| CPC H04N 21/25825 (2013.01) [G06V 10/25 (2022.01); G06V 20/40 (2022.01); G06V 20/46 (2022.01); G06V 20/49 (2022.01); H04N 21/4318 (2013.01); H04N 21/440272 (2013.01); H04N 21/4728 (2013.01); H04N 21/4854 (2013.01); H04N 21/4858 (2013.01)] | 20 Claims |

|
1. A computer-implemented method comprising:
identifying one or more objects within a video scene;
determining a semantic context for at least one of the identified objects in the video scene,
generating a video crop that will include at least one specified object that is defined according to the determined semantic context, wherein the generated video crop includes a maximum number of objects that are part of the determined semantic context; and
applying the generated video crop to the video scene, tracking which video crops were generated and applied to one or more of the video scenes; and comparing at least one cropped version of the video scene to a user-cropped version of the same video scene to identify one or more differences in cropping.
|