Support-vector-machine tree-based domain knowledge learning toward automated sports video classification

Xiao, Guoqiang; Jiang, Yang; Song, Gang; Jiang, Jianmin

Abstract

We propose a support-vector-machine (SVM) tree to hierarchically learn from domain knowledge represented by low-level features toward automatic classification of sports videos. The proposed SVM tree adopts a binary tree structure to exploit the nature of SVMs binary classification, where each internal node is a single SVM learning unit, and each external node represents the classified output type. Such a SVM tree presents a number of advantages, which include: 1. low computing cost; 2. integrated learning and classification while preserving individual SVMs learning strength; and 3. flexibility in both structure and learning modules, where different numbers of nodes and features can be added to address specific learning requirements, and various learning models can be added as individual nodes, such as neural networks, AdaBoost, hidden Markov models, dynamic Bayesian networks, etc. Experiments support that the proposed SVM tree achieves good performances in sports video classifications. © 2010 Society of Photo-Optical Instrumentation Engineers.

Citation

Xiao, G., Jiang, Y., Song, G., & Jiang, J. (2010). Support-vector-machine tree-based domain knowledge learning toward automated sports video classification. Optical Engineering, 49(12), Article 127003. https://doi.org/10.1117/1.3518080

• Journal Article Type: Article
• Online Publication Date: Dec 1, 2010
• Publication Date: Dec 1, 2010
• Deposit Date: Nov 8, 2023
• Journal: Optical Engineering
• Print ISSN: 0091-3286
• Electronic ISSN: 1560-2303
• Publisher: Society of Photo-optical Instrumentation Engineers
• Peer Reviewed: Peer Reviewed
• Volume: 49
• Issue: 12
• Article Number: 127003
• DOI: https://doi.org/10.1117/1.3518080
• Public URL: https://hull-repository.worktribe.com/output/4435458