| View-invariant action recognition from point triplets. | |
| | |
MedLine Citation:
|
PMID: 19696457 Owner: NLM Status: MEDLINE |
Abstract/OtherAbstract:
|
We propose a new view-invariant measure for action recognition. For this purpose, we introduce the idea that the motion of an articulated body can be decomposed into rigid motions of planes defined by triplets of body points. Using the fact that the homography induced by the motion of a triplet of body points in two identical pose transitions reduces to the special case of a homology, we use the equality of two of its eigenvalues as a measure of the similarity of the pose transitions between two subjects, observed by different perspective cameras and from different viewpoints. Experimental results show that our method can accurately identify human pose transitions and actions even when they include dynamic timeline maps, and are obtained from totally different viewpoints with different unknown camera parameters. |
| | |
Authors:
|
Yuping Shen; Hassan Foroosh |
Related Documents
:
|
6354037 - Compound action-potential tuning curves in normal and acoustically traumatized cats. 6238127 - Perceiving affordances: visual guidance of stair climbing. 1600077 - A reconstruction of charge movement during the action potential in frog skeletal muscle. 15641407 - Perception of biological motion: a stimulus set of human point-light actions. 8197627 - Effects of pulsed ultrasound on the mouse neonate: hind limb paralysis and lung hemorrh... 2149707 - Alkali light chains are involved in stabilization of myosin head. |
Publication Detail:
|
Type: Journal Article; Research Support, Non-U.S. Gov't |
Journal Detail:
|
Title: IEEE transactions on pattern analysis and machine intelligence Volume: 31 ISSN: 0162-8828 ISO Abbreviation: - Publication Date: 2009 Oct |
Date Detail:
|
Created Date: 2009-08-21 Completed Date: 2009-10-06 Revised Date: - |
Medline Journal Info:
|
Nlm Unique ID: 9885960 Medline TA: IEEE Trans Pattern Anal Mach Intell Country: United States |
Other Details:
|
Languages: eng Pagination: 1898-905 Citation Subset: IM |
Affiliation:
|
University of Central Florida, Orlando, FL 32816-2362, USA. ypshen@cs.ucf.edu |
Export Citation:
|
APA/MLA Format Download EndNote Download BibTex |
| MeSH Terms | |
Descriptor/Qualifier:
|
Algorithms Databases, Factual Human Activities Humans Motion Movement / physiology* Pattern Recognition, Automated / methods* Posture / physiology* |
From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine
Previous Document: Two-dimensional multilabel active learning with an efficient online adaptation model for image class...
Next Document: Shape and motion reconstruction from 3D-to-1D orthographically projected data via object-image relat...