摘要
CamShift是利用目标颜色信息对目标跟踪的算法,当目标运动过快时,由于运动方向的不确定性,Cam-Shift不能准确跟踪目标,导致跟踪丢失.针对存在的问题,文章在Camshift算法中引入目标运动轨迹预测思想,提出了一种能有效跟踪运动目标的新方法.该方法能准确预测运动目标的位置,减少在算法中搜索目标的次数,进而提高目标跟踪的准确性和速度.实验结果表明,该方法对运动目标能够快速、有效地进行跟踪.
Camshift is a kind of algorithm using color information for the motive target tracking. When the target moves fast, the uncertainty of the motion causes the camshift not to be precisely track the target, thus forming tracking failure. Aiming at several Problems in Camshift algorithm,the paper introduces the idea of position prediction to Camshift algorithm,a new algorithm is presented for multiple moving objecfs detection and tracking in a static background. The method can accurately predict the position of moving target, reduce the number of searching target in the current frame,and improve processing speed. The practical application proves that the improved algorithm can realize the rapid and accurate tracking of moving objects.
出处
《安徽工程大学学报》
CAS
2012年第2期74-77,共4页
Journal of Anhui Polytechnic University
基金
安徽省自然科学基金资助项目(11040606m153)
安徽高校省级自然科学研究基金资助项目(kj2012b009)
