CN116739183A - Mine safety risk early warning prediction system - Google Patents
Mine safety risk early warning prediction system Download PDFInfo
- Publication number
- CN116739183A CN116739183A CN202310962424.5A CN202310962424A CN116739183A CN 116739183 A CN116739183 A CN 116739183A CN 202310962424 A CN202310962424 A CN 202310962424A CN 116739183 A CN116739183 A CN 116739183A
- Authority
- CN
- China
- Prior art keywords
- image
- sub
- module
- area
- images
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012937 correction Methods 0.000 claims abstract description 80
- 230000004927 fusion Effects 0.000 claims abstract description 70
- 239000003623 enhancer Substances 0.000 claims description 32
- 238000006243 chemical reaction Methods 0.000 claims description 19
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000000354 decomposition reaction Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 13
- 238000000034 method Methods 0.000 claims description 12
- 230000015572 biosynthetic process Effects 0.000 claims description 9
- 238000003786 synthesis reaction Methods 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 230000007274 generation of a signal involved in cell-cell signaling Effects 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 230000002194 synthesizing effect Effects 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 description 11
- 238000005516 engineering process Methods 0.000 description 11
- 238000004458 analytical method Methods 0.000 description 6
- 239000011159 matrix material Substances 0.000 description 6
- 229910052500 inorganic mineral Inorganic materials 0.000 description 5
- 239000011707 mineral Substances 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 4
- 230000000712 assembly Effects 0.000 description 3
- 238000000429 assembly Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000003707 image sharpening Methods 0.000 description 1
- 238000003706 image smoothing Methods 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 238000011418 maintenance treatment Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000035484 reaction time Effects 0.000 description 1
- 238000011282 treatment Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21F—SAFETY DEVICES, TRANSPORT, FILLING-UP, RESCUE, VENTILATION, OR DRAINING IN OR OF MINES OR TUNNELS
- E21F17/00—Methods or devices for use in mines or tunnels, not covered elsewhere
- E21F17/18—Special adaptations of signalling or alarm devices
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/16—Image acquisition using multiple overlapping images; Image stitching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/17—Terrestrial scenes taken from planes or by drones
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
- G06V20/653—Three-dimensional objects by matching three-dimensional models, e.g. conformal mapping of Riemann surfaces
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Multimedia (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Mining & Mineral Resources (AREA)
- Tourism & Hospitality (AREA)
- Software Systems (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- Marine Sciences & Fisheries (AREA)
- Primary Health Care (AREA)
- Animal Husbandry (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Agronomy & Crop Science (AREA)
- Educational Administration (AREA)
- Remote Sensing (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Geology (AREA)
- Image Processing (AREA)
Abstract
The invention provides a mine safety risk early warning prediction system, which belongs to the technical field of safety early warning, and comprises the following components: the image modeling module is used for carrying out image modeling on the mine mountain to obtain a preliminary mountain structure model; the range determining module is used for determining a region correction range; the laser modeling module is used for modeling the area correction range to obtain an area correction range model; the azimuth determining module is used for determining the fusion azimuth of the area correction range model in the preliminary mountain structure model; the area determining module is used for determining a deformation area of the mine based on the complete mountain structure model; the danger prediction module is used for predicting a mine danger area based on the current curvature and the initial curvature corresponding to the deformation area in the preset mountain structure model; the danger early warning module is used for sending an early warning signal based on the position of the mine danger area; the invention is used for realizing more accurate early warning of the area possibly suffering from the surface depression on the premise of being separated from hardware in contact with the ground.
Description
Technical Field
The invention relates to the technical field of safety early warning, in particular to a mine safety risk early warning prediction system.
Background
At present, along with the development of industrialization and informatization, the demand of mineral resources is increased, so that the exploitation of the mineral resources is increased continuously, the productivity of many mine enterprises is increased continuously, as most of the mine enterprises have longer service lives, shallow mineral resources are exploited completely, most of the shallow mineral resources are deep mineral resources, underground spaces with different sizes are formed after deep primary ore bodies and associated waste stones are exploited, under the influence of factors such as gravity action and unbalanced ground stress, ground cracks are firstly generated in goaf areas, the ground collapse of the goafs is gradually developed, and verified property safety accidents and even personal safety accidents are caused. Therefore, mine safety risk early warning is of great importance in the field of mining.
