A new hierarchical method for automatic road centerline extraction in urban areas using LIDAR data

Abstract

Road detection and road extraction are important and challenging issues in the fields of photogrammetry and remote sensing. Researchers have conducted wide research in this regard based on multispectral images and achieved relatively useful results. Image-data driven methods have some shortcomings such as shadows, eliminating small and long vehicles, geometric distortions, and occlusions. In recent years, in order to overcome the above limitations and complexities, several attempts have been done based on LIDAR data. The present paper proposes an automatic hierarchical road detection and extraction method. The main goal of this research is to increase the level of continuity of the road detection and extraction processes. This method includes the preprocessing of intensity data using a local minima filter, applying the Mean Shift segmentation to the refined intensity data, and finally integrating it with various nDSM-based Products. The proposed method involves not only considering both small and long vehicles as road features but also neglecting some parts of large parking lots based on the nearby neighborhood of parked vehicles as much as possible as non-road features. The next step was the process of road centerline extraction by adopting a Voronoi-diagram based approach and then removing dangle lines in several iterations. The proposed method was applied to the Vaihingen and Toronto datasets (ISPRS). The completeness of the two datasets is 95.85% and 88%, and the correctness of these datasets are 83.68% and 72.2%, respectively. The results were indicative of the great potential of the proposed method for effective road centerline extraction in urban areas.