Development of an Automatic Crack Inspection System for Concrete Tunnel Lining Based on Computer Vision Technologies

This paper presents an automatic crack inspection system for concrete tunnel lining based on image processing technique and computer vision. The system includes a video image acquisition device, an image stitching software, and a crack detection software. Firstly, the video image acquisition device uses six video cameras and three illuminators mounted on a steel framework which is capable of sliding from side to top of the inspecting vehicle to shoot the full surface of the tunnel lining. Secondly, the image stitching software based on image matching technique was developed to create layout panorama from the tunnel lining surface images, making it easier to visualize a large and detailed section of the tunnel lining. Finally, we propose a semi-automatic crack detection software relied on a combination of image processing technique and interactive genetic algorithm (iGA) to crack detection for concrete surface images of the tunnel lining. Experimental results demonstrate the effectiveness of the proposed method.