| Road information as a type of basic geographic information is very important for services such as geospatial applications,cartographic,infrastructure planning,city planning,and traffic navigation.Therefore an urgent need for updating road information promptly.In this thesis,A framework of road information modeling has been proposed,for rural and urban scenarios respectively,and an integrated system has been evaluated and developed to deal with road feature extraction using the Remote sensing image and LiDAR analysis.For road extraction in rural regions,we propose a road extraction method based on geometric feature inference.In this method,we make full use of the linear characteristics of roads and construct a geometric knowledge base of rural roads using the information on selected sample road segments.Based on the knowledge base,we identify the parallel line pairs in images,and further conduct grouping and connection instructed by knowledge reasoning,and finally obtain complete rural roads.As the extraction of roads in urban areas is greatly affected by buildings,shadows,vehicles,and parking lots,we combine high-resolution Remote sensing images and dense LiDAR data to fully exploit the precise spectral and horizontal spatial resolution of aerial images and the accurate vertical information provided by airborne LiDAR.Object-oriented image analysis methods are employed to process feature classification and road detection in aerial images.In this process,we first utilize an adaptive mean shift(MS)segmentation algorithm to segment the original images into meaningful object-oriented clusters.Then the support vector machine(SVM)algorithm is further applied to the MS segmented image to extract road objects.Road surface detected in LiDAR intensity images is taken as a mask to remove the effects of shadows and trees.In addition,normalized DSM(nDSM)obtained from LiDAR is employed to filter out other above-ground objects,such as buildings and vehicles. |
PDF Full Text Request