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 ›› 2012, Vol. 38 ›› Issue (5): 179-182. doi: 10.3969/j.issn.1000-3428.2012.05.055

• 人工智能及识别技术 • 上一篇    下一篇

基于边缘对称性和HOG的行人检测方法

姚雪琴a,李晓华b,周激流b   

  1. (四川大学 a. 电子信息学院;b. 计算机学院,成都 610065)
  • 收稿日期:2011-09-26 出版日期:2012-03-05 发布日期:2012-03-05
  • 作者简介:姚雪琴(1987-),女,硕士研究生,主研方向:模式识别,行人检测;李晓华,副教授、博士;周激流,教授、博士生导师
  • 基金资助:
    四川省科技支撑计划基金资助项目(2011GZ0187)

Pedestrian Detection Method Based on Edge Symmetry and HOG

YAO Xue-qin a, LI Xiao-hua b, ZHOU Ji-liu b   

  1. (a. College of Electronics and Information Engineering; b. College of Computer Science, Sichuan University, Chengdu 610065, China)
  • Received:2011-09-26 Online:2012-03-05 Published:2012-03-05

摘要: 传统基于HOG特征的行人检测方法存在检测速度慢的问题。为此,提出一种基于边缘对称性和HOG的行人检测方法。利用对称差分提取输入窗口的垂直边缘,根据垂直边缘的对称性快速检测出行人候选区,采用HOG特征和线性支持向量机对行人候选区进行验证。实验结果表明,该方法在保持传统方法检测率的同时,能提高检测速度。

关键词: 行人检测, 对称差分, 垂直边缘, 边缘对称性, HOG特征, 线性支持向量机, 十折交叉验证

Abstract: The detection speed of traditional pedestrian detection method based on Histograms of Oriented Gradient(HOG) feature is slow. In order to detect pedestrian faster, a pedestrian detection method based on edge symmetry and HOG is proposed. Symmetric difference is used to extract the vertical edge of the input window. Candidate pedestrians can be detected rapidly according to the symmetry of the vertical edge. Candidate pedestrians are validated by using HOG feature and linear Support Vector Machine(SVM). Experimental results show that the proposed method can increase the detection speed while maintaining the comparable detection rate to the traditional method based on HOG feature.

Key words: pedestrian detection, symmetric difference, vertical edge, edge symmetry, Histograms of Oriented Gradient(HOG) feature, linear Support Vector Machine(SVM), 10-fold cross-validation

中图分类号: