IP Library Granted Patent US 9,940,970
Granted Patent B2
US 9,940,970 · App. 14/408,213 · Granted Apr 10, 2018

Video remixing system

View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 9,940,970
App. No.
14/408,213
Granted
Apr 10, 2018
Kind
B2
Abstract

A method comprising obtaining, by an automatic video media remixing service, at least one source of media content to be used as a reference media content; analysing the at least one reference media content according to at least one stylistic parameter; and determining, on the basis of the at least one stylistic parameter, at least one editing rule or parameter for controlling creation of an automatic media remix.

Claims (61)

1. A method comprising:

obtaining, by an automatic media remixing service, at least one source of media content to be used as a reference media content;

receiving a selection associated with at least one stylistic parameter from a user;

analyzing the at least one reference media content according to at least one stylistic parameter characteristic to said at least one reference media content; and

determining, on the basis of the at least one stylistic parameter characteristic to said at least one reference media content and analysis of the at least one reference media content according to the at least one stylistic parameter, at least one editing rule or parameter for controlling creation of an automatic media remix by analyzing sensory data to determine one or more points in time indicative of an event of interest in order to make switches between different aesthetic sources of media content to be used in the automatic media remix.

2. A method according to claim 1 , wherein

the at least one reference media content is a reference video clip, which is a professionally edited video clip, such as a movie, a documentary, a sport video or a music video.

3. A method according to claim 2 , wherein

the at least one stylistic parameter includes one or more of the following:

number of shots in the reference video clip;

effects used in shot transitions;

shot duration;

cinematic technique used in shots;

audio-specific editing parameters.

4. A method according to claim 3 , wherein

the cinematic technique used in shots includes one or more of the following: shot type; color style; camera angle; number of people appearing in the shot; a static or a shaking shot; a dominating shape appearing within a frame; a direction of a dominant movement in the shot.

5. A method according to claim 3 , wherein

the audio-specific editing parameters includes one or more of the following: tempo, beats, downbeats, the music structure; amplitude peaks; amplitude valleys; slower amplitude changes; music key; music chords, occurrence of certain rhythmic patterns.

6. A method according to claim 2 , further comprising

indexing the analysed at least one reference video clip to belong to at least one class which is identified by at least a director and/or a genre of the video clip.

7. A method according to claim 2 , further comprising

creating an aesthetic model on the basis of the analysed at least one stylistic parameter, said aesthetic model being a director-specific or a genre-specific or an actor-specific or a producer-specific or a country-specific aesthetic model comprising at least one editing rule or parameter for controlling creation of an automatic media remix.

8. A method according to claim 7 , wherein

a single reference video clip is used as a basis for the aesthetic model.

9. A method according to claim 7 , wherein

a plurality of reference video clips from the same director are used as a basis for the director-specific aesthetic model, or a plurality of reference video clips from the same genre are used as a basis for the genre-specific aesthetic model, or a plurality of reference video clips from the same actor are used as a basis for the actor-specific aesthetic model, or a plurality of reference video clips from the same producer are used as a basis for the producer-specific aesthetic model, or a plurality of reference video clips from the same country are used as a basis for the country-specific aesthetic model.

10. An apparatus comprising at least one processor, and memory including computer program code, the memory and the computer program code configured to, with the at least one processor, cause the apparatus to at least:

obtain at least one source of media content to be used as a reference media content;

receive a selection associated with at least one stylistic parameter from a user;

analyze the at least one reference media content according to at least one stylistic parameter characteristic to said at least one reference media content; and

determine, on the basis of the at least one stylistic parameter characteristic to said at least one reference media content and analysis of the at least one reference media content according to the at least one stylistic parameter, at least one editing rule or parameter for controlling creation of an automatic media remix by analyzing sensory data to determine one or more points in time indicative of an event of interest in order to make switches between different aesthetic sources of media content to be used in the automatic media remix.

11. An apparatus according to claim 10 , wherein

the at least one reference media content is a reference video clip, which is a professionally edited video clip, such as a movie, a documentary, a sport video or a music video.

12. An apparatus according to claim 11 , wherein

the at least one stylistic parameter includes one or more of the following:

number of shots in the reference video clip;

effects used in shot transitions;

shot duration;

cinematic technique used in shots;

audio-specific editing parameters.

13. An apparatus according to claim 12 , wherein

the cinematic technique used in shots includes one or more of the following: shot type; color style; camera angle; number of people appearing in the shot; a static or a shaking shot; a dominating shape appearing within a frame; a direction of a dominant movement in the shot.

14. An apparatus according to claim 12 , wherein

the audio-specific editing parameters includes one or more of the following: tempo, beats, downbeats, the music structure; amplitude peaks; amplitude valleys; slower amplitude changes; music key; music chords, occurrence of certain rhythmic patterns.

15. An apparatus according to claim 11 , further comprising computer program code configured to, with the at least one processor, cause the apparatus to at least:

index the analysed at least one reference video clip to belong to at least one class which is identified by at least a director and/or a genre of the video clip.

16. An apparatus according to claim 11 , further comprising computer program code configured to, with the at least one processor, cause the apparatus to at least:

create an aesthetic model on the basis of the analysed at least one stylistic parameter, said aesthetic model being a director-specific or a genre-specific or an actor-specific or a producer-specific or a country-specific aesthetic model comprising at least one editing rule or parameter for controlling creation of an automatic media remix.

17. An apparatus according to claim 16 , wherein

a single reference video clip is used as a basis for the aesthetic model.

18. An apparatus according to claim 16 , wherein

a plurality of reference video clips from the same director are used as a basis for the director-specific aesthetic model, or a plurality of reference video clips from the same genre are used as a basis for the genre-specific aesthetic model, or a plurality of reference video clips from the same actor are used as a basis for the actor-specific aesthetic model, or a plurality of reference video clips from the same producer are used as a basis for the producer-specific aesthetic model, or a plurality of reference video clips from the same country are used as a basis for the country-specific aesthetic model.

19. An apparatus according to claim 16 , further comprising computer program code configured to, with the at least one processor, cause the apparatus to at least:

receive a user request for creating a media remix from an event, said user request including a request to create the media remix according to a certain cinematic style;

obtain a plurality of source video clips from said event; and

apply an aesthetic model corresponding to the requested cinematic style when creating an automatic media remix from said event.

20. A non-transitory computer readable medium storing a computer program, the computer program comprising instructions causing, when executed on at least one processor, at least one apparatus to:

obtain at least one source of media content to be used as a reference media content;

receive a selection associated with at least one stylistic parameter from a user;

analyze the at least one reference media content according to at least one stylistic parameter characteristic to said at least one reference media content; and

determine, on the basis of the at least one stylistic parameter characteristic to said at least one reference media content and analysis of the at least one reference media content according to the at least one stylistic parameter, at least one editing rule or parameter for controlling creation of an automatic media remix by analyzing sensory data to determine one or more points in time indicative of an event of interest in order to make switches between different aesthetic sources of media content to be used in the automatic media remix.