Urban traffic monitoring from aerial LIDAR data with a Two-Level Marked Point Process model

Author

Bores, A. ; Benedek, Csaba

Author_Institution

Distrib. Events Anal. Res. Lab., Comput. & Autom. Res. Inst., Budapest, Hungary

fYear

2012

fDate

11-15 Nov. 2012

Firstpage

1379

Lastpage

1382

Abstract

In this paper we present a new model for joint extraction of vehicles and coherent vehicle groups in airborne LIDAR point clouds collected from crowded urban areas. Firstly, the 3D point set is segmented into terrain, vehicle, roof, vegetation and clutter classes. Then the points with the corresponding class labels and intensity values are projected to the ground plane, where the optimal vehicle and traffic segment configuration is described by a Two-Level Marked Point Process (L²MPP) model of 2D rectangles. Finally, a stochastic algorithm is utilized to find the optimal configuration.

Keywords

feature extraction; optical radar; road traffic; solid modelling; stochastic processes; traffic information systems; 2D rectangles; 3D point set; L²MPP model; aerial LIDAR data; airborne LIDAR point clouds; coherent vehicle groups; ground plane; stochastic algorithm; traffic segment configuration; two-level marked point process model; urban traffic monitoring; vehicles joint extraction; Atmospheric modeling; Data models; Feature extraction; Joints; Laser radar; Lattices; Vehicles;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition (ICPR), 2012 21st International Conference on

Conference_Location

Tsukuba

ISSN

1051-4651

Print_ISBN

978-1-4673-2216-4

Type

conf

Filename

6460397