Method of creating a semantic video summary using information from secondary sources

• US 8,051,446 B1
• Filed: 12/06/1999
• Issued: 11/01/2011
• Est. Priority Date: 12/06/1999
• Status: Expired due to Fees

• Current Assignee: Sharp Kabushiki Kaisha (Hon Hai Precision Industry Co., Ltd.)
• Original Assignee: Sharp Laboratories of America Incorporated (Hon Hai Precision Industry Co., Ltd.)
• Inventors: Qian, Richard, Van Beek, Peter J. L.
• Primary Examiner(s): HUYNH, AN SON PHI
• Application Number:
  US09/455,964
• Time in Patent Office: 4,348 Days
• Field of Search: 725/39, 725/51, 725/53, 725/112, 725/109, 725/110, 725/41, 725/52, 715/719, 715/723
• US Class Current: 725/39
• CPC Class Codes: G06F 16/738 Presentation of query results
• CPC Class Codes: H04N 21/8549 Creating video summaries, e.g. movie trailer retrieval in video databases by using presentations in form of a video summary G06F16/739

Abstract

Creating semantic summaries and abstractions of video requires high level knowledge of the domain of the video. Obtaining this high level information without human intervention is problematic. A method of producing video summaries and abstractions is provided where high level knowledge necessary for meaningful summarization is obtained from existing sources such as the worldwide web or an electronic programming guide. With this information, the summarization system can automatically identify significant events or subjects and extract video related to these events or subjects.

Claims

1. A method of creating a semantic summary of a video comprising the steps of:

(a) identifying a domain of said video;

(b) using said domain to locate information related to said video at a source other than said video;

(c) extracting a datum related to a semantic event from said information, said semantic event describing a portion of said video;

(d) identifying said portion of said video related to said datum; and

(e) creating a summary of said identified portion of said video in response to the extraction of said datum.

2. The method of claim 1 wherein said information is a textual summary of events.

3. The method of claim 1 wherein said information is included in a worldwide web site.

4. The method of claim 1 wherein said information is included in an electronic programming guide.

5. The method of claim 1 wherein said domain is identified from an electronic programming guide.

6. The method of claim 1 further comprising the step of displaying said summary to a user.

7. A method of abstracting video comprising the steps of:

(a) locating an index of said video from a source external to said video;

(b) identifying a domain of said video for creating a video abstraction;

(c) using said domain together with said index to identify portions of said video for inclusion in said video abstraction;

(d) extracting said identified portions of said video from said video to form said video abstraction in response to the location of said index; and

(e) displaying said video abstraction to a user.

8. The method of claim 7 wherein said index is included in a worldwide web site.

9. The method of claim 7 wherein said index is included in an electronic programming guide.

10. The method of claim 7 further comprising the step of identification of said domain by a user of said abstraction.

11. A method of creating a semantic summary of a video comprising the steps of:

(a) identifying a domain of said video;

(b) using said domain to locate a textual summary of said video;

(c) extracting a datum related to a semantic event relevant to said video summary from said textual summary;

(d) locating content in said video corresponding to said datum; and

(e) extracting said content related to said semantic event from said video in response to extraction of said datum from said video for inclusion in said semantic summary including at least one portion of said video.

12. A method of abstracting video comprising the steps of:

(a) locating an index of said video in at least one of a worldwide web site and a programming guide;

(b) identification of a domain of said video for creating a video abstraction by a user;

(c) using said domain together with said index to identify portions of said video for inclusion in said video abstraction; and

(d) extracting said identified portions of said video from said video to form said video abstraction.