期刊文献+

基于背景加权直方图的Mean shift目标跟踪

Mean Shift Tracking with Background-weighted Histogram
下载PDF
导出
摘要 在对Mean shift算法进行运动目标跟踪中发现,当运动目标与背景颜色相近时,会降低跟踪的准确性。而采用基于背景加权的Mean shift跟踪方法,能有效减少背景相似特征的干扰。在Mean shift算法框架下引入转化因子,将其引入到目标模型中,从而减少背景突出特征。实验结果表明,该算法和传统Mean shift算法相比不但减少了迭代次数,而且提高了跟踪的准确度。 When the moving object and background colors are similar,using Mean shift tracking algorithm will reduce the tracking accuracy.Mean shift tracking with background-weighted histogram can effectively reduce the background interfer- ence.in the Mean shift algorithm framework,to reduce the salient background features,the transformation factor is incorporat- ed into the target model.
作者 谢海波
机构地区 上海海事大学
出处 《工业控制计算机》 2016年第7期88-89,共2页 Industrial Control Computer
关键词 目标跟踪 Mean SHIFT算法 背景加权直方图 target tracking,Mean shift algorithm,background-weighted histogram
  • 相关文献

参考文献6

  • 1贺贵明,李凌娟,贾振堂.一种快速的基于对称差分的视频分割算法[J].小型微型计算机系统,2003,24(6):966-968. 被引量:16
  • 2B.K.P.Horn,B.G.Schunck.Determining optical flow [J].1981,17 (1-3) : 185-203.
  • 3王江涛,杨静宇.遮挡情况下基于Kalman均值偏移的目标跟踪[J].系统仿真学报,2007,19(18):4216-4220. 被引量:30
  • 4D.Comaniciu,V.Ramesh,P.Meer. Kernet-Based object tracking [J].IEEE Transaction on Pattern Analysis and Machine Intelligence.2003,25(5):564-575.
  • 5J.Jeyakar,R.Babu,KR.RamakrishnanRobust object tracking with background-weig-hted local kernels [J].Computer Vision Un- der- standing.2009,112(3):296-307.
  • 6Jiang Peng,Jin WeiDong.Statistical Bac-kground Subtraction with Adaptive Threshold[C]//lnternational Congress on Image and Sign-al Processing.2012:124-126.

二级参考文献11

  • 1彭宁嵩,杨杰,刘志,张风超.Mean-Shift跟踪算法中核函数窗宽的自动选取[J].软件学报,2005,16(9):1542-1550. 被引量:165
  • 2林明秀,刘伟佳,徐心和.基于模板匹配的多模式车辆跟踪算法[J].系统仿真学报,2007,19(7):1519-1522. 被引量:13
  • 3K Fukunaga, L D Hostetler. The estimation of the gradient of a density function, with applications in pattern recognition [J]. IEEE Transaction on Information Theory (S0018-9448), 1975, 21(1): 32-40.
  • 4D Comaniciu, V Ramesh, P Meer. Kernel-based object tracking [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence (S0162-8828), 2003, 25(5): 564-577.
  • 5D Comaniciu, P Meer. Mean shift: A robust approach toward feature space analysis [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence (S0162-8828), 2002, 24(5): 603-619.
  • 6R Collins. Mean-shift blob tracking through scale space [C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition, volume Ⅱ. Washington: IEEE, 2003: 234-240.
  • 7G R Bradski. Computer vision face tracking as a component of a perceptual user interface [C]// IEEE Workshop on Applications of Computer Vision. Washington: IEEE, 1998: 214-219.
  • 8A Elgammal, R Duraiswami, L Davis. Probabilistic tracking in joint feature-spatial spaces [C]// IEEE Computer Society Conference on Computer Vision and Pattern Recognition, volume Ⅰ. Washington: IEEE, 2003: 781-788.
  • 9Changjiang Yang, Ramani Duraiswami, Larry Davis. Efficient Mean-Shift Tracking via a New Similarity Measure [C]// IEEE Computer Society Conference on Computer Vision and Pattern Recognition, volume Ⅰ. Washington: IEEE, 2005: 176-183.
  • 10林通,石青云.一种基于边缘生长的灰度和彩色图象分割方法[J].中国图象图形学报(A辑),2000,5(11):911-915. 被引量:44

共引文献44

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