Machine learning-based subject tracking

A system for tracking subjects, in an area of real space, comprising:

• a processing system receiving a plurality of synchronized sequences of images of respective fields of view in the real space at image capturing cycles, the processing including:
• logic to process images in a first set of sequences in the plurality of synchronized sequences at a first image capturing cycle to identify a feature of a particular tracked subject, the feature having a first location represented by positions in three dimensions of the area of real space and a timestamp;
• logic to process images in a second set of sequences including more than one member in the plurality of synchronized sequences at a second image capturing cycle to identify a candidate feature of a particular tracked subject, the candidate feature having a second location represented by positions in three dimensions of the area of real space and a timestamp;
• and
• logic to track movement of the particular tracked subject by matching the feature from the first image capturing cycle with the candidate feature in the second image capturing cycle.