Method for converting landscape video to portrait mobile layout using a selection interface

1. A method of converting media dimensions, comprising:

identifying, by a temporal analyzer executing on a computing device, a set of frames from a video in a first orientation as belonging to a scene;

receiving, by a focus region analyzer executing on the computing device, via a user interface, first and second selected coordinates on a frame of the set of frames identified as belonging to the scene;

identifying, by an image analyzer executing on the computing device, a first region within the frame comprising a first feature corresponding to the first selected coordinate;

identifying, by the image analyzer executing on the computing device, a second region within the frame comprising a second feature;

generating, by a cropping calculator executing on the computing device, a first score for the first feature and a second score for the second feature, the first score greater than the second score based on the first feature corresponding to the first selected coordinate;

determining, by the cropping calculator, that the second score exceeds a threshold;

cropping, by an image processor executing on the computing device, responsive to the determination, the frame of the set of frames identified as belonging to the scene to include the first region and the second region within a predetermined display area comprising a subset region of the frame in a second orientation;

identifying, by the image analyzer, within the frame, a third region comprising a third feature corresponding to the second selected coordinate;

determining, by the temporal analyzer, between the frame and a second frame of the set of frames identified as belonging to the scene, a motion vector for the third feature; and

cropping, by the image processor, the second frame of the set of frames identified as belonging to the scene based on the motion vector for the third feature.

2. The method of claim 1 , further comprising:

identifying, by the image processor, an initial subset region of the frame in the second orientation includes the second region including the second feature;

determining, by the image processor, that the initial subset region excludes the first region including the first feature corresponding to the first selected coordinate; and

modifying, by the image processor, the initial subset region of the frame to include the first region comprising the first feature and the second region comprising the second feature to generate the subset region of the frame in the second orientation, responsive to determining that the initial subset region excludes the first region.

3. The method of claim 1 , further comprising:

identifying, by the image analyzer, for each frame belonging to the scene, the first region and the second region comprising the first feature and the second feature within the frame; and

wherein cropping further comprises cropping, responsive to the identification of the first region and the second region in each frame of the set of frames, the frame to include the first region and the second region within the predetermined display area comprising the subset region of the frame in the second orientation.

4. The method of claim 1 , wherein receiving the first selected coordinate on the frame further comprises receiving, via the user interface, a bounding box on the frame of the set of frames identified as belonging to the scene; and

wherein identifying the first region further comprises identifying the first region comprising the first feature based on the bounding box selected using the user interface.

5. The method of claim 1 , further comprising

receiving, by the focus region analyzer, via the user interface, the second selected coordinate on the frame of the subset of frames, subsequent to cropping the frame;

adjusting, by the image analyzer, the first region to generate a fourth region comprising the first feature corresponding to the second selected coordinate;

generating, by the cropping calculator executing on the computing device, a fourth score for the first feature, a fifth score for the second feature, and a sixth score for a third feature, the sixth score greater than the fifth score based on a first distance between the second selected coordinate and the second feature and a second distance between the second selected coordinate and the third feature; and

cropping, by the image processor, the frame to include a third region corresponding to the third feature and the fourth region within a second predetermined display area comprising a second subset region of the frame in the second orientation.

6. The method of claim 1 , further comprising:

receiving, by the focus region analyzer, via the user interface, a feature identifier for a second frame of the set of frames identified as belonging to the scene;

identifying, by the image analyzer, within the second frame a fourth region comprising a fourth feature corresponding to the feature identifier using a semantic knowledge graph;

identifying, by the image analyzer, within the second frame a fifth region comprising a fifth feature;

generating, by the cropping calculator, a fourth score for the fourth feature, a fifth score for the fifth feature, the fourth score greater than the fifth score based on the fourth feature corresponding to the feature identifier received via the user interface; and

cropping, by the image processor, the second frame of the set of frames identified as belonging to the scene to include the fourth region and the fifth region within a second predetermined display area comprising a subset region of the second frame in the second orientation.

7. The method of claim 1 , further comprising:

receiving, by the focus region analyzer, via the user interface, an overlay image to add to the frame at a specified coordinate; and

adding, by the image processor, subsequent to the cropping of the frame, the overlay image to the subset region of the frame at the specified coordinate.

8. The method of claim 1 , wherein the second feature comprises text, and wherein generating the second score for the second feature further comprises generating the second score for the second feature based on at least one of a characteristic of the second feature proportional to a size of the text and a distance of the text from a center of the frame.

9. The method of claim 1 , wherein the second feature comprises a face, and wherein generating the second score for the second feature based on a characteristic of the second feature further comprises generating the second score based on a size of the face relative to the frame.

