Fast Highlight Detection and Scoring for Broadcast Soccer Video Summarization using On-Demand Feature Extraction and Fuzzy Inference

In this paper, a fast highlight detection and scoring method is proposed using an ondemand feature extraction and a fuzzy inference system. The proposed method partitions video to highlights and analyzes their content using an on-demand feature extraction approach. Then, a score is assigned to each highlight using a Fuzzy Inference System (FIS) according to the analyzed content. The assigned score determines importance of the events occurred in the highlight. This method is useful for flexible video summarization. The proposed method for on-demand feature extraction is a heuristic model of attention control that reduces computational complexity of the algorithm greatly. Additionally, FIS offers a simple and robust solution for content analysis. Experimental results illustrate that the proposed method is fast and processes about 130 frames per second on a personal computer. In addition, objective and subjective evaluations show that the proposed method generates high quality results for highlight detection, scoring and video summarization.