Title

View-Invariant Action Recognition From Point Triplets

Keywords

Action alignment; Action recognition; Homology; Pose transition; View invariance

Abstract

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. © 2009 IEEE.

Publication Date

8-4-2009

Publication Title

IEEE Transactions on Pattern Analysis and Machine Intelligence

Volume

31

Issue

10

Number of Pages

1898-1905

Document Type

Article

Personal Identifier

scopus

DOI Link

https://doi.org/10.1109/TPAMI.2009.41

Socpus ID

69549135122 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/69549135122

This document is currently not available here.

Share

COinS