作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2013, Vol. 39 ›› Issue (4): 239-242. doi: 10.3969/j.issn.1000-3428.2013.04.055

• 人工智能及识别技术 • 上一篇    下一篇

基于分块的自适应多特征融合目标跟踪

周芳燕,唐 建,何劲松   

  1. (中国科学技术大学电子科学与技术系,合肥 230027)
  • 收稿日期:2011-12-21 出版日期:2013-04-15 发布日期:2013-04-12
  • 作者简介:周芳燕(1986-),女,硕士研究生,主研方向:目标跟踪算法,图像处理;唐 建,讲师、博士;何劲松,副教授、 博士

Adaptive Multi-feature Combination Object Tracking Based on Blocking

ZHOU Fang-yan, TANG Jian, HE Jin-song   

  1. (Department of Electronic Science and Technology, University of Science and Technology of China, Hefei 230027, China)
  • Received:2011-12-21 Online:2013-04-15 Published:2013-04-12

摘要: 基于RGB直方图的目标跟踪易受背景相似颜色的影响。针对该问题,提出一种分块的自适应多特征权值融合跟踪算法。采用K-S相似性度量准则对边缘方向直方图(EOH)和RGB直方图的特征权值进行融合,实现目标跟踪。实验结果表明,与单一的RGB或EOH特征跟踪算法相比,该算法的跟踪准确率较高,具有较强的抗遮挡能力。

关键词: 分块, 遮挡, RGB直方图, 边缘方向直方图, 自适应权值融合, K-S相似性度量

Abstract: Tracking algorithm based on RGB histogram is sensitive to the similarity color in background, leading to failure in tracking. In view of the above problem, a tracking algorithm based on blocking with multi-feature combination is proposed. This algorithm adopts K-S similarity measure in Edge Orientation Histogram(EOH) and RGB histogram, with adaptive combination to track object. Experimental results show that it has better performance than single feature as well as robust to occlusion.

Key words: blocking, occlusion, RGB histogram, Edge Orientation Histogram(EOH), adaptive weight combination, K-S similarity measure

中图分类号: