Road Information Extraction from High-Resolution Remote Sensing Images Based on Road Reconstruction

Tingting Zhou,Haoyang Fu,Chenglin Sun

doi:10.3390/rs11010079

Abstract

Traditional road extraction algorithms, which focus on improving the accuracy of road surfaces, cannot overcome the interference of shelter caused by vegetation, buildings, and shadows. In this paper, we extract the roads via road centerline extraction, road width extraction, broken centerline connection, and road reconstruction. We use a multiscale segmentation algorithm to segment the images, and feature extraction to get the initial road. The fast marching method (FMM) algorithm is employed to obtain the boundary distance field and the source distance field, and the branch backing-tracking method is used to acquire the initial centerline. Road width of each initial centerline is calculated by combining the boundary distance fields, before a tensor field is applied for connecting the broken centerline to gain the final centerline. The final centerline is matched with its road width when the final road is reconstructed. Three experimental results show that the proposed method improves the accuracy of the centerline and solves the problem of broken centerline, and that the method reconstructing the roads is excellent for maintain their integrity.

Highlights

As the main body of modern transportation system, roads mean geographical, political, and economic significance, which are the main recorded and identified object in GIS and maps.The technology of road extraction using images appeared in the middle of the 20th century, due to the need for intelligent transportation [1]
The methods can be divided into four categories: (1) Road extraction method based on region segmentation; (2) Road extraction method based on template matching; (3) Road extraction method based on edge; and (4)
Experimental results are shown in Figure 11–13, where (a) is the picture fused by panchromatic and multispectral images; (b) is the initial road, which is extracted by statistical region merge (SRM) multiscale segmentation and feature extraction; (c) is the initial centerline, in which the broken centerlines are marked with red rectangles; (d) is the tensor field obtained by the initial centerline; (e) is the complete centerline after the connection, an unconnected broken centerline marked with red rectangle; and (f) 11 isofthe

Summary

Introduction

As the main body of modern transportation system, roads mean geographical, political, and economic significance, which are the main recorded and identified object in GIS and maps. The technology of road extraction using images appeared in the middle of the 20th century, due to the need for intelligent transportation [1]. With the rapid development of remote sensing in the recent 10 years, high-resolution remote sensing images provide the possibility of using remote sensing images for road extraction. Scholars put forward many algorithms and models, according to the different characteristics of image sources, image segmentation, rule sets of road extraction, and purposes of usage. The methods can be divided into four categories: (1) Road extraction method based on region segmentation; (2) Road extraction method based on template matching; (3) Road extraction method based on edge; and (4)

Objectives

Results

Discussion

Conclusion