Pasar al contenido principal

VISION POR COMPUTADOR EGOCENTRICA PARA LA INTERACCION CON EL ENTORNO DE PERSONAS CON DISCAPACIDAD VISUAL

DPI2015-65962-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 2015
Plan Estatal 2013-2016 Plan Estatal de Investigación Científica y Técnica y de Innovación
Unidad de gestión Dirección General de Investigación Científica y Técnica
Centro beneficiario UNIVERSIDAD DE ZARAGOZA
Identificador persistente http://dx.doi.org/10.13039/501100003329

Resultados relacionados

Resultados totales (Incluyendo duplicados): 15
Encontrada(s) 1 página(s)

Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Building an enhanced vocabulary of the robot environment with a ceiling pointing camera

  • Rituerto, A.
  • Andreasson, H.
  • Murillo, A.C.
  • Lilienthal, A.
  • Guerrero, J.J.
Mobile robots are of great help for automatic monitoring tasks in different environments. One of the first tasks that needs to be addressed when creating these kinds of robotic systems is modeling the robot environment. This work proposes a pipeline to build an enhanced visual model of a robot environment indoors. Vision based recognition approaches frequently use quantized feature spaces, commonly known as Bag of Words (BoW) or vocabulary representations. A drawback using standard BoW approaches is that semantic information is not considered as a criteria to create the visual words. To solve this challenging task, this paper studies how to leverage the standard vocabulary construction process to obtain a more meaningful visual vocabulary of the robot work environment using image sequences. We take advantage of spatio-temporal constraints and prior knowledge about the position of the camera. The key contribution of our work is the definition of a new pipeline to create a model of the environment. This pipeline incorporates (1) tracking information to the process of vocabulary construction and (2) geometric cues to the appearance descriptors. Motivated by long term robotic applications, such as the aforementioned monitoring tasks, we focus on a configuration where the robot camera points to the ceiling, which captures more stable regions of the environment. The experimental validation shows how our vocabulary models the environment in more detail than standard vocabulary approaches, without loss of recognition performance. We show different robotic tasks that could benefit of the use of our visual vocabulary approach, such as place recognition or object discovery. For this validation, we use our publicly available data-set.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Wearable Structured Light System in Non-Rigid Configuration

  • Paniagua, Carmen
  • López-Nicolás, Gonzalo
  • Guerrero, J.J.
Traditionally, structured light methods have been studied in rigid configurations. In these configurations the position and orientation between the light emitter and the camera are fixed and known beforehand. In this paper we break with this rigidness and present a new structured light system in non-rigid configuration. This system is composed by a wearable standard perspective camera and a simple laser emitter. Our non-rigid configuration permits free motion of the light emitter with respect to the camera. The point-based pattern emitted by the laser permits us to easily establish correspondences between the image from the camera and a virtual one generated from the light emitter. Using these correspondences, our method computes rotation and translation up to scale of the planes of the scene where the point pattern is projected and reconstructs them. This constitutes a very useful tool for navigation applications in indoor environments, which are mainly composed of planar surfaces.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Improving Robot Mobility by Combining Downward-Looking and Frontal Cameras

  • Gonzalez, Ramon
  • Rituerto, Alejandro
  • Guerrero, J.J.
This paper presents a novel attempt to combine a downward-looking camera and a forward-looking camera for terrain classification in the field of off-road mobile robots. The first camera is employed to identify the terrain beneath the robot. This information is then used to improve the classification of the forthcoming terrain acquired from the frontal camera. This research also shows the usefulness of the Gist descriptor for terrain classification purposes. Physical experiments conducted in different terrains (quasi-planar terrains) and different lighting conditions, confirm the satisfactory performance of this approach in comparison with a simple color-based classifier based only on frontal images. Our proposal substantially reduces the misclassification rate of the color-based classifier (~10% versus ~20%).
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

