Method and system for automatic generation of an animated message from one or more images
A method and a system for automatically generating a video clip from one or more still images are provided herein. The method includes: obtaining one or more images containing at least one object over a background; detecting at least one object in the one or more images; deriving one or more relationships between at least two of: the background, the at least one object, or a portion thereof; determining, based on the derived one or more relationships, a spatio-temporal arrangement of at least two of: at least one portion of said one or more images, the at least one detected object, or a portion thereof; and producing a clip based on the determined spatio-temporal arrangement. The system may implement the method over a smartphone platform.
1. A method comprising:
obtaining one or more images containing at least one object over a background;
detecting at least one object in the one or more images;
deriving one or more relationships between at least two of: the background, the at least one object, or a portion thereof;
determining, based on the derived one or more relationships, a spatio-temporal arrangement of at least two of: at least one portion of said one or more images, the at least one detected object, or a portion thereof; and
producing a clip based on the determined spatio-temporal arrangement.
2. The method according to claim 1 , wherein the one or more images is a single still photo.
3. The method according to claim 2 , wherein the relationships comprise a calculated score.
4. The method according to claim 2 , further comprising obtaining incoming music as an input and synchronizing the spatio-temporal arrangement with the incoming music.
5. The method according to claim 1 , further comprising obtaining text as an input, wherein the producing of a clip further includes adding the text to a spatio-temporal location that is based on at least one of: the derived geometric features of the at least one detected object, the one or more derived relationships.
6. The method according to claim 1 , further comprising obtaining text as an input and analyzing the obtained text, wherein the determining a spatio-temporal arrangement is further based on the analysis of the obtained text.
7. The method according to claim 1 , further comprising obtaining text as an input, wherein the producing of a clip further includes adding the text, wherein the added text is further animated based on at least one of: geometric features of the at least one detected object, or the one or more derived relationships.
8. The method according to claim 1 , further comprising obtaining text as an input, and determining a color of the text based on colors represented in the image.
9. The method according to claim 8 , wherein the determined color is a color salient in the image.
10. The method according to claim 1 , further comprising obtaining text as an input, and determining a location for adding the text onto the one or more images, wherein the location is determined based on saliency analysis of the one or more images.
11. The method according to claim 1 , wherein the producing of a clip further comprises automatically adding an audio track which is contextually related to the at least one of: a scene appearing in the background, the at least one detected objects.
12. The method according to claim 2 , wherein the producing of a clip further comprises automatically adding at least one external graphical asset which is contextually related to the at least one of: a scene appearing in the background, the at least one detected object, and matadata associated with said image, an input text.
13. The method according to claim 2 , wherein the spatio-temporal arrangement further comprises duplicating at least one of the detected objects or portions thereof.
14. The method according to claim 2 , wherein the spatio-temporal arrangement further comprises omitting at least one of the detected objects.
15. The method according to claim 2 , wherein the determining of the spatio-temporal arrangement comprises cropping the image, substantially around at least one of the detected objects, based on the one or more derived relationships.
16. The method according to claim 2 , wherein the determining a spatio-temporal arrangement is further based on meta-data other than the geometrical meta-data of at least some of the detected objects.
17. The method according to claim 2 , wherein the production further comprises generating at least one transition between at least two of: at least one portion of said image, the at least one detected object or a portion thereof.
18. The method according to claim 1 , wherein the production further comprises generating a music sequence along the sequence of the extracted objects, based at least partially on the one or more derived relationships.
19. The method according to claim 15 , wherein the spatio-temporal arrangement results in at least two consecutive selections of the same object undergoing two different cropping operations.
20. The method according to claim 1 , wherein the one or more images include at least two objects, wherein the relationship defines an inter-object relationship between the at least two objects.
21. The method according to claim 20 , wherein the inter-object relationships comprises at least one of the following relationships: the objects are looking at each other: the objects are within a predefined time-space from each other; the objects are talking to each other; the objects are engaged in a similar activity.
22. The method according to claim 20 , wherein the inter-object relationships score is affected positively by a preference for placing two objects close in time in a case said two objects are strongly related.
23. The method according to claim 2 , wherein the producing of a clip further comprises automatically adding a visual effect which is contextually related to the at least one of: a scene appearing in the background, the at least one detected object.
24. The method according to claim 1 , wherein the producing of a clip further comprises automatically adding an external text which is contextually related to the at least one of: a scene appearing in the background, the at least one detected object, a meta-data attached to the one or more input photos.
25. A system comprising:
a memory configured to store one or more images containing at least one object over a background; and
a computer processor configured to:
detect at least one object in the one or more images;
derive one or more relationships between at least two of: the background, the at least one object, or a portion thereof;
determine, based on the derived one or more relationships, a spatio-temporal arrangement of at least two of: at least one portion of said one or more images, the at least one detected object, or a portion thereof; and
produce a clip based on the determined spatio-temporal arrangement.
26. A non-transitory computer readable medium comprising a set of instructions that when executed cause at least one processor to:
obtain one or more images containing at least one object over a background; and
detect at least one object in the one or more images;
derive one or more relationships between at least two of: the background, the at least one object, or a portion thereof;
determine, based on the derived one or more relationships, a spatio-temporal arrangement of at least two of: at least one portion of said one or more images, the at least one detected object, or a portion thereof; and
produce a clip based on the determined spatio-temporal arrangement.