Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/13664
Title: Tracking and indexing of human actions in video image sequences
Authors: GAMHEWAGE CHAMINDA DE SILVA
Keywords: Computer Vision, Human Detection, Image Sequence Analysis, Video Indexing, Tracking, Event Recognition
Issue Date: 26-Feb-2004
Source: GAMHEWAGE CHAMINDA DE SILVA (2004-02-26). Tracking and indexing of human actions in video image sequences. ScholarBank@NUS Repository.
Abstract: A computer vision system that can detect the presence of humans and recognize their actions in a closed environment is presented. An innovative approach for background modeling and adaptation is followed by a novel method to detect humans present in the scene and acquire human model parameters. The detected humans are tracked and the recorded model parameters are validated against a set of rules to recognize actions and events. The image sequence is indexed using the results for faster searching. Testing the system on a number of image sequences yielded an average accuracy of 90.5%.
URI: http://scholarbank.nus.edu.sg/handle/10635/13664
Appears in Collections:Master's Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
deSilvaGC.pdf8.02 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

238
checked on Dec 11, 2017

Download(s)

119
checked on Dec 11, 2017

Google ScholarTM

Check


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