Presentation is loading. Please wait.

Presentation is loading. Please wait.

A Novel Framework for Semantic Annotation and Personalized Retrieval of Sports Video IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 10, NO. 3, APRIL 2008.

Similar presentations


Presentation on theme: "A Novel Framework for Semantic Annotation and Personalized Retrieval of Sports Video IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 10, NO. 3, APRIL 2008."— Presentation transcript:

1 A Novel Framework for Semantic Annotation and Personalized Retrieval of Sports Video IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 10, NO. 3, APRIL 2008

2 Outline  Introduction  Semantic Annotation of Sports Video Text Analysis Video Analysis Text/Video Alignment Video Annotation and Indexing  Personalized Video Retrieval  Experiment and Evaluation

3  Introduction  Semantic Annotation of Sports Video Text Analysis Video Analysis Text/Video Alignment Video Annotation and Indexing  Personalized Video Retrieval  Experiment and Evaluation

4

5  Introduction  Semantic Annotation of Sports Video Text Analysis Video Analysis Text/Video Alignment Video Annotation and Indexing  Personalized Video Retrieval  Experiment and Evaluation

6 Text Analysis  Caption text overlaid on the video The recognition of caption text overlaid on sports video using OCR is not ideal due to the quality of the broadcast sports video.  Closed caption Closed caption is a transcript from speech to text thus contains a lot of information irrelevant to the games and lacks of a well-defined structure.

7 Text Analysis  Web-casting text is another text source related to sports video It is available in many sports websites such as BBC and ESPN and can be easily accessed during or after the game The content of web-casting text is more focused on events of sports games and has a well-defined structure Since webcasting text is a text counterpart of broadcast sports video, it includes detailed information of an event in sports games

8

9

10 The analysis of web-casting text  ROI Segmentation  Keyword Identification  Text Event Detection

11

12 ROI Segmentation

13 Keyword Identification

14 Text Event Detection  Example 1 (soccer): 79:19 Goal by Didier Drogba (Chelsea) drilled left-footed from right side of six-yard box (6 yards). Chelsea 4-1 Bayern Munich  Example 2 (basketball): 8:52 Kobe Bryant makes 17-foot two point shot (Smush Parker assists). LA Lakers 9-11 Denver

15 Text Event Detection  The presentation style of the event for soccer and basketball in web-casting text is slightly different, but the event and event semantics can be easily extracted and represented using a common structure as follows. by of at Goal by Frank Lampard of Chelsea at 58:58 (soccer)

16  Introduction  Semantic Annotation of Sports Video Text Analysis Video Analysis Text/Video Alignment Video Annotation and Indexing  Personalized Video Retrieval  Experiment and Evaluation

17 Video Analysis  Shot Classification  Replay Detection  Video Event Modeling Event with replay far view shot, close-up shots, replay, close-up shots, far view shot

18

19  Introduction  Semantic Annotation of Sports Video Text Analysis Video Analysis Text/Video Alignment Video Annotation and Indexing  Personalized Video Retrieval  Experiment and Evaluation

20 Text/Video Alignment  Event Moment Detection Clock Digits Location Clock Digits Recognition  Event Boundary Detection Hidden Markov Model (HMM)

21  Introduction  Semantic Annotation of Sports Video Text Analysis Video Analysis Text/Video Alignment Video Annotation and Indexing  Personalized Video Retrieval  Experiment and Evaluation

22 Video Annotation and Indexing  For each game, we annotate the video in two levels L1 : annotation exhibits an overall game summary including game name, date, place, teams, number of audience, scores, etc L2 : annotates each event in the video using text semantics extracted from the text event and video boundaries obtained from text/video alignment by of at

23 Video Annotation and Indexing

24  Introduction  Semantic Annotation of Sports Video Text Analysis Video Analysis Text/Video Alignment Video Annotation and Indexing  Personalized Video Retrieval  Experiment and Evaluation

25

26  Introduction  Semantic Annotation of Sports Video Text Analysis Video Analysis Text/Video Alignment Video Annotation and Indexing  Personalized Video Retrieval  Experiment and Evaluation

27 Text Event Detection  The precisions and recalls of all the events except precision of the shot event for soccer (97.1%) achieve 100%.

28 Shot Classification and Replay Detection

29 Event Boundary Detection

30

31

32

33 Evaluation on Personalized Retrieval


Download ppt "A Novel Framework for Semantic Annotation and Personalized Retrieval of Sports Video IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 10, NO. 3, APRIL 2008."

Similar presentations


Ads by Google