Segmentation of individual actions from a stream of human motion is an open problem in computer vision. This paper approaches the problem of segmenting higher-level activities into their component sub-actions using Hidden Markov Models modified to handle missing data in the observation vector. By controlling the use of missing data, action labels can be inferred from the observation vector during inferencing, thus performing segmentation and classification simultaneously. The approach is able to segment both prominent and subtle actions, even when subtle actions are grouped together. The advantage of this method over sliding windows and Viterbi state sequence interrogation is that segmentation is performed as a trainable task, and the temporal relationship between actions is encoded in the model and used as evidence for action labelling.
History
Event
International Conference on Pattern Recognition (17th : 2004 : Cambridge, U. K.)
Pagination
440 - 445
Publisher
IEEE
Location
Cambridge, U. K.
Place of publication
Washington, D. C.
Start date
2004-08-23
End date
2004-08-26
ISSN
1051-4651
ISBN-10
0769521282
Language
eng
Notes
This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.
Publication classification
E1.1 Full written paper - refereed
Copyright notice
2004, IEEE
Editor/Contributor(s)
J Kittler, M Petrou, M Nixon
Title of proceedings
ICPR 2004 : Proceedings of the 17th International Conference on Pattern Recognition