Pedestrian recognition in road sequences
- 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: In Proceedings
- Keywords: ITS; SVM; feature extraction; pedestrian recognition; road vehicles; vision
- Book title: Proceedings of the 5th WSEAS International Conference on Signal Processing, Robotics and Automation
- Pages: 273-278
- Address: Stevens Point, Wisconsin, USA
- ISBN: 960-8457-41-6
- 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.