J4 ›› 2011, Vol. 38 ›› Issue (5): 95-100.doi: 10.3969/j.issn.1001-2400.2011.05.016

• Original Articles • Previous Articles     Next Articles

Fast contour tracking algorithm for human body in infrared images

GAO Jing1,2;XU Jianjun1;BI Duyan1   

  1. (1. Eng. College, Air Force Eng. Univ.,  Xi'an  710038, China;
    2. The Research Inst. of Equipment System Development and Evaluation of Air Force Equipment Research Academy, Beijing  100076, China)
  • Received:2010-08-27 Online:2011-10-20 Published:2012-01-14
  • Contact: GAO Jing E-mail:afeu777@163.com

Abstract:

A novel algorithm based on the level set is proposed for tracking the precise contour of the human body in infrared videos. The algorithm first adopts the nearest neighbor decision method to construct the velocity expression for the fast level set only in the target region and its neighbor background region but not in the whole image plane, then contour tracking is realized by evolving the zero level set curve using the dynamic neighbor region fast level set algorithm proposed in this paper. Experiments show that this algorithm can adapt to the scale change of the target and the split or mergence of the target, and lead to the exact contour of the human body.

Key words: infrared image, human tracking, dynamic neighbor region, fast level set, contour

CLC Number: 

  • TP391