You are not logged in.
Openly accessible

Robust recognition and segmentation of human actions using HMMs with missing observations

Peursum, Patrick, Bui, Hung H., Venkatesh, Svetha and West, Geoff 2005, Robust recognition and segmentation of human actions using HMMs with missing observations, EURASIP journal on applied signal processing, vol. 2005, no. 13, pp. 2110-2126.

Attached Files
Name Description MIMEType Size Downloads
venkatesh-robustrecognition-2005.pdf Published version application/pdf 1.13MB 37

Title Robust recognition and segmentation of human actions using HMMs with missing observations
Author(s) Peursum, Patrick
Bui, Hung H.
Venkatesh, SvethaORCID iD for Venkatesh, Svetha orcid.org/0000-0001-8675-6631
West, Geoff
Journal name EURASIP journal on applied signal processing
Volume number 2005
Issue number 13
Start page 2110
End page 2126
Total pages 17
Publisher SpringerOpen
Place of publication Heidelberg, Germany
Publication date 2005-08-01
ISSN 1687-6172
1687-6180
Keyword(s) human motion analysis
action segmentation
HMMs
Summary This paper describes the integration of missing observation data with hidden Markov models to create a framework that is able to segment and classify individual actions from a stream of human motion using an incomplete 3D human pose estimation. Based on this framework, a model is trained to automatically segment and classify an activity sequence into its constituent subactions during inferencing. This is achieved by introducing action labels into the observation vector and setting these labels as missing data during inferencing, thus forcing the system to infer the probability of each action label. Additionally, missing data provides recognition-level support for occlusions and imperfect silhouette segmentation, permitting the use of a fast (real-time) pose estimation that delegates the burden of handling undetected limbs onto the action recognition system. Findings show that the use of missing data to segment activities is an accurate and elegant approach. Furthermore, action recognition can be accurate even when almost half of the pose feature data is missing due to occlusions, since not all of the pose data is important all of the time.
Notes Reproduced with the kind permission of the copyright owner
Language eng
Field of Research 080104 Computer Vision
Socio Economic Objective 890205 Information Processing Services (incl. Data Entry and Capture)
HERDC Research category C1.1 Refereed article in a scholarly journal
Copyright notice ©2005, Hindawi Publishing Corporation
Free to Read? Yes
Persistent URL http://hdl.handle.net/10536/DRO/DU:30044266

Document type: Journal Article
Collections: School of Information Technology
Open Access Collection
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 8 times in TR Web of Science
Scopus Citation Count Cited 17 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 255 Abstract Views, 37 File Downloads  -  Detailed Statistics
Created: Thu, 05 Apr 2012, 16:02:13 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.