Share Email Print

Proceedings Paper

Automatic road extraction for airborne lidar data
Author(s): Yuan Wang; Siying Chen; Yinchao Zhang; He Chen; Pan Guo; Jian Yang
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Airborne LiDAR, as a precise and fast earth’s surface three-dimensional (3D) measuring method, has been widely used in the past decades. It provides a new approach for acquiring road information. By analyzing the characteristics of LiDAR datasets as well as that of the road in the datasets, a morphological method has been proposed to automatically extract the road from airborne LiDAR datasets. Firstly, ground points are segmented from raw LiDAR data by morphological operations. The key factor in this process is how to select the window sizes in different scale spaces, and setting the elevation threshold to prevent over-segmentation in each scale space. Secondly, candidate road points are segmented from the ground points, which are obtained from previous step, by intensity constraint, local point density and region area constraint, and so on. Thirdly, morphological opening operation and closing operation were used to process the candidate road points segmented from above steps. The opening operation may effectively filter the noise areas, and greatly maintain the road detail. The closing operation may fill the small holes within the road, connecting nearby roads, and smoothing the road boundary, without signification area change. The main road can be extracted from the raw airborne LiDAR points by previous three steps. Finally, the proposed method has been verified by LiDAR data which consists of complex road networks. The result shows that the proposed method can automatically extract road from airborne LiDAR data with higher efficiency and precision.

Paper Details

Date Published: 19 September 2013
PDF: 7 pages
Proc. SPIE 8905, International Symposium on Photoelectronic Detection and Imaging 2013: Laser Sensing and Imaging and Applications, 890528 (19 September 2013); doi: 10.1117/12.2034862
Show Author Affiliations
Yuan Wang, Beijing Institute of Technology (China)
Siying Chen, Beijing Institute of Technology (China)
Yinchao Zhang, Beijing Institute of Technology (China)
He Chen, Beijing Institute of Technology (China)
Pan Guo, Beijing Institute of Technology (China)
Jian Yang, Beijing Institute of Technology (China)

Published in SPIE Proceedings Vol. 8905:
International Symposium on Photoelectronic Detection and Imaging 2013: Laser Sensing and Imaging and Applications
Farzin Amzajerdian; Astrid Aksnes; Weibiao Chen; Chunqing Gao; Yongchao Zheng; Cheng Wang, Editor(s)

© SPIE. Terms of Use
Back to Top