However, the existing mine safety risk early warning prediction system only carries out analysis early warning through various hardware contacted with the ground, because the mine environment is bad, the hardware contacted with the ground for a long time is easy to rust and damage, and early warning is difficult to accurately carry out, for example, the publication number is CN112885038A, the publication date is 2021, the Chinese invention patent with the patent names of a ground collapse early warning device and a ground collapse early warning system, and the method comprises the following steps: the triggering unit comprises a plurality of triggering components which are sequentially butted up and down, and different triggering components correspond to different strata; the early warning unit is arranged at the top of the triggering unit and comprises a plurality of alarm assemblies which are in one-to-one correspondence with the triggering assemblies, and each alarm assembly is connected with the corresponding triggering assembly through different connecting assemblies; when a certain triggering component falls off from the queue, the triggering component is pulled by the corresponding connecting component under the action of gravity to trigger the corresponding alarm component so as to judge that the stratum corresponding to the triggering component has a cavity. The invention can solve the problems that the ground lower part is not easy to be perceived when the collapse initially occurs, and serious safety accidents are easy to be caused after the collapse is gradually expanded. However, the patent cannot analyze the surface of the collapse place by means of a few devices, and analysis and early warning are only carried out by a plurality of hardware contacted with the ground, and because the mine environment is severe and the hardware contacted with the ground for a long time is easy to rust and damage, the early warning is difficult to accurately carry out.
Therefore, the invention provides a mine safety risk early warning and predicting system which is used for realizing more accurate early warning of an area where the danger of surface subsidence possibly occurs on the premise of separating hardware in contact with the ground so as to ensure the safety production of a mine.
Disclosure of Invention
The invention provides a mine safety risk early warning prediction system which is used for carrying out preliminary modeling on the surface of a mine mountain through an external image pair of the mine mountain to obtain a preliminary mountain structure model, a region needing further re-modeling existing in the preliminary mountain structure model can be determined through a range determination module, the region needing re-modeling is modeled through a laser modeling module to obtain a region correction range model, a region which is difficult to reflect a real structure is modeled in the model appearing in the image modeling, the accuracy and the data integrity of the built complete mountain structure model are further ensured, a deformation region appearing in the mine can be determined through the combination of an azimuth determination module and the region determination module, the danger prediction module is used for accurately predicting a mine dangerous region through analysis of the deformation region, and the region which is possibly appearing in the surface depression danger can be predicted accurately only by means of mine mountain surface data acquired by an unmanned plane, namely, on the premise of being separated from hardware contacted with the ground, more accurate early warning on the region which is likely to appear in the surface depression danger is realized, so that the safety production of the mine is ensured.
The invention provides a mine safety risk early warning prediction system, which comprises:
the image modeling module is used for carrying out frequency decomposition and fusion on the mine mountain images subjected to plane conversion to obtain fusion images, and constructing a primary mountain structure model based on the fusion images;
the range determining module is used for carrying out unit area decomposition and boundary enhancement on the fusion image to obtain a boundary enhancer image, and determining a region correction range based on a correction value of the boundary enhancer image;
the laser modeling module is used for re-modeling the area correction range to obtain an area correction range model;
the azimuth determining module is used for processing based on the preliminary mountain model and the area correction range model and determining the fusion azimuth of the area correction range model in the preliminary mountain structure model;
the area determining module is used for obtaining a complete mountain structure model based on the fusion azimuth, and determining a deformation area of the mine through the complete mountain structure model and a preset mountain structure model;
the danger prediction module is used for carrying out concave curvature calculation on the deformation area of the mine to obtain the current curvature of the deformation area, and predicting the mine danger area based on the current curvature and the initial curvature corresponding to the deformation area in a preset mountain structure model;
And the danger early warning module is used for sending an early warning signal based on the position of the mine danger area.
Preferably, a mine safety risk early warning prediction system, an image modeling module, includes:
the image acquisition sub-module is used for acquiring images of the area where the mine is located based on shooting equipment arranged on the unmanned aerial vehicle, so as to obtain a plurality of mine mountain images;
the image conversion sub-module is used for inputting a plurality of mine mountain images into a preset plane conversion model to obtain corresponding spliced images;
and the graph fusion sub-module is used for carrying out frequency decomposition on all the spliced images, then fusing to obtain a fused image, and carrying out model building based on the fused image to obtain a primary mountain structure model.
Preferably, a mine safety risk early warning prediction system, the graph fuses submodule, includes:
the image conversion unit is used for carrying out Fourier transform on the spliced image to obtain a spectrogram, and determining the brightness value of each pixel point in the spectrogram as a frequency component representation value in the spliced image;
the region determining unit is used for determining the same frequency component representation value in different spliced images, and taking a region surrounded by pixel points corresponding to all the same frequency component representation values in each two spliced images as a spliced region between the two spliced images;
The image stitching unit is used for stitching all the images which can be stitched in pairs based on all the areas which can be stitched to obtain a fusion image;
the model building unit is used for extracting three-dimensional point clouds from the fusion image, and modeling is carried out based on the three-dimensional point cloud data to obtain a preliminary mountain structure model.
