Computer Science ›› 2017, Vol. 44 ›› Issue (Z11): 217-220.doi: 10.11896/j.issn.1002-137X.2017.11A.045

Previous Articles     Next Articles

Meanshift Target Tracking Algorithm of Adaptive HLBP Texture Feature

DU Jing-wen, HUANG Shan and YANG Shuang-xiang   

  • Online:2018-12-01 Published:2018-12-01

Abstract: In combination of the image texture feature extraction method,which is based on Haar local binary pattern(HLBP),a new target tracking algorithm was proposed,and applied to Meanshift tracking framework.Visual Studio 2010 and the opencv2.4.9 were the experimental platforms.We compared the results of the new algorithm with the results of other two kinds of algorithms,which are traditional Meanshift target tracking algorithm and the target tracking algorithm based on local binary pattern texture feature (LBP).Experimental results show that,in the case of simple or complicated background,the proposed tracking approach always shows steady and accurate tracking features,and in the event of partial occlusions,it can correctly track the target.

Key words: Local binary pattern,Haar feature,Meanshift tracking algorithm,Partial occlusions

[1] 胡铟,杨静宇.基于分块颜色直方图的MeanShift跟踪算法[J].系统仿真学报,2009,0(8):66-70.
[2] 杜凯,巨永锋,靳引利,等.自适应分块颜色直方图的MeanShift跟踪算法[J].武汉理工大学学报,2012,4(6):141-143.
[3] 徐海明,黄山,李云彤.基于改进的MeanShift鲁棒跟踪算法[J].计算机工程与科学,2015,7(6):1161-1167.
[4] 张英,车进,牟晓凯,等.改进的MeanShift运动目标跟踪算法[J].电视技术,2016,0(10):97-100.
[5] 史宝明,贺元香,邢玉娟.融合边缘特征的MeanShift跟踪算法[J].兰州文理学院学报,2015,9(6):49-52.
[6] 李冠彬,吴贺丰.基于颜色纹理直方图的带权分块均值漂移目标跟踪算法[J].计算机辅助设计和图形学学报,2011,2(8):1232-1235.
[7] 周书仁,殷建平.基于Haar特性的LBP纹理特征[J].软件学报,2013,4(8):1909-1926.
[8] 袁瑜键.基于纹理特征的目标识别与跟踪技术研究[D].北京:北京理工大学,2016.
[9] OJALA T,PIETIKAINEN M,HARWOOD D.A comparative study of texture measures with classification based on featured distributions[J].Pattern Recognition,1996,9(1):51-59.
[10] 李洋.基于Meanshift的运动目标跟踪算法研究[D].沈阳:沈阳理工大学,2015.
[11] 姜明新.智能视频监控中的目标跟踪技术研究[D].大连:大连理工大学,2013.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!