Lewis, Paul (2017) Automated extraction of road median from airborne laser scanning data. In: 38th Asian Conference on Remote Sensing - Space Applications: Touching Human Lives, ACRS 2017, 23-27 October 2017, New Delhi (India).

Download (787kB)

Abstract

Airborne Laser Scanning (ALS) systems enable the acquisition of an accurately georeferenced set of 3D dense point cloud data that can be used to develop more efficient approaches for managing road infrastructures. These systems can contribute to the produc tion of useful knowledge about road median, which is a narrow strip of land that separates traffic on opposite sides of the road. The road median is one of the fundamental feature, whose correct identification is a prerequisite to obtain precise informatio n about road and other objects along it. The acquired ALS data can be used to locate, measure and classify the road median in a timely and cost -effective manner in order to facilitate their maintenance. In this paper, we present an automated algorithm for extracting road median from ALS data. We use the road vector polylines to reduce the search space in the LiDAR data, which enables a more accurate estimation of the road median. The frequency distribution of elevation values is used to r emove the crossing highway s above the road sections. We threshold the LiDAR elevation and intensity attributes to get an initial estimation of the road median . We make the morphological operations based knowledge analysis to complete the shape of road median and remove oth er road surface elements that are introduced through the use of thresholding. We tested our algorithm on two 1 -km road sections consisting of distinct types of road medians based on concrete and grass -hedge barrier. T he successful extraction of median s along thes e two road sections demonstrate the robustness of our automated algorithm. These research findings provide valuable insight and prototype road median extraction tool -set for both national road authorities and survey companies.

Item Type:	Conference or Workshop Item (Paper)
Keywords:	Airborne Laser Scanning; Attributes; Road Median; Frequency Distribution; Knowledge Analysis;
Academic Unit:	Faculty of Science and Engineering > Research Institutes > National Centre for Geocomputation, NCG
Item ID:	10440
Depositing User:	Dr. Paul Lewis
Date Deposited:	21 Jan 2019 17:13
Refereed:	Yes
URI:	https://zenodo.org/record/1157858\#.XEXF...
Use Licence:	This item is available under a Creative Commons Attribution Non Commercial Share Alike Licence (CC BY-NC-SA). Details of this licence are available here

Repository Staff Only(login required)

Item control page

Downloads

Origin of downloads