José Tomás García

2012 Special Issue: Using GNG to improve 3D feature extraction-Application to 6DoF egomotion

Several recent works deal with 3D data in mobile robotic problems, e.g. mapping or egomotion. Data comes from any kind of sensor such as stereo vision systems, time of flight cameras or 3D lasers, providing a huge amount of unorganized 3D data. In this paper, we describe an efficient method to build complete 3D models from a Growing Neural Gas (GNG). The GNG is applied to the 3D raw data and it reduces both the subjacent error and the number of points, keeping the topology of the 3D data. The GNG output is then used in a 3D feature extraction method. We have performed a deep study in which we quantitatively show that the use of GNG improves the 3D feature extraction method. We also show that our method can be applied to any kind of 3D data. The 3D features obtained are used as input in an Iterative Closest Point (ICP)-like method to compute the 6DoF movement performed by a mobile robot. A comparison with standard ICP is performed, showing that the use of GNG improves the results. Final results of 3D mapping from the egomotion calculated are also shown.

Growing neural gas for vision tasks with time restrictions

Self-organizing neural networks try to preserve the topology of an input space by means of their competitive learning. This capacity is being used for the representation of objects and their motion. In addition, these applications usually have real-time constraints. In this work, diverse variants of a self-organizing network, the Growing Neural Gas, that allow an acceleration of the learning process are considered. However, this increase of speed causes that, in some cases, topology preservation is lost and, therefore, the quality of the representation. So, we have made a study to quantify topology preservation using different measures to establish the most suitable learning parameters, depending on the size of the network and on the available time for its adaptation.

Using 3D GNG-based reconstruction for 6DoF egomotion

Several recent works deal with 3D data in mobile robotic problems, e.g. mapping. Data come from any kind of sensor (time of flight cameras and 3D lasers) providing a huge amount of unorganized 3D data. In this paper we detail an efficient method to build complete 3D models from a Growing Neural Gas (GNG). We show that the use of GNG provides better results than other approaches. The GNG obtained is then applied to a sequence. From GNG structure, we propose to calculate planar patches and thus obtaining a fast method to compute the movement performed by a mobile robot by means of a 3D models registration algorithm. Final results of 3D mapping are also shown.

6DoF egomotion computing using 3D GNG-based reconstruction

Several recent works deal with 3D data in mobile robotic problems: mapping and SLAM related problems. Data come from any kind of sensor (time of flight cameras and 3D lasers) providing a huge amount of unorganized 3D data. In this paper we detail an efficient method to build complete 3D models from a Growing Neural Gass (GNG). The GNG obtained is then applied to a sequence. From neurons in the GNG, we propose to calculate planar patches and thus obtaining a fast method to compute the movement performed by a mobile robot by means of a 3D models registration algorithm.

Blogs: A learning tool proposal for an Audiovisual Engineering Course

Digital Signal Processors is an optional course in the Audiovisual Engineering Degree of the University of Alicante. This year a pilot project on developing a blog for the course has been introduced (http://blogs.ua.es/pds0910). This way, students must complete - working collaboratively- a set of assigned blog entries on different extension tasks related to the concepts taught in the theory sessions. The blog entries have been always supervised by the teaching staff, who act as system administrators, as well. Students had a very positive attitude towards this learning tool, allowing us to develop new strategies for the upcoming semesters.

Characterization and synthesis of objects using growing neural gas

In this article it is made a study of the characterization capacity and synthesis of objects of the self-organizing neural models. These networks, by means of their competitive learning, try to preserve the topology of an input space. This capacity is being used for the representation of objects and their movement with topology preserving networks. We characterized the object to represent by means of the obtained maps and kept information solely on the coordinates and the colour from the neurons. From this information it is made the synthesis of the original images, applying mathematical morphology and simple filters on the information which it is had.

Predictions tasks with words and sequences: Comparing a novel recurrent architecture with the Elman network

The classical connectionist models are not well suited to working with data varying over time. According to this, temporal connectionist models have emerged and constitute a continuously growing research field. In this paper we present a novel supervised recurrent neural network architecture (SARASOM) based on the Associative Self-Organizing Map (A-SOM). The A-SOM is a variant of the Self-Organizing Map (SOM) that develops a representation of its input space as well as learns to associate its activity with an arbitrary number of additional inputs. In this context the A-SOM learns to associate its previous activity with a delay of one iteration. The performance of the SARASOM was evaluated and compared with the Elman network in a number of prediction tasks using sequences of letters (including some experiments with a reduced lexicon of 10 words). The results are very encouraging with SARASOM learning slightly better than the Elman network.

Visual features extraction based egomotion calculation from a infrared time-of-flight camera

3D data have been used for robotics tasks in the last years. These data provide valuable information about the robot environment. Traditionally, stereo cameras has been used to obtain 3D data, but these kind of cameras do not provide information in the lack of texture. There is a new camera, SR4000, which uses infrared light in order to get richer information. In this paper we first analyze this camera. Then, we detail an efficient ICP-like method to build complete 3D models combining Growing Neural Gas (GNG) and visual features. First, we adapt the GNG to the 3D cloud points. Then, we propose the calculation of visual features and its registration to the elements of the GNG. Finally, we use correspondences between frames, an ICP-like method to calculate egomotion. Results of mapping from the egomotion are shown.

La sociología del sistema mundial como herramienta para el análisis multifactorial de las migraciones internacionales

In recent years there exists a critical trend from Social Science which intends to go beyond the classical approaches as regards migrations. However, the critical analysis is insufficient; it is necessary to develop methodological approaches which improve the studies applicability. This paper upholds the necessity for adapting structures and categories of analysis to a multi-factorial and multidisciplinary model with the aim of understanding in all its dimensions such a complex phenomenon as migrations are.