东北大学学报:自然科学版 ›› 2015, Vol. 36 ›› Issue (4): 465-468.DOI: 10.12068/j.issn.1005-3026.2015.04.003

• 信息与控制 • 上一篇    下一篇

基于非局部稀疏特征的行人检测方法

彭怡书, 颜云辉, 赵久梁, 张尧   

  1. (东北大学 机械工程与自动化学院, 辽宁 沈阳110819)
  • 收稿日期:2014-03-23 修回日期:2014-03-23 出版日期:2015-04-15 发布日期:2014-11-07
  • 通讯作者: 彭怡书
  • 作者简介:彭怡书(1985-),男,湖南郴州人,东北大学博士研究生; 颜云辉(1960-),男,江苏丹阳人,东北大学教授,博士生导师.
  • 基金资助:
    国家自然科学基金资助项目(51374063); 中央高校基本科研业务费专项资金资助项目(N120603003).

Pedestrian Detection Based on Nonlocal Sparse Feature

PENG Yi-shu, YAN Yun-hui, ZHAO Jiu-liang, ZHANG Yao   

  1. School of Mechanical Engineering & Automation, Northeastern University, Shenyang 110819, China.
  • Received:2014-03-23 Revised:2014-03-23 Online:2015-04-15 Published:2014-11-07
  • Contact: PENG Yi-shu
  • About author:-
  • Supported by:
    -

摘要: 利用周围邻域信息约束进行加权稀疏表示以达到行人检测的目的.采用Fisher判别字典学习的方法,得到一个能够更好地提取图像的具有更强辨别性稀疏特征的字典,利用图像中周围信息约束,求得该字典表示下的稀疏特征,并根据对当前图像块的稀疏表示残差进行分类.INRIA数据库的实验表明非局部稀疏特征具有明显的区分能力.同时,对行人目标进行邻域约束,能够有效地表示出同目标区域的稀疏特征.

关键词: 行人检测, 非局部, 稀疏表示, 判别字典, 优化配矿

Abstract: By using the constraints around the neighborhoods for weighted sparse representation, the pedestrian detection problem was solved. A dictionary with a strong extracting discriminate and sparse features power was obtained by using the Fisher discriminant dictionary learning method. With the constraint of the neighborhoods, the image patch was represented as a sparse feature via the dictionary. By computing the representation of the residuals and comparing the residuals with a threshold, the patch label was determined to finish the classification task. The experiments on INRIA person datasets showed that non-local sparse feature has an obvious power of discrimination. The constraint of the neighborhoods makes the sparse feature represented effectively.

Key words: pedestrian detection, nonlocal, sparse representation, discriminate dictionary;optimization ore matching

中图分类号: