A method, device and system for detecting structural apparent cracks

Abstract

The application discloses a method, device and system for detecting structural apparent cracks. Wherein, the method includes training a crack detection model by using a crack data set with image labels; each sample image of the crack data set is a cropped image block, and the cracks of the image block are marked at the pixel level. Segment the high-resolution image of the appearance of the structure to be inspected collected by a movable image acquisition device carrying a range finder into multiple image blocks; input each image block into the crack detection model to identify whether each image block includes cracks And extract the crack feature information to obtain the pixel-level segmentation map of the high-resolution image; automatically stitch each pixel-level segmentation map to obtain the crack segmentation map of the structure to be detected. According to the actual physical size of the crack determined by the crack segmentation map and the automatically read crack specification width limit, the danger degree of the crack to the structure to be detected is automatically evaluated. This application can accurately and efficiently extract fracture feature information from high-resolution images with complex backgrounds.

Description

technical field [0001] The present application relates to the technical field of construction engineering, in particular to a method, device and system for detecting structural apparent cracks. Background technique [0002] It is understandable that bridges, roads, tunnels, dams, houses and other buildings may gradually deform or even have building cracks when they are subjected to earthquake action or have a long service life or uneven settlement. The existence of cracks may cause the entire building structure to Instability or damage and collapse will affect the safe use of the entire building structure. Although cracks are very common in concrete structures, when the size of the crack exceeds a certain limit, it will seriously affect the normal use and normal bearing of the building. In the process of safety assessment and crack repair of building structures, it is necessary to accurately evaluate and measure the cracks in the building structure. [0003] Over the past ...

AI Technical Summary

Problems solved by technology

[0004] However, the background of the structural image taken in the real environment is extremely complex, and the image contains a variety of interference information, which is not conducive to the extraction of crack information

And the images taken are generally high-resolution images. Even if the mobile terminal is equipped with a high-performance graphics processor (that is, GPU), directly testing such a high-resolution image will cause insufficient memory.

Images