基于差分的光流法在目标检测跟踪中的应用

Application of Optical Flow Algorithms Based on Difference in Target Detection and Tracking

介绍光流法和差分法在图像处理中的应用情况,并对两种算法在处理跟踪目标时的优缺点进行比较。将两种算法进行有机的结合,即先用差分法对图像进行预处理,再使用光流法对预处理的结果进行计算,并借助于TMS320DM642平台进行验证。结果表明,改进后的处理方法能有效地提高运动目标跟踪的实时性,系统稳定性好。

The applications of the optical flow and difference algorithms in image processing were introduced. The advantages and disadvantages of the two algorithms in targets tracking were compared. The optical flow algorithm was combined with the difference, namely using difference algorithm to pretreat the image and then using flow algorithm to calculate the pretreatment image. The improved algorithm was verified with the platform of TMS320DM642. The experimental result shows that the improved method enhance the real-time performance of the target tracking system and the system is very stable.