Please use this identifier to cite or link to this item:
Scopus Web of ScienceĀ® Altmetric
Type: Conference paper
Title: Informative shape representations for human action recognition
Author: Wang, L.
Suter, D.
Citation: 18th International Conference on Pattern Recognition (ICPR'06) 2006, Volume 2, 2006: pp.1266-1269
Publisher: IEEE
Publisher Place: Online
Issue Date: 2006
Series/Report no.: International Conference on Pattern Recognition
ISBN: 0769525210
ISSN: 1051-4651
Conference Name: International Conference on Pattern Recognition (18th : 2006 : Hong Kong)
Editor: Tang, Y.Y.
Wang, S.P.
Lorette, G.
Yeung, D.S.
Yan, H.
Statement of
Liang Wang and David Suter
Abstract: Shape and kinematics are two important cues in human movement analysis. Due to real difficulties in extracting kinematics from videos accurately, this paper proposes to address the problem of human action recognition by spatiotemporal shape analysis. Without explicit feature tracking and complex probabilistic modeling of human movements, we directly convert an associated sequence of human silhouettes derived from videos into two types of computationally efficient representations, i.e., average motion energy and mean motion shape, to characterize actions. Supervised pattern classification techniques using various distance measures are used for recognition. The encouraging experimental results are obtained on a recent dataset including 10 different actions from 9 subjects.
DOI: 10.1109/ICPR.2006.711
Published version:
Appears in Collections:Aurora harvest
Computer Science publications

Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.