Reviewers
|
Book & Monographs
|
Conference
|
Contact Us
SEARCH
|
My Profile
|
My Shopping Cart
|
Logout
Home
Publication Ethics
Open Access Policy
Guidelines
Journals
▼pphmjopenaccess.com▼
Engineering
Mathematics
Statistics
All Journals
Submit a Manuscript
Author Login
Author Registration
Forget Password
Journal Menu
Journal Home
Editorial Board
Guidelines for Authors
Indexing
Contents
Contents
Subscribe
Publication Ethics and Publication Malpractice Statement
Content
Volume 19 (2022)
Volume 19, (In Progress)
Pg 1 - 11 (June 2022)
Volume 18 (2019)
Volume 18, Issue 1
Pg 1 - 37 (June 2019)
Volume 17 (2018)
Volume 17, Issue 2
Pg 55 - 74 (December 2018)
Volume 17, Issue 1
Pg 1 - 54 (June 2018)
Volume 16 (2016)
Volume 16, Issue 3-4
Pg 61 - 101 (November 2016)
Volume 16, Issue 1-2
Pg 1 - 60 (May 2016)
Volume 15 (2015)
Volume 15, Issue 1-2
Pg 1 - 55 (November 2015)
Volume 14 (2015)
Volume 14, Issue 2
Pg 59 - 109 (May 2015)
Volume 14, Issue 1
Pg 1 - 57 (February 2015)
Volume 13 (2014)
Volume 13, Issue 2
Pg 73 - 152 (November 2014)
Volume 13, Issue 1
Pg 1 - 72 (August 2014)
Volume 12 (2014)
Volume 12, Issue 2
Pg 61 - 128 (May 2014)
Volume 12, Issue 1
Pg 1 - 60 (February 2014)
Volume 11 (2013)
Volume 11, Issue 2
Pg 51 - 107 (November 2013)
Volume 11, Issue 1
Pg 1 - 50 (August 2013)
Volume 10 (2013)
Volume 10, Issue 2
Pg 77 - 131 (May 2013)
Volume 10, Issue 1
Pg 1 - 76 (February 2013)
Volume 9 (2012)
Volume 9, Issue 2
Pg 83 - 159 (November 2012)
Volume 9, Issue 1
Pg 1 - 82 (August 2012)
Volume 8 (2012)
Volume 8, Issue 2
Pg 69 - 145 (May 2012)
Volume 8, Issue 1
Pg 1 - 67 (February 2012)
Volume 7 (2011)
Volume 7, Issue 2
Pg 99 - 168 (November 2011)
Volume 7, Issue 1
Pg 1 - 97 (August 2011)
Volume 6 (2011)
Volume 6, Issue 2
Pg 105 - 204 (May 2011)
Volume 6, Issue 1
Pg 1 - 104 (February 2011)
Volume 5 (2010)
Volume 5, Issue 2
Pg 131 - 263 (November 2010)
Volume 5, Issue 1
Pg 1 - 129 (August 2010)
Volume 4 (2010)
Volume 4, Issue 2
Pg 93 - 184 (May 2010)
Volume 4, Issue 1
Pg 1 - 92 (February 2010)
Volume 3 (2009)
Volume 3, Issue 3
Pg 175 - 266 (November 2009)
Volume 3, Issue 2
Pg 87 - 174 (July 2009)
Volume 3, Issue 1
Pg 1 - 85 (March 2009)
Volume 2 (2008)
Volume 2, Issue 3
Pg 201 - 284 (November 2008)
Volume 2, Issue 2
Pg 97 - 199 (July 2008)
Volume 2, Issue 1
Pg 1 - 96 (March 2008)
Volume 1 (2007)
Volume 1, Issue 3
Pg 189 - 283 (November 2007)
Volume 1, Issue 2
Pg 105 - 187 (July 2007)
Volume 1, Issue 1
Pg 1 - 104 (March 2007)
Categories
▼pphmjopenaccess.com▼
Engineering
Mathematics
Statistics
All Journals
Advances in Computer Science and Engineering
Advances in Computer Science and Engineering
Volume 3, Issue 3, Pages 175 - 186 (November 2009)
3D HUMAN POSTURE ESTIMATION BASED ON LINEAR REGRESSION OF HOG FEATURES FROM MONOCULAR IMAGES
Katsunori Onishi (Japan), Tetsuya Takiguchi (Japan) and Yasuo Ariki (Japan)
Abstract:
In this paper, we propose a method to estimate the 3D human posture from monocular image without using the markers. A 3D human body is expressed by a multi-joint model, and a set of the joint angles describes a posture. The proposed method estimates the posture using Histograms of Oriented Gradients (HOG) feature vectors that can express the shape of the object in the input image obtained from monocular camera. In addition, the feature dimension of the background region is reduced for reliability by principal component analysis (PCA) computed at every block of HOG. The joint angles in Human multi-joint model are estimated by linear regression analysis applied to its feature vector extracted from the input image. As a result of comparison experiment with the Shape Contexts features, the RMS error was reduced by about 5.35 degrees.
Keywords and phrases:
posture estimation, histograms of oriented gradients, principal analysis, linear regression.
Number of Downloads:
286 |
Number of Views:
612
Next
P-ISSN: 0973-6999
Journal Stats
Publication count:
171
Citation count (Google Scholar):
0
h10-index (Google Scholar):
0
h-index (Google Scholar):
0
Downloads :
53654
Views:
144378
Downloads/publish articles:
313.77
Citations (Google Scholar)/publish articles:
0
This website is best viewed at 1024x768 or higher resolution with Microsoft Internet Explorer 6 or newer.