Automated Pedestrian Data-collection and Flow Analysis in Public Spaces

Though a wealth of data exists for the characterization of pedestrian movement, a majority of it originates from experimental settings owing to the current state of trackers for real-world scenarios. While these trackers are steadily improving, they remain insufficiently reliable for the accurate, microscopic tracking of individuals. We propose the application of evolutionary algorithms to the calibration of parameters of existing trackers in order to further optimize their performance in complex cases, with an initial focus on feature-based tracking methods. Preliminary results demonstrate a two-fold improvement of tracking accuracy and as a strong correlation in performance between cases.