光电工程, 2010, 37 (10): 29, 网络出版: 2011-01-05  

一种动态模板匹配的卡尔曼滤波跟踪方法

Object Tracking Algorithm Based on Combining Dynamics Template Matching and Kalman Filter
作者单位
电子科技大学 光学工程系,成都 610054
摘要
在视频跟踪系统中,运动目标检测是实现跟踪的前提和难点。为了能够有效地检测出目标,提出了一种基于动态模板匹配和卡尔曼滤波的目标跟踪算法。首先将前两帧图像差分检测运动目标区域,提取特征点;然后利用卡尔曼滤波在搜索区域中找到与目标模型最匹配的候选目标位置并与当前帧目标模板进行匹配;最后将特征点流失率作为限定阈值,采用模板更新策略动态更新模板。跟踪实验表明,该算法具有很好的匹配精度与实时性,对目标姿态变化、大小变化、遮挡问题等有很好的鲁棒性。
Abstract
The moving object detection is a prerequisite and difficult point in the video tracking system to realize tracking.In order to detect moving object effectively, an object tracking algorithm is proposed based on combining dynamics template matching and Kalman filter. First, make the former two frames inter-difference to get the area of the moving object and extract the feature points. Then, find the best match with the object model candidate object location by Kalman filter in the search area and match it with the object template of the current frame. Finally, the loss rate of feature points will serve as the limited threshold, and we update template according to dynamic template update strategy. Several experiments of the object tracking show that the approach is accurate and fast, and it has a better robust performance during the posture changing, the size changing and the shelter instance.

梁锡宁, 杨刚, 余学才, 王世阳, 朱良销, 苏柯, 陈涛. 一种动态模板匹配的卡尔曼滤波跟踪方法[J]. 光电工程, 2010, 37(10): 29. LIANG Xi-ning, YANG Gang, YU Xue-cai, WANG Shi-yang, ZHU Liang-xiao, SU Ke, CHEN Tao. Object Tracking Algorithm Based on Combining Dynamics Template Matching and Kalman Filter[J]. Opto-Electronic Engineering, 2010, 37(10): 29.

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!