System and method for automatic video reconstruction with dynamic point of interest

A system for automatically generating video reconstruction, the system comprising:

• a display configured to output a first video, and output a second video in which the first video is reconstructed;
• and
• a processor configured to process data for the first video and reconstruct the second video,
• wherein the processor is further configured to divide the first video into a plurality of first frames, determine a first object of interest from the plurality of first frames, and divide the plurality of first frames into a plurality of second frames based on the first object of interest, and reconstruct the first video into the second video based on the plurality of second frames,
• wherein the processor is further configured to determine the first object of interest based on a user selection on a user interface or based on an intent recognition module using a natural language processing, wherein the user interface provides a preview of objects present in the plurality of first frames, and wherein the intent recognition module processes a text to determine whether an intent of the text is selecting to focus on a particular object or selecting an unwanted object,
• wherein, in a case of determining the first object of interest based on the intent recognition module, the processor is further configured to convert the plurality of first frames by performing:
• extracting at least one of a point of interest or a line of interest for the first object of interest included in a first frame of the plurality of first frames;
• and
• if the intent of the text is selecting the unwanted object, deleting the first object of interest from the plurality of first frames to obtain the plurality of second frames not including the first object of interest;
• or
• if the intent of the text is selecting to focus on the particular object, reconstructing the first frame based on the at least one of the point of interest or the line of interest to obtain the plurality of second frames including the first object of interest.

A computer program product comprising a non-transitory computer-readable medium storing instructions that, when executed by at least one hardware processor, cause the at least one hardware processor to perform operations comprising:

• dividing a first video into a plurality of first frames;
• determining a first object of interest in the plurality of first frames based on a user selection on a user interface or based on an intent recognition module using a natural language processing, wherein the user interface provides a preview of objects present in the plurality of first frames, and wherein the intent recognition module processes a text to determine whether an intent of the text is selecting to focus on a particular object or selecting an unwanted object;
• converting the plurality of first frames into a plurality of second frames based on the first object of interest;
• and
• reconstructing the first video into a second video based on the plurality of second frames,
• wherein, in a case of determining the first object of interest based on the intent recognition module, the converting the plurality of first frames comprises:
• extracting at least one of a point of interest or a line of interest for the first object of interest included in a first frame of the plurality of first frames;
• and
• if the intent of the text is selecting the unwanted object, deleting the first object of interest from the plurality of first frames to obtain the plurality of second frames not including the first object of interest;
• or
• if the intent of the text is selecting to focus on the particular object, reconstructing the first frame based on the at least one of the point of interest or the line of interest to obtain the plurality of second frames including the first object of interest.