关键词: 运动车辆检测, 计算机视觉, 车底阴影, 最大类间方差法

Abstract:

Vehicle intelligent auxiliary drive system is an important part of the intelligent transport system.Using the computer vision to detect moving vehicle is the essential problem of the intelligent vehicle navigation.Real time detection of the location information of the preceding vehicle detection is the premise for security driving.A detection method for preceding vehicles based on the shadow of chassis is presented.The key thought is using the detection of the shadow to detect the preceding vehicle with the lane detection.First,the Otsu threshold segmentation is used to extract the lane and generate the AOI.Then,two adaptive thresholds are adopted to extract the interesting lines of the chassis and the road so that the moving vehicle is detected.The experiment on highway shows that this algorithm satisfies the need of the security driving,and can exactly detect the preceding moving vehicle thus reducing the risks of traffic accidents.

Key words: moving vehicle detection;computer vision;shadow of chassis;otsu