Trajectory matching based on use of quality indicators empowered by weighted confidence values

A system for iteratively matching a plurality of spatiotemporal trajectories of a plurality of users according to a threshold, wherein the system comprises at least one processor, one or more memories, and a quality classifier, and wherein the one or more memories are coupled to the at least one processor and store programming instructions for execution by the at least one processor to:

• receive a plurality of first spatiotemporal trajectories and a plurality of second spatiotemporal trajectories, wherein each of the plurality of first spatiotemporal trajectories and the plurality of second spatiotemporal trajectories is generated based on location data gathered by a different tracking system;
• and
• the quality classifier being configured to:
• classify the plurality of first spatiotemporal trajectories into first low quality trajectories and first high quality trajectories, and classify the plurality of second spatiotemporal trajectories into second low quality trajectories and second high quality trajectories;
• and
• wherein the programming instructions are for execution by the at least one processor to:
• identify a plurality of high quality trajectories pairs by matching between the first high quality trajectories and the second high quality trajectories;
• identify a plurality of low quality trajectories pairs by matching between the first low quality trajectories and the second low quality trajectories;
• associate each of the plurality of low quality trajectories pairs and each of the plurality of high quality trajectories pairs with a confidence value indicative of a disparity of a respective pair;
• adjust a plurality of confidence values of at least two of the plurality of low quality trajectories pairs and the plurality of high quality trajectories pairs;
• and
• re-input the plurality of spatiotemporal trajectories into the quality classifier, wherein the plurality of spatiotemporal trajectories are part of the low quality trajectories pair or the high quality trajectories pair whose adjusted confidence value is below the threshold.