Method and system for automatic B-roll video production
A method and a system for automatic B-roll editing of video production are provided herein. The method may include: obtaining a plurality of media entities comprising at least one video entity having a visual channel and an audio channel; analyzing the media entities, to produce content-related data indicative of a content of the media entities; automatically selecting at least a first and a second visual portion and an audio portion, wherein the first visual and the audio portions are synchronized and have non-identical durations, and wherein the second visual and the audio portions are non-synchronized; and creating a video production by combining the automatically selected visual portions and audio portions.
1. A method comprising:
obtaining a plurality of media entities comprising at least one video entity having a visual channel and an audio channel;
analyzing the media entities, to produce content-related data indicative of a content of the media entities;
automatically selecting visual and audio portions, comprising at least a first and a second visual portions and an audio portion, wherein the first visual portion and the audio portion are synchronized and have non-identical durations, and wherein the second visual portion and the audio portion are non-synchronized; and
creating a video production by combining the automatically selected visual and audio portions.
2. The method according to claim 1 , wherein the video production comprises two or more B-roll visual portions, wherein a B-roll is a selected visual portion that is non-synchronized with the selected audio portion.
3. The method according to claim 1 , wherein the video production comprises at least one video cut that is not synched with the corresponding audio cut, wherein the video cut is a transition between two consecutive selected visual portions at the video production, and wherein the audio cut is a transition between two consecutive selected audio portions at the video production.
4. The method according to claim 1 , wherein the video production comprises multiple visual portions synchronized with a common audio portion.
5. The method according to claim 2 , wherein the B-rolls comprise at least one video portion.
6. The method according to claim 2 , wherein at least two B-rolls have a common audio portion and where timing of the B-rolls is aligned with content of the common audio portion.
7. The method according to claim 1 , wherein the automatic selection of specified visual portions depends upon the content of at least one audio portion that corresponds to a source media other than said specified visual portions.
8. The method according to claim 1 , wherein the automatic audio selection is based on one of: speech analysis and music analysis of the audio channel.
9. The method according to claim 1 , wherein the automatic audio selection is based on sentences analysis of the audio channel.
10. The method according to claim 2 , further comprising analyzing the first visual portion to determine time related score indicative of predefined criteria, and determining a timing of the B-rolls based on the score.
11. The method according to claim 2 , further comprising associating one or more of the B-rolls with a respective video portion being its respective A-roll to form a single bundle, and applying a video production action to the bundle in its entirety.
12. The method according to claim 11 , wherein the action comprises changing a start or an end time of the bundle.
13. The method according to claim 11 , wherein the action comprises changing the location of the bundle relative to other selected portions.
14. The method according to claim 11 , further enabling a user to remove or add assets from the bundle.
15. The method according to claim 10 , wherein the score comprises saliency of a scene captured in said first visual portion.
16. The method according to claim 2 , wherein the B-rolls comprise user-generated content.