Recognizing human actions using key poses

Date
2010
Advisor
Instructor
Source Title
2010 20th International Conference on Pattern Recognition
Print ISSN
1051-4651
Electronic ISSN
Publisher
IEEE
Volume
Issue
Pages
1727 - 1730
Language
English
Type
Conference Paper
Journal Title
Journal ISSN
Volume Title
Abstract

In this paper, we explore the idea of using only pose, without utilizing any temporal information, for human action recognition. In contrast to the other studies using complex action representations, we propose a simple method, which relies on extracting "key poses" from action sequences. Our contribution is two-fold. Firstly, representing the pose in a frame as a collection of line-pairs, we propose a matching scheme between two frames to compute their similarity. Secondly, to extract "key poses" for each action, we present an algorithm, which selects the most representative and discriminative poses from a set of candidates. Our experimental results on KTH and Weizmann datasets have shown that pose information by itself is quite effective in grasping the nature of an action and sufficient to distinguish one from others. © 2010 IEEE.

Course
Other identifiers
Book Title
Keywords
A-frames, Action sequences, Complex actions, Data sets, Human actions, Human-action recognition, Key pose, Matching scheme, Pose information, SIMPLE method, Temporal information, Gesture recognition
Citation
Published Version (Please cite this version)