A multi-modal highlight extraction scheme for sports videos using an information-theoretic excitability measure

Abstract

A generic method for sports video highlight selection is presented in this study. Processing begins where the video is divided into short segments and several multi-modal features are extracted from each video segment. Excitability is computed based on the likelihood of the features lying in certain regions of their probability density functions that are exciting and rare. The proposed measure is used to rank order the partitioned segment stream to compress the overall video sequence and produce a contiguous set of highlights. Experiments are performed on baseball videos using excitement in the commentators' speech, audio energy, slow motion replay, scene cut density, and motion activity as features. Subjective evaluation of excitability and ranking of video segments yield a higher correlation with the proposed measure compared to well-established techniques indicating the effectiveness of the approach.

Multi-modal highlight generation for sports videos using an information-theoretic excitability measure

“…In this paper, we extend the feature space and propose an information-theoretic measure of excitability for sports highlight selection in a generic framework [16]. Our proposed measure is based on a simple but powerful principle of information theory: the less likely an event, the more information it contains.…”