Preferably, a mine safety risk early warning prediction system, the synthesis unit includes:
an image generation subunit, configured to generate a first sub-image corresponding to the image that can be spliced under each frequency component based on the spectrogram;
an image area dividing subunit, configured to determine all first partial sub-images of the low-frequency component and all second partial sub-images of the high-frequency component in the mosaicable area in the two mosaicable images to be fused;
the low-frequency processing subunit is used for determining the average value of the gray values of all the pixel points at the same position in all the first partial sub-images, and giving the average value of the gray values to the pixel points at the corresponding positions in the blank image to obtain a low-frequency fusion image;
the high-frequency processing subunit is used for determining the maximum value of the gray values of all the pixel points at the same position in all the second partial sub-images, and giving the maximum value of the gray values to the pixel points at the corresponding positions in the blank image to obtain a high-frequency fusion image;
And the image splicing subunit is used for superposing and synthesizing the low-frequency fusion image and the high-frequency fusion image to obtain a new spliceable region, and splicing the two spliceable images to be fused based on the new spliceable region to obtain a fusion image.
Preferably, a mine safety risk early warning prediction system, a range determining module, includes:
the boundary optimization sub-module is used for dividing the fusion image constructing the preliminary mountain structure model into a plurality of second sub-images with unit areas, carrying out image boundary detection on all the second sub-images, determining boundary parts of all the second sub-images, and carrying out boundary enhancement on the boundary parts of all the second sub-images to obtain a boundary enhancement sub-image set;
a correction value calculation sub-module for determining a correction value for each boundary-enhancement sub-image in the set of boundary-enhancement sub-images based on the following formula:
；
in the method, in the process of the invention,a is the ordinate value of the lower boundary of the boundary enhancer image in the plane rectangular coordinate system, b is the ordinate value of the upper boundary of the boundary enhancer image in the plane rectangular coordinate system, c is the abscissa value of the left boundary of the boundary enhancer image in the plane rectangular coordinate system, d is the abscissa value of the right boundary of the boundary enhancer image in the plane rectangular coordinate system, & gt >Coordinates in the boundary enhancer image>Maximum value of pixel difference values between a pixel point at a position and each pixel point in an enhanced boundary in a corresponding boundary enhancer image,/v>Coordinates in the boundary enhancer image>Minimum value of pixel difference values between pixel point at and each pixel point in enhanced boundary in corresponding boundary enhancer image, +.>Is an independent variable derivative;
and the range judging sub-module is used for taking the boundary enhancement sub-images with the correction value larger than the rated correction value in the boundary enhancement sub-image set as the areas to be corrected and taking the area ranges corresponding to all the areas to be corrected in the primary mountain structure model as the area correction ranges.
Preferably, a mine safety risk early warning prediction system, the laser modeling module includes:
the laser sampling sub-module is used for determining a plurality of scanning points in the area correction range, and controlling the unmanned aerial vehicle to scan at the corresponding actual positions of the scanning points in the mine mountain to obtain three-dimensional point cloud data of the corresponding scanning points;
the coincidence ratio calculating submodule is used for calculating the coincidence ratio of the three-dimensional point cloud data of all adjacent scanning points;
the supplementary scanning sub-module is used for inserting a new scanning point between adjacent scanning points with the contact ratio smaller than the minimum contact ratio threshold value, and obtaining three-dimensional point cloud data of the new scanning point in a supplementary mode until the contact ratio between the three-dimensional point cloud data of all the adjacent scanning points which are determined up to the latest is not smaller than the minimum contact ratio threshold value, and obtaining first three-dimensional point cloud data;
The point cloud duplicate removal sub-module is used for randomly removing one group of three-dimensional point cloud data of adjacent scanning points with the coincidence degree exceeding a maximum coincidence degree threshold value in the first three-dimensional point cloud data to obtain second three-dimensional point cloud data;
the registration point sub-module is used for determining the same three-dimensional point cloud in the three-dimensional point cloud data of the adjacent scanning points in the second three-dimensional point cloud data as a registration point corresponding to the adjacent scanning points;
the point cloud synthesis sub-module is used for carrying out point cloud synthesis on the three-dimensional point cloud data corresponding to the adjacent scanning points based on the registration points to obtain the complete point cloud of the area correction range;
the model construction submodule is used for constructing a region correction range model based on the complete point cloud of the region correction range.
Preferably, a mine safety risk early warning prediction system, the position determining module includes:
the dimension unification submodule is used for unifying dimensions of the preliminary mountain structure model and the region correction range model;
and the position determination submodule is used for determining the fusion orientation of the area correction range model in the preliminary mountain structure model.
Preferably, a mine safety risk early warning prediction system, the area determining module includes:
the fusion sub-module fuses the region correction range model and the preliminary mountain structure model based on the fusion azimuth to obtain a complete mountain structure model;
And the deformation determination submodule is used for comparing the complete mountain structure model with a preset mountain structure model to determine a deformation area.
