Deriving Vehicle Topology and Attribute Information Over Transportation Corridors From LIDAR Data

D. Grejner-Brzezinska, C. Toth

Abstract:	The focus of this paper is to study the feasibility of using LiDAR (Light Detection and Ranging) data collected over the transportation corridors for traffic flow estimates, such as (1) vehicle count estimates based on extracting vehicles from dense LiDAR point cloud, (2) classification of extracted vehicles into main categories, and (3) velocity estimates based on modeling the vehicle categories and using sensor navigation data. LiDAR capability to identify the shapes (especially the vertical profiles of the vehicles) has been demonstrated, proving LiDAR's ability to preserve the vehicle geometry better as compared to conventional image projection (again, primarily the vertical profile), where it can be significantly distorted. It will be demonstrated that if LIDAR data of sufficient spatial density are available, vehicle extraction and their coarse classification can be efficiently performed. In this paper we will present the preliminary results of a LIDAR-based vehicle extraction method that proves the high potential of this technology. Finally, the feasibility of using LiDAR data for velocity estimates will be briefly discussed.
Published in:	Proceedings of the 59th Annual Meeting of The Institute of Navigation and CIGTF 22nd Guidance Test Symposium (2003) June 23 - 25, 2003 Hyatt Regency Hotel Albuquerque, NM
Pages:	404 - 410
Cite this article:	Grejner-Brzezinska, D., Toth, C., "Deriving Vehicle Topology and Attribute Information Over Transportation Corridors From LIDAR Data," Proceedings of the 59th Annual Meeting of The Institute of Navigation and CIGTF 22nd Guidance Test Symposium (2003), Albuquerque, NM, June 2003, pp. 404-410.
Full Paper:	ION Members/Non-Members: 1 Download Credit Sign In