Long-distance precision inspection method for bridge cracks with image processing

• We provide a long-distance image acquisition device for detecting cracks.
• We provide an integrated image processing method for extracting cracks.
• An improved image segmentation algorithm based on C–V model is provided.
• We develop dedicated software for the crack detection system.
• We realize the image mosaic for producing a crack panorama.

The detection of cracks is the most important step during the inspection of bridge substructures. However, traditional crack detection methods are subjective and expensive. Therefore, crack detection techniques based on image processing have been proposed. In this paper, a long-distance image acquisition device and an integrated image processing method are proposed for precisely extracting cracks. The proposed method consists of three parts. Firstly, general steps for crack extraction are realized which include image clipping, enhancement, smoothing, segmentation, crack marking and rotation. Secondly, the electronic distance measurement algorithm is approved to calculate the crack width in millimeters. Finally, an improved image segmentation algorithm based on C–V model is provided for crack extraction. We evaluate the proposed method on a collection of 1000 bridge images which have been gathered under different conditions. Experimental results show that the modified algorithm could effectively improve the detection precision rate and reduce the running time.