Content-based Video Retrieval Based on Similarity of Camera Motion

Abstract

This paper proposes a method for content-based sports video retrieval using camera work information. Since particular camera work for a typical scene exists in sports videos, camera work transition becomes an effective cue for retrieving a sports scene based on its content. The proposed method extracts a series of camera parameters from both a user-specified scene of a retrieval key and a video stream of a retrieval target, and detects scenes having content similar to that of the key from the target by applying continuous DP matching. The method was evaluated using a video stream of a baseball game. Recall-Precision curves make its effectiveness clear.