Please use this identifier to cite or link to this item:
|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.
Multiple human objects
Skin color detection
Tacking in multiple cameras
|Citation:||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|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Oct 26, 2018
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.