Summarization of sumo video content

• US 8,028,234 B2
• Filed: 03/08/2005
• Issued: 09/27/2011
• Est. Priority Date: 01/28/2002
• 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: Li, Baoxin
• Primary Examiner(s): LEE, TING ZHOU
• Application Number:
  US11/074,860
• Publication Number:
  US 20050155053A1
• Time in Patent Office: 2,394 Days
• Field of Search: 715/723, 715/719, 725/37, 386/46, 386/241, 386/326
• US Class Current: 715/719
• CPC Class Codes: G06F 16/739 in form of a video summary, e.g. the video summary being a video sequence, a composite still image or having synthesized frames
• CPC Class Codes: G06F 16/7834 using audio features
• CPC Class Codes: G06F 16/7844 using original textual content or text extracted from visual content or transcript of audio data
• CPC Class Codes: G06F 16/785 using colour or luminescence
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06V 20/47 Detecting features for summarising video content
• CPC Class Codes: H04N 21/23418 involving operations for analysing video streams, e.g. detecting features or characteristics television picture signal circuitry for scene change detection H04N5/147; filtering for image enhancement G06T5/00; methods or arrangements for recognising scenes G06V20/00; arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59
• 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

Summarization of video content, such as a video that includes sumo, by a method that provides a description of the video, identifies a plurality of segments of the video based upon the provided description, and generates another video based upon the identified segments, having less frames than the original video.

Claims

1. A method of processing a video having a plurality of frames, said method comprising:

a) processing image pixels of said video in a manner that automatically identifies a first plurality of segments of said video that respectively display Sumo bouts of likely interest to a viewer, wherein said processing is free from a need to compare characteristics of any frame of said video to characteristics of frames of model sequences and free from a need to reference a text-based description of any sequence of frames of said video, by inferring the start of said Sumo bouts of likely interest to a viewer from a comparison among data of said video, where said video includes a second plurality of segments not of likely interest to said viewer, and said first plurality of segments of said video omits at least one segment of said second plurality of segments;

(b) creating a text-based description of the identified said segments in response to the identification of said plurality of segments, said text-based description not being graphically presented in the pixel data of any frame of said video being processed;

(c) automatically selecting at least one segment of said video using said text-based description;

(d) generating a video summary in response to the selection of said segments, wherein said video summary includes frames of said video and has less frames than said video;

where

(e) each of said Sumo bouts is characterized by a start time based upon when the players line up to charge one another and an end time based upon when one of the players either;

(1) steps outside a ring bounding an area of play;

or

(2) touches ground with a part of his body other than the feet and where said at least one segment each has a first frame proximately corresponding to said start time and a last frame proximately corresponding to said end time.

2. The method of claim 1 where said first frame is selected so as to include in said at least one segment at least a portion of a pre-bout ceremony.