Title :
Environment Understanding: Robust Feature Extraction from Range Sensor Data
Author :
Romeo, Antonio ; Montano, Luis
Author_Institution :
Dept. de Inf. e Ingenieria de Sistemas, Univ. de Zaragoza
Abstract :
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
Keywords :
feature extraction; learning (artificial intelligence); mobile robots; principal component analysis; stochastic processes; Fisher linear discriminant analysis; indoor environment supervised learning; pattern recognition; principal components analysis; range sensor data; robust feature extraction; scale changes; shape distortions; stochastic preprocessing methods; Face recognition; Feature extraction; Image analysis; Indoor environments; Navigation; Principal component analysis; Robot localization; Robustness; Sensor phenomena and characterization; Stochastic processes;
Conference_Titel :
Intelligent Robots and Systems, 2006 IEEE/RSJ International Conference on
Conference_Location :
Beijing
Print_ISBN :
1-4244-0258-1
Electronic_ISBN :
1-4244-0259-X
DOI :
10.1109/IROS.2006.282509