Tunnel constructor risk early warning method

Abstract

The invention discloses a tunnel constructor risk early warning method, which comprises the following steps: constructing an early warning model according to reference image data marked with feature data and corresponding types, obtaining target image data, determining the type corresponding to each feature data in the target image data according to the early warning model, judging whether the number of the types is two or not, and if yes, sending an early warning signal, wherein the types comprise a first type for representing surrounding rock cracks and a second type for representing constructors. By applying the method, the early warning model can simultaneously determine whether the surrounding rock crack and the constructor exist in the target image data, so that the problem of low recognition accuracy of the surrounding rock crack in the target image data caused by manual recognition is avoided, automatic recognition of the surrounding rock crack is realized, and the accuracy and the efficiency of early warning of the constructor are improved.

Description

technical field [0001] The present application relates to the technical field of tunnel detection, in particular to a risk warning method for tunnel construction personnel. Background technique [0002] Landslide is the main factor leading to the downtime of tunnel boring machine (TBM) construction, which often brings serious personal and property losses, greatly increases construction costs and delays the construction period. The root cause of the tunnel collapse is that the integrity of the surrounding rock is insufficient. During the excavation process, the cracks in the surrounding rock make it lose its stability, thus causing the collapse disaster. [0003] At present, the risk warning method for tunnel construction personnel is as follows: establish an initial background model and dynamically update the background model in real time, determine the approximate location of the construction personnel (such as construction personnel) through the establishment of the model,...

AI Technical Summary

Problems solved by technology

[0003]At present, the risk warning method for tunnel construction personnel is as follows: establish an initial background model and update the background model dynamically in real time, and initially determine the approximate position, construct a local structure similarity measurement function and a local grayscale statistical measurement function, obtain the target image, use the local structural similarity measurement function and local grayscale statistical measurement function to determine the discrimination between the foreground object and the background information in the target image, and segment Out of the construction personnel area, after confirming the construction personnel in the target picture, manually identify and judge whether there are surrounding rock cracks in the tunnel near the construction personnel. Since the tunnel is dark and the size of the surrounding rock cracks is different, the manual early warning method reduces the Accuracy and efficiency of early warning

Images