Please use this identifier to cite or link to this item:
Title: Human activities recognition by head movement using partial recurrent neural network
Authors: Tan, H.C.C. 
Kui, J.
De Silva, L.C. 
Keywords: (Elman) partial recurrent neural network
Connectionist motion-based recognition approach
Human activities recognition
Human head tracking
Spatial temporal sequence analysis
Static monocular color camera
Issue Date: 2003
Citation: Tan, H.C.C., Kui, J., De Silva, L.C. (2003). Human activities recognition by head movement using partial recurrent neural network. Proceedings of SPIE - The International Society for Optical Engineering 5150 III : 2007-2014. ScholarBank@NUS Repository.
Abstract: Traditionally, human activities recognition has been achieved mainly by the statistical pattern recognition methods or the Hidden Markov Model (HMM). In this paper, we propose a novel use of the connectionist approach for the recognition of ten simple human activities - walking, sitting down, getting up, squatting down and standing up, in both lateral and frontal views, in an office environment. By means of tracking the head movement of the subjects over consecutive frames from a database of different color image sequences, and incorporating the Elman model of the partial recurrent neural network (RNN) that learns the sequential patterns of relative change of the head location in the images, the proposed system is able to robustly classify all the ten activities performed by unseen subjects from both sexes, of different race and physique, with a recognition rate as high as 92.5%. This demonstrates the potential of employing partial RNN to recognize complex activities in the increasingly popular human-activities-based applications.
Source Title: Proceedings of SPIE - The International Society for Optical Engineering
ISSN: 0277786X
DOI: 10.1117/12.503257
Appears in Collections:Staff Publications

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


checked on Oct 21, 2021


checked on Oct 21, 2021

Page view(s)

checked on Oct 14, 2021

Google ScholarTM



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