Loading [MathJax]/extensions/MathMenu.js
Human pose recognition by memory-based hierarchical feature matching | IEEE Conference Publication | IEEE Xplore

Human pose recognition by memory-based hierarchical feature matching


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 wi...Show More

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.
Date of Conference: 10-13 October 2004
Date Added to IEEE Xplore: 07 March 2005
Print ISBN:0-7803-8566-7
Print ISSN: 1062-922X
Conference Location: The Hague

References

References is not available for this document.