CN-121767893-B - Mine safety monitoring method and system for open-air mining area

CN121767893BCN 121767893 BCN121767893 BCN 121767893BCN-121767893-B

Abstract

The invention relates to the technical field of image processing, in particular to a mine safety monitoring method and system for an open-air mining area. According to the method, firstly, different sliding windows are constructed to slide on the wedge-shaped slope image, the periodic characteristics of the slope surface are extracted by using similarity evaluation indexes, the similarity of each area of the image is comprehensively evaluated, secondly, the period of the image in the vertical and horizontal directions is determined based on the similarity evaluation indexes, the block grid parameters are optimized, the algorithm processing scale is matched with the period characteristics of the image, so that the pertinence and detail performance of image enhancement are improved, and finally, the enhanced image is used for calculating crack risk evaluation indexes, so that the accuracy and reliability of crack risk evaluation are remarkably improved, and the accuracy and the robustness of monitoring of landslide disasters are enhanced.

Inventors

Bei Weishan
ZHANG YINGLEI
ZHAO XUEBIN
ZHANG ZHIBO
GAO XUEBAO
WANG YUANBO
YANG CHAO
ZHANG ZHIXIN

Assignees

开信(南京)控股集团有限公司

Dates

Publication Date: 20260512
Application Date: 20260304

Claims (9)

1. A mine safety monitoring method for an open-air mining area, the method comprising: Acquiring wedge slope images of a mine area, respectively constructing sliding windows in the vertical and horizontal directions, and obtaining similarity evaluation indexes under different sliding in the vertical and horizontal directions according to pixel gray level differences and structural similarity between images in the sliding windows before and after sliding in the vertical and horizontal directions; Performing curve fitting on the similarity evaluation indexes under the sliding in different directions in the vertical and horizontal directions and the sliding amounts under the sliding in different directions to obtain extreme points on a fitting curve; Optimizing the size parameters of the blocking grids of the CLAHE algorithm in the vertical and horizontal directions according to the period of the wedge slope image in the vertical and horizontal directions, and carrying out image enhancement to obtain an enhanced wedge slope image; Acquiring a crack risk evaluation index of a crack region in the enhanced wedge slope image, and monitoring landslide disasters according to the crack risk evaluation index; The optimizing the size parameters of the partitioned grid of the CLAHE algorithm in the vertical and horizontal directions comprises the following steps: Substituting the period in the corresponding direction into a block grid size parameter design formula for any direction to obtain a block grid size parameter in each direction; The design formula of the size parameters of the blocking grid is as follows: wherein: Dividing the grid size parameters; () Taking a maximum function; () Taking a minimum function; ROU ()'s taking the smallest integer power function of 2 greater than the input value; Y, the size of the wedge slope image in any direction; X, presetting a second constant; The period of the wedge slope image in any direction.
2. The mine safety monitoring method of an open-air mining area according to claim 1, wherein the method for acquiring the pixel gray scale difference between the images in the sliding window before and after the sliding in the vertical and horizontal directions comprises: Sliding the sliding window in any direction on the wedge slope image along the corresponding direction, comparing absolute values of differences between gray values of pixels at each position in the image in all sliding windows after sliding and pixels at corresponding positions in the initial sliding window, determining gray difference absolute values, taking an average value of the gray difference absolute values in each sliding window as the gray difference of the pixels under sliding, and obtaining the gray difference of the pixels under sliding in the corresponding direction.
3. The mine safety monitoring method of an open-air mining area according to claim 1, wherein the method for acquiring the similarity evaluation index under different sliding in the vertical and horizontal directions comprises: Taking the sum of pixel gray differences under different sliding in any direction and a preset first constant as denominator, taking the structural similarity as a numerator, and taking the obtained ratio as a similarity evaluation index under different sliding in the corresponding direction.
4. The mine safety monitoring method of an open air mining area according to claim 1, wherein the curve fitting method comprises: And taking the sliding quantity in any direction as an abscissa, taking a similarity evaluation index corresponding to the sliding quantity as an ordinate, and performing curve fitting by using a least square method to obtain a fitting curve in the corresponding direction, wherein the sliding quantity is an actual displacement step value between the sliding window sliding position and the initial position.
5. The method for mine safety monitoring of an open air mining area according to claim 4, wherein the method for obtaining extreme points on the fitted curve comprises: The curvature of each sliding quantity at the corresponding point on the fitting curve is obtained, all points are classified twice according to the curvature, the class of points with the maximum average curvature are reserved, and the reserved points are classified twice according to the similarity evaluation index corresponding to the points, so that the extreme points on the fitting curve are obtained.
6. The mine safety monitoring method of an open air mining area according to claim 5, wherein the periodic acquisition method comprises: and calculating the average value of all the differences in the difference set as the period in the corresponding direction.
7. The mine safety monitoring method of an open air mining area according to claim 1, wherein the crack risk evaluation indexes comprise three kinds of evaluation indexes, namely a crack width growth rate, a trunk crack length and a branch crack number.
8. The mine safety monitoring method of an open air mining area according to claim 7, wherein monitoring landslide hazard based on crack risk assessment indicators comprises: If any type of indexes in the crack risk evaluation indexes are larger than a preset safety threshold value under the corresponding dimension, judging that the crack area is at a first-level high risk; if any two types of indexes in the crack risk evaluation indexes are larger than a preset safety threshold value under the corresponding dimension, judging that the crack area is at a second-level risk; if three types of indexes in the crack risk evaluation indexes are all larger than a preset safety threshold value under the corresponding dimension, judging that the crack area is three-level high risk.
9. A mine safety monitoring system for an open air mining area comprising a memory, a processor and a computer program stored in the memory and operable on the processor, wherein the processor, when executing the computer program, carries out the steps of a mine safety monitoring method for an open air mining area according to any one of claims 1 to 8.

