Road damage detection from high-resolution RS image

This paper presents a road damage extraction method based on object-oriented change detection method using road vector data overlaid on post-earthquake image. It is complex to identify all kinds of road damages in earthquakes. For the purpose of traffic capacity analysis, focusing on roads in good condition will simplify the problem, no matter how the roads are destroyed. The whole road line is provided by road network vector of appropriate scale. Subtract the good road and the damaged parts are clearly shown. This method can realize quantitative analysis on road seismic damage when lack of pre-earthquake images. In this paper it is applied to road damage extraction in Wenchuan earthquake, using high resolution remote sensing images shot just several days after the event.

1. INTRODUCTION

An MS 8.0 earthquake occurred on May 12th, 2008 in Wenchuan, Sichuan province in China. Various geological disasters such as landslide, mudslide and collapse caused severe damage to the local traffic [1]. State road 213, 317, and provincial highway 302 were cut off, not to mention a large number of damaged low-grade highways. Bad traffic made many towns as difficult to reach as islands, bringing a great impact to our relief work after the earthquake.