Video-attribute-information output apparatus, video digest forming apparatus, computer program product, and video-attribute-information output method

• US 8,103,107 B2
• Filed: 01/11/2008
• Issued: 01/24/2012
• Est. Priority Date: 01/18/2007
• Status: Expired due to Fees

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Yamamoto, Koji
• Primary Examiner(s): Ahmed, Samir
• Assistant Examiner(s): Li, Ruiping
• Application Number:
  US12/007,570
• Publication Number:
  US 20080175486A1
• Time in Patent Office: 1,474 Days
• Field of Search: 382/190, 382/206, 382/306, 348/700
• US Class Current: 382/206
• CPC Class Codes: A63B 71/0616 Means for conducting or scheduling competition, league, tournaments or rankings
• CPC Class Codes: A63B 71/0622 Visual, audio or audio-visual systems for entertaining, instructing or motivating the user
• 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 16/7844 using original textual content or text extracted from visual content or transcript of audio data
• CPC Class Codes: G06V 20/40 in video content extracting overlay text G06V20/62; video retrieval G06F16/70; processing of video elementary streams in video servers H04N21/234; processing of video elementary streams in video clients H04N21/44

Abstract

An attribute-information-area extracting unit extracts an attribute information area in which attribute information is displayed when the attribute information area does not change between certain frames of adjacent scenes obtained by dividing a video content by a scene dividing unit. A character-areas extracting unit extracts character areas in which video attribute information in individual characters that is metadata of the video content of the attribute information area are present, and a character-area-meaning assigning unit assigns meanings to the character areas. A character-area reading unit reads the video attribute information, from the character areas to which meanings are assigned, thereby outputting the video attribute information.

Claims

1. A video-attribute-information output apparatus comprising:

a scene dividing unit that detects a change in scenes where there is little similarity between frames of video content, and divides the video content into a plurality of scenes;

an attribute-information-area extracting unit that extracts an attribute information area in which attribute information is displayed and which has no change between specific frames of adjacent scenes that are obtained by dividing by the scene dividing unit;

a character-area extracting unit that extracts character areas in which video attribute information in individual characters that is metadata of the video content is present, from the attribute information area extracted by the attribute-information-area extracting unit;

a character-area-meaning assigning unit that assigns meanings to the character areas extracted by the character-area extracting unit, by referring to rule information that specifies the meanings for the character areas;

a video-attribute-information output unit that reads the video attribute information from the character areas to which the meanings are assigned, and outputs the video attribute information;

a typical scene extracting unit that extracts typical scenes that are images shot in a same composition and repeatedly appear in the video content, from the adjacent scenes obtained by dividing by the scene dividing unit; and

a region judging unit that judges whether each of the extracted typical scenes has the extracted attribute information area, wherein

the character-area extracting unit extracts character areas in which the individual characters are present in the extracted attribute information area and judged as being in a typical scene by the region judging unit.

2. The apparatus according to claim 1, wherein the attribute-information-area extracting unit extracts attribute information areas from a boundary between a typical scene and a scene immediately before the typical scene.

3. The apparatus according to claim 1, wherein the typical scene extracting unit includes:

a classifying unit that classifies the scenes obtained by the dividing unit into groups in accordance with similarity based on features of the scenes; and

a determining unit that determines all the scenes classified into the group as the typical scenes, when the images shot in the same composition appear in the scenes of a group at a frequency equal to or higher than a criterion level.

4. The apparatus according to claim 3, wherein the criterion level used by the determining unit is whether a total number of images of the group that are shot in the same composition exceeds a predetermined threshold value.

5. The apparatus according to claim 3, wherein the criterion level used by the determining unit is whether a total hours of images of the group that are shot in the same composition accounts for a predetermined percentage or higher of a time length of the video content.

6. The apparatus according to claim 1, wherein

the rule information includes contents of meanings, first rules that are brought into correspondence with the contents of the meanings and are to be followed when grouping the character areas in accordance with at least one of a relationship of relative positions and a relationship of colors, and second rules that specify a positional relationship of the character areas;

and

the character-area-meaning assigning unit selects a content of meaning for a group of character areas that satisfy a second rule from among the character areas grouped in accordance with the first rules, and assigns meaning to the group of the character areas.

7. The apparatus according to claim 1, wherein the video-attribute-information output unit corrects a recognition result when there is any inconsistency in the video attribute information read from the character areas to which the meaning is assigned.

8. The apparatus according to claim 1, further comprising an event detecting unit that detects the video attribute information output from the video-attribute-information output unit, as event information, when the video attribute information is compared with event rule information that includes a relationship between changing patterns of the video attribute information and the events, and a specific pattern is found therein.

9. A video digest forming apparatus comprising:

a video-attribute-information output apparatus according to claim 1;

an importance calculating unit that calculates a level of importance for each event included in the video attribute information output from the video-attribute-information output apparatus;

a video segment selecting unit that selects a video segment of the video content to be included in a digest video picture in accordance with the level of importance calculated by the importance calculating unit;

a description-use event selecting unit that selects a description-use event from a list of events to use in preparation of a description that is to be included in the digest video picture;

a description preparing unit that prepares the description from the description-use event selected by the description-use event selecting unit; and

an integrating unit that combines the selected video segment and the description, and forms digest video information that includes both of the video segment and the description.

10. The apparatus according to claim 9, wherein the integrating unit sequentially outputs the digest video information including the description-use event selected by the description-use event selecting unit, and reproduces the digest video information in a skipping manner.

11. The apparatus according to claim 9, wherein the integrating unit highlights character areas that exhibit changes during reproduction in a skipping manner.

12. A computer program product having a non-transitory computer readable medium including program instructions for outputting video attribute information, wherein the instructions, when executed by a computer, cause the computer to perform:

detecting a change in scenes where there is little similarity between frames of video content, and dividing the video content into a plurality of scenes;

extracting an attribute information area in which attribute information is displayed and which has no change between specific frames of the divided adjacent scenes;

extracting character areas in which video attribute information in individual characters that is metadata of the video content is present, from the extracted attribute information area;

assigning meanings to the extracted character areas by referring to rule information that specifies the meanings for the character areas;

reading the video attribute information from the character areas to which the meanings are assigned, and outputting the video attribute information;

extracting typical scenes that are images shot in a same composition and repeatedly appear in the video content, from the adjacent scenes obtained by dividing; and

judging whether each of the extracted typical scenes has the extracted attribute information area, wherein

the extracting extracts character areas in which the individual characters are present in the extracted attribute information area and judged as being in a typical scene.

13. A video-attribute-information output method comprising:

detecting a change in scenes where there is little similarity between frames of video content, and dividing the video content into a plurality of scenes;

extracting an attribute information area in which attribute information is displayed and which has no change between specific frames of the divided adjacent scenes;

extracting character areas in which video attribute information in individual characters that is metadata of the video content is present, from the extracted attribute information area;

assigning meanings to the extracted character areas by referring to rule information that specifies the meanings for the character areas;

reading the video attribute information from the character areas to which the meanings are assigned, and outputting the video attribute information;

extracting typical scenes that are images shot in a same composition and repeatedly appear in the video content, from the adjacent scenes obtained by dividing; and

judging whether each of the extracted typical scenes has the extracted attribute information area, wherein

the extracting extracts character areas in which the individual characters are present in the extracted attribute information area and judged as being in a typical scene.