Description

Mine safety monitoring method and system for open-air mining area Technical Field The invention relates to the technical field of image processing, in particular to a mine safety monitoring method and system for an open-air mining area. Background The occurrence of a slope landslide hazard is accompanied by the formation of a crack region on the slope, with a wedge-shaped slope being one of the most common types of slopes in open-air production areas. The formation mechanism of the wedge-shaped slope is that two or more rock stratum cutting surfaces are mutually cut, cracks are formed in the mutually cut areas, and the cracks are continuously expanded along with the movement of the cutting surfaces, so that the occurrence of landslide disasters of the wedge-shaped slope is finally caused, and the monitoring of the crack areas is the monitoring of the landslide disasters. In the obtained wedge slope image, factors such as too dark or too bright local areas, difficulty in detail identification and the like of the image are considered, before slope landslide monitoring is carried out in the prior art, the wedge slope image can be enhanced by utilizing a CLAHE algorithm, and subsequent crack risk evaluation is carried out on the basis of enhancing the wedge slope image. However, in a real mine area, the content of the wedge-shaped side slope surface is complex and the details are rich, and various real factors such as rock stratum textures, tiny cracks, turf and the like exist, so that the best image enhancement effect on the wedge-shaped side slope image cannot be obtained only by adopting a CLAHE algorithm of experience parameters, and the accuracy and the stability of analysis on the crack area are further affected. Disclosure of Invention In order to solve the technical problems that the best image enhancement effect cannot be obtained by using the CLAHE algorithm of experience parameters in the prior art, and further the accurate monitoring of a crack area is affected, the invention aims to provide a mine safety monitoring method and system of an open-air mining area, and the adopted technical scheme is as follows: The invention provides a mine safety monitoring method for an open-air mining area, which comprises the following steps: Acquiring wedge slope images of a mine area, respectively constructing sliding windows in the vertical and horizontal directions, and obtaining similarity evaluation indexes under different sliding in the vertical and horizontal directions according to pixel gray level differences and structural similarity between images in the sliding windows before and after sliding in the vertical and horizontal directions; Performing curve fitting on the similarity evaluation indexes under the sliding in different directions in the vertical and horizontal directions and the sliding amounts under the sliding in different directions to obtain extreme points on a fitting curve; Optimizing the size parameters of the blocking grids of the CLAHE algorithm in the vertical and horizontal directions according to the period of the wedge slope image in the vertical and horizontal directions, and carrying out image enhancement to obtain an enhanced wedge slope image; Acquiring a crack risk evaluation index of a crack region in the enhanced wedge slope image, and monitoring landslide disasters according to the crack risk evaluation index. Further, the method for acquiring the pixel gray level difference between the images in the sliding window before and after the sliding in the vertical and horizontal directions comprises the following steps: Sliding the sliding window in any direction on the wedge slope image along the corresponding direction, comparing absolute values of differences between gray values of pixels at each position in the image in all sliding windows after sliding and pixels at corresponding positions in the initial sliding window, determining gray difference absolute values, taking an average value of the gray difference absolute values in each sliding window as the gray difference of the pixels under sliding, and obtaining the gray difference of the pixels under sliding in the corresponding direction. Further, the method for acquiring the similarity evaluation index under different sliding in the vertical and horizontal directions comprises the following steps: Taking the sum of pixel gray differences under different sliding in any direction and a preset first constant as denominator, taking the structural similarity as a numerator, and taking the obtained ratio as a similarity evaluation index under different sliding in the corresponding direction. Further, the curve fitting method includes: And taking the sliding quantity in any direction as an abscissa, taking a similarity evaluation index corresponding to the sliding quantity as an ordinate, and performing curve fitting by using a least square method to obtain a fitting curve in the corresponding direction, wherein the sliding qu