RUA
(10.025 recursos)
Este sitio es un repositorio institucional para facilitar el acceso a las publicaciones producidas por los miembros de la universidad. La interfaz del sitio está disponible en parte en español y en parte en Inglés. Un canal RSS está disponible para que los usuarios se mantengan al día con los nuevos materiales añadidos. El sitio dispone de ayuda en español solamente.
Mostrando recursos 1 - 9 de 9
1.
Three-dimensional mapping from stereo images with geometrical rectification - Gallego Sánchez, Antonio Javier; Molina Carmona, Rafael; Villagrá Arnedo, Carlos
In this paper we present a method for mapping 3D unknown environments from stereo images. It is based on a dense disparity image obtained by a process of window correlation. To each image in the sequence a geometrical rectification process is applied, which is essential to remove the conical perspective of the images obtained with a photographic camera. This process corrects the errors in coordinates x and y to obtain a better matching for the map information. The mapping method is an application of the geometrical rectification and the 3D reconstruction, whose main purpose is to obtain a realistic appearance...
2.
Three-dimensional mapping from stereo images with geometrical rectification - Gallego Sánchez, Antonio Javier; Molina Carmona, Rafael; Villagrá Arnedo, Carlos
In this paper we present a method for mapping 3D unknown environments from stereo images. It is based on a dense disparity image obtained by a process of window correlation. To each image in the sequence a geometrical rectification process is applied, which is essential to remove the conical perspective of the images obtained with a photographic camera. This process corrects the errors in coordinates x and y to obtain a better matching for the map information. The mapping method is an application of the geometrical rectification and the 3D reconstruction, whose main purpose is to obtain a realistic appearance...
3.
Applying distance histograms for robust object recognition - Arques Corrales, Pilar; Pujol López, Francisco Antonio; Llorens Largo, Faraón; Pujol López, Mar; Rizo Aldeguer, Ramón
One of the main goals of vision systems is to recognize objects in real world to perform appropriate actions. This implies the ability of handling objects and, moreover, to know the relations between these objects and their environment in what we call scenes. Most of the time, navigation in unknown environments is difficult due to a lack of easily identifiable landmarks. Hence, in this work, some geometric features to identify objects are considered. Firstly, a Markov random field segmentation approach is implemented. Then, the key factor for the recognition is the calculation of the so-called distance histograms, which relate the...
4.
3D robot mapping : combining active and non active sensors in a probabilistic framework - Aznar Gregori, Fidel; Sempere Tortosa, Mireia Luisa; Pujol López, Mar; Rizo Aldeguer, Ramón; Molina Carmona, Rafael
Map reconstruction and robot location are two essential problems in the field of robotics and artificial intelligence. A robot could need a model of the environment that can be incomplete and therefore the robot must work considering the uncertainty. Bayesian Units consider the uncertainty and allow the fusion of information from different sensors. In this paper a map reconstruction system in 3D based on Bayesian Units is presented. The reconstruction is carried out integrating the data obtained by a laser and by an omnivision system. In addition, to improve the quality of the reconstruction, the fusion of several Bayesian Units...
5.
Real time image segmentation using an adaptive thresholding approach - Arques Corrales, Pilar; Aznar Gregori, Fidel; Pujol López, Mar; Rizo Aldeguer, Ramón
The aim of image segmentation is the partition of the image in homogeneous regions. In this paper we propose an approximation based on Markov Random Fields (MRF) able to perform correct
segmentation in real time using colour information. In a first approximation a simulated annealing approach is used to obtain the optimal segmentation. This segmentation will be improved using an
adaptive threshold algorithm, to achieve real time. The experiment results using the proposed segmentation prove its correctness, both for the obtained labelling and for the response time.
6.
A new artificial life formalization model : a worm with a Bayesian brain - Aznar Gregori, Fidel; Pujol López, Mar; Rizo Aldeguer, Ramón; Suau Pérez, Pablo
This paper shows an application of Bayesian Programming to model a simple artificial life problem: that of a worm trying to live in a world full of poison. Any model of a real phenomenon is incomplete because there will always exist unknown, hidden variables that influence the phenomenon. To solve this problem we apply a new formalism, Bayesian programming, which has previously been used in autonomous robot programming. The proposed worm model has been used to train a population of worms using genetic algorithms. We will see the advantages of our method compared with a classical approach. Finally, we discuss...
7.
A cybernetic multiresolution system for disparity estimation in stereo vision - Compañ Rosique, Patricia; Satorre Cuerda, Rosana; Rizo Aldeguer, Ramón
Purpose:
Our aim is obtaining a dense and reliable disparity map from a stereoscopic pair under any luminosity condition.
From the disparity map it is possible to obtain some information about the objects appearing in the scene, such as their position and their distance to the camera.
Design:
The disparity map is obtained using a correspondence method based on a multiresolution scheme. It also uses the Simulated Annealing Algorithm to minimize the energy function, which integrates information coming from several sources: grey levels, non-parametric transforms, edges and geometrical constraints. The multiresolution scheme allows us to interpolate the disparity map obtained in each level and...
8.
Rectified reconstruction from stereo pairs and robot mapping - Gallego Sánchez, Antonio Javier; Molina Carmona, Rafael; Compañ Rosique, Patricia; Villagrá Arnedo, Carlos
The reconstruction and mapping of real scenes is a crucial element in several fields such as robot navigation. Stereo vision can be a powerful solution. However the perspective effect arises, as well as other problems, when the reconstruction is tackled using depth maps obtained from stereo images. A new approach is proposed to avoid the perspective effect, based on a geometrical rectification using the vanishing point of the image. It also uses sub-pixel precision to solve the lack of information for distant objects. Finally, the method is applied to map a whole scene, introducing a cubic filter.
9.
Driving bots with a neuroevolved brain : Screaming Racers - Gallego Durán, Francisco; Llorens Largo, Faraón; Pujol López, Mar; Rizo Aldeguer, Ramón
The Videogame Industry of today is now just as strong as, and generates similar revenues to the Film Industry. Computer Games are distributed throughout the world and are sold to millions of people. Of the many different types of games, one of the most popular genres is car racing. Developers of this type of game are increasingly improving their Artificial Intelligence Systems so that their virtual drivers can exhibit Human-Level behaviours, and even higher. In this paper we show how these virtual drivers can be generically evolved using Neuroevolution, so obtaining several, distinct driving-bots with an increasing level of performance....
1.