10. A system for converting media dimensions, comprising:

a temporal analyzer executable on a computing device, configured to identify a set of frames from a video in a first orientation as belonging to a scene;

a focus region analyzer executable on the computing device, configured to receive, via a user interface, first and second selected coordinates on a frame of the set of frames identified as belonging to the scene;

an image analyzer executable on the computing device configured to:

identify a first region within the frame comprising a first feature corresponding to the first selected coordinate; and

identify within the frame a second region comprising a second feature;

a cropping calculator executable on the computing device configured to:

generate a first score for the first feature and a second score for the second feature, the first score greater than the second score based on the first feature corresponding to the first selected coordinate; and

determine that the second score exceeds a threshold; and

an image processor executable on the computing device configured to crop, responsive to the determination, the frame of the set of frames identified as belonging to the scene to include the first region and the second region within a predetermined display area comprising a subset region of the frame in a second orientation,

wherein the image analyzer is further configured to identify within the frame, a third region comprising a third feature corresponding to the second selected coordinate;

wherein the temporal analyzer is further configured to determine, between the frame and a second frame of the set of frames identified as belonging to the scene, a motion vector for the third feature; and

wherein the image processor is further configured to crop the second frame of the set of frames identified as belonging to the scene based on the motion vector for the third feature.

11. The system of claim 10 , wherein the image processor is further configured to:

identify an initial subset region of the frame in the second orientation includes the second region including the second feature;

determine that the initial subset region excludes the first region including the first feature corresponding to the first selected coordinate; and

modify the initial subset region of the frame to include the first region comprising the first feature and the second region comprising the second feature to generate the subset region of the frame in the second orientation, responsive to determining that the initial subset region excludes the first region.

12. The system of claim 10 , wherein the image analyzer is further configured to identify, for each frame belonging to the scene, the first region and the second region comprising the first feature and the second feature within the frame; and

wherein the image processor is further configured to crop, responsive to the identification of the first region and the second region in each frame of the set of frames, the frame to include the first region and the second region within the predetermined display area comprising the subset region of the frame in the second orientation.

13. The system of claim 10 , wherein the focus region analyzer is further configured to receive, via the user interface, a bounding box on the frame of the set of frames identified as belonging to the scene; and

wherein the image analyzer is further configured to identify the first region comprising the first feature based on the bounding box selected using the user interface.

14. The system of claim 10 , wherein the focus region analyzer is further configured to receive, via the user interface, the second selected coordinate on the frame of the subset of frames, subsequent to cropping the frame;

wherein the image analyzer is further configured to adjust the first region to generate a fourth region comprising the first feature corresponding to the second selected coordinate;

wherein the cropping calculator is further configured to generate a fourth score for the first feature, a fifth score for the second feature, and a sixth score for a third feature, the sixth score greater than the fifth score based on a first distance between the second selected coordinate and the second feature and a second distance between the second selected coordinate and the third feature; and

wherein the image processor is further configured to crop the frame to include a third region corresponding to the third feature and the fourth region within a second predetermined display area comprising a second subset region of the frame in the second orientation.

15. The system of claim 10 , wherein the focus region analyzer is further configured to receive, via the user interface, a feature identifier for a second frame of the set of frames identified as belonging to the scene;

wherein the image analyzer is further configured to identify, within the second frame a fourth region comprising a fourth feature corresponding to the feature identifier using a semantic knowledge graph and to identify, within the second frame a fifth region comprising a fifth feature;

wherein the cropping calculator is further configured to generate a fourth score for the fourth feature, a fifth score for the fifth feature, the fourth score greater than the fifth score based on the fourth feature corresponding to the feature identifier received via the user interface; and

wherein the image processor is further configured to crop the second frame of the set of frames identified as belonging to the scene to include the fourth region and the fifth region within a second predetermined display area comprising a subset region of the second frame in the second orientation.

16. The system of claim 10 , wherein the image analyzer is further configured to identify a fourth region within the frame comprising a fourth feature;

wherein the cropping calculator is further configured to generate a fourth score for the fourth region and to determine that the fourth score is less than the threshold; and

wherein the image processor is further configured to crop the fourth region from the frame responsive to the determination.

17. The system of claim 10 , wherein the second feature comprises text, and wherein the cropping calculator is further configured to generate the second score for the second feature based on at least one of a characteristic of the second feature proportional to a size of the text and a distance of the text from a center of the frame.

18. The system of claim 10 , wherein the second feature comprises a face, and wherein the cropping calculator is further configured to generate the second score based on a size of the face relative to the frame.