Preferably, a mine safety risk early warning prediction system, a risk prediction module, includes:
the initial curvature calculation sub-module is used for carrying out concave curvature calculation on the deformation area based on a preset mountain structure model to obtain the initial curvature of the deformation area;
the concave curvature sub-module is used for carrying out concave curvature calculation based on the structural change of the complete mountain structure model at the position of the deformation area to obtain the current curvature of the deformation area;
and the prediction sub-module is used for predicting the deformation area as a mine dangerous area when the difference value between the current curvature and the initial curvature is larger than a preset value.
Preferably, a mine safety risk early warning prediction system, a risk early warning module includes:
the signal generation sub-module is used for generating a corresponding early warning signal based on the position of the mine dangerous area;
and the signal sending sub-module is used for sending the early warning signal to the monitoring early warning background.
Compared with the prior art, the invention has the following beneficial effects: the method comprises the steps that a preliminary mountain structure model is obtained only through a mine mountain surface image pair, a region needing further re-modeling existing in the preliminary mountain structure model can be determined through a range determination module, the region needing re-modeling is modeled through a laser modeling module, a region correction range model is obtained, a region, which is difficult to reflect a real structure, of the model appearing in image modeling is modeled more accurately, the accuracy and the data integrity of the built complete mountain structure model are further guaranteed, a deformation region appearing in a mine can be determined by combining the azimuth determination module with the region determination module, a dangerous prediction module is used for accurately predicting a mine dangerous region through analysis of the deformation region, and the region with the occurrence of the surface depression danger can be predicted more accurately only by means of mine mountain surface data acquired by an unmanned plane, namely, on the premise of being separated from hardware in contact with the ground, the region with the occurrence of the surface depression danger is more accurately achieved, and safety production of the mine is guaranteed.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims.
The technical scheme of the invention is further described in detail through examples.
Detailed Description
The following description of the preferred embodiments of the present invention is provided for the purpose of illustration and explanation only and is not intended to limit the present invention.
Example 1: the invention provides a mine safety risk early warning prediction system, which comprises:
the image modeling module is used for carrying out frequency decomposition and fusion on the mine mountain images subjected to plane conversion to obtain fusion images, and constructing a primary mountain structure model based on the fusion images;
the range determining module is used for carrying out unit area decomposition and boundary enhancement on the fusion image to obtain a boundary enhancer image, and determining a region correction range based on a correction value of the boundary enhancer image;
the laser modeling module is used for re-modeling the area correction range to obtain an area correction range model;
The azimuth determining module is used for processing the preliminary mountain model and the area correction range model and determining the fusion azimuth of the area correction range model in the preliminary mountain structure model;
the area determining module is used for obtaining a complete mountain structure model based on the fusion azimuth, and determining a deformation area of the mine through the complete mountain structure model and a preset mountain structure model;
the danger prediction module is used for carrying out concave curvature calculation on the deformation area of the mine to obtain the current curvature of the deformation area, and predicting the mine danger area based on the current curvature and the initial curvature corresponding to the deformation area in a preset mountain structure model;
and the danger early warning module is used for sending an early warning signal based on the position of the mine danger area.
In this embodiment, the mine mountain image is an image of the mine mountain surface captured by the unmanned aerial vehicle.
In this embodiment, the mine mountain is a complete mountain structure including an internal passage structure and an external surface structure of the mine.
In this embodiment, the preliminary mountain structure model is a model obtained based on preliminary modeling of an image of the mine mountain surface, where the model may have a case where some partial area structures thereof are not displayed (due to a mask in the mine mountain image).
In this embodiment, the area correction range is an area where the model appearing in modeling based on an image of the surface of the mine mountain is difficult to reflect a real structure, for example, an area where trees are blocked.
In the embodiment, the modeling is performed again, namely, a laser signal is emitted to a target position in the deformation area through unmanned aerial vehicle laser scanning equipment in the area correction range, then the reflected laser signal is collected, the distance information of the target position in the deformation area is measured through information such as light speed, laser from emission to return, and the like, and then three-dimensional coordinate information of the target position in the deformation area is calculated by combining information such as an IMU, an odometer, a GNSS and the like, so that the modeling is realized.
In this embodiment, the region correction range model is a model of a region in the preliminary mountain structure model that is difficult to reflect a real structure.
In this embodiment, the processing of the preliminary mountain model and the area correction range model is: the preliminary mountain model and the region correction range model are unified in size (for example, both are processed to 750 pixels)422 pixels in size) to ensure that they can be directly stitched together.
In this embodiment, the fusion orientation is the fusion position of the preliminary mountain model and the region correction range model.
In the embodiment, the complete mountain structure model is a model formed by combining the preliminary mountain model and the area correction range model, and reflects the information of the surface of the complete mine mountain.
