Back to Search
Start Over
SPATIO-TEMPORAL CO-OCCURRENCE CHARACTERIZATIONS FOR HUMAN ACTION CLASSIFICATION.
- Source :
- Malaysian Journal of Computer Science; 2017, Vol. 30 Issue 3, p154-173, 20p
- Publication Year :
- 2017
-
Abstract
- The human action classification task is a widely researched topic and is still an open problem. Many state-ofthe- arts approaches involve the usage of bag-of-video-words with spatio-temporal local features to construct characterizations for human actions. In order to improve beyond this standard approach, we investigate the usage of co-occurrences between local features. We propose the usage of co-occurrences information to characterize human actions. A trade-off factor is used to define an optimal trade-off between vocabulary size and classification rate. Next, a spatio-temporal co-occurrence technique is applied to extract co-occurrence information between labeled local features. Novel characterizations for human actions are then constructed. These include a vector quantized correlogram-elements vector, a highly discriminative PCA (Principal Components Analysis) co-occurrence vector and a Haralick texture vector. Multi-channel kernel SVM (support vector machine) is utilized for classification. For evaluation, the well known KTH as well as the UCF-Sports action datasets are used. We obtained state-of-the-arts classification performance. We also demonstrated that we are able to fully utilize co-occurrence information, and improve the standard bag-of-video-words approach. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 01279084
- Volume :
- 30
- Issue :
- 3
- Database :
- Supplemental Index
- Journal :
- Malaysian Journal of Computer Science
- Publication Type :
- Academic Journal
- Accession number :
- 126398001
- Full Text :
- https://doi.org/10.22452/mjcs.vol30no3.1