Title :
Exploring the space of a human action
Author :
Sheikh, Yaser ; Sheikh, Mumtaz ; Shah, Mubarak
Author_Institution :
Sch. of Comput. Sci., Central Florida Univ., Orlando, FL, USA
Abstract :
One of the fundamental challenges of recognizing actions is accounting for the variability that arises when arbitrary cameras capture humans performing actions. In this paper, we explicitly identify three important sources of variability: (1) viewpoint, (2) execution rate, and (3) anthropometry of actors, and propose a model of human actions that allows us to investigate all three. Our hypothesis is that the variability associated with the execution of an action can be closely approximated by a linear combination of action bases in joint spatio-temporal space. We demonstrate that such a model bounds the rank of a matrix of image measurements and that this bound can be used to achieve recognition of actions based only on imaged data. A test employing principal angles between subspaces that is robust to statistical fluctuations in measurement data is presented to find the membership of an instance of an action. The algorithm is applied to recognize several actions, and promising results have been obtained.
Keywords :
image motion analysis; image recognition; statistical analysis; actor anthropometry; execution rate; human action recognition; image measurement; image recognition; principal angle; spatio-temporal space; statistical fluctuation; Anthropometry; Cameras; Computer science; Computer vision; Humans; Image recognition; Laboratories; Linear approximation; Object recognition; Space exploration;
Conference_Titel :
Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on
Print_ISBN :
0-7695-2334-X
DOI :
10.1109/ICCV.2005.90