Research on the Real-Time Detection Method for Image Processing - Based Civil Structure Crack

Abstract

Early discovery of civil structure crack facilitates timely treatment, such as repair, reinforcement and grouting. The image processing - based rapid and accurate detection method for civil structure crack brings important research value. In view of complicated construction site of civil project and complex and diversified civil structure, existing method cannot realize crack detection and geometric measurement accurately. Therefore, this article researches the real-time image processing-based detection method for civil structure crack. Bilateral filtering algorithm was used to finish smoothing processing. Crack edge of civil structure was extracted with interpolation calculation - based subpixel edge detection algorithm, to obtain more accurate crack edge position. Civil structure crack was detected based on end-to-end object detection network YOLO. The effectiveness of the model built was verified according to experimental results.