A Comparative Study of Car Tracking Algorithms for Road Traffic Surveillance Applications

In this paper, we approach the important topic of video surveillance systems which automatically identify and track moving vehicles in different environments. A comparative evaluation has been performed on four algorithms which have been adapted for counting vehicles. Among these algorithms, two of them utilize contour detection techniques to accomplish this task, while the remaining two rely on feature detection techniques to count vehicles passing through a designated region of interest using both contour detection and feature detection techniques. The proposed algorithms have been implemented and tested on a set of video sequences and an accuracy measure was computed to determine the most effective algorithm. The results show that the YOLO-based algorithm has the best average accuracy, while the Algorithm 1, which is based on background detection and tracking, has the most consistent performance.