A Multiclass Classifier to Detect Pedestrians and Acquire Their Moving Styles
In a pedestrian detection system, to discover the intention of a pedestrian and warn the driver, it is necessary to obtain the pedestrian’s main moving style. In this paper, an efficient multiclass classifier is presented to detect pedestrians and classify their moving style simultaneously. The multiclass classifier composes of three two-class classifiers and each of them is trained with a SVM algorithm. Experiments based on a single camera pedestrian detection system show that the multiclass classifier has an acceptable detection rate; at the same time, it can judge whether a pedestrian is walking along the road or across the road.
KeywordsSingle Classifier Intelligent Transportation System Intelligent Vehicle Multiclass Classification Moving Style
- 1.Evgeniou, T., Papageorgiou, C., Poggio, T.: A trainable pedestrian detection system. In: IEEE Intelligent Vehicles Symposium, Stuttgart, Germany, October 1998, pp. 241–246 (1998)Google Scholar
- 4.Joachims, T.: Making large-scale SVM learning practical. In: Schölkopf, B., Burges, C.J.C., Smola, A.J. (eds.) Advances in Kernel Methods — Support Vector Learning. MIT Press, Cambridge (1998)Google Scholar