基于彩色边缘的运动车辆检测

Moving vehicles detection based on color edge

在RGB空间中对彩色交通视频图像进行多通道边缘检测,利用融合的边缘信息进行多帧迭加建立自适应背景模型,通过背景模型抽取运动车辆.受车速,车流量,噪声等影响,得到的是不完整的目标边缘,依靠边缘生长对目标进行修补,以提高运动车辆检测的准确性,保证边缘的连续性.实验结果表明,该方法计算量小,能够满足实时系统的要求,可有效地检测运动车辆.

This paper employs a muhichannel edge detecting approach to traffic color video image in RGB space, an adaptive background model is built on the frames iteration of fused edge information and the moving vehicles are based on the background model subtraction. The edge of target is in- complete because of effecting by speed of vehicles, freight flow, noise and so on. Mending the edge of target with edge growing in order to improve the accuracy of moving vehicles detection and smooth the edge. The experimental results show that the method needs little calculation, and can satisfy the requirement of the real - time system and detect moving vehicles effectively.