Group Sequential Communication (GSC): Especificação e Análise de Desempenho de umMecanismo de Comunicação de Tempo Real Compatível ao Padrão IEEE 802.11/11e Aplicado à Automação Industrial

This thesis proposes the specification and performance analysis of a real-time communication mechanism for IEEE 802.11/11e standard. This approach is called Group Sequential Communication (GSC). The GSC has a better performance for dealing with small data packets when compared to the HCCA mechanism by adopting a decentralized medium access control using a publish/subscribe communication scheme. The main objective of the thesis is the HCCA overhead reduction of the Polling, ACK and QoS Null frames exchanged between the Hybrid Coordinator and the polled stations. The GSC eliminates the polling scheme used by HCCA scheduling algorithm by using a Virtual Token Passing procedure among members of the real-time group to whom a high-priority and sequential access to communication medium is granted. In order to improve the reliability of the mechanism proposed into a noisy channel, it is presented an error recovery scheme called second chance algorithm. This scheme is based on block acknowledgment strategy where there is a possibility of retransmitting when missing real-time messages. Thus, the GSC mechanism maintains the real-time traffic across many IEEE 802.11/11e devices, optimized bandwidth usage and minimal delay variation for data packets in the wireless network. For validation purpose of the communication scheme, the GSC and HCCA mechanisms have been implemented in network simulation software developed in C/C++ and their performance results were compared. The experiments show the efficiency of the GSC mechanism, especially in industrial communication scenarios.

Detección automática con snakes y representación 3D sobre imágenes cerebrales

Comunicación presentada en la VI Conferencia de la Asociación Española para la Inteligencia Artificial (CAEPIA'95), Alicante, 15-17 noviembre 1995.

Deformable templates for plaque thickness estimation of intravascular ultrasound sequences

Comunicación presentada en el VII Symposium Nacional de Reconocimiento de Formas y Análisis de Imágenes, SNRFAI, Barcelona, abril 1997.

Snakes based tracking and texture analysis of microscopic images

Comunicación presentada en el VII Symposium Nacional de Reconocimiento de Formas y Análisis de Imágenes, SNRFAI, Barcelona, abril 1997.

Plantillas deformables espacio-temporales para el tracking y reconocimiento gestual

Comunicación presentada en la VII Conferencia de la Asociación Española para la Inteligencia Artificial, CAEPIA, Málaga, 12-14 noviembre, 1997.

Estimación del movimiento coherente: computación evolutiva como alternativa al annealing determinista

Comunicación presentada en SCETA, Seminario Sobre Computación Evolutiva, celebrado en la VII Conferencia de la Asociación Española para la Inteligencia Artificial, CAEPIA, Málaga, 12-14 noviembre 1997.

Deformable templates for tracking and analysis of intravascular ultrasound sequences

Deformable Template models are first applied to track the inner wall of coronary arteries in intravascular ultrasound sequences, mainly in the assistance to angioplasty surgery. A circular template is used for initializing an elliptical deformable model to track wall deformation when inflating a balloon placed at the tip of the catheter. We define a new energy function for driving the behavior of the template and we test its robustness both in real and synthetic images. Finally we introduce a framework for learning and recognizing spatio-temporal geometric constraints based on Principal Component Analysis (eigenconstraints).

A combined probabilistic framework for learning gestures and actions

In this paper we introduce a probabilistic approach to support visual supervision and gesture recognition. Task knowledge is both of geometric and visual nature and it is encoded in parametric eigenspaces. Learning processes for compute modal subspaces (eigenspaces) are the core of tracking and recognition of gestures and tasks. We describe the overall architecture of the system and detail learning processes and gesture design. Finally we show experimental results of tracking and recognition in block-world like assembling tasks and in general human gestures.

Estimación bayesiana de características en robots móviles mediante muestreo de la densidad a posteriori

Comunicación presentada en el I Congrés Català d’Intel·ligència Artificial, Tarragona, Octubre de 1998.

Bayesian models for finding and grouping junctions

In this paper, we propose two Bayesian methods for detecting and grouping junctions. Our junction detection method evolves from the Kona approach, and it is based on a competitive greedy procedure inspired in the region competition method. Then, junction grouping is accomplished by finding connecting paths between pairs of junctions. Path searching is performed by applying a Bayesian A* algorithm that has been recently proposed. Both methods are efficient and robust, and they are tested with synthetic and real images.

A study of a soft computing based method for 3D scenario reconstruction

Several recent works deal with 3D data in mobile robotic problems, e.g., mapping. Data comes from any kind of sensor (time of flight, Kinect or 3D lasers) that provide a huge amount of unorganized 3D data. In this paper we detail an efficient approach to build complete 3D models using a soft computing method, the Growing Neural Gas (GNG). As neural models deal easily with noise, imprecision, uncertainty or partial data, GNG provides better results than other approaches. The GNG obtained is then applied to a sequence. We present a comprehensive study on GNG parameters to ensure the best result at the lowest time cost. From this 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.

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.

GPGPU implementation of growing neural gas: application to 3D scene reconstruction

Self-organising neural models have the ability to provide a good representation of the input space. In particular the Growing Neural Gas (GNG) is a suitable model because of its flexibility, rapid adaptation and excellent quality of representation. However, this type of learning is time-consuming, especially for high-dimensional input data. Since real applications often work under time constraints, it is necessary to adapt the learning process in order to complete it in a predefined time. This paper proposes a Graphics Processing Unit (GPU) parallel implementation of the GNG with Compute Unified Device Architecture (CUDA). In contrast to existing algorithms, the proposed GPU implementation allows the acceleration of the learning process keeping a good quality of representation. Comparative experiments using iterative, parallel and hybrid implementations are carried out to demonstrate the effectiveness of CUDA implementation. The results show that GNG learning with the proposed implementation achieves a speed-up of 6× compared with the single-threaded CPU implementation. GPU implementation has also been applied to a real application with time constraints: acceleration of 3D scene reconstruction for egomotion, in order to validate the proposal.

Real-time 3D semi-local surface patch extraction using GPGPU

Feature vectors can be anything from simple surface normals to more complex feature descriptors. Feature extraction is important to solve various computer vision problems: e.g. registration, object recognition and scene understanding. Most of these techniques cannot be computed online due to their complexity and the context where they are applied. Therefore, computing these features in real-time for many points in the scene is impossible. In this work, a hardware-based implementation of 3D feature extraction and 3D object recognition is proposed to accelerate these methods and therefore the entire pipeline of RGBD based computer vision systems where such features are typically used. The use of a GPU as a general purpose processor can achieve considerable speed-ups compared with a CPU implementation. In this work, advantageous results are obtained using the GPU to accelerate the computation of a 3D descriptor based on the calculation of 3D semi-local surface patches of partial views. This allows descriptor computation at several points of a scene in real-time. Benefits of the accelerated descriptor have been demonstrated in object recognition tasks. Source code will be made publicly available as contribution to the Open Source Point Cloud Library.

Parallel Computational Intelligence-Based Multi-Camera Surveillance System

In this work, we present a multi-camera surveillance system based on the use of self-organizing neural networks to represent events on video. The system processes several tasks in parallel using GPUs (graphic processor units). It addresses multiple vision tasks at various levels, such as segmentation, representation or characterization, analysis and monitoring of the movement. These features allow the construction of a robust representation of the environment and interpret the behavior of mobile agents in the scene. It is also necessary to integrate the vision module into a global system that operates in a complex environment by receiving images from multiple acquisition devices at video frequency. Offering relevant information to higher level systems, monitoring and making decisions in real time, it must accomplish a set of requirements, such as: time constraints, high availability, robustness, high processing speed and re-configurability. We have built a system able to represent and analyze the motion in video acquired by a multi-camera network and to process multi-source data in parallel on a multi-GPU architecture.