Image Processing for Detection of Tunnel Wall Deformation with Wide Dynamic Range Continuous Scan Image

摘要

The purpose of this system is to obtain proper and efficient images to monitor deformations, and diagnose tunnel conditions. We are developing an automatic image processing algorithm, to extract deformations like cracks, as the first step for this purpose. It can automatically extract cracks on standard tunnel walls as a result. We applied various techniques to this algorithm. One is to distinguish cracks from the obtained images of the tunnel wall. Actually there are several noise elements in those images. We must separate actual cracks from noises. The other is to measure various dimensions such as the length or width of cracks. These data can rank the deformations, and get a prognosis of their growth accordingly.