Publication: Análisis de entornos urbanos de tráfico y estimación del movimiento del vehículo para el desarrollo de sistemas avanzados de ayuda a la conducción
Loading...
Identifiers
Publication date
2014
Defense date
2015-01-29
Authors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
Impact
Export
Abstract
Los entornos urbanos de tráfico representan, por su alta complejidad, un desafío para los sistemas inteligentes de transporte, debido a la gran variedad de situaciones y elementos diferentes que pueden acontecer en estos entornos y que deben ser manejadas por estos sistemas. A este respecto, las soluciones presentadas hasta el momento son variadas en lo concerniente a sensores y métodos, obteniendo estos trabajos resultados muy dispares de precisión, complejidad, coste o carga computacional.
El trabajo presentado en esta disertación, desarrolla un conjunto de algoritmos y métodos para dar soporte a la implementación de una gran variedad de sistemas avanzados de ayuda a la conducción o navegación autónoma en estos entornos. El sistema descrito se basa en el análisis del entorno del vehículo y la estimación del movimiento del mismo mediante el empleo de un sistema de visión estereoscópica, donde se ha prestado una especial atención, a la hora de definir las características del desarrollo, a posibilitar su implementación en tiempo real. Se ha hecho hincapié tanto en la justificación matemática de los algoritmos presentados, como en la evaluación del efecto de la variación de los valores de configuración de funcionamiento del sistema, evaluándose a su vez los resultados del mismo mediante el empleo de bases de datos de acceso público, analizándose cerca de 11.000 imágenes a lo largo de 9 km de recorrido en entornos urbanos.
Traffic urban environments represent, because of its complexity, a challenge for Intelligent Transport Systems due to the great variety of situations and different elements that can happen in these environments and that must be faced by these systems. In connection with this, so far there are a variety of solutions as regards sensors and methods, so the results of precision, complexity, cost or computational load obtained by these works are different. The work presented in this dissertation develops a set of algorithms and methods in order to give support to the implementation of a great variety of advanced driver assistance systems or autonomous navigation in these environments. The system described is based on the analysis of the vehicle environment and its motion estimation by using a stereoscopic vision system which focuses, when defining the characteristics of the development, on enable its implementation in real time. It has been emphasized both the mathematical justification of the algorithms presented and the evaluation of the effect of varying the settings of the system, evaluating its results by using database access public, analyzing around 11,000 images along 9 km in urban environments.
Traffic urban environments represent, because of its complexity, a challenge for Intelligent Transport Systems due to the great variety of situations and different elements that can happen in these environments and that must be faced by these systems. In connection with this, so far there are a variety of solutions as regards sensors and methods, so the results of precision, complexity, cost or computational load obtained by these works are different. The work presented in this dissertation develops a set of algorithms and methods in order to give support to the implementation of a great variety of advanced driver assistance systems or autonomous navigation in these environments. The system described is based on the analysis of the vehicle environment and its motion estimation by using a stereoscopic vision system which focuses, when defining the characteristics of the development, on enable its implementation in real time. It has been emphasized both the mathematical justification of the algorithms presented and the evaluation of the effect of varying the settings of the system, evaluating its results by using database access public, analyzing around 11,000 images along 9 km in urban environments.
Description
Keywords
Tráfico urbano, Sistemas inteligentes de transporte, Ayuda a la conducción, Visión estereoscópica, Algoritmos