J4 ›› 2015, Vol. 42 ›› Issue (3): 61-66.doi: 10.3969/j.issn.1001-2400.2015.03.011

• 研究论文 • 上一篇    下一篇



  1. (西安电子科技大学 计算机学院,陕西 西安  710071)
  • 收稿日期:2014-05-20 出版日期:2015-06-20 发布日期:2015-07-27
  • 通讯作者: 贺文骅
  • 作者简介:贺文骅(1986-),男,西安电子科技大学博士研究生,E-mail: snailly18@gmail.com.
  • 基金资助:


Online visual tracking method based on superpixel hybrid voting

HE Wenhua;LIU Zhijing;QU Jianming   

  1. (School of Computer Science and Technology, Xidian Univ., Xi'an  710071, China)
  • Received:2014-05-20 Online:2015-06-20 Published:2015-07-27
  • Contact: HE Wenhua



关键词: 目标跟踪, 局部特征, 目标分割, 霍夫变换


It is a great challenge to track an object robustly when variations occur such as changes in illumination, appearance or partial occlusion. In this paper, we propose a target tracking algorithm combining superpixel and hybrid Hough voting. Local features are extracted from the context as supporters to construct a hybrid voting model. By this model, the target center is estimated by the Hough voting scheme. Local features are also distinguished to vote for the target and background, respectively. These voting results are combined into superpixels. Finally, the tracking task is formulated as the maximum a posterior estimate in the voting space. We demonstrate the performance of the algorithm on several public video sequences, which shows that our method is better than other online tracking approaches.

Key words: visual tracking, local features, segmentation, Hough transforms