Advanced inspection system of tunnel wall deformation using image processing

We have developed an efficient tunnel scanner with line sensor cameras capable of taking high-precision panoramic annular images of the surface of a tunnel lining at low cost. In this paper, we first describe the improvement made to the focus adjustment method, and then propose an image processing technique to remove image fluctuation. We also describe the sub-pixel-style image processing algorithm developed to extract minute cracks from a standard wall image and measure their characteristics such as width, length, direction etc. to a high level of accuracy. As a result, the overall costs have been kept down and the practicability of this detection system has made significant progress.