摘要
针对单一特征所带来的跟踪不稳定问题,该文提出一种基于纹理特征粒子滤波/Mean Shift的改进目标跟踪算法。该算法中建立一种选择反馈机制,首先对目标同时进行基于纹理信息的粒子滤波和基于颜色信息的Mean Shift两种算法的跟踪,然后对两种算法的跟踪结果进行比较,选择结果较好的输出,并把结果反馈到粒子滤波与Mean Shift中作为下一帧处理的初始值。实验结果表明,该方法克服了单一特征所带来的跟踪不稳定问题且具有较强的鲁棒性。
Focusing on the problem of the instability brought about by the use of single feature,an improved object tracking algorithm was proposed in this paper based on particle filter with texture feature and mean shift with color feature.The feedback mechanism was modified in both particle filter and mean shift.Firstly,the object was tracked through particle filter with texture feature and mean shift with color feature simultaneously.After that,better result was selected by comparing the tracking results from two ...
出处
《杭州电子科技大学学报（自然科学版）》
2009年第6期49-52,共4页
Journal of Hangzhou Dianzi University：Natural Sciences
基金
国家自然科学基金资助项目(60675043)
浙江省科技计划资助项目(C21051)
浙江省宁波市自然基金资助项目(A610002)
浙江省教育厅科研资助项目(Y03228)
