Stereo vision-based pedestrian recognition for ITS applications

Parra, Ignacio; Llorca, David F.; Sotelo, Miguel Ángel; Revenga, Pedro; Bergasa, Luis M.; Ocaña, Manuel; Nuevo, Jesús; Flores, Ramón F.
Year: 2006
Type of Publication: Article
Keywords: Pedestrian recognition; ITS; vision; SVM; feature extraction; road vehicles
Journal: WSEAS Transactions on Information Science and Applications
Volume: 3
Number: 3
Pages: 554-561
Month: March
This paper presents a vision-based pedestrian recognition method in the framework of Intelligent Transportation Systems. The basic components of pedestrians are first located in the image and then combined with a SVM-based classifier. This poses the problem of pedestrian detection and recognition in real, cluttered road images. Candidate pedestrians are located using a subtractive clustering attention mechanism. A distributed learning approach is proposed in order to better deal with pedestrians variability, illumination conditions, partial occlusions and rotations. An extensive comparison has been carried out using different feature extraction methods, as a key to image understanding in real traffic conditions. A database containing thousands of pedestrian examples extracted from real traffic images has been created for learning purposes. The results achieved up to date show interesting conclusions that suggest a combination of methods as an essential clue for optimal recognition performance
Hits: 8829