Road is not only a basic feature of geographic information, but also the most frequently changed feature. Due to rapid development, road information of the map is not consistent with the actual case of land features. Road extraction from digital images is of fundamental importance in effective urban planning and updating GIS databases. There is an urgent need for updating road information in a timely manner. Therefore, a large amount of research is being dedicated on the development of efficient methods to extract the geographic features (such as roads) from digital remote sensed images. This paper applies semi-automatic approach to extract different road types from high-resolution remote sensing images. The approach is based on a K-Nearest Neighbor(KNN)and membership function algorithm(MFA) method. First the outline of the road is detected based on different segmentation scales. Membership function algorithm(MFA)-threshold value method reflecting various spatial, spectral, and texture attributes is to modify and optimize. Then the entire image was classified to form a road image. Finally, the quality of detected roads is evaluated. The results of the accuracy evaluation demonstrate that the proposed road extraction approach can provide high accuracy for extraction of different road types.

Date Published: 9 August 2018
PDF: 6 pages
Proc. SPIE 10806, Tenth International Conference on Digital Image Processing (ICDIP 2018), 1080654 (9 August 2018); doi: 10.1117/12.2503031

Published in SPIE Proceedings Vol. 10806:
Tenth International Conference on Digital Image Processing (ICDIP 2018)
Xudong Jiang; Jenq-Neng Hwang, Editor(s)