Edge-based sports video classification using HMM
| dc.contributor.author | Krishna, Mohan, C. | |
| dc.contributor.author | Yegnanarayana, B. | |
| dc.date.accessioned | 2020-03-30T10:02:50Z | |
| dc.date.available | 2020-03-30T10:02:50Z | |
| dc.date.issued | 2007 | |
| dc.description.abstract | In this paper, we propose a method for sports videos genre classification using edge-based feature, namely edge direction histogram and edge intensity histogram. We demonstrate that these features provide discriminative information useful for sports video classification. We use hidden Markov models (HMMs) to model the sports video categories. Evidence from the two edge based features are combined using a linear weighting rule. We also show that combining evidence from complementary edge features results in improved classification performance. We demonstrate the application of this framework to five sport genre types, namely, cricket, football, tennis, basketball and volleyball. Copyright � 2007 IICAI. | en_US |
| dc.identifier.citation | Proceedings of the 3rd Indian International Conference on Artificial Intelligence, IICAI 2007, 2007, Vol., , pp.559-564 | en_US |
| dc.identifier.uri | https://idr.nitk.ac.in/handle/123456789/7806 | |
| dc.title | Edge-based sports video classification using HMM | en_US |
| dc.type | Book chapter | en_US |