A generic tool for interactive complex image editing

  • Cambra, Ana B.
  • Murillo, Ana C.
  • Muñoz, Adolfo
Plenty of complex image editing techniques require certain per-pixel property or magnitude to be known, e.g., simulating depth of field effects requires a depth map. This work presents an efficient interaction paradigm that approximates any per-pixel magnitude from a few user strokes by propagating the sparse user input to each pixel of the image. The propagation scheme is based on a linear least-squares system of equations which represents local and neighboring restrictions over superpixels. After each user input, the system responds immediately, propagating the values and applying the corresponding filter. Our interaction paradigm is generic, enabling image editing applications to run at interactive rates by changing just the image processing algorithm, but keeping our proposed propagation scheme. We illustrate this through three interactive applications: depth of field simulation, dehazing and tone mapping.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Stairs detection with odometry-aided traversal from a wearable RGB-D camera

  • Perez-Yus, A.
  • Gutierrez-Gomez, D.
  • Lopez-Nicolas, G.
  • Guerrero, J. J.
Stairs are one of the most common structures present in human-made scenarios, but also one of the most dangerous for those with vision problems. In this work we propose a complete method to detect, locate and parametrise stairs with a wearable RGB-D camera. Our algorithm uses the depth data to determine if the horizontal planes in the scene are valid steps of a staircase judging their dimensions and relative positions. As a result we obtain a scaled model of the staircase with the spatial location and orientation with respect to the subject. The visual odometry is also estimated to continuously recover the current position and orientation of the user while moving. This enhances the system giving the ability to come back to previously detected features and providing location awareness of the user during the climb. Simultaneously, the detection of the staircase during the traversal is used to correct the drift of the visual odometry. A comparison of results of the stair detection with other state-of-the-art algorithms was performed using public dataset. Additional experiments have also been carried out, recording our own natural scenes with a chest-mounted RGB-D camera in indoor scenarios. The algorithm is robust enough to work in real-time and even under partial occlusions of the stair.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Integration of in vitro and in silico Models Using Bayesian Optimization With an Application to Stochastic Modeling of Mesenchymal 3D Cell Migration

  • Merino-Casallo, F.
  • Gomez-Benito, M.J.
  • Juste-Lanas, Y.
  • Martinez-Cantin, R.
  • Garcia-Aznar, J.M.
Cellular migration plays a crucial role in many aspects of life and development. In this paper, we propose a computational model of 3D migration that is solved by means of the tau-leaping algorithm and whose parameters have been calibrated using Bayesian optimization. Our main focus is two-fold: to optimize the numerical performance of the mechano-chemical model as well as to automate the calibration process of in silico models using Bayesian optimization. The presented mechano-chemical model allows us to simulate the stochastic behavior of our chemically reacting system in combination with mechanical constraints due to the surrounding collagen-based matrix. This numerical model has been used to simulate fibroblast migration. Moreover, we have performed in vitro analysis of migrating fibroblasts embedded in 3D collagen-based fibrous matrices (2 mg/ml). These in vitro experiments have been performed with the main objective of calibrating our model. Nine model parameters have been calibrated testing 300 different parametrizations using a completely automatic approach. Two competing evaluation metrics based on the Bhattacharyya coefficient have been defined in order to fit the model parameters. These metrics evaluate how accurately the in silico model is replicating in vitro measurements regarding the two main variables quantified in the experimental data (number of protrusions and the length of the longest protrusion). The selection of an optimal parametrization is based on the balance between the defined evaluation metrics. Results show how the calibrated model is able to predict the main features observed in the in vitro experiments.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Exploiting line metric reconstruction from non-central circular panoramas

  • Bermudez-Cameo, J.
  • Saurer, O.
  • Lopez-Nicolas, G.
  • Guerrero, J.J.
  • Pollefeys, M.
In certain non-central imaging systems, straight lines are projected via a non-planar surface encapsulating the 4 degrees of freedom of the 3D line. Consequently the geometry of the 3D line can be recovered from a minimum of four image points. However, with classical non-central catadioptric systems there is not enough effective baseline for a practical implementation of the method. In this paper we propose a multi-camera system configuration resembling the circular panoramic model which results in a particular non-central projection allowing the stitching of a non-central panorama. From a single panorama we obtain well-conditioned 3D reconstruction of lines, which are specially interesting in texture-less scenarios. No previous information about the direction or arrangement of the lines in the scene is assumed. The proposed method is evaluated on both synthetic and real images.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Extrinsic Calibration of Multiple RGB-D Cameras From Line Observations

