Bridge pavement crack classification and recognition method based on width learning neural network

Abstract

The invention relates to a bridge pavement crack classification and recognition method based on a width learning neural network, and belongs to the field of image processing and computer vision. The accurate identification and classification of bridge crack positions and crack attributes are realized by utilizing the width learning neural network, the method mainly solves the problem that the existing bridge crack detection method based on the width learning neural network cannot directly obtain the width and length information of a crack, and combines a PC end and a mobile phone end to carryout the classification and identification on the bridge crack, so that the more accurate, more convenient and higher-reliability method is brought to the classification and recognition of the bridge cracks, and the bridge crack detection efficiency and the accuracy and stability of a detection result are improved.

Description

technical field [0001] The invention belongs to the fields of image processing and computer vision, and relates to a bridge pavement crack classification and recognition method based on a width learning neural network. Background technique [0002] As the hub of traffic systems such as roads, highways, and railways, bridges need to be regularly inspected and evaluated for their health. The main forms of damage caused by concrete structures are cracks, deformation, corrosion and so on. Moreover, bridges are usually made of concrete. According to the survey, more than 90% of the damage of concrete bridges is caused by bridge cracks. Cracks on the bridge surface not only mean that there is structural damage inside the bridge, but also can effectively reflect the structural damage. In the current working state, and the water vapor generated from the outside is easier to enter the interior of the bridge, thereby accelerating the corrosion of internal structures such as steel bar...

AI Technical Summary

Problems solved by technology

[0004] (1) Low safety: it belongs to high-altitude operation, and the inspectors need to go down to the bridge for inspection, so the safety is not guaranteed;

[0005] (2) Low detection efficiency: The detection efficiency will be affected by the complexity of the bridge bottom environment and the experience and physical strength of the quality inspection workers, which is time-consuming;

[0006] (3) Low detection accuracy: it is mainly observed and detected by human eyes, which is easily affected by human subjective factors;

[0007] (4) High labor intensity: there are many bridges, and the inspection workload is heavy, which is completed manually, and the intensity is relatively high;

[0008] (5) High cost: Professionals are required to operate, and a lot of manpower and material resources are used for detection, which is expensive;

[0009] (6) Low degree of informatization: It is impossible to accurately establish historical data of bridge cracks, it is not convenient for the management and maintenance of dangerous bridges, and it is also unable to provide decision-making support information for government management departments

As a seemingly simple target, cracks are variable and complex due to the background and structural characteristics. The existing bridge crack detection methods still have many defects, which are far from meeting their needs.

[0012] All in all, there are various features used to detect bridge cracks, but the simple and efficient detection of bridge cracks is still a difficult point. How to quickly, efficiently and accurately extract the structural features of bridge cracks is a challenging problem.

Images