DocumentCode
2693956
Title
Human pose recognition by memory-based hierarchical feature matching
Author
Urano, Takehiro ; Matsui, Toshihiro ; Nakata, Toru ; Mizoguchi, Hiroshi
Author_Institution
Dept. of Mech. Eng., Tokyo Univ. of Sci., Japan
Volume
7
fYear
2004
fDate
10-13 Oct. 2004
Firstpage
6412
Abstract
A human posture recognition system based on a memory-based approach is studied. Human body images extracted by depth data are labeled and stored in a database together with compressed feature values consist of higher-order local correlation values and outline diameters. The compressed features are used to speed up the database search in a hierarchical manner. The system can classify human body postures into 6 categories in the experiment. The system was robust against change of humans and light condition.
Keywords
feature extraction; gesture recognition; image matching; visual databases; higher-order local correlation values; human posture recognition system; memory-based approach; memory-based hierarchical feature matching; visual database; Data mining; Face recognition; Hamming distance; Humans; Image coding; Image databases; Image recognition; Impedance matching; Robustness; Spatial databases;
fLanguage
English
Publisher
ieee
Conference_Titel
Systems, Man and Cybernetics, 2004 IEEE International Conference on
ISSN
1062-922X
Print_ISBN
0-7803-8566-7
Type
conf
DOI
10.1109/ICSMC.2004.1401408
Filename
1401408
Link To Document