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.
| Original language | English |
|---|---|
| Article number | 6784347 |
| Pages (from-to) | 1856-1860 |
| Number of pages | 5 |
| Journal | IEEE Geoscience and Remote Sensing Letters |
| Volume | 11 |
| Issue number | 11 |
| DOIs | |
| Publication status | Published - 1 Jan 2014 |
Keywords
- geodesic method
- Kernel density estimation (KDE)
- mean shift
- road extraction
- semi-automatic
- very high resolution (VHR) satellite images
ASJC Scopus subject areas
- Geotechnical Engineering and Engineering Geology
- Electrical and Electronic Engineering