change rows were established. These manoeuvres enabled the robot to autonomously cover the entire crop by following a previously established plan and without stepping on the crop row, which is an essential behaviour for covering crops such as maize without damaging them., The Spanish Government has provided full and continuing support for this research work through projects AGL2011-30442-C02–02 and AGL2014-52465-C4-3-R., We acknowledge support by the CSIC Open Access Publication Initiative through its Unit of Information Resources for Research (URICI)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

An Approach to the Use of Depth Cameras for Weed Volume Estimation

  • Andújar, Dionisio
  • Dorado, José
  • Fernández-Quintanilla, César
  • Ribeiro Seijas, Ángela
The use of depth cameras in precision agriculture is increasing day by day. This type of sensor has been used for the plant structure characterization of several crops. However, the discrimination of small plants, such as weeds, is still a challenge within agricultural fields. Improvements in the new Microsoft Kinect v2 sensor can capture the details of plants. The use of a dual methodology using height selection and RGB (Red, Green, Blue) segmentation can separate crops, weeds, and soil. This paper explores the possibilities of this sensor by using Kinect Fusion algorithms to reconstruct 3D point clouds of weed-infested maize crops under real field conditions. The processed models showed good consistency among the 3D depth images and soil measurements obtained from the actual structural parameters. Maize plants were identified in the samples by height selection of the connected faces and showed a correlation of 0.77 with maize biomass. The lower height of the weeds made RGB recognition necessary to separate them from the soil microrelief of the samples, achieving a good correlation of 0.83 with weed biomass. In addition, weed density showed good correlation with volumetric measurements. The canonical discriminant analysis showed promising results for classification into monocots and dictos. These results suggest that estimating volume using the Kinect methodology can be a highly accurate method for crop status determination and weed detection. It offers several possibilities for the automation of agricultural processes by the construction of a new system integrating these sensors and the development of algorithms to properly process the information provided by them., The Spanish Ministry of Economy and Competitiveness has provided support for this research via projects AGL2014-52465-C4-3-R and AGL2014-52465-C4-1-R, and Bosch Foundation. We acknowledge support by the CSIC Open Access Publication Initiative through its Unit of Information Resources for Research (URICI).
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Últimos avances en tecnologías para la detección y el control de las malas hierbas

  • Fernández-Quintanilla, César
  • Dorado, José
  • Andújar, Dionisio
  • Peña Barragán, José Manuel
  • Ribeiro Seijas, Ángela
  • Castro, Ana Isabel de
  • López Granados, Francisca
Durante los últimos años el desarrollo de nuevas tecnologías para la agricultura de precisión ha alcanzado un considerable grado de madurez. En el ámbito específico de la gestión de las malas hierbas se han desarrollado numerosas tecnologías tanto de detección como de actuación. A los procedimientos disponibles para la detección desde satélite o d,esde avión se han unido otros mucho más precisos para la detección desde drones volando a baja altura. Por otro lado, la disponibilidad actual de sensores y cámaras 2D y 3D de muy alta resolución y de ordenadores más rápidos capaces de procesar grandes volúmenes de datos abre la posibilidad de llevar a cabo actuaciones en tiempo real. En este trabajo se expone una breve síntesis de los últimos avances producidos en sistemas de detección aérea y terrestre así como de algunos de los equipos inteligentes disponibles para el control físico o químico de las malas hierbas detectadas., Parte de los trabajos expuestos están siendo financiados por los proyectos AGL2014-52465-C4-1R; C4-3R y C4-4R integrados todos en un proyecto coordinado (Ministerio de Economía y Competitividad, fondos FEDER: Fondo Europeo de Desarrollo Regional)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

A Geometrical Model to Predict the Spatial Expansion of Sorghum Halepense in Maize Fields

  • Andújar, Dionisio
  • Rodriguez, X.
  • Rueda-Ayala, Víctor
  • Ribeiro Seijas, Ángela
  • Fernández Quintanilla, Cesar
  • Dorado, Jose
New technologies, such as Differential Global Positioning Systems (DGPS) and Geographic Information Systems (GIS), may be useful in order to create models to predict the spatio-temporal behaviour of weeds. The aim of this study was to generate a geometric model able to predict the patch expansion of S. halepense, a problematic perennial weed in maize crops in Central Spain. From previous infestation maps, the model describes new possible spreading areas for the upcoming growing season, and therefore, herbicide treatments can be planned on time. Two different experiments were implemented, in which initial patch density and size were examined. Patches of different size (1, 10 and 100 m2) and density (4, 20 and 100 shoots m−2), were established. These patches were visually identified, their perimeter defined and their density characterized, during three growing seasons (from 2008 to 2010 campaigns). According to this information different descriptors were built: (1) area and density of each patch; (2) the relative growth in width and length, according to space and time and compared with previous years; and (3) the increased density ratio, calculated in relation of patch size and distance to previous patch in the new infestation areas of expansion. All these descriptors were added to the model in order to predict the patch expansion in the last studied season (i. e., 2010) using previous maps (i. e., season 2008 and 2009). The model uses geometrical assimilation to predict, and two expansion assumptions were considered: (a) a conservative approach based on triangular geometry; and (b) a rectangular geometry which maximizes the simulated infested area. The results were compared with the ground truth map created in 2010. Each method showed weaknesses and strengths. The triangular approach minimized the infested area, mainly in the small patches, and therefore it could predict the expansion of previously established patches, but not the emergence of new ones. In contrast, the rectangular approach simulated the position of new foci, maximizing the infested area. Therefore, although a substantial reduction of herbicides is possible using both models, a final decision must be taken individually for each field., The Spanish Ministry of Economy and Competitiveness has provided support for this research via project AGL2014-52465-C4-3., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Using depth cameras to extract structural parameters to assess the growth state and yield of cauliflower crops

