Road extraction framework by using cellular neural network from remote sensing images

Abstract

Researches on Road Extraction are incessant. Theses researches aims at the automatic identification of remote sensing images. The way to extract roads quickly, accurately and automatically has been a cutting-edge problem in remote sensing related fields, since the availability of high spatial resolution images from new generation commercial sensors. In this paper, we present a novel automatic road extraction approach which uses a Cellular neural Network. The approach makes full use of spectral and geometric properties of roads in the imagery, and proposes a Framework named "CNN- Cellular neural Network". A primary result shows that the accuracy of this algorithm is very high, fast and can be implemented on hardware chipset. © 2011 IEEE.