Choix d'un espace de repr\'esentation image adapt\'e \`a la d\'etection de r\'eseaux routiers

TL;DR

This paper presents a novel method combining image decomposition, Gestalt-based alignment detection, and active contours to improve road network detection in aerial and satellite images.

Contribution

It introduces a new approach that integrates multiple techniques for more accurate road network detection in complex imagery.

Findings

Effective detection of road networks demonstrated on aerial and satellite images.

Improved accuracy over traditional methods in complex environments.

Combines decomposition, Gestalt theory, and active contours for enhanced results.

Abstract

These last years, algorithms allowing to decompose an image into its structures and textures components have emerged. In this paper, we present an application of this type of decomposition to the problem road network detection in aerial or satelite imagery. The algorithmic procedure involves the image decomposition (using a unique property), an alignment detection step based on the Gestalt theory, and a refinement step using statistical active contours.