Self-organised clustering for road extraction in classified imagery

The extraction of road networks from digital imagery is a fundamental image analysis operation. Common problems encountered in automated road extracti on include high sensitivity to typical scene clutter in high-resolution ima gery, and inefficiency to meaningfully exploit multispectral imagery (MSI). With a ground sample distance (GSD) of less than 2 m per pixel, roads can be broadly described as elongated regions. We propose an approach of elonga ted region-based analysis for 2D road extraction from high-resolution image ry, which is suitable for MSI, and is insensitive to conventional edge defi nition. A self-organising road map (SORM) algorithm is presented. inspired from a specialised variation of Kohonens self-organising map (SOM) neural n etwork algorithm. A spectrally classified high-resolution image is assumed to be the input for our analysis. Our approach proceeds by performing spati al cluster analysis as a mid-level processing technique. This allows us to improve tolerance to road clutter in high-resolution images, and to minimis e the effect on road extraction of common classification errors. This appro ach is designed in consideration of the emerging trend towards high-resolut ion multispectral sensors. Preliminary results demonstrate robust road extr action ability due to the non-local approach, when presented with noisy inp ut. (C) 2001 Elsevier Science B.V. All rights reserved.