  • Perez-Yus, A.
  • Fernandez-Moral, E.
  • Lopez-Nicolas, G.
  • Guerrero, J.J.
  • Rives, P.
This letter presents a novel method to estimate the relative poses between RGB and depth cameras without the requirement of an overlapping field of view, thus providing flexibility to calibrate a variety of sensor configurations. This calibration problem is relevant to robotic applications that can benefit of using several cameras to increase the field of view. In our approach, we extract and match lines of the scene in the RGB and depth cameras, and impose geometric constraints to find the relative poses between the sensors. An analysis of the observability properties of the problem is presented. We have validated our method in both synthetic and real scenarios with different camera configurations, demonstrating that our approach achieves good accuracy and is very simple to apply, in contrast with previous methods based on trajectory matching using visual odometry or simultaneous localization and mapping.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

A multimodal dataset for object model learning from natural human-robot interaction

  • Azagra, P.
  • Golemo, F.
  • Mollard, Y.
  • Lopes, M.
  • Civera, J.
  • Murillo, A.C.
Learning object models in the wild from natural human interactions is an essential ability for robots to perform general tasks. In this paper we present a robocentric multimodal dataset addressing this key challenge. Our dataset focuses on interactions where the user teaches new objects to the robot in various ways. It contains synchronized recordings of visual (3 cameras) and audio data which provide a challenging evaluation framework for different tasks. Additionally, we present an end-to-end system that learns object models using object patches extracted from the recorded natural interactions. Our proposed pipeline follows these steps: (a) recognizing the interaction type, (b) detecting the object that the interaction is focusing on, and (c) learning the models from the extracted data. Our main contribution lies in the steps towards identifying the target object patches of the images. We demonstrate the advantages of combining language and visual features for the interaction recognition and use multiple views to improve the object modelling. Our experimental results show that our dataset is challenging due to occlusions and domain change with respect to typical object learning frameworks. The performance of common out-of-the-box classifiers trained on our data is low. We demonstrate that our algorithm outperforms such baselines.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Fitting line projections in non-central catadioptric cameras with revolution symmetry

  • Bermúdez-Cameo, Jesús
  • López-Nicolás, Gonzalo
  • Guerrero, José J.
Line-images in non-central cameras contain much richer information of the original 3D line than line projections in central cameras. The projection surface of a 3D line in most catadioptric non-central cameras is a ruled surface, encapsulating the complete information of the 3D line. The resulting line-image is a curve which contains the 4 degrees of freedom of the 3D line. That means a qualitative advantage with respect to the central case, although extracting this curve is quite difficult. In this paper, we focus on the analytical description of the line-images in non-central catadioptric systems with symmetry of revolution. As a direct application we present a method for automatic line-image extraction for conical and spherical calibrated catadioptric cameras. For designing this method we have analytically solved the metric distance from point to line-image for non-central catadioptric systems. We also propose a distance we call effective baseline measuring the quality of the reconstruction of a 3D line from the minimum number of rays. This measure is used to evaluate the different random attempts of a robust scheme allowing to reduce the number of trials in the process. The proposal is tested and evaluated in simulations and with both synthetic and real images.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Integrating an autonomous robot on a dance and new technologies festival

  • Abad, P.
  • Franco, M.
  • Castillón, R.
  • Alonso, I.
  • Cambra, A.
  • Sierra, J.
  • Riazuelo, L.
  • Montano, L.
  • Murillo, A.C.
This paper presents the results of a project to integrate an autonomous mobile robot into a modern dance performance at a dance and new technologies festival. The main goal is to integrate a simple low cost mobile robot into the dance performance, in order to study the possibilities that this kind of platforms can offer to the artists. First, this work explains the process and design to embed the robotic platform into the choreography theme. Another contribution described in this work is the system architecture proposed and built to make the robot behaviours match the artists requirements: precise, synchronized and robust robot movements. Finally, we discuss the main issues and lessons learned for this kind of robotics and arts applications and summarize the results obtained, including the successful final live performance results.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Semantic and structural image segmentation for prosthetic vision

