Crack identification method of highway tunnel based on image processing

Abstract

In this paper, the images of tunnel surface are obtained by tunnel lining rapid inspection system, and tunnel crack forest dataset (TCFD) is established. The disaster characteristics of tunnel cracks are analyzed and summarized. Solutions of tunnel crack segmentation (TCS) method are developed for the detection and recognition of cracks on tunnel lining. According to the image features of the tunnel lining and the optical principal of detection equipment, effective image pre-processing steps are carried out before crack extraction. The tunnel image of TCFD is divided into appropriate number of blocks to magnify the local features of tunnel cracks. Local threshold segmentation method is used to traverse the blocks successively, and the first target block with crack is obtained. The seed in the target block were obtained by adaptive localization method and mapped to the whole image. Region growing is performed through crack seed until complete tunnel crack is extracted. The results show that the precision, recall rate and F-measure of tunnel cracks under the TCS method can reach 92.58%, 93.07% and 92.82% without strong interference. According to the binary images processed by TCS method, the projection images of different types of tunnel cracks and their respective laws are obtained. Furthermore, the TCS method is implemented and deployed as a GUI software application.

Keywords

• Tunnel engineering
• Crack identification
• Image binarization
• Tunnel crack
• Region growing
• Contrast limited adaptive histogram equalization