Large-Scale Multi-Sensor Monitoring of Pedestrian Dynamics in Public Spaces: Preliminary Results
Alexandra Beaulieu, Bilal Farooq · Transportation Research Board 95th Annual MeetingTransportation Research Board · 2016
Pedestrian monitoring in large-scale settings is a challenging problem that arises in modern society. Manual techniques are costly, and an attempt has been made to automate the process. In this paper the authors incorporate different types of automatic sensor technologies to monitor pedestrian activities at the entire facility level. A case study is done during a large street festival in Montreal covering more than ten street blocks. The authors use WiFi sensors developed in-house to determine origin-destination sequences of pedestrians. One hundred hours of video recordings were collected and computer vision tools are being used for automated processing. Infrared counters are used during the ten days of the festival to obtain extrapolation factors that are then applied to the WiFi data to calculate the exact festival attendance. The results are to be used by the festival organization group for future planning, operations and financing.