01589791

Component

The study of maneuverability of vehicles in high demand urban road networks through vehicles’ trajectories is a challenge for traffic engineers and researchers. The collection of such high resolution data has been exclusively supported by costly fixed location camera systems and computer vision algorithms in isolated or sequential sections. Recently, with the advances in computer vision, low cost cameras have been used with quite a success in extracting kinematic characteristics. In this paper, the authors discuss several limitations accompanying the use of camcorders and how they can be alleviated with the use of Unmanned Aerial Vehicles (UAVs). Following, a low-cost semi-automatic way of extracting detailed vehicle trajectory data through UAV video footage is presented. Steps to reduce errors due to camera instability and to achieve sufficient calibration are also described. Two experiments are presented; the first refers to vehicle tracking at a four legged intersection and the second to tracking pedestrian flow. Following, a discussion concerning the use of UAVs to replace or extend current systems’ capabilities is conducted.

This paper was sponsored by TRB committee ABJ35 Standing Committee on Highway Traffic Monitoring.

01584066

16-3429

English

16p

2016

Transportation Research Board 95th Annual Meeting

Digital/other

Figures; References; Tables

Arterial highways; Data collection; Drones; Kinematics; Microscopic traffic flow; Urban areas; Vehicle trajectories; Video cameras

Aviation; Data and Information Technology; Highways; Operations and Traffic Management; Vehicles and Equipment; I72: Traffic and Transport Planning; I90: Vehicles

Transportation Research Board Annual Meeting 2016 Paper #16-3429

TRIS, TRB, ATRI

Jan 12 2016 5:30PM