System and method for semi-automatic video editing

• US 9,570,107 B2
• Filed: 06/28/2015
• Issued: 02/14/2017
• Est. Priority Date: 03/08/2010
• Status: Active Grant

• Current Assignee: Vimeo, Inc. (Match Group, Inc.)
• Original Assignee: Magisto Ltd. (Match Group, Inc.)
• Inventors: Boiman, Oren, Rav-Acha, Alexander
• Primary Examiner(s): ADAMS, EILEEN M
• Application Number:
  US14/752,942
• Publication Number:
  US 20150302894A1
• Time in Patent Office: 597 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G11B 27/031 Electronic editing of digitised analogue information signals, e.g. audio or video signals
• CPC Class Codes: G11B 27/28 by using information signals recorded by the same method as the main recording G11B27/22 takes precedence
• CPC Class Codes: G11B 27/329 on a disc [VTOC]
• CPC Class Codes: G11B 27/34 Indicating arrangements indicating means incorporated in magazine or cassette G11B23/046 and G11B23/0875; indicating measured values in general G01D
• CPC Class Codes: H04N 21/47205 for manipulating displayed content, e.g. interacting with MPEG-4 objects, editing locally
• CPC Class Codes: H04N 5/76 Television signal recording
• CPC Class Codes: H04N 9/87 Regeneration of colour television signals H04N9/80 takes precedence

Abstract

A system and a method for semi-automatic video editing is provided herein. The method may include in one embodiment the following steps: processing a media stream comprising at least one of: a plurality of images and a video stream, to extract metadata relating to at least one characteristic of the media stream; displaying to a user the extracted metadata; receiving from the user an instruction to generate a modified media stream wherein said instruction is responsive to the at least one characteristic represented by the extracted metadata; and generating a modified media stream, in response to said instruction. The system may implement the aforementioned method using a computer processor, a display, and a user interface.

Claims

1. A method comprising:

processing a media stream comprising at least one of;

a plurality of images and a video stream, to extract metadata relating to at least one characteristic of the media stream;

displaying to a user the extracted metadata;

receiving from the user an instruction to generate a modified media stream wherein said instruction is responsive to the at least one characteristic represented by the extracted metadata;

generating a modified media stream, in response to said instruction; and

generating a mosaic of visual entities, wherein a first visual entity of the mosaic represents the modified media stream; and

wherein at least a second visual entity of the mosaic is not representative of the edited null of media stream, wherein a relationship between a size of the first and second visual entities is responsive to a relationship between importance levels associated with the first and second visual entities.

2. The method according to claim 1, wherein the visual entities comprise still pictures and video streams.

3. The method according to claim 1, wherein the generating of the modified media stream in triggered in response to a detection of camera activity.

4. A method comprising:

processing a media stream comprising at least one of;

a plurality of images and a video stream, to compute metadata relating to characteristics of the media stream;

displaying to a user an edited media stream generated automatically based on the computed metadata;

receiving from the user an instruction to modify the edited media stream, wherein the instruction relates to at least one characteristic that is represented by the metadata; and

generating a modified edited media stream, responsive to the instruction,

wherein a characteristic of the media stream comprises an importance of a specific object, wherein a portion of the specific object appears in the media stream, wherein the instruction to modify the edited media stream consist at least of increasing the importance of said specific object, and wherein the generating a modified edited media stream includes showing said specific object more often in the modified edited media stream than in the edited media stream.

5. The method according to claim 4, wherein the metadata comprise at least one image portion showing an object detected in the media stream, and wherein the instruction is carried out by the user by choosing at least one of the shown image portions.

6. The method according to claim 4, wherein the modified edited media is shorter than the media stream.

7. The method according to claim 4, wherein the modified media stream is generated by applying a non-parametric method.

8. The method according to claim 4, wherein the modified media stream is generated responsive to a speech attribute that is indicative of an importance level of media frames that are associated with speech.

9. The method according to claim 4, wherein a characteristic of the media stream comprises an importance of a specific object, wherein a portion of the specific object appears in the media stream.

10. The method according to claim 4, wherein a characteristic of the media stream comprises an importance of a specific person, wherein a face of the specific person appears in the media stream.

11. The method according to claim 4, wherein a characteristic of the media stream is an importance of a specific scene, wherein the specific scene appears in the media stream.

12. The method according to claim 4, wherein the modified media stream is generated responsive to a face attribute that is indicative of an importance level of media portions that comprise faces.

13. The method according to claim 4, wherein the modified edited media stream is generated responsive to an action attribute that is indicative of an importance level of media frames that are associated with action.

14. The method according to claim 4, wherein the modified media stream is being displayed while acquiring an additional portion of a media stream.

15. The method according to claim 4, wherein the generating of the modified media stream is triggered wherever the user is located at a predetermined location.

16. The method according to claim 4, wherein the generating of the modified media stream is triggered in response to an activity of another user that is associated with the user.

17. The method according to claim 4, wherein the media stream further comprises audio frames that are synchronized with the video stream, wherein the modified media stream comprises selected audio frames and a modified video stream, wherein the modified video stream comprises video frames synchronized with selected audio frames and additional video content, and wherein the modified video stream and the modified audio stream are synchronized.