基于改进动态阈值的运动车辆实时快速检测方法*

提出了复杂交通环境下一种新的运动车辆检测方法。基于背景差分获得运动图像，利用自适应阈值选取方法分别对差分图像的三个颜色通道进行二值化，从而实现运动目标的精确检测。根据检测结果，采用中值更新方法实现背景图像的实时更新。实验结果表明，这种基于改进动态阈值和自适应背景相结合的快速检测算法可以从复杂交通场景图像序列中快速有效地检测出运动目标，能够很好地满足智能交通监控系统中运动车辆实时检测的要求。

Moving vehicle detection algorithm based on improved dynamic threshold

This paper proposed a new moving vehicle detection method in complex scenes. Based on background difference image, respectively binarized three color channels with adaptive threshold method to accurately detect moving objects. Accor-ding to previously detected targets, induced median updating strategy to achieve real-time background update. Experimental results on outdoor image sequences demonstrate that the proposed algorithm can detect moving objects in complex traffic scenes effectively and rapidly, which can meet the requirements of real-time detection of moving vehicles in intelligent transportation surveillance system.