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

• 人工智能及识别技术 • 上一篇    下一篇

改进型WLD与LBP特征融合的行人检测

谭飞刚,殷苌茗,周书仁   

  1. (长沙理工大学计算机与通信工程学院,长沙 410004)
  • 收稿日期:2012-12-27 出版日期:2014-03-15 发布日期:2014-03-13
  • 作者简介:谭飞刚(1987-),男,硕士研究生,主研方向:模式识别,图像处理;殷苌茗,教授、博士;周书仁,博士。
  • 基金资助:
    国家自然科学基金资助项目(60973113);湖南省自然科学基金资助项目(12JJ6057);湖南省标准化战略基金资助项目(2011031);长沙市科技计划基金资助项目(K1203015-11)。

Pedestrian Detection Fused with Improved WLD and LBP Feature

TAN Fei-gang, YIN Chang-ming, ZHOU Shu-ren   

  1. (Computer & Communication Engineering School, Changsha University of Science & Technology, Changsha 410004, China)
  • Received:2012-12-27 Online:2014-03-15 Published:2014-03-13

摘要: 为提高行人检测的识别率,提出一种基于改进型韦伯局部描述子(WLD)和局部二元模式(LBP)的特征融合方法进行行人检测。对图像进行二维离散Haar小波变换得到4个不同频率的子图像,对其中1个低频部分提取WLD特征,对3个高频部分提取LBP特征,并将各个子图像的特征串接为1个向量,得到WLD-LBP特征。在INRIA Person数据集上利用SVM作为分类器进行测试,实验结果表明,与单独WLD特征、梯度方向直方图(HOG)特征、PHOG特征以及HOG-LBP特征融合方法相比,该方法的识别率最高,可达98.1%,并且对光照和噪声也有较好的鲁棒性。

关键词: 二维离散小波变换, 特征融合, 行人检测, WLD特征, LBP特征

Abstract: This paper presents a feature fusion method(WLD-LBP) based on an improved Weber Local Descriptor(WLD) and Local Binary Pattern(LBP) through a two-dimensional discrete haar wavelet transform. The algorithm starts with a two-dimensional discrete haar wavelet for the image so as to obtain the subimages of four different frequencies. Making full use of the WLD and LBP, we extract the WLD characteristics of the low frequency part, and LBP features of the other three high-frequency portion, and then a vector consisted with the characteristics of the image is produced which we called WLD-LBP characteristics. Five groups of test experiments were conducted on INRIA Person databases using SVM as classifier,comparing with the characristics of WLD, Histogam of Oriented Gradient(HOG), PHOG and feature fusion of HOG-LBP,respectively. The results demonstrate the effectiveness with the highest recofnition rate up to 98.1% and robustness to illumination and noise of the proposed method.

Key words: 2-D discrete wavelet transform, feature fusion, pedestrian detection, Weber Local Descriptor(WLD), Local Binary Pattern(LBP)

中图分类号: