Embedded technology and algorithm for video-based vehicle queue length detection

Abstract

The vehicle queue length detection, specially based on video, is an important and practical research area of Intelligent Transportation Systems (ITS). It has promising application prospect in such areas as urban traffic control, highway toll system etc. In this paper, by analyzing the video sequence obtained from the fixed-camera, the vehicle movements of each road lane, such as left turn, go straight, turn right, are detected by using telescopic virtual coil, and then the vehicle motion detection and vehicle presence detection are used to calculate the vehicle queue length. On this basis, the vehicle queue detection algorithms are improved, and their threshold values are modified in the paper correspondently. And, the DM642 platform is designed to implement the real-time detection of vehicle queue length on the crossroads. Application experiments prove that the solution can detect the vehicle queue length with high precision, and the detection results meet the accuracy and stability requirements of practical application.