Glass curtain wall crack detection method

Abstract

The invention relates to a glass curtain wall crack detection method. The method comprises the following steps: step (1), acquiring a glass curtain wall image; (2) converting the glass curtain wall image into a gray level image; (3) calculating a first feature of the grayscale image based on an improved ULBP descriptor; step (4), carrying out dimension reduction on the first feature of the grayscale image to obtain a macro feature; and step (5), inputting the macro features into a classifier, and detecting whether cracks exist in the glass curtain wall image through the classifier. According to the invention, the crack of the glass curtain wall can be effectively detected, and the detection precision is high.

Description

technical field [0001] The invention relates to the technical field of glass crack detection, in particular to a glass curtain wall crack detection method. Background technique [0002] The detection of structural damage is critical to the safety and maintenance of buildings. Cracks in glass facades of high-rise buildings are one of the important factors affecting the safety of buildings, residents and pedestrians. Therefore, its early detection can save a lot of time and maintenance costs and eliminate potential secondary hazards. [0003] High-rise buildings such as skyscrapers are common in modern cities, so the automatic detection of cracks in glass curtain walls of skyscrapers is of great significance. The glass curtain wall of this type of building is mainly made of strengthened glass and other decorative materials. The glass curtain wall needs to be monitored and maintained on a regular and long-term basis to ensure the safety of the building and to ensure the safe...

AI Technical Summary

Problems solved by technology

Similarly, the specific identification process may be affected by different image sizes, lighting conditions, operator experience, etc., resulting in misjudgment of crack detection

Images