  • Sanchez-Garcia, M.
  • Martinez-Cantin, R.
  • Guerrero, J. J.
Prosthetic vision is being applied to partially recover the retinal stimulation of visually impaired people. However, the phosphenic images produced by the implants have very limited information bandwidth due to the poor resolution and lack of color or contrast. The ability of object recognition and scene understanding in real environments is severely restricted for prosthetic users. Computer vision can play a key role to overcome the limitations and to optimize the visual information in the prosthetic vision, improving the amount of information that is presented. We present a new approach to build a schematic representation of indoor environments for simulated phosphene images. The proposed method combines a variety of convolutional neural networks for extracting and conveying relevant information about the scene such as structural informative edges of the environment and silhouettes of segmented objects. Experiments were conducted with normal sighted subjects with a Simulated Prosthetic Vision system. The results show good accuracy for object recognition and room identification tasks for indoor scenes using the proposed approach, compared to other image processing methods.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Fully distributed Bayesian optimization with stochastic policies

  • Garcia-Barcos, J.
  • Martinez-Cantin, R.
Bayesian optimization has become a popular method for high-throughput computing, like the design of computer experiments or hyperparameter tuning of expensive models, where sample efficiency is mandatory. In these applications, distributed and scalable architectures are a necessity. However, Bayesian optimization is mostly sequential. Even parallel variants require certain computations between samples, limiting the parallelization bandwidth. Thompson sampling has been previously applied for distributed Bayesian optimization. But, when compared with other acquisition functions in the sequential setting, Thompson sampling is known to perform suboptimally. In this paper, we present a new method for fully distributed Bayesian optimization, which can be combined with any acquisition function. Our approach considers Bayesian optimization as a partially observable Markov decision process. In this context, stochastic policies, such as the Boltzmann policy, have some interesting properties which can also be studied for Bayesian optimization. Furthermore, the Boltzmann policy trivially allows a distributed Bayesian optimization implementation with high level of parallelism and scalability. We present results in several benchmarks and applications that show the performance of our method.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Bayesian optimization with adaptive kernels for robot control

  • Martinez-Cantin, R.
Active policy search combines the trial-and-error methodology from policy search with Bayesian optimization to actively find the optimal policy. First, policy search is a type of reinforcement learning which has become very popular for robot control, for its ability to deal with complex continuous state and action spaces. Second, Bayesian optimization is a sample efficient global optimization method that uses a surrogate model, like a Gaussian process, and optimal decision making to carefully select each sample during the optimization process. Sample efficiency is of paramount importance when each trial involves the real robot, expensive Monte Carlo runs, or a complex simulator. Black-box Bayesian optimization generally assumes a cost function from a stationary process, because nonstationary modeling is usually based on prior knowledge. However, many control problems are inherently nonstationary due to their failure conditions, terminal states and other abrupt effects. In this paper, we present a kernel function specially designed for Bayesian optimization, that allows nonstationary modeling without prior knowledge, using an adaptive local region. The new kernel results in an improved local search (exploitation), without penalizing the global search (exploration), as shown experimentally in well-known optimization benchmarks and robot control scenarios. We finally show its potential for the design of the wing shape of a UAV.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Funneled Bayesian Optimization for Design, Tuning and Control of Autonomous Systems

  • Martinez Cantin, Ruben
In this paper, we tackle several problems that appear in robotics and autonomous systems: algorithm tuning, automatic control, and intelligent design. All those problems share in common that they can be mapped to global optimization problems where evaluations are expensive. Bayesian optimization (BO) has become a fundamental global optimization algorithm in many problems where sample efficiency is of paramount importance. BO uses a probabilistic surrogate model to learn the response function and reduce the number of samples required. Gaussian processes (GPs) have become a standard surrogate model for their flexibility to represent a distribution over functions. In a black-box settings, the common assumption is that the underlying function can be modeled with a stationary GP. In this paper, we present a novel kernel function specially designed for BO, that allows nonstationary behavior of the surrogate model in an adaptive local region. This kernel is able to reconstruct nonstationarity even with the irregular sampling distribution that arises from BO. Furthermore, in our experiments, we found that this new kernel results in an improved local search (exploitation), without penalizing the global search (exploration) in many applications. We provide extensive results in well-known optimization benchmarks, machine learning hyperparameter tuning, reinforcement learning, and control problems, and UAV wing optimization. The results show that the new method is able to outperform the state of the art in BO both in stationary and nonstationary problems.