Traffic Flow Parameter Estimation and Road Surface Modeling From Airborne LiDAR Data

Dorota Grejner-Brzezinska, Charles Toth, Eva Paska, Shahram Moafipoor

Abstract:	The National Consortium for Remote Sensing in Transportation-Flows (NCRST-F), led by The Ohio State University, and sponsored by the U.S. Department of Transportation and NASA, was established in 2001. Our partners in NCRST-F are the University of Arizona and George Mason University. The major focus of the OSU research team is to improve the efficiency of the transportation system by the integration of remotely sensed data with the traditional ground data to monitor and manage traffic flows. Our research team is concerned with the vehicle extraction and traffic pattern modeling based on airborne digital data, collected by frame cameras and LiDAR systems (Light Detection and Ranging). This paper is an extension of our earlier publications, where theoretical and practical studies on the feasibility of using LiDAR data and airborne imagery collected over the transportation corridors for estimation of traffic flow parameters were presented. In this contribution the actual example of traffic flow estimation obtained from high-accuracy data set, collected in February 2004 in Toronto, Canada is presented. In particular, vehicle extraction, classification into major categories, and velocity estimation, as a primary parameter describing the traffic flow, are discussed and analyzed. The updated algorithms and methodology of extracting vehicle information together with the road surface modeling with LiDAR, precisely georeferenced by GPS/INS sensors, and augmented by LiDAR intensity information, are discussed. We demonstrate that our algorithms are fast and efficient and are capable of autonomous traffic flow information extraction. It is shown, however, that for better accuracy and reliability, a fusion of LiDAR with frame image data is desirable. Nonetheless, based on the high spatial density LiDAR data, we demonstrate that vehicle extraction and their coarse classification as well as estimation of flow can be efficiently performed in parallel to the efficient and automated road surface extraction and modeling.
Published in:	Proceedings of the 17th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS 2004) September 21 - 24, 2004 Long Beach Convention Center Long Beach, CA
Pages:	1392 - 1402
Cite this article:	Grejner-Brzezinska, Dorota, Toth, Charles, Paska, Eva, Moafipoor, Shahram, "Traffic Flow Parameter Estimation and Road Surface Modeling From Airborne LiDAR Data," Proceedings of the 17th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS 2004), Long Beach, CA, September 2004, pp. 1392-1402.
Full Paper:	ION Members/Non-Members: 1 Download Credit Sign In