Abstract
This letter addresses the problem of analyzing spatio–temporal patterns for action recognition. In this letter we organize the whole training set in a single tensor, with each mode indicating one factor which influences the result of recognition, e.g., various view points. A novel method is proposed for tensor decomposition by discriminant analysis of multiscale features which represent the motion details on different scales. In addition, the nearest neighbor classifier (NNC) is employed for action classification. Experiments on the self-manufactured action database under ideal conditions showed that the proposed method was better than state-of-the-art methods under various view angles in terms of accuracy. Experiments on the commonly used KTH database also showed that the proposed method had low time complexity and was robust against changing view points.
Original language | English |
---|---|
Pages (from-to) | 95-98 |
Number of pages | 4 |
Journal | IEEE Signal Processing Letters |
Volume | 19 |
Issue number | 2 |
Early online date | 16 Dec 2011 |
DOIs | |
Publication status | Published - Feb 2012 |
Bibliographical note
Author's personal website and employer's publicly accessible websitesPreprint - Must be removed upon publication of final version and replaced with either full citation to IEEE work with a Digital Object Identifier or link to article abstract in IEEE Xplore or Authors post-print
Preprint - Set-phrase must be added once submitted to IEEE for publication ("This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible")
Preprint - Set phrase must be added when accepted by IEEE for publication ("(c) 20xx IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.")
Preprint - IEEE must be informed as to the electronic address of the pre-print
Postprint - Publisher copyright and source must be acknowledged (see above set statement)
Publisher's version/PDF cannot be used
Publisher copyright and source must be acknowledged
Keywords
- Action recognition
- discriminant analysis
- multiscale features
- multiview
- tensor