Pedestrian detection and tracking using temporal differencing and HOG features

被引：32

作者：

Barbu, Tudor ^{[1
]}

机构：

[1] Romanian Acad, Inst Comp Sci, Iasi, Romania

来源：

COMPUTERS & ELECTRICAL ENGINEERING | 2014年 / 40卷 / 04期

关键词：

Template matching;

D O I：

10.1016/j.compeleceng.2013.12.004

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

This article proposes a multiple human detection and tracking approach. A moving person identification technique is provided first. The video objects are detected using a novel temporal differencing based procedure and several mathematical morphology-based operations. Then, our technique determines what moving image objects represent pedestrian people, by testing several conditions related to human bodies and detecting the skin regions from the movie frames. A robust human tracking method using a Histogram of Oriented Gradient (HOG) based template matching process is then introduced in our paper. Some person detection and tracking experiments and method comparisons are also described. (C) 2013 Elsevier Ltd. All rights reserved.

引用

页码：1072 / 1079

页数：8

共 25 条

[1]

[Anonymous], 2005, PROC CVPR IEEE

[2]

[Anonymous], 2005, Computer Vision and Pattern Recognition-Workshops

[3]

Barbu T, 2011, INT J COMPUT COMMUN, V6, P21

[4] Variational Image Denoising Approach with Diffusion Porous Media Flow [J].