Title :
Action Recognition Using Space-Time Shape Difference Images
Author :
Qu, Hao ; Wang, Liang ; Leckie, Christopher
Author_Institution :
Dept. of Comput. Sci. & Software Eng., Univ. of Melbourne, Melbourne, VIC, Australia
Abstract :
A common approach to human action recognition is to use 2-D silhouettes in the space-time volume as a basis for further extraction of useful features. In this paper, we present a novel motion representation based on difference images. We show that this representation exploits the dynamics of motion, and show its effectiveness in action recognition. Moreover, experimental results demonstrate that this method is highly accurate and is not sensitive to the resolution of the video.
Keywords :
feature extraction; image motion analysis; image resolution; shape recognition; 2D silhouettes; feature extraction; human action recognition; motion dynamics; motion representation; space-time shape difference images; space-time volume; video resolution; Accuracy; Clustering algorithms; Feature extraction; Histograms; Humans; Shape; Training; feature extraction; human action recognition; space-time differences;
Conference_Titel :
Pattern Recognition (ICPR), 2010 20th International Conference on
Conference_Location :
Istanbul
Print_ISBN :
978-1-4244-7542-1
DOI :
10.1109/ICPR.2010.893
