- Title
- Action recognition using spatio-temporal distance classifier correlation filter
- Creator
- Anwaar-Ul Haq; Gondal, Iqbal; Murshed, Manzur
- Date
- 2011
- Type
- Text; Conference proceedings
- Identifier
- http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/157128
- Identifier
- vital:11511
- Identifier
-
https://doi.org/10.1109/DICTA.2011.86
- Identifier
- ISBN:978-1-4577-2006-2
- Abstract
- The problem of recognizing human actions is characterized by complex dynamics and strong variations in their executions. Despite this inconvenience, space-time correlations provide valuable clues for their discrimination. Therefore, space-time correlators like emph{Maximum Average Correlation Height} (MACH) filters have successfully been used for action recognition with encouraging results. However, their utility is challenged due to number of factors: (i) these filters are trained only for one class at a time and separate filters are required for each class increasing computational overhead, (ii) these filters simply take average of similar action instances and behave no better than average filters and (iii) misaligned action datasets create problems for these filters as they are not shift-invariant. In this paper, we address these issues by posing action recognition as a multi-class discrimination problem and propose a emph{single} 3D frequency domain filter, named Action ST-DCCF for multiple action classes that mitigates inherent discrepancies of correlation filters. It presents a different interpretation of correlation filters as a method of applying spatio-temporal transformation to the data rather than simply minimizing correlation energy across all possible shifts. Experiments on a variety of action datasets are performed to evaluate our approach. Experimental results are comparable to the existing action recognition approaches.
- Publisher
- IEEE
- Relation
- 2011 International Conference on Digital Image Computing Techniques and Applications (DICTA), Noosa, QLD, 6th-8th Dec, 2011
- Rights
- Copyright IEEE
- Rights
- This metadata is freely available under a CCO license
- Subject
- Correlation; Training; Frequency domain analysis; Accuracy; Vectors; Testing; Humans
- Reviewed
- Hits: 2463
- Visitors: 2387
- Downloads: 0
Thumbnail | File | Description | Size | Format |
---|