A Gibbs Point Process for Road Extraction from Remotely Sensed Images

作者：Radu Stoica, Xavier Descombes, Josiane Zerubia

摘要

In this paper we propose a new method for the extraction of roads from remotely sensed images. Under the assumption that roads form a thin network in the image, we approximate such a network by connected line segments.

论文关键词：Gibbs point processes, Candy model, hypothesis tests, reversible jump MCMC dynamics, aerial and satellite images, road extraction

论文评审过程：

论文官网地址：https://doi.org/10.1023/B:VISI.0000013086.45688.5d