In the embodiment, the mountain structure model is preset by modeling the mine mountain surface through laser modeling equipment in advance.
In this embodiment, the deformation region is a region in which curvature of the mine mountain structure changes.
In this embodiment, the concave curvature is calculated by analyzing a preset mountain structure model portion corresponding to the position of the deformation region based on the second basic formula of the existing curved surface, so that the curvature at the position of any point (set as point a) of the deformation region is equal to the curvature of the tangent vector direction curve at the position of the point a, then the mathematical relationship between the curvature of the point a of the deformation region and the gaussian curvature is determined based on the euler formula (the curvature of any tangent direction passing through the curved surface point a satisfies the euler formula), the curvature of the deformation region a is calculated according to the mathematical relationship between the gaussian curvature (the gaussian curvature is a real symmetric matrix, then it can be decomposed into the product of an orthogonal matrix and a diagonal matrix) and the curvature of the point a of the deformation region, the above-mentioned process is performed on all points of the deformation region, the curvature at all points of the deformation region is calculated, and the maximum curvature is set as the concave curvature of the deformation region.
In this embodiment, the curvature data is the initial curvature and the current curvature of the deformed region.
In this embodiment, the mine hazard zone is a zone where the surface collapse of the mountain or the structural stress does not meet the overall stability requirement of the mountain occurs later.
The beneficial effects of the technology are as follows: the method comprises the steps that a preliminary mountain structure model is obtained only through a mine mountain surface image pair, a region needing further re-modeling existing in the preliminary mountain structure model can be determined through a range determination module, the region needing re-modeling is modeled through a laser modeling module, a region correction range model is obtained, a region, which is difficult to reflect a real structure, of the model appearing in image modeling is modeled more accurately, the accuracy and the data integrity of the built complete mountain structure model are further guaranteed, a deformation region appearing in a mine can be determined by combining the azimuth determination module with the region determination module, a dangerous prediction module is used for accurately predicting a mine dangerous region through analysis of the deformation region, and the region with the occurrence of the surface depression danger can be predicted more accurately only by means of mine mountain surface data acquired by an unmanned plane, namely, on the premise of being separated from hardware in contact with the ground, the region with the occurrence of the surface depression danger is more accurately achieved, and safety production of the mine is guaranteed.
Example 2: on the basis of embodiment 1, a mine safety risk early warning prediction system, an image modeling module, includes:
the image acquisition sub-module is used for acquiring images of the area where the mine is located based on shooting equipment arranged on the unmanned aerial vehicle, so as to obtain a plurality of mine mountain images;
the image conversion sub-module is used for inputting a plurality of mine mountain images into a preset plane conversion model to obtain corresponding spliced images;
and the graph fusion sub-module is used for carrying out frequency decomposition on all the spliced images, then fusing to obtain a fused image, and carrying out model building based on the fused image to obtain a primary mountain structure model.
In this embodiment, the preset planar conversion model is a model trained in advance by using a large number of image conversion examples (that is, examples including images in other coordinates different from the world coordinate system and corresponding images converted into images in the world coordinate system), and the model can convert images in other different coordinate systems different from the world coordinate system into images (for example, images in the world coordinate system) that can be spliced.
In this embodiment, the image that can be spliced is an image under the same coordinate system that is output after the preset conversion model.
The beneficial effects of the technology are as follows: the method can convert a plurality of mine mountain images in different coordinate systems into a spliced image in the same coordinate system based on a preset plane conversion model, so that coordinate conversion of the mine images is realized, a subsequent image fusion step is facilitated, and further, the spliced images obtained after all coordinate conversion are fused to obtain a primary mountain structure model.
Example 3: on the basis of embodiment 1, a mine safety risk early warning prediction system, a graph fusion sub-module, includes:
the image conversion unit is used for carrying out Fourier transform on the spliced image to obtain a spectrogram, and determining the brightness value of each pixel point in the spectrogram as a frequency component representation value in the spliced image;
the region determining unit is used for determining the same frequency component representation value in different spliced images, and taking a region surrounded by pixel points corresponding to all the same frequency component representation values in each two spliced images as a spliced region between the two spliced images;
the image stitching unit is used for stitching all the images which can be stitched in pairs based on all the areas which can be stitched to obtain a fusion image;
The model building unit is used for extracting three-dimensional point clouds from the fusion image, and modeling is carried out based on the three-dimensional point cloud data to obtain a preliminary mountain structure model.
In this embodiment, the frequency component characterization value is a numerical value characterizing the magnitude of the frequency component at the corresponding pixel point.
In this embodiment, the mosaicable region is a partial image of the same portion of the mine mountain structure included in the two mosaicable images.
In this embodiment, the fusion image is an image obtained by fusing all the images that can be spliced in pairs.
