Methods, systems, and computer-readable media for detecting scene changes in a video

A image processing computing device comprising:

• at least one processor;
• a memory coupled to the at least one processor which is configured to be capable of executing programmed instructions stored in the memory comprising:
• detecting a plurality of scenes from a sequence of video frames;
• identifying a plurality of scene boundary differences corresponding to the plurality of detected scenes;
• determining a scene invariant fixed average for the plurality of scene boundary differences and a scene dependent varying average for each of the plurality of detected scenes corresponding to the identified plurality of scene boundary differences;
• comparing, for each of the plurality of detected scenes, the scene boundary difference between the scene invariant fixed average and the scene dependent varying average;
• combining the detected scenes when the scene boundary difference is less than the scene invariant fixed average and the scene dependent varying average;
• and
• identifying each of the plurality of detected scenes corresponding to when the scene boundary difference is greater than the scene invariant fixed average and the scene dependent varying average.

A non-transitory computer-readable medium having stored thereon instructions for detecting scene changes in a sequence of video frames comprising machine executable code which when executed by a processor, causes the processor to perform steps comprising:

• detecting a plurality of scenes from a sequence of video frames;
• identifying a plurality of scene boundary differences corresponding to the plurality of detected scenes;
• determining a scene invariant fixed average for the plurality of scene boundary differences and a scene dependent varying average for each of the plurality of detected scenes corresponding to the identified plurality of scene boundary differences;
• comparing, for each of the plurality of detected scenes, the scene boundary difference between the scene invariant fixed average and the scene dependent varying average;
• combining the detected scenes when the scene boundary difference is less than the scene invariant fixed average and the scene dependent varying average;
• and
• identifying each of the plurality of detected scenes corresponding to when the scene boundary difference is greater than the scene invariant fixed average and the scene dependent varying average.