Abstract | ||
---|---|---|
This paper proposes a method for human action classification by utilizing correlations between SURF based descriptors. This approach provides us a novel type of descriptor that can be used for action classification. The method proposed is tested using an SVM classification technique. For evaluation purposes, the KTH action recognition dataset, which is a standard benchmark for this area is used as it is one of the most well known and challenging dataset. The method proposed was able to successfully classify different action classes. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/ICIP.2012.6467131 | Image Processing |
Keywords | Field | DocType |
correlation methods,image classification,spatiotemporal phenomena,support vector machines,transforms,video signal processing,KTH action recognition dataset,SURF-based spatio-temporal correlated descriptors,SVM classification technique,human action classification,standard benchmark,SURF,classification,correlations,human action | Pattern recognition,Computer science,Action recognition,Support vector machine,Artificial intelligence,Contextual image classification,Machine learning | Conference |
ISSN | ISBN | Citations |
1522-4880 E-ISBN : 978-1-4673-2532-5 | 978-1-4673-2532-5 | 3 |
PageRank | References | Authors |
0.39 | 4 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Aznul Qalid Md Sabri | 1 | 16 | 3.39 |
J. Boonaert | 2 | 14 | 1.13 |
Stéphane Lecoeuche | 3 | 6 | 1.46 |
El Mustapha Mouaddib | 4 | 3 | 0.39 |