Lie Guo
Personal Homepage
Paper Publications
基于腿部梯度方向直方图特征优化的行人检测
Hits:

Indexed by:期刊论文

Date of Publication:2013-02-15

Journal:高技术通讯

Included Journals:PKU、ISTIC、CSCD、Scopus

Volume:23

Issue:2

Page Number:203-207

ISSN No.:1002-0470

Key Words:交通安全;行人检测;梯度方向直方图(HOG);Gentle Adaboost

Abstract:针对传统的基于梯度方向直方图(HOG)特征的行人检测耗时较长的问题,提出了基于腿部HOG特征优化的行人检测方法.该方法采用加权Fisher线性判别(WLFD)代替线性SVM来选择最具区分性的HOG特征,在保持分类能力的同时减少训练时间和存储空间,而且选择查找表型弱分类器的Gentle Adaboost算法来训练优化权重组合HOG特征,形成一个强分类器来检测行人.通过对线性SVM、加权Fisher与阈值型以及加权Fisher与查找表型三种弱分类器的对比试验表明,基于加权Fisher与查找表型HOG特征优化后不仅提高了检测精度,而且训练时间和检测时间也能明显降低.

Personal information

Associate Professor
Supervisor of Doctorate Candidates
Supervisor of Master's Candidates

Gender:Male

Alma Mater:吉林大学

Degree:Doctoral Degree

School/Department:机械工程学院

Discipline:Vehicle Engineering. Vehicle Operation Engineering

Business Address:海涵楼417A

Contact Information:15524800674

Click:

Open time:..

The Last Update Time:..


Address: No.2 Linggong Road, Ganjingzi District, Dalian City, Liaoning Province, P.R.C., 116024

MOBILE Version