高师理科学刊2016，Vol.36Issue(7)：29-33,5.DOI:10.3969/j.issn.1007-9831.2016.07.008
基于分步降维HOG-LBP特征的行人头部分类算法
Pedestrianhead classification algorithm with two-step dimension reduction HOG- LBPfeature
摘要
Abstract
Traditionalpedestrian head classification algorithm based on PCA-HOG feature has the problem of degradation of the discrimination in the subspace.In order to handle this problem,thepedestrian head classification is completed based on the proposedtwo-step dimension reduction HOG- LBPfeature.Firstly,two category of HOG sample set are obtained according to the sample labels.The PCA algorithm is carried out on each sample set step by step.Then the LBP texture features are combined with the dimension reduced HOG feature to form the final head descriptor.Lastly,experiments were performed by SVM classifier on practical test samples,and the experimental results show that,comparing with the traditional PCA algorithm,the presented HOG-LBP features can effectively improve the classification performance of pedestrian head.关键词
HOG/LBP/PCA/头部检测Key words
HOG/LBP/PCA/head detection分类
信息技术与安全科学引用本文复制引用
李玲,王江涛..基于分步降维HOG-LBP特征的行人头部分类算法[J].高师理科学刊,2016,36(7):29-33,5.基金项目
国家自然科学基金资助项目（61203272）；安徽省高校优秀青年人才支持计划重点项目（gxyqZD2016113）；安徽省自然科学基金项目（1508085MF116）；淮北师范大学教学研究项目 （）
