Environment Understanding: Robust Feature Extraction from Range Sensor Data

This paper proposes an approach allowing indoor environment supervised learning to recognize relevant features for environment understanding. Stochastic preprocessing methods in combination with either of usual pattern recognition schemes are used. Preprocessing method treated is a combination of the principal components analysis and the Fisher linear discriminant analysis well adapted to the sensorial information and to the kind of environments considered. The supervised method is applied to the raw range data obtained from typical indoor environments, obtaining good recognition performances without geometrical feature extraction, allowing its real time implementation. Our work focuses on the preprocessing method, giving a geometrical interpretation of their main components, and analyzing their robustness to shape distortions and scale changes