GTC Silicon Valley-2019: Edge Computing with Jetson TX2 for Monitoring Flows of Pedestrians and Vehicles
Note: This video may require joining the NVIDIA Developer Program or login
GTC Silicon Valley-2019 ID:S9206:Edge Computing with Jetson TX2 for Monitoring Flows of Pedestrians and Vehicles
Johan Barthelemy(SMART Infrastructure Facility University of Wollongong),Nicolas Verstaevel(SMART Infrastructure Facility University of Wollongong)
We'll discuss how we're using several Jetson TX2-based edge computing devices and LPWAN networks to monitor in real time the flow of vehicles and pedestrians in a network. In particular, we'll describe our work to better understand and predict pedestrian and vehicle flow around the Liverpool CBD to ease congestion, provide better transport options, and improve health and safety. In our solution, each device in the monitored network processes the live feed from its own camera. We'll explain how we use the YOLO v3 object detector to analyze these frames and extract the pedestrians and vehicles in each, then pass this information onto a tracker algorithm (Kalman filter) to determine their trajectories. After a frame is processed, it is discarded and only aggregated indicators are sent over the LPWAN network to a dashboard to reduce privacy concerns and bandwidth requirements.