Line extraction algorithm based on image vectorization

The raster-vector conversion of remote sensing image is a very important task in the extraction and updating of linear objects in cartographic processes. In this paper we present a vectorization method, based on constrained Delaunay triangulation, for line extraction. The constraints are provided by a preprocessing step insuring that these edges belong to line structures in the original image. The vectorization is performed using CDT and resulting triangles are grouped into polygins that make up the vector image. The skeleton of these polygons represents the extracted linear structures. The algorithm is automatic, fast and has very satisfing results when tested on road segments.