In this embodiment, the technology of extracting the three-dimensional point cloud from the fused image may, for example, utilize a GraphX convolution network to implement conversion from a 2D picture to the three-dimensional point cloud.
In this embodiment, the three-dimensional point cloud data is the three-dimensional coordinates of the pixel points at the actual mountain position, including the specific position and the corresponding depth.
The beneficial effects of the technology are as follows: and determining the spliced areas containing the same part of mine mountain structures in different spliced images based on the same frequency components contained in the different spliced images, splicing all the spliced images in pairs based on the spliced areas, realizing effective splicing of the spliced images, extracting three-dimensional point cloud data without redundancy based on fusion images obtained by final splicing, and finally realizing accurate construction of a primary mountain structure model.
Example 4: on the basis of embodiment 3, a mine safety risk early warning prediction system, an image stitching unit, includes:
an image generation subunit, configured to generate a first sub-image corresponding to the image that can be spliced under each frequency component based on the spectrogram;
an image-area dividing sub-unit configured to determine all first partial sub-images of the stitchable zones in the low-frequency component (all first partial sub-images herein include part of the two stitchable zones (i.e., the stitchable images included in each of the two stitchable images) in all sub-images of the low-frequency component) and all second partial sub-images of the high-frequency component (all second partial sub-images herein include part of the two stitchable zones in all sub-images of the high-frequency component) in the two stitchable images to be fused;
the low-frequency processing subunit is used for determining the average value of the gray values of all the pixel points at the same position in all the first partial sub-images, and giving the average value of the gray values to the pixel points at the corresponding positions in the blank image to obtain a low-frequency fusion image;
the high-frequency processing subunit is used for determining the maximum value of the gray values of all the pixel points at the same position in all the second partial sub-images, and giving the maximum value of the gray values to the pixel points at the corresponding positions in the blank image to obtain a high-frequency fusion image;
And the image splicing subunit is used for superposing and synthesizing the low-frequency fusion image and the high-frequency fusion image to obtain a new spliceable region, and splicing the two spliceable images to be fused based on the new spliceable region to obtain a fusion image.
In this embodiment, the generation of the first sub-image corresponding to the image capable of being spliced under each frequency component based on the spectrogram is:
determining the brightness value of each pixel point in the spectrogram, taking the median of the brightness values of all the pixel points in the spectrogram as a dividing threshold, taking the pixel points which are not smaller than the dividing threshold as high-frequency components of the spectrogram, and taking the rest points except the high-frequency components in the spectrogram as low-frequency components;
taking the ratio of the ordinal number of each frequency component in all frequency components to the total number of all frequency components as a pixel decomposition ratio;
reserving pixel values of pixel points corresponding to the current frequency component, taking the product of the pixel values of the pixel points which are remained except the pixel points corresponding to the current frequency component in the combinable image and the pixel decomposition ratio as a decomposition pixel value of the corresponding pixel point under the current frequency component, and generating a first sub-image of the current frequency component based on the pixel values of the current frequency component in the combinable image and the decomposition pixel values of the pixel points which are remained except the pixel points corresponding to the current frequency component in the combinable image under the current frequency component.
In this embodiment, the two images to be fused are two images that have the same frequency component and that can be fused.
In this embodiment, the low-frequency fused image is a fused image obtained by pixel-averaging all the first partial sub-images of the low-frequency component in the mosaicable region in the two mosaicable images to be fused.
In this embodiment, the high-frequency fused image is a fused image obtained by performing pixel maximization on all first partial sub-images of the low-frequency component in the mosaicable region in the two mosaicable images to be fused.
The beneficial effects of the technology are as follows: the sub-images of all frequency components of the fusion image are distinguished according to high frequency and low frequency, and the high frequency and low frequency fusion image is obtained by processing according to different processing methods, so that the fusion image which is more accurate and easier to carry out subsequent processing can be obtained.
