Method and system for generating adaptive fast forward of egocentric videos

A system comprising:

• a memory configured to store a video footage containing a sequence of image frames captured by a non-stationary capturing device;
• and
• a computer processor configured to:
• estimate a moving direction of the non-stationary capturing device for a plurality of frames in the sequence of image frames;
• and
• generate a shortened video footage having fewer frames than said video footage, by sampling the sequence of image frames,
• wherein the sampling is carried out by selecting specific image frames that reduce an overall cost associated with a deviation from a specific direction related to said moving direction, calculated for at least some of said plurality of image frames.

A non-transitory computer readable medium comprising a set of instructions that when executed cause at least one computer processor to:

• obtain a video footage containing a sequence of image frames captured by a non-stationary capturing device;
• estimate a moving direction of the non-stationary capturing device for a plurality of frames in the sequence of image frames;
• and
• generate a shortened video footage having fewer frames than said video footage, by sampling the sequence of image frames,
• wherein the sampling is carried out by selecting specific image frames that reduce an overall cost associated with a deviation from a specific direction related to said moving direction, calculated for at least some of said plurality of image frames.