A Big-Bang Big-Crunch fuzzy logic based system for sports video scene classification

Sports video summarization and classification is becoming a very important topic due to the pressing need to automatically classify sports scenes to enable better sport analysis, refereeing, training and advertisement. The vast majority of the techniques applied to sports video classifications involved black box techniques such as support vector machines (SVMs) and neural networks, which do not provide models that could be easily analysed and understood by human users. Fuzzy logic classification systems provide white box techniques encompassing linguistic rules and labels that can easily be understood and analysed by humans. However, the traditional fuzzy classification systems can result in huge rule bases due to the curse of the dimensionality problem. This paper presents a fuzzy logic based system for sports video scene classification using the Big Bang-Big Crunch technique to optimize the rules, thus producing high classification accuracy with a small number of rules, increasing system interpretability. Various experiments conducted on football videos demonstrated that the system produces a fuzzy classification system with only eight rules with average classification accuracy of 83%, outperforming other black box classification models which employ neural networks.