首页 | 本学科首页   官方微博 | 高级检索  
     

基于运动补偿的Snake视频对象跟踪算法
引用本文:郭礼华,李建华,杨树堂. 基于运动补偿的Snake视频对象跟踪算法[J]. 红外与激光工程, 2005, 34(1): 93-97
作者姓名:郭礼华  李建华  杨树堂
作者单位:上海交通大学,电子信息与电气工程学院,上海,200030
基金项目:国家863高科技资助项目(2002AA145090)
摘    要:当对象移动幅度大时,Snake视频对象跟踪算法中的曲线迭代过程易陷入局部最小,为此,提出一种运动补偿预处理的解决方法。此方法预先估计对象的运动信息,然后对Snake曲线的初始轮廓位置进行运动补偿,最后进行Snake跟踪。实验表明,这种方法不仅跟踪效果好,而且能有效地减少Snake曲线演化的迭代次数。

关 键 词:Snake模型 主动轮廓模型 视频对象跟踪 运动补偿 运动估计
文章编号:1007-2276(2005)01-0093-05
收稿时间:2004-06-22
修稿时间:2004-06-22

Video object tracking method based on motion compensation Snake model
GUO Li-hua,LI Jian-hua,YANG Shu-tang. Video object tracking method based on motion compensation Snake model[J]. Infrared and Laser Engineering, 2005, 34(1): 93-97
Authors:GUO Li-hua  LI Jian-hua  YANG Shu-tang
Abstract:If a somewhat fast moving object exists in successive images, Snake′s nodes may fall into the local minima in their motion to the new positions of the target object in next image. In this paper,Snake tracking algorithm based on the motion compensation is presented to overcome this problem. Firstly, the motion information of object is analyzed. Secondly, the object′s position is made compensated according to this motion information.Finally, the object is tracked by Snake model. The final experimental results prove that this method performances a good tracking result and can greatly decrease the number of the Snake′s contour evolvement.
Keywords:Snake model  Active contour model  Video object tracking  Motion compensation  Motion estimation  
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号