Crack automatic detection method based on improved lightweight CNN and transfer learning

Abstract

The crack automatic detection method based on the improved lightweight CNN and transfer learning comprises the steps of performing semantic segmentation processing on a collected crack image, and removing image background noise interference; constructing a model, embedding a CBAM module in the model, and training the model embedded with the CBAM module to obtain a trained model; inputting the crack image after semantic segmentation processing into the trained model for identification, and outputting an identification result; according to the method, cracks can be quickly separated from a complex picture background, the influence of image background noise is effectively reduced, the model generalization ability is improved by using a transfer learning fine tuning technology, damage functions are integrated on the premise of meeting lightweight, the recognition efficiency and accuracy of the model are improved, and the application prospect is wide. The capability of extracting complex crack image features by the network is improved; and integration of mobile terminals can be realized, and the method has practical engineering application value for realizing automatic detection and identification of cracks.

Description

technical field [0001] The invention relates to the technical field of crack detection, in particular to an automatic crack detection method based on improved lightweight CNN and transfer learning. Background technique [0002] With the rapid development of the economy, the construction speed of various buildings is getting faster and faster, such as: buildings, bridges, dams and various industrial buildings. At the same time, these buildings will also be damaged during long-term use. Therefore, buildings need to be inspected and repaired on a regular basis to prevent safety accidents. At present, the most common method is the manual monitoring method based on vision, which uses visual inspection, manual drawing, etc. to identify cracks in the building and record them. However, manual inspection has low timeliness and low cost performance, and requires a lot of manpower and material resources. It is difficult to find hidden safety hazards in the building in time, and the ins...

AI Technical Summary

Problems solved by technology

[0004] The embodiment of this application provides an automatic crack detection method based on improved lightweight CNN and transfer learning, aiming to solve the problem of low accuracy of the existing crack recognition technology

Images