Title :
A Semi-Automatic Method for Road Centerline Extraction From VHR Images
Author :
Zelang Miao ; Bin Wang ; Wenzhong Shi ; Hua Zhang
Author_Institution :
Dept. of Land Surveying & Geo-Inf., Hong Kong Polytech. Univ., Kowloon, China
Abstract :
This letter presents a semi-automatic approach to delineating road networks from very high resolution satellite images. The proposed method consists of three main steps. First, the geodesic method is used to extract the initial road segments that link the road seed points prescribed in advance by users. Next, a road probability map is produced based on these coarse road segments and a further direct thresholding operation separates the image into two classes of surfaces: the road and nonroad classes. Using the road class image, a kernel density estimation map is generated, upon which the geodesic method is used once again to link the foregoing road seed points. Experiments demonstrate that this proposed method can extract smooth correct road centerlines.
Keywords :
differential geometry; geophysical image processing; image segmentation; probability; roads; VHR satellite imaging; geodesic method; initial road segment extraction; kernel density estimation map; road centerline extraction; road class imaging; road network delineating; road probability map; road seed points link; semiautomatic method; thresholding operation; very high resolution satellite imaging; Educational institutions; Estimation; Feature extraction; Kernel; Remote sensing; Roads; Satellites; Kernel density estimation (KDE); geodesic method; mean shift; road extraction; semi-automatic; very high resolution (VHR) satellite images;
Journal_Title :
Geoscience and Remote Sensing Letters, IEEE
DOI :
10.1109/LGRS.2014.2312000