Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/69294
Title: An Automatic System for Multiple Human Tracking & Actions Recognition in Office Environment
Authors: Henry, T.C.C. 
Ruwan Janapriya, E.G.
De Silva, L.C. 
Keywords: Activities/action recognition
Monocular
Multiple human objects
Skin color detection
Tacking in multiple cameras
Issue Date: 2003
Source: Henry, T.C.C.,Ruwan Janapriya, E.G.,De Silva, L.C. (2003). An Automatic System for Multiple Human Tracking & Actions Recognition in Office Environment. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings 3 : 45-48. ScholarBank@NUS Repository.
Abstract: An automatic system for human detection and recognition of common actions found in a office environment was presented. The human object detection and its presence verification was based on the CbCr skin color model, which had demonstrated to be feature invariant and efficient. The linear vector quantization (LVQ) action classifier was found to be robust enough to classify 10 action sequences executed by subjects of different builds and sizes, and attained a classification rate of 78%.
Source Title: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
URI: http://scholarbank.nus.edu.sg/handle/10635/69294
ISSN: 15206149
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Page view(s)

21
checked on Dec 9, 2017

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.