A real-time vehicle detection and tracking system in outdoor traffic scenes

This work presents a moving vehicle detection and tracking system, MVDT, for real-time operation in outdoor scenes. MVDT consists of three major components: road detection, vehicle detection, and vehicle tracking. The road detection algorithm utilizes a plane-fitting feature, the vehicle detection uses both segmented blob and snakes blob features in a neural network classifier, and a fast vehicle tracking algorithm is designed to locate vehicles in consecutive image frames. We show through experiments that MVDT is effective in detecting moving vehicles in various outdoor scenes and can indeed reach real-time operation requirements.