A Study on 3D Road Extraction From Three Linear Scanner

摘要

The extraction of 3D road network from high-resolutionrnaerial images is still one of the current challenges in digitalrnphotogrammetry and computer vision. For many years, there arernmany researcher groups working for this task, but unt il now, therernare no papers for doing this with TLS (Three linear scanner), whichrnhas been developed for the past several years, and has veryrnhigh-resolution (about 3 cm in ground resolution).rnIn this paper, we present a methodology of road extraction fromrnhigh-resolution digital imagery taken over urban areas using thisrnmodern photogrammetry's scanner (TLS). The key features of thernapproach are: (1) Because of high resolution of TLS image, ourrnextraction method is especially designed for constructing 3D roadrnmap for next -generation digital navigation map; (2) for extractingrnroad, we use the global context of the intensity variations associatedrnwith different features of road (I.e. zebra line and center line), priorrnto any local edge. So extraction can become comparatively easy,rnbecause we can use different special edge detector accordingrndifferent features.rnThe results achieved with our approach show that it is possiblernand economic to extract 3D road data from Three Linear Scanner tornconstruct next -generation digital navigation road map.