Example 5: on the basis of embodiment 1, a mine safety risk early warning prediction system, a range determination module, includes:
the boundary optimization sub-module is used for dividing the fusion image constructing the preliminary mountain structure model into a plurality of second sub-images with unit areas, carrying out image boundary detection on all the second sub-images, determining boundary parts of all the second sub-images, and carrying out boundary enhancement on the boundary parts of all the second sub-images to obtain a boundary enhancement sub-image set;
A correction value calculation sub-module for determining a correction value for each boundary-enhancement sub-image in the set of boundary-enhancement sub-images based on the following formula:
；
in the method, in the process of the invention,a is the correction value of the boundary enhancer image, and a is the sitting of the lower boundary of the boundary enhancer image at right angles to the planeThe ordinate value in the standard system, b is the ordinate value of the upper boundary of the boundary enhancer image in the plane rectangular coordinate system, c is the abscissa value of the left boundary of the boundary enhancer image in the plane rectangular coordinate system, d is the abscissa value of the right boundary of the boundary enhancer image in the plane rectangular coordinate system, and c is the coordinate value of the left boundary of the boundary enhancer image in the plane rectangular coordinate system>Coordinates in the boundary enhancer image>Maximum value of pixel difference values between a pixel point at a position and each pixel point in an enhanced boundary in a corresponding boundary enhancer image,/v>Coordinates in the boundary enhancer image>Minimum value of pixel difference values between pixel point at and each pixel point in enhanced boundary in corresponding boundary enhancer image, +.>Is an independent variable derivative;
and the range judging sub-module is used for taking the boundary enhancement sub-images with the correction value larger than the rated correction value in the boundary enhancement sub-image set as the areas to be corrected and taking the area ranges corresponding to all the areas to be corrected in the primary mountain structure model as the area correction ranges.
In this embodiment, the second sub-image per unit area is a sub-image in which the fused image is divided into a plurality of sub-images each having a length and a width of 1 dm.
In this embodiment, the image boundary detection is to perform boundary detection on all sub-images based on an existing edge detection algorithm, and determine boundary portions of all sub-images.
In the embodiment, the boundary enhancement is to perform image smoothing and sharpening on the mine mountain contours in all the sub-images based on the existing neighborhood enhancement algorithm, so that the mine mountain contours are more obvious.
In this embodiment, the boundary-enhanced sub-image set is a combination of all sub-images subjected to boundary enhancement.
In this embodiment, the correction value may represent the true representativeness of the boundary enhanced sub-image to its corresponding mountain surface.
In this embodiment, the rated correction value is a critical value of the actual representativeness of the boundary enhancement sub-image to the corresponding mountain surface, and when the correction value is greater than the rated correction value, the boundary enhancement sub-image indicates that the corresponding mountain surface cannot be actually reflected, and the boundary enhancement sub-image is set as the area to be corrected, otherwise, the boundary enhancement sub-image can actually reflect the corresponding mountain surface.
The beneficial effects of the technology are as follows: the fusion image is segmented, and whether the segmented sub-image is an area to be corrected is judged by analyzing the segmented sub-image, so that the flow is reduced, and the analysis processing speed is increased.
Example 6: on the basis of embodiment 1, a mine safety risk early warning prediction system, a laser modeling module, includes:
the laser sampling sub-module is used for determining a plurality of scanning points in the area correction range, and controlling the unmanned aerial vehicle to scan at the corresponding actual positions of the scanning points in the mine mountain to obtain three-dimensional point cloud data of the corresponding scanning points;
the coincidence ratio calculating submodule is used for calculating the coincidence ratio of the three-dimensional point cloud data of all adjacent scanning points;
the supplementary scanning sub-module is used for inserting a new scanning point between adjacent scanning points with the contact ratio smaller than the minimum contact ratio threshold value, and obtaining three-dimensional point cloud data of the new scanning point in a supplementary mode until the contact ratio between the three-dimensional point cloud data of all the adjacent scanning points which are determined up to the latest is not smaller than the minimum contact ratio threshold value, and obtaining first three-dimensional point cloud data;
the point cloud duplicate removal sub-module is used for randomly removing one group of three-dimensional point cloud data of adjacent scanning points with the coincidence degree exceeding a maximum coincidence degree threshold value in the first three-dimensional point cloud data to obtain second three-dimensional point cloud data;
the registration point sub-module is used for determining the same three-dimensional point cloud in the three-dimensional point cloud data of the adjacent scanning points in the second three-dimensional point cloud data as a registration point corresponding to the adjacent scanning points;
The point cloud synthesis sub-module is used for carrying out point cloud synthesis on the three-dimensional point cloud data corresponding to the adjacent scanning points based on the registration points to obtain the complete point cloud of the area correction range;
the model construction submodule is used for constructing a region correction range model based on the complete point cloud of the region correction range.
In this embodiment, the scanning point is set to be the scanning point every 10 meters based on an arbitrary point of the edge of the area correction range as the start point until the last interval is less than 10 meters.
In this embodiment, the overlap ratio is a percentage of the total number of the same three-dimensional point cloud data in all three-dimensional point cloud data of adjacent scanning points to the sum of all three-dimensional point cloud data of two scanning points.
In this embodiment, the minimum overlap ratio threshold is a minimum value of overlap ratio of three-dimensional point cloud data of adjacent scan points, and a value smaller than the minimum overlap ratio threshold indicates that the interval between two corresponding scan points is too large, and the overlap ratio of the data is too low, so that a new scan point needs to be inserted in the middle.
