Signature-based object tracking in video feed

A computer system comprising:

• a processing system;
• and
• a computer storage media that stores computer-executable instructions that are executable by the processing system to at least:
• calculate a first signature for a first region of a first video frame of a video feed based on content of the first video frame, the first region being associated with a detected object of interest within the video feed, the first signature characterizing a strength of edges within the first region;
• calculate a second signature for a second region of a second video frame of the video feed based on content of the second video frame, the second video frame being subsequent to the first video frame within the video feed, the second signature characterizing a strength of edges within the second region;
• determine a measure of difference between the first signature and the second signature;
• and
• based on the amount of difference between the first signature and the second signature exceeding a threshold, trigger a signature-based object detection on the video feed.

A computer program product comprising a computer storage media that stores computer-executable instructions that are executable by a processing system to at least:

• calculate a first signature for a first region of a first video frame of a video feed based on content of the first video frame, the first region being associated with a detected object of interest within the video feed, wherein calculating the first signature comprises:
• dividing the first region into a first plurality of sub-regions;
• calculating a first plurality of sub-region signatures, each sub-region signature corresponding to a different sub-region of the first plurality of sub-regions;
• and
• concatenating the first plurality of sub-region signatures;
• calculate a second signature for a second region of a second video frame of the video feed based on content of the second video frame, the second video frame being subsequent to the first video frame within the video feed, the second region being associated with the detected object of interest within the video feed, wherein calculating the second signature comprises:
• dividing the second region into a second plurality of sub-regions;
• calculating a second plurality of sub-region signatures, each sub-region signature corresponding to a different sub-region of the second plurality of sub-regions;
• and
• concatenating the second plurality of sub-region signatures;
• determine a measure of difference between the first signature and the second signature;
• and
• based on the amount of difference between the first signature and the second signature exceeding a threshold, trigger a signature-based object detection on the video feed.