Global location of mobile robots using Artificial Neural Networks in omnidirectional images

This paper presents a comparison of Mobile Robots localization methods through Artifical Neural Networks in omnidirectional images. After an overview about Mobile Robotics, this work focuses on omnidirectional vision. The motivation for this work is the implementation and comparison of feature extraction techniques that can be used in omnidirectional images seeking invariance to rotation and building descriptors that can be used in Neural Networks. Five feature extraction techniques with their adaptations for omnidirectional image were presented and compared. The results were shown in order to choose the most suitable feature extractor for this application. The feature extractors are evaluated with respect to time processing and quality of scene description (accuracy of Artificial Neural Network) The results are satisfactory and elect GIST descriptor as the most suitable for the application.