详情

原文传递 Monitoring and Predicting Pedestrian Behavior Using Traffic Cameras.

题名：	Monitoring and Predicting Pedestrian Behavior Using Traffic Cameras.
作者：	Navarro-Serment, L. E.
关键词：	Behavior, Cameras, Deployment, Detection and identification, Machine vision, Mathematical prediction, Monitoring, Pedestrian movement, Pedestrian safety, Real time control, Traffic signal control systems, Traffic surveillance, Trajectory, Data and Information Technology, Highways, Operations and traffic management, Pedestrians, Bicyclists, Safety and human factors, Carnegie Mellon University
摘要：	Effective traffic monitoring and control systems must consider all moving objects. While vehicle detection systems have become common, sensor-based solutions capable of detecting and monitoring pedestrian activity have yet to become an integral part of a smart and effective infrastructure capable of protecting these most vulnerable traffic participants. Such systems could alert incoming vehicles about dangerous situations involving pedestrians, or provide adaptive traffic light control systems with information about the motion of people, so that they can operate and make decisions cognizant of all moving objects. In currently ongoing research work the project team is developing a vision-based framework which is capable of detecting, tracking, and predicting the trajectories of people in real time. These abilities constitute the core of a system capable of monitoring any developments concerning pedestrian motion. In this project, the team proposes a natural extension of this work: they focus on the deployment aspects of this framework. The team will address the challenges of bringing a new site into effective action, such as on-site camera calibration and the initial identification of a context to make predictions. The expected outcome is the creation, implementation, and demonstration of a framework which can be deployed in the field, and is capable of providing pedestrian information to systems like SURTRAC—a real time traffic signal control system. The milestones envisioned, to accomplish in one year, are: (1) Definition of methodology for initial station set up for on-site testing; (2) Design and test communications structure; (3) Live testing; and (4) Initial assessment of the impact on systems using pedestrian information. The project team is composed of a Master's student and researchers with many years of experience in computer vision for autonomous systems.
报告类型：	科技报告