Automatic Road Extraction from Airborne LiDAR Data in Urban Area

Automatic Road Extraction from Airborne LiDAR Data in Urban Area

Hamid Reza Riyahi Bakhtyari1 Mohammad Talebi2

1) Assistant Professor, faculty of Natural Resources and Earth Sciences, Shahrekord University,
2) MSc. Graduated of Remote Sensing and GIS, Kharazmi University,

IOI Code : XBBA-DKAHK
Publication : 4th International Congress of Developing Agriculture, Natural Resources, Environment and Tourism of Iran(4icsda.ir)
Abstract :
    Automatic road extraction from urban area is a challenging issue because of high complexity. An approach to achieve automated road extraction from Airborne Laser Scanning (ALS) data is presented. The proposed approach consists of two steps. In the first step, Support Vector Machine (SVM) algorithm was applied on intensity and distance data merely to classify data into two groups of road and non road categories. In the second step, the road category was improved by removing unwanted non-road pixels using morphological operation. Due to the lack of aerial photos of the study area, reference map prepared by manual digitizing of Google Earth images. Through comparing the achieved results with ground truth road map as reference data, the performance measures such as completeness, correctness, and quality were calculated. Results of the evaluation showed the value completeness, correctness, and quality were 84.01%, 79.92%, and 69.37% respectively. These measures prove that the proposed approach detects and extract roads in a robust manner. The results of this study show that morphological operators play an important role in improving the accuracy and quality of the results.

Keywords : airborne lidar svm road extraction morphological operator