A Vehicle Detection and Tracking Algorithm Based on Edge Information
Wahg Guo · 2007
To solve the vehicle detection and tracking problems in Intelligent Traffic Systems(ITS),this paper proposes a new vehicle detection and tracking algorithm based on edge information.Firstly we extracted the accurate background edge of the current frame with a background edge extraction model and eliminate it to obtain the edge of foreground vehicles.Then we used morphological method to repair the foreground edge,and found the contours of vehicles to determine the tracking regions.Because of the particularity of moving vehicles,we supposed the vehicle rate in the next frame was the same as the rate in the current frame,and matched them by combining with the shape information of the tracking regions.The experimental results show that this algorithm is simple and efficient.It is suitable for real-time vehicle detection and tracking systems.