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 ›› 2010, Vol. 36 ›› Issue (22): 206-207. doi: 10.3969/j.issn.1000-3428.2010.22.074

• 人工智能及识别技术 • 上一篇    下一篇

基于HOG的行人快速检测

叶 林a,陈岳林b,林景亮a   

  1. (桂林电子科技大学 a. 机电工程学院;b. 信息科技学院,广西 桂林 541004)
  • 出版日期:2010-11-20 发布日期:2010-11-18
  • 作者简介:叶 林(1985-),男,硕士研究生,主研方向:图像处理,模式识别;陈岳林,教授、硕士;林景亮,硕士

Pedestrian Fast Detection Based on Histograms of Oriented Gradient

YE Lina, CHEN Yue-linb, LIN Jing-lianga   

  1. (a. School of Mechanical and Electrical Engineering; b. Institute of Information Technolgy,Guilin University of Electronic Technology, Guilin 541004, China;
  • Online:2010-11-20 Published:2010-11-18

摘要:

为了更好更快速地实现对行人的检测,提出一种基于空间梯度直方图的行人检测算法。该算法在分类识别时用Boosted Cascad算法级联结构的分类器,将那些对不包含行人信息的区域进行筛选排除,从而使信息量减少。实验结果表明,该算法在不降低检测效果的情况下明显提高了行人检测效率,具有较强的鲁棒性。

关键词: 行人检测, HOG算子, 支持向量机, Boosted Cascad算法

Abstract:

This paper integrates the Boosted Cascad algorithm with the Histograms of Oriented Gradients(HOG) features to achieve a fast and accurate pedestrain detection system. Through using the structure of the Boosted Cascad algorithm, the areas of information less are removed, the amount of computation are reduced. Experimental result shows that the pedestrian detection efficiency of the new method is high and has strong robustness.

Key words: pedestrian detection, HOG descriptor, SVM, Boosted Cascad algorithm

中图分类号: