运动车辆的视频动态目标检测

The Detection of Video Dynamic Targets for the Moving Vehicle

对运动车辆抖动以及摄像头平移运动引起的一些干扰问题进行了研究,提出了在求和绝对误差(Sum of Absolute Difference,SAD)算法的基础上运用光流法,以此来消除平移运动及抖动产生的视频干扰信号,从而获得稳定的视频流,实现在运动车辆上用摄像头对动态目标的准确检测。结果表明,该方法能够有效地检测出运动目标,并且满足实时性。

Research on some interference problems that translational motion of the camera and moving vehicles jitter cause, optical flow algorithm based on the SAD was used to generate a stabilized video by removing unwanted the interference of translational camera motions as well as vehicles jitter. Ultimately, the correct detection of video dynamic target on the moving vehicle was gotten by this study. The experimental results indicate that the method can eflE^ctively detect moving objects and meet the real-time requirements.