Loading...

Automatic Highlight Detection in Football Videos using Audio and Video Information

Azkia, Ali | 2012

571 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 43480 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Manzuri, Mohammad Taghi
  7. Abstract:
  8. Today, with the spread of various videos especially sports video and availability of them, the need for automated methods for search and retrieval of concepts from videos is strongly felt. On the other hand, summarizing video in order to making significant parts of them available is very important. One of the broadest scope that researchers have provided methods for extracting semantic concepts, is soccer videos. Often to extract high-level events, we need a definition and use of intermediate concepts. In this thesis "replay", "audio highlights" and "view type" are used to extract important events in the game. Here, two new methods are introduced for replay detection and view type classification. Finally, combining these intermediate concepts, the highlights will be identified and they are used for video summarization. Performance of the proposed method is evaluated on a data set over five hours. The data set used is diverse, and from different publishers and under various conditions is collected. Preliminary results have been achived only by considering the audio concepts, is high recall, but the false positives also is high, so the precision is much lower. With the addition of visual information, while a relatively small reduction in recall, precision has increased a conisderable extent. The results show that the proposed method is appropriate.

  9. Keywords:
  10. Video Summarization ; Semantic Concepts Extraction ; Replay Detection

 Digital Object List

  • محتواي پايان نامه
  •   view

 Bookmark

No TOC