期刊文献+

基于均值漂移的快速模板匹配算法 被引量:4

A Target Tracking Algorithm Based on Mean Shift and Fast Template Matching
下载PDF
导出
摘要 提出了一种基于均值漂移和模板匹配的目标跟踪算法。算法工作时分为预测、模板匹配与目标定位及模板更新3个阶段。在预测阶段,结合上一帧跟踪得到的目标位置,利用均值漂移方法对目标位置进行预测,并以预测位置为中心、以相应的大小为覆盖范围定义模板匹配的搜索波门;在模板匹配阶段,采用快速模板匹配算法,将目标模板与搜索波门进行由粗到精的快速匹配,并计算所得匹配结果与目标模板的匹配程度,如果该匹配度大于给定的阈值,则将快速模板匹配的结果作为当前帧图像的跟踪结果,否则,以均值漂移算法预测的目标位置作为当前帧图像的跟踪结果,最后由当前帧的跟踪结果控制模板更新过程以更新目标的模板,最终完成对目标的稳定跟踪。同时该算法结合颜色和边缘特征对旋转、变形不敏感的优点提高跟踪的鲁棒性。该方法运算速度快,准确度高,能够满足实时性要求。 This paper proposes a target tracking algorithm based on mean shift and template matching. The algo- rithm is divided into three stages: prediction, template matching, target positioning, and template updating. In the prediction stage, combined with the target position obtained from the previous frame tracking, the target position is predicted using the mean shift method, and the template matching search gate is defined with the predicted position as the center and the corresponding size as the coverage area. At the template matching stage, using fast template matching algorithm, the target template and search gate are quickly matched from coarse to fine, and the matching degree between matching result and target template is calculated. If the matching degree is greater than the given threshold, the fast template matching will be performed and the result will be used as the tracking result of the cur- rent frame image. Otherwise, the target position predicted of the current frame image. Finally, the template updating by the mean shift algorithm is used as the tracking results process is controlled by the tracking results of the current frame to update the target template, and the stable tracking of the target is finally completed. At the same time, the algorithm improves the robust of tracking by combining the advantages of color and edge features to the insensitivity of rotation and deformation. The method has fast calculation speed and high accuracy, it can meet real-time require- ments.
作者 段亮弟 宋平 陈众 赵鹏 Duan Liangdi;Song Ping;Chen Zhong;Zhao Peng(PLA 63870 Unit,Huayin 714200,China)
机构地区 [
出处 《西北工业大学学报》 EI CAS CSCD 北大核心 2018年第4期792-799,共8页 Journal of Northwestern Polytechnical University
关键词 算法 帧图像 图像处理 目标位置 目标跟踪 均值漂移 模板匹配 目标模板 algorithm frame image image processing target position target tracking mean shift template matching target template
  • 相关文献

参考文献3

二级参考文献23

  • 1韩晓波.基于背景建模和动态分块的目标跟踪[J].电子技术(上海),2010(10):21-23. 被引量:2
  • 2朱永松,国澄明.基于相关系数的相关跟踪算法研究[J].中国图象图形学报(A辑),2004,9(8):963-967. 被引量:37
  • 3毛克诚,孙付平.扩展卡尔曼滤波与采样卡尔曼滤波性能比较[J].海洋测绘,2006,26(5):4-6. 被引量:12
  • 4孙中森,孙俊喜,宋建中,乔双.一种抗遮挡的运动目标跟踪算法[J].光学精密工程,2007,15(2):267-271. 被引量:30
  • 5Latecki L J,Miezianko,R.Object tracking with dynamic template update and occlusion detection[C]//IEEE 18thinternational Conference on Pattern Recognition,Hong Kong,China:IEEE,2006:188-193.
  • 6Kaneko T,Hori O.Template update criterion for template matching of image sequences[C]//IEEE Computer Vision and Pattern Recognition Quebec,Canada:IEEE,2002:211-214.
  • 7Zhong Y,Jain A K.Object tracking using deformable templates[C]// IEEE Transactions on Pattern Analysis and Machine Intelligence,Washington,USA:IEEE,2000:544-549.
  • 8Lucas B,Kanade T.An iterative image registration technique with an application to stereo vision[C]//Proceedings of the International Joint Conference on Artificial Intelligence,Vancouver,Canada:IEEE,1981:674-679.
  • 9Welch G,Bishop G.An introduction to the kalman filter[R].Carolina:University of North Carolina at Chapel Hill,1997.
  • 10Gordon N,Salmond D.Novelapproach to nonlinear/non-Gaussian Bayesian state estimation[J].IEE Proceedings-F,1993,140(2):107-113.

共引文献45

同被引文献42

引证文献4

二级引证文献9

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部