J4 ›› 2011, Vol. 38 ›› Issue (6): 146-151.doi: 10.3969/j.issn.1001-2400.2011.06.024

• 研究论文 • 上一篇    下一篇

融合边缘片断与水平集分割的目标跟踪算法

高晶;毕笃彦;赵晓林   

  1. (空军工程学院 信号与信息处理实验室,陕西 西安  710038)
  • 收稿日期:2010-10-12 出版日期:2011-12-20 发布日期:2011-11-29
  • 通讯作者: 高晶
  • 作者简介:高晶(1981-),男,空军工程大学博士研究生,E-mail: afeu777@163.com
  • 基金资助:

    国家863计划资助项目(2007AA701206)

Non-rigid object tracking based on the boundary fragment  feature and level set segmentation

GAO Jing;BI Duyan;ZHAO Xiaolin   

  1. (Signal and Information Processing Lab., Air Force Eng. Univ., Xi'an  710038, China)
  • Received:2010-10-12 Online:2011-12-20 Published:2011-11-29
  • Contact: GAO Jing

摘要:

提出了一种融合边缘片断特征与水平集分割的非刚体目标跟踪算法.首先通过Gentle AdaBoost训练器训练得到目标边缘特征字典;然后在每一帧图像中把目标边缘特征字典与图像边缘作Chamfer匹配,通过把具备鉴别能力的图像边缘片断特征嵌入到水平集能量函数中,用来降低背景中边缘信息的干扰.实验结果表明,在非刚体目标局部被遮挡的情况下,仍能准确获得目标轮廓,体现出了该跟踪算法良好的跟踪性能.

关键词: 目标跟踪, 水平集分割, 边缘片断特征

Abstract:

To track non-rigid objects exactly, conventional methods typically suffer from two problems: 1) fast local shape deformation and 2) occlusion. This paper proposes a novel non-rigid object tracking algorithm based on boundary fragments matching and level set segmentation. Our approach embeds the discriminative object boundary feature learned by Adaboost into the levelset energy function. Both efficiency and adaptability of our algorithm are demonstrated by experimental results.

Key words: object tracking, level set setmentation, boundary fragments

中图分类号: 

  • TP391.4