Title :
Human action recognition employing 2DPCA and VQ in the spatio-temporal domain
Author :
Naiel, Mohamed A. ; Abdelwahab, Moataz M. ; Mikhael, Wasfy B.
Author_Institution :
Sch. of Commun. & Inf. Technol., Nile Univ., Sixth October, Egypt
Abstract :
In this paper a novel algorithm for human action recognition is presented. This approach is based on Two-Dimensional Principal Component Analysis (2DPCA) and Vector Quantization (VQ) in the spatial-temporal domain. This method reduces computational complexity by a factor of 98, while maintaining the storage requirement and the recognition accuracy, compared with some of the most recent approaches in the field. Experimental results applied on the Weizmann dataset confirm the excellent properties of the proposed algorithm.
Keywords :
computational complexity; image motion analysis; principal component analysis; vector quantisation; 2DPCA; VQ; Weizmann dataset; computational complexity; human action recognition; spatiotemporal domain; two-dimensional principal component analysis; vector quantization; Accuracy; Algorithm design and analysis; Computer vision; Humans; Principal component analysis; Testing; Training;
Conference_Titel :
NEWCAS Conference (NEWCAS), 2010 8th IEEE International
Conference_Location :
Montreal, QC
Print_ISBN :
978-1-4244-6806-5
Electronic_ISBN :
978-1-4244-6804-1
DOI :
10.1109/NEWCAS.2010.5604002