  • Andújar, Dionisio
  • Ribeiro Seijas, Ángela
  • Fernández Quintanilla, César
  • Dorado, José
The use of robotic systems for horticultural crops is widely known. However, the use of these systems in cruciferous vegetables remains a challenge. The case of cauliflower crops is of special relevance because it is a hand-harvested crop for which the cutting time is visually chosen. This methodology leads to a yield reduction, as some inflorescences are cut before ripening because the leaves hide their real state of maturity. This work proposes the use of depth cameras instead of visual estimation. Using Kinect Fusion algorithms, depth cameras create a 3D point cloud from the depth video stream and consequently generate solid 3D models, which have been compared to the actual structural parameters of cauliflower plants. The results show good consistency among depth image models and ground truth from the actual structural parameters. In addition, the best time for individual fruit cutting could be detected using these models, which enabled the optimization of harvesting and increased yields. The accuracy of the models deviated from the ground truth by less than 2 cm in diameter/height, whereas the fruit volume estimation showed an error below 0.6% overestimation. Analysis of the structural parameters revealed a significant correlation between estimated and actual values of the volume of plants and fruit weight. These results show the potential of depth cameras to be used as a precise tool in estimating the degree of ripeness during the harvesting of cauliflower and thereby optimizing the crop profitability., The Spanish Ministry of Economy and Competitiveness has provided support for this research via projects: AGL2011-25243 and AGL2014-52465-C4-3-R., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Merge Fuzzy Visual Servoing and GPS-Based Planning to Obtain a Proper Navigation Behavior for a Small Crop-Inspection Robot

  • Bengochea Guevara, José M.
  • Conesa Muñoz, Jesús
  • Andújar, Dionisio
  • Ribeiro Seijas, Ángela
The concept of precision agriculture, which proposes farming management adapted to crop variability, has emerged in recent years. To effectively implement precision agriculture, data must be gathered from the field in an automated manner at minimal cost. In this study, a small autonomous field inspection vehicle was developed to minimise the impact of the scouting on the crop and soil compaction. The proposed approach integrates a camera with a GPS receiver to obtain a set of basic behaviours required of an autonomous mobile robot to inspect a crop field with full coverage. A path planner considered the field contour and the crop type to determine the best inspection route. An image-processing method capable of extracting the central crop row under uncontrolled lighting conditions in real time from images acquired with a reflex camera positioned on the front of the robot was developed. Two fuzzy controllers were also designed and developed to achieve vision-guided navigation. A method for detecting the end of a crop row using camera-acquired images was developed. In addition, manoeuvres necessary for the robot to change rows were established. These manoeuvres enabled the robot to autonomously cover the entire crop by following a previously established plan and without stepping on the crop row, which is an essential behaviour for covering crops such as maize without damaging them, The Spanish Government has provided full and continuing support for this research work through projects AGL2011-30442-C02–02 and AGL2014-52465-C4-3-R. The authors wish to thank Pedro Hernáiz and his team (ICA-CSIC) for their invaluable help in the field trials. The authors wish to acknowledge the invaluable technical support of Damian Rodriguez., Peer reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

A LiDAR-Based System to Assess Poplar Biomass

  • Andújar, Dionisio
  • Escolà i Agustí, Alexandre
  • Rosell Polo, Joan Ramon
  • Sanz Cortiella, Ricardo
  • Rueda-Ayala, Victor
  • Fernandez Quintanilla, C.
  • Ribeiro, Angela
  • Dorado, José
This study evaluated the capabilities of a LiDAR-based system to characterize poplar trees for biomass production. The precision of the system was assessed by analyzing the relationship between the distance records and biophysical parameters. The terrestrial laser scanner (TLS) system consisted of a 2D time-of-flight LiDAR sensor, a gimbal to dynamically stabilize the sensor and a RTK-GPS to georeference its location and, subsequently, the sensor data. The sensor and its stabilizer were fixed facing downwards, on a metal frame designed for this purpose. Then, it was mounted on an all-terrain vehicle to perform 2D scans in planes perpendicular to the travel direction. Distances between the sensor and the surrounding objects had a high spatial resolution, providing high density 3D point clouds. Results on the reliability of the LiDAR system to estimate plant height showed a significant relationship between the sensor readings and actual poplar height and biomass data. In addition, tree biomass and tree volume were properly estimated in the point cloud. Regression analysis showed significant estimates of 0.79 and 0.89 for biomass and volume, respectively. These results reveal the potential of the LiDAR sensor to estimate both, plant height and plant biomass. This sensor's capability, added to its relative low cost, fast reaction, and the high number of readings per second consolidate the ideal system for estimating the productivity of biomass in energy crops. http://link.springer.com/article/10.1007%2Fs10343-016-0369-1, This research was funded by the CICyT (Commision Interministerial de Ciencia y Tecnología, Spain), under Agreement No. AGL2011-25243 and AGL2014-52465-C4.