SYSTEMS AND METHODS FOR TOPIC-SPECIFIC VIDEO PRESENTATION

• US 20130279881A1
• Filed: 04/19/2012
• Published: 10/24/2013
• Est. Priority Date: 04/19/2012
• Status: Active Grant

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Denney, Bradley, Lu, Juwei
• Granted Patent: US 8,958,645 B2
• Time in Patent Office: Days
• US Class Current: 386/241
• CPC Class Codes: G06F 16/743 a collection of video files or sequences
• CPC Class Codes: G06V 20/47 Detecting features for summarising video content
• CPC Class Codes: G06V 20/49 Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes
• CPC Class Codes: G11B 27/031 Electronic editing of digitised analogue information signals, e.g. audio or video signals
• CPC Class Codes: G11B 27/105 of operating discs
• CPC Class Codes: H04N 21/2668 Creating a channel for a dedicated end-user group, e.g. insertion of targeted commercials based on end-user profiles information retrieval from the Internet by querying with filtering and personalisation G06F16/9535; arrangements for replacing or switching information during the broadcast H04H20/10; push services over packet-switching network H04L12/1859; adaptation of message content in packet-switching networks H04L51/063
• 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
• CPC Class Codes: H04N 5/91 Television signal processing therefor

Abstract

Systems and methods for summarizing a video assign frames in a video to at least one of two or more groups based on a topic, generate a respective first similitude measurement for the frames in a group relative to the other frames in the group based on a feature, rank the frames in a group relative to one or more other frames in the group based on the respective first similitude measurement of the respective frames, and select a frame from each group as a most-representative frame based on the respective rank of the frames in a group relative to the other frames in the group.

Claims

1. A method for presenting video content, the method comprising:

assigning a first plurality of frames of a video to a first group based on a first topic;

assigning a second plurality of frames of the video to a second group based on the first topic, wherein the video includes at least the first plurality of frames and the second plurality of frames;

generating respective similitude measurements for the frames in the first plurality of frames relative to one or more other frames in the first plurality of frames based on a first feature;

ranking the frames in the first plurality of frames relative to the other frames in the first plurality of frames based on the respective similitude measurements of the frames in the first plurality of frames;

selecting a frame from the first plurality of frames as a most representative frame based on the respective ranks of the frames in the first plurality of frames;

generating respective similitude measurements for the frames in the second plurality of frames relative to one or more other frames in the second plurality of frames based on a second feature;

ranking the frames in the second plurality of frames relative to the other frames in the second plurality of frames based on the respective similitude measurements of the frames in the second plurality of frames; and

selecting a frame from the second plurality of frames as a most representative frame based on the respective ranks of the frames in the second plurality of frames.

2. The method of claim 1, wherein generating similitude measurements includes generating links, and links are generated according to

3. The method of claim 2, wherein frames are ranked according to

4. The method of claim 1, wherein the first topic comprises an object, a frame feature, or a change in a frame feature between adjacent frames in a sequence of frames of the video.

5. The method of claim 4, wherein the object is a person, vehicle, animal, building, plant, or geographical feature.

6. The method of claim 1, wherein the first feature is a sound, a color, a texture, a light gradient, a white balance, a light intensity, a volume, a location, camera exposure, zoom, or a light histogram.

7. The method of claim 1, wherein generating the respective similitude measurements for the frames in the first plurality of frames relative to one or more other frames in the first plurality of frames is further based on two or more fourth features.

8. The method of claim 7, wherein generating the similitude measurements includes generating links, and links and are generated according to

9. The method of claim 1, wherein selecting a frame from the first plurality of frames as the most representative frame is further based on a criterion associated with the first topic.

10. The method of claim 1, further comprising generating a video summary that includes the frame selected from the first plurality of frames as the most representative frame and the frame selected from the second plurality of frames as the most representative frame.

11. One or more computer-readable media storing computer executable instructions that, when executed by one or more computing devices, cause the one or more computing devices to perform operations comprising:

assigning frames in a video to one of two or more groups based on a topic;

generating respective first similitude measurements for the frames in a group relative to the other frames in the group based on a feature;

ranking the frames in a group relative to other frames in the group based on the respective first similitude measurements of the respective frames; and

selecting one or more frames from each group as most-representative frames based on the respective ranks of the frames in a group relative to the other frames in the group.

12. The one or more computer-readable media of claim 11, wherein ranking the frames in a group relative to the other frames in the group is further based on a total number of frames in the group.

13. The one or more computer-readable media of claim 12, wherein ranking the frames in a group relative to the other frames in the group is further based on a local maximum in the respective first similitude measurements for the frames in the group.

14. The one or more computer-readable media of claim 11, wherein the operations further comprise:

generating respective second similitude measurements for the frames in a group relative to the other frames in the group,

wherein ranking the frames in a group relative to other frames in the group is further based on the respective second similitude measurements for the respective frames.

15. A system for presenting video content, the system comprising:

one or more computer-readable media configured to store a video, a first topic, and a first similarity measurement function; and

one or more processors configured to cause the system to

assign a first plurality of frames of the video to a first group based on the first topic;

generate respective similitude measurements for the frames in the first plurality of frames relative to other frames in the first plurality of frames based on a first similarity measurement function;

rank the frames in the first plurality of frames relative to the other frames in the first plurality of frames based on the respective similitude measurements of the frames in the first plurality of frames; and

select a frame from the first plurality of frames as a first most representative frame based on the respective rank of the frames in the first plurality of frames.

16. The system of claim 15, wherein generating a similitude measurement includes generating links, and links are generated according to

17. The system of claim 16, wherein the links are further generated according to

18. The system of claim 15, wherein the processors are further configured to cause the system to generate a video summary that includes the first most representative frame.

19. The systems of claim 15, wherein one or more processors are further configured to cause the system to

assign a second plurality of frames of the video to a second group based on a second topic;

generate respective similitude measurements for the frames in the second plurality of frames relative to other frames in the second plurality of frames based on a second similarity measurement function;

rank the frames in the second plurality of frames relative to the other frames in the second plurality of frames based on the respective similitude measurements of the frames in the second plurality of frames; and

select a frame from the second plurality of frames as a second most representative frame based on the respective rank of the frames in the second plurality of frames.