Spatio-Temporal Pyramid Matching for Sports Videos

초록

In this paper, we address the problem of querying video shots based on content-based matching. Our proposed system automatically partitions a video stream into video shots that maintain continuous movements of objects. Finding video shots of the same category is not an easy task because objects in a video shot change their locations over time. Our spatio-temporal pyramid matching (STPM) is the modied spatial pyramid matching (SPM) [15], which considers temporal information in conjunction with spatial locations to match objects in video shots. In addition, we model the mathematical condition in which temporal information contributes to match video shots. In order to improve the matching performance, dynamic features including movements of objects are considered in addition to static features such as edges of objects. In our experiments, several methods based on dierent feature sets and matching methods are compared, and our spatio-temporal pyramid matching performed better than existing methods in video matching for sports videos.