In this embodiment, the first three-dimensional point cloud data is all three-dimensional point cloud data when the new scan point is inserted and corresponding three-dimensional point cloud data is acquired, and the coincidence ratio between the three-dimensional point cloud data of all adjacent scan points is guaranteed to be not less than the minimum coincidence ratio threshold value.
In this embodiment, the maximum coincidence degree threshold is the maximum coincidence degree of the three-dimensional point cloud data of the adjacent scanning points, and when the maximum coincidence degree threshold is larger than the maximum coincidence degree threshold, the interval between the two corresponding scanning points is too small, the coincidence degree of the data is too high, and one group needs to be randomly removed from the two groups of scanning point data.
In this embodiment, the second three-dimensional point cloud data is all three-dimensional point cloud data from which a random set of three-dimensional point cloud data in adjacent scanning points whose overlap ratio exceeds the maximum overlap ratio threshold value in the first three-dimensional point cloud data is removed.
In this embodiment, the registration point is the same three-dimensional point cloud in the three-dimensional point cloud data of the adjacent scanning points in the second three-dimensional point cloud data, and the point cloud synthesis is performed by taking the registration point as a reference point.
The beneficial effects of the technology are as follows: the unmanned aerial vehicle scans a plurality of scanning points to obtain more accurate three-dimensional point cloud data, whether new scanning points are needed to be inserted or three-dimensional point cloud data of the scanning points are needed to be removed is determined by judging the coincidence degree of the three-dimensional point cloud data of adjacent scanning points, the reaction time is saved, the point cloud synthesis is carried out according to registration points, and the complete point cloud of the area correction range is more conveniently and rapidly obtained.
Example 7: on the basis of embodiment 1, a mine safety risk early warning prediction system, an azimuth determination module, includes:
the dimension unification submodule is used for unifying dimensions of the preliminary mountain structure model and the region correction range model;
and the position determination submodule is used for determining the fusion orientation of the area correction range model in the preliminary mountain structure model.
In this embodiment, the dimension unification treats both the preliminary mountain model and the region correction range model as 750 pixels by 422 pixels, and determines that they can be directly merged.
In the embodiment, the fusion orientation is a fusion position of the region correction model in the preliminary mountain structure model, and model splicing is performed based on the fusion position.
The beneficial effects of the technology are as follows: the preliminary mountain model and the area correction range model can be processed and combined in the same scale, and the model can be fused more conveniently and simply.
Example 8: on the basis of embodiment 1, a mine safety risk early warning prediction system, an area determination module, includes:
the fusion sub-module fuses the region correction range model and the preliminary mountain structure model based on the fusion azimuth to obtain a complete mountain structure model;
And the deformation determination submodule is used for comparing the complete mountain structure model with a preset mountain structure model to determine a deformation area.
In this embodiment, fusing the region correction range model and the preliminary mountain structure model based on the fusion orientation to obtain the complete mountain structure model includes: and removing the part of the area to be corrected in the preliminary mountain structure model, and directly splicing the area correction model to the preliminary mountain structure model to obtain the complete mountain structure model.
In this embodiment, compare complete mountain structure model with predetermine mountain structure model, confirm deformation region, include:
and taking different areas in the complete mountain structure model and the preset mountain structure model as deformation areas.
The beneficial effects of the technology are as follows: the deformation area is conveniently and accurately determined by comparing the complete mountain structure model with a preset mountain structure model.
Example 9: on the basis of embodiment 1, a mine safety risk early warning prediction system, a risk prediction module, includes:
the initial curvature calculation sub-module is used for carrying out concave curvature calculation on the deformation area based on a preset mountain structure model to obtain the initial curvature of the deformation area;
The concave curvature sub-module is used for carrying out concave curvature calculation based on the structural change of the complete mountain structure model at the position of the deformation area to obtain the current curvature of the deformation area;
and the prediction sub-module is used for predicting the deformation area as a mine dangerous area when the difference value between the current curvature and the initial curvature is larger than a preset value.
In this embodiment, the preset mountain structure model is a mountain structure model built by collecting data in advance (when no structural deformation occurs in the mine mountain) using equipment.
In this embodiment, the concave curvature is calculated by analyzing a preset mountain structure model portion corresponding to the position of the deformation region based on the second basic formula of the existing curved surface, so that the curvature at the position of any point (set as point a) of the deformation region is equal to the curvature of the tangent vector direction curve at the position of the point a, then the mathematical relationship between the curvature of the point a of the deformation region and the gaussian curvature is determined based on the euler formula (the curvature of any tangent direction passing through the curved surface point a satisfies the euler formula), the curvature of the deformation region a is calculated according to the mathematical relationship between the gaussian curvature (the gaussian curvature is a real symmetric matrix, then it can be decomposed into the product of an orthogonal matrix and a diagonal matrix) and the curvature of the point a of the deformation region, the above-mentioned process is performed on all points of the deformