Road extraction from SAR imagery based on an improved particle filtering and snake model

This article presents an improved approach for road extraction from synthetic aperture radar (SAR) imagery. First, an improved fast road detector is used to obtain road response and direction, as well as to reduce false alarm rates resulting from bright line objects. Particle filtering is then applied in selecting road seed points, and particle weight is designed on the basis of the road characteristics derived from SAR images. Finally, a snake model is used to connect the seed points to form a road. Results show that the proposed method is effective, with enhanced completeness, correctness, and quality even under the influence of high-backscattering context objects near roads.