Method, device, and computer program product for video compression

An electronic device, comprising:

• a processor;
• and
• a memory coupled to the processor, wherein the memory has instructions stored therein which, when executed by the processor, cause the electronic device to perform actions comprising:
• segmenting, in response to one or more features of an object in a video having a periodic change, the video into a plurality of segments based on a cycle of the periodic change;
• identifying focal regions in frames of the video that are associated with the object;
• and
• compressing the video based on the plurality of segments and the focal regions;
• wherein compressing the video based on the plurality of segments and the focal regions comprises:
• dividing, for a segment of the plurality of segments, frames of the segment into a plurality of frame clusters based on a similarity of the focal regions between the frames of the segment;
• and
• compressing the segment based on the division of the plurality of frame clusters;
• wherein compressing the segment based on the division of the plurality of frame clusters comprises:
• determining a central frame of a frame cluster of the plurality of frame clusters, wherein the central frame is a frame in the frame cluster that is the closest to the center of the frame cluster;
• and
• in response to a similarity of the focal regions between the central frame and another frame in the frame cluster satisfying a threshold, removing the other frame from the segment.

A computer program product tangibly stored on a non-transitory computer-readable medium and comprising machine-executable instructions, wherein the machine-executable instructions, when executed by a machine, cause the machine to execute a video compression method, the method comprising:

• segmenting, in response to one or more features of an object in a video having a periodic change, the video into a plurality of segments based on a cycle of the periodic change;
• identifying focal regions in frames of the video that are associated with the object;
• and
• compressing the video based on the plurality of segments and the focal regions;
• wherein compressing the video based on the plurality of segments and the focal regions comprises:
• dividing, for a segment of the plurality of segments, frames of the segment into a plurality of frame clusters based on a similarity of the focal regions between the frames of the segment;
• and
• compressing the segment based on the division of the plurality of frame clusters;
• wherein compressing the segment based on the division of the plurality of frame clusters comprises:
• determining a central frame of a frame cluster of the plurality of frame clusters, wherein the central frame is a frame in the frame cluster that is the closest to the center of the frame cluster;
• and
• in response to a similarity of the focal regions between the central frame and another frame in the frame cluster satisfying a threshold, removing the other frame from the segment.