基于阴影抑制和自适应背景更新的车辆检测系统

A Vehicle Detection System with Adaptive Background Update and Shadow Suppression

在基于视频的交通监控系统中,车辆的正确检测是关键,目前采用的典型方法是背景相减法.为了提高对多车道上运动车辆检测的正确率,该文提出的车辆检测系统采用了快速自适应背景生成与更新算法,并结合基于轮廓跟踪的阴影去除技术,可以达到精确定位车辆的目的.实验图像数据表明:该检测技术较传统方法更具鲁棒性和准确性,并且从算法实现的角度来看,具有简单易用、实时性较高的特点.

Vehicle detection is a crucial step in a video-based traffic surveillance system. A typical method is background subtraction. In this work, a new vehicle detection system is designed using algorithms for fast adaptive background extraction, update and shadow suppression with contour track to improve the precision of vehicle localization. Details of the algorithm are outlined, and experimental results are shown and evaluated. The results show that the system is more robust and accurate than traditional techniques, and is simple to implement and suitable for real-time detection.