Please use this identifier to cite or link to this item:
Type: Conference paper
Title: Human motion recognition using gaussian processes classification
Author: Zhou, H.
Wang, L.
Suter, D.
Citation: Proceedings of the 19th International Conference on Pattern Recognition (ICPR), Tampa, Florida, USA., 2008: pp.1-4
Publisher: IEEE
Publisher Place: Online
Issue Date: 2008
Series/Report no.: International Conference on Pattern Recognition
ISBN: 9781424421749
ISSN: 1051-4651
Conference Name: International Conference on Pattern Recognition (19th : 2008 : Florida)
Statement of
Hang Zhou, Liang Wang and David Suter
Abstract: This paper investigates the applicability of Gaussian processes (GP) classification for recognition of articulated and deformable human motions from image sequences. Using tensor subspace analysis (TSA), space-time human silhouettes (extracted from motion videos) are transformed to low-dimensional multivariate time series, based on which structure-based statistical features are calculated to summarize the motion properties. GP classification is then used to learn and predict motion categories. Experimental results on two real-world state-of-the-art datasets show that the proposed approach is effective, and outperforms support vector machine (SVM).
Description (link):
Appears in Collections:Aurora harvest 5
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.