基于达芬奇平台的运动目标跟踪算法

在运动目标跟踪过程中，考虑到达芬奇平台的数据处理能力，结合Vibe算法和Mean Shift算法的思想提出一种改进的运动目标跟踪算法，同时为了解决Vibe算法在目标由运动变为静止后遗留在前景图像中的鬼影难以消除的问题，对视频图像序列中的每个像素点建立前景计数器，根据前景计数器的值判断背景模型的更新速度。针对达芬奇平台对算法进行优化，把改进的运动目标跟踪算法移植到TMS320DM6467T达芬奇平台下进行处理，实验结果表明改进的算法具有良好的跟踪效果。

Moving Target Tracking Algorithm Based on Davinci Platform

In the process of moving target tracking, considering the data processing ability of Davinci platform, combining the Vibe algorithm with the mean shift algorithm, an improved moving target tracking algorithm is presented. At the same time, in order to solve the problem that it is difficult to eliminate the ghosts left in the foreground image after the moving target becomes stationary state in the Vibe algorithm, we set up foreground counters for each pixel in the video image sequence, and judge the renewal speed of background model according to the value of counter. And the algorithm is optimized based on Davinci platform. At last, the improved moving target tracking algorithm is transplanted into TMS320DM6467T platform. Experiment results show that the improved algorithm is of good tracking performance to moving target.