Human Edge Segmentation From 2D Images By Histogram of Oriented Gradients and Edge Matching Algorithm

被引：0

作者：

Sombatpiboonporn, Phakjira ^{[1
]}

Charoenpong, Theekapun ^{[1
]}

Chianrabutra, Chamaporn ^{[2
]}

Supasuteekul, Ajaree ^{[3
]}

Pattanaworapan, Kanjana ^{[4
]}

机构：

[1] Srinakharinwirot Univ, Fac Engn, Dept Biomed Engn, Nakhonnayok, Thailand

[2] Kasetsart Univ, Fac Engn, Dept Elect Mech Mfg Engn, Bangkok, Thailand

[3] Srinakharinwirot Univ, Fac Engn, Dept Mech Engn, Nakhonnayok, Thailand

[4] Bangkok Univ, Sch Entrepreneurship & Management, Bangkok, Thailand

来源：

2019 FIRST INTERNATIONAL SYMPOSIUM ON INSTRUMENTATION, CONTROL, ARTIFICIAL INTELLIGENCE, AND ROBOTICS (ICA-SYMP 2019) | 2019年

关键词：

Human segmentation; Human detection; Histogram of oriented gradient; Template matching technique; MOTION;

D O I：

10.1109/ica-symp.2019.8646191

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Current research performance is limited to segment precise human edge. In this paper, we proposed an edge matching algorithm for human edge segmentation from 2D images by means of the histogram of oriented gradients technique and SVM classification. The algorithm having four steps, namely image sequence acquisition, human detection, edge segmentation and human edge segmentation, were carried out in this work. Data was collected from 710 full body human image. Based on the finding of this work, error results of the human edge in the parts of head, neck, body, and leg were 9.86, 13.60, 6.63, and 637 pixels, respectively. The advantages of the proposed method is this method can segment human from image by using only one image and a small group of databases.

引用

页码：29 / 32

页数：4

共 10 条

[1] [Anonymous], 2005, Computer Vision and Pattern Recognition-Workshops
[2] On Detection of Multiple Object Instances Using Hough Transforms
Barinova, Olga
Lempitsky, Victor
Kholi, Pushmeet
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2012, 34 (09) : 1773 - 1784
[3] Human detection from images and videos: A survey
Duc Thanh Nguyen
Li, Wanqing
Ogunbona, Philip O.
[J]. PATTERN RECOGNITION, 2016, 51 : 148 - 175
[4] Eng HL, 2004, INT C PATT RECOG, P257
[5] Human detection in outdoor scene using spatio-temporal motion analysis
Haga, T
Sumi, K
Yagi, Y
[J]. PROCEEDINGS OF THE 17TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 4, 2004, : 331 - 334
[6] Shape-based human detection for threat assessment
Lee, DJ
Zhan, PC
Thomas, A
Schoenberger, R
[J]. VISUAL INFORMATION PROCESSING XIII, 2004, 5438 : 81 - 91
[7] Human Detection Using Partial Least Squares Analysis
Schwartz, William Robson
Kembhavi, Aniruddha
Harwood, David
Davis, Larry S.
[J]. 2009 IEEE 12TH INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2009, : 24 - 31
[8] Detecting human motion with support vector machines
Sidenbladh, H
[J]. PROCEEDINGS OF THE 17TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 2, 2004, : 188 - 191
[9] Tsogkas S., 2015, DEEP LEARNING SEMANT, P1
[10] Zhang SB, 2013, 2013 NINTH INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION (ICNC), P1349, DOI 10.1109/ICNC.2013.6818189

← 1 →