Monitoring and Predicting Pedestrian Behavior Using Traffic Cameras

University Transportation Centers Program2018PDFTech ReportNavarro-Serment, Luis E.Carnegie Mellon UniversityTechnologies for Safe and Efficient Transportation. University Transportation CenterUniversity of PennsylvaniaUnited States. Department of Transportation. Office of the Assistant Secretary for Research and TechnologyUnited States. Department of Transportation. University Transportation Centers (UTC) ProgramTechnologies for Safe and Efficient Transportation. University Transportation CenterUnited StatesAlgorithmsBehaviorIntersectionsMathematical predictionMonitoringPedestrian detectorsPedestrian movementPedestriansReal time informationTraffic surveillanceTrajectoryVideo camerasFinal ReportThis project addresses the need for timely and accurate information about pedestrian traffic in urban areas. This is particularly important at locations where it is not uncommon to find more pedestrians than vehicles during certain times of the day. Through the work conducted in this project, we move closer to deploying systems for detecting, tracking, and forecasting human behavior in dynamic environments. This information can be used by other systems as part of an infrastructure-based framework to effectively protect pedestrians: the more vulnerable traffic participants. Most intersections lack awareness of pedestrian traffic: their perception infrastructure\u2014when available\u2014is usually limited to the detection of vehicles at very specific places. In this study we consider the use of video cameras to monitor pedestrian traffic in settings where a static camera that has an unobstructed view of the road is used to detect and track pedestrians. An example set up is shown in Fig. 1, where four monocular cameras mounted on the traffic light structures monitor a busy intersection. Typically, a single camera cannot cover the entire area, so multiple cameras are used at each intersection; this increases costs, and consequently it is desirable to use as few cameras as possible.136