Systems and methods for multi-pass adaptive people counting

摘要

People are counted in a segment of video with a video processing system that is configured with a first set of parameters. This produces a first output. Based on this first output, a second set of parameters is chosen. People are then counted in the segment of video using the second set of parameters. This produces a second output. People are counted with a video played forward. People are counted with a video played backwards. The results of these two counts are reconciled to produce a more accurate people count.

主权项

1. A method of counting people: in a video using multiple passes, comprising:
counting people in a segment of video with a video processing system configured with a first set of parameters to produce a first output; determining a second set of parameters based on at least the first output; and, counting people in the segment of video with the video processing system configured with the second set of parameters to produce a second output; wherein the second set of parameters is chosen from a group of sets of parameters that include sets of parameters optimized for low congestion scenes, high congestion scenes, and standard congestion scenes.