Video summarization is defined as creating a shorter video clip or a video poster which includes all but only the important scenes in an original video stream. In this paper, we propose two methods of generating a summary of arbitrary length for sports videos. One is to create a concise video clip by temporally compressing the amount of the video data. The other is to provide a video poster by spatially presenting the image keyframes which represent the whole video content. Both methods deal with the videos with metadata to summarize the video semantically. We experimentally verified the effectiveness of our method by comparing the results with man-made video summaries as well as by conducting the questionnaires to the users.
展开▼
