Directional space-time oriented gradients for 3D visual pattern analysis

Norouznezhad, Ehsan, Harandi, Mehrtash T., Bigdeli, Abbas, Baktash, Mahsa, Postula, Adam and Lovell, Brian C. (2012). Directional space-time oriented gradients for 3D visual pattern analysis. In: Computer Vision, ECCV 2012 - 12th European Conference on Computer Vision, Proceedings. 12th European Conference on Computer Vision, ECCV 2012, Florence, Italy, (736-749). 7 - 13 October 2012. doi:10.1007/978-3-642-33712-3_53


Author Norouznezhad, Ehsan
Harandi, Mehrtash T.
Bigdeli, Abbas
Baktash, Mahsa
Postula, Adam
Lovell, Brian C.
Title of paper Directional space-time oriented gradients for 3D visual pattern analysis
Conference name 12th European Conference on Computer Vision, ECCV 2012
Conference location Florence, Italy
Conference dates 7 - 13 October 2012
Proceedings title Computer Vision, ECCV 2012 - 12th European Conference on Computer Vision, Proceedings   Check publisher's open access policy
Journal name Lecture Notes in Computer Science   Check publisher's open access policy
Place of Publication Heidelberg, Germany
Publisher Springer
Publication Year 2012
Year available 2012
Sub-type Fully published paper
DOI 10.1007/978-3-642-33712-3_53
Open Access Status Not yet assessed
ISBN 9783642337116
9783642337123
ISSN 0302-9743
1611-3349
Volume 7574
Issue 3
Start page 736
End page 749
Total pages 14
Language eng
Abstract/Summary Various visual tasks such as the recognition of human actions, gestures, facial expressions, and classification of dynamic textures require modeling and the representation of spatio-temporal information. In this paper, we propose representing space-time patterns using directional spatio-temporal oriented gradients. In the proposed approach, a 3D video patch is represented by a histogram of oriented gradients over nine symmetric spatio-temporal planes. Video comparison is achieved through a positive definite similarity kernel that is learnt by multiple kernel learning. A rich spatio-temporal descriptor with a simple trade-off between discriminatory power and invariance properties is thereby obtained. To evaluate the proposed approach, we consider three challenging visual recognition tasks, namely the classification of dynamic textures, human gestures and human actions. Our evaluations indicate that the proposed approach attains significant classification improvements in recognition accuracy in comparison to state-of-the-art methods such as LBP-TOP, 3D-SIFT, HOG3D, tensor canonical correlation analysis, and dynamical fractal analysis.
Subjects 1700 Computer Science
2614 Theoretical Computer Science
Q-Index Code E1
Q-Index Status Provisional Code
Institutional Status UQ

Document type: Conference Paper
Sub-type: Fully published paper
Collection: School of Information Technology and Electrical Engineering Publications
 
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 8 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Thu, 28 Nov 2013, 18:55:01 EST by System User on behalf of School of Information Technol and Elec Engineering