可扩展梯度直方图人体检测算法研究与实现

广西师范大学学报（自然科学版） ›› 2011, Vol. 29 ›› Issue (3): 168-172.

可扩展梯度直方图人体检测算法研究与实现

孟凡辉, 王浩, 方宝富, 彭伟

合肥工业大学计算机与信息学院,安徽合肥230009

收稿日期:2011-06-02 出版日期:2011-08-20 发布日期:2018-12-03
通讯作者: 王浩(1962—),男,江苏泰州人,合肥工业大学教授。E-mail:jsjxwangh@hfut.edu.cn
基金资助:
国家自然科学基金资助项目(61070131)

Research and Implementation of Human Detection Based on ExtendedHistograms of Oriented Gradients

MENG Fan-hui, WANG Hao, FANG Bao-fu, PENG Wei

School of Computer and Information,Hefei University of Technology,Hefei Anhui 230009,China

Received:2011-06-02 Online:2011-08-20 Published:2018-12-03

摘要/Abstract

摘要： 人体检测已经成为机器视觉研究的一个热门课题,针对以梯度直方图作为人体特征描述的人体检测算法存在密集人群检测率较低这一问题。本文根据人体特征差异性,提出一种可扩展梯度直方图人体检测算法,使用非统一的区域方式提取图片梯度直方图描述算子,有效改善传统梯度直方图算法在密集人群检测中漏检率过高的情况。

关键词: 机器视觉, 人体检测, 密集人群, 梯度直方图, 可扩展梯度直方图

Abstract: Human detection has become a hot topic in the field of machine vision.Traditional histograms of oriented gradients(HOG) for human detection have a lower detection rate in dense population.To solve this problem,an extended HOG for human detection is proposed based on differences in human characterisics,which can extract the HOG descriptor of Image with different blocks.Experimental results show this method gives a better performance in dense population thanthe traditional method.

Key words: machine vision, human detection, dense population, HOG, extended histograms of oriented gradients(EHOG)

中图分类号:

TP181

孟凡辉, 王浩, 方宝富, 彭伟. 可扩展梯度直方图人体检测算法研究与实现[J]. 广西师范大学学报（自然科学版）, 2011, 29(3): 168-172.

MENG Fan-hui, WANG Hao, FANG Bao-fu, PENG Wei. Research and Implementation of Human Detection Based on ExtendedHistograms of Oriented Gradients[J]. Journal of Guangxi Normal University(Natural Science Edition), 2011, 29(3): 168-172.

参考文献

[1] DALAL N.Finding people in images and videos[D].Grenoble,France:The French National Institute for Research in Computer Science and Control,2006.
[2] DALAI N,TRIGGS B.Histograms of oriented gradients for human detection[C]//Computer Vision and Pattern Recognition(CVPR05).San Diego:IEEE Computer Society,2005,1:886-893.
[3] YILMAZ A,JAVED O,SHAH M.Object tracking:a survey[J].ACM Computing Surveys,2006,38(4):45.
[4] VIOLA P,JONES M.Rapid object detection using a boosted cascade ofsimple features[C]//Computer Vision andPattern Recognition.Kauai:IEEE Computer Society,2001,1:1-9.
[5] DAVID G L.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[6] DOLLAR P,WOJEK C,SCHIELE B,ea al.Pedestrian detection:a benchmark[C]//Computer Vision and Pattern Recognition.Miami:IEEE Computer Society,2009:304-311.
[7] 曾春,李晓华,周激流.基于感兴趣区梯度方向直方图的行人检测[J].计算机工程,2009,35(24):182-184.
[8] KELVIN Lee,Che Yon Choo,Hui Qing See,et al.Human detection usinghistogram of oriented gradients and human body ratio estimation[C]//Computer Science and Information Technology (ICCSIT).Rome:[s.n.],2010:18-22.
[9] MIKOLAJCZYK K,SCHMID C,ZISSERMAN A.Human detection based on a probabilistic assembly of robust part detectors[M].Computer Science.Prague:Springer,2004,3021:69-82.
[10] DALAL N,TRIGGS B,SCHMID C.Human detection using oriented histograms of flow and appearance[M].Computer Science.Graz,Austria:Springer,2006,3952:428-441.
[11] 张小川.基于梯度直方图和支持向量机的人体目标跟踪[D].辽宁:大连理工大学电子与信息工程学院,2009.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed