CAJ | 학술논문

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。
재운동목표근종과정중，고필도체분기평태적수거처리능력，결합Vibe산법화Mean Shift산법적사상제출일충개진적운동목표근종산법，동시위료해결Vibe산법재목표유운동변위정지후유류재전경도상중적귀영난이소제적문제，대시빈도상서렬중적매개상소점건립전경계수기，근거전경계수기적치판단배경모형적경신속도。침대체분기평태대산법진행우화，파개진적운동목표근종산법이식도TMS320DM6467T체분기평태하진행처리，실험결과표명개진적산법구유량호적근종효과。
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 or-der to solve the problem that it is difficult to eliminate the ghosts left in the foreground image after the moving target becomes sta-tionary state in the Vibe algorithm, we set up foreground counters for each pixel in the video image sequence, and judge the re-newal 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.