Slope crack identification method, system and device and storage medium

Abstract

The invention discloses a slope crack identification method, system and device and a storage medium. The method comprises the following steps: acquiring a hyperspectral remote sensing image, a near-infrared remote sensing image and a visible light image of a target area; constructing a crack classification and recognition network model, and training the crack classification and recognition network model by taking the hyperspectral remote sensing image, the near-infrared remote sensing image and the visible light image as a training set until the optimal weight of the crack classification and recognition network model is obtained; and inputting a to-be-identified image into the crack classification and identification network model to obtain an identification result of the crack in the to-be-identified image. The hyperspectral image and the near-infrared image have richer spectral information in a full wave band, and can reflect finer physical characteristics of the crack. According to the method, the crack classification and recognition network model is trained through the hyperspectral remote sensing image, the near-infrared remote sensing image and the visible light image at the same time, so that the crack classification and recognition network model can extract richer features, and the classification and recognition precision of the model is improved.

Description

technical field [0001] The invention relates to the technical field of landslide protection, in particular to a slope crack identification method, system, equipment and storage medium. Background technique [0002] Landslides are specific and complex forms of slope movement caused by the reduction of the internal resistance of soil rocks and plants (often manifested as sliding, loosening, collapse and loss) under the influence of gravity, and are the most frequent geological disasters in nature. In recent years, due to the frequent occurrence of extreme weather events caused by the expansion of urban agglomerations and climate change, the loss / movement of surface mass is on the rise, and landslide disasters occur frequently. Therefore, how to effectively monitor landslide disasters is very important. [0003] Cracks are the precursory features of landslides, so accurate monitoring of slope cracks plays an important role in preventing landslide disasters. The traditional sol...

AI Technical Summary

Problems solved by technology

The traditional solution is to conduct manual surveys, but this solution is inefficient and has certain risks

The existing schemes use neural networks and images to identify slope cracks. Compared with manual surveys, the efficiency can be improved. However, the input images of the existing schemes are relatively single, usually visible light images collected by CCD cameras, and the features are not obvious. The classification and recognition accuracy of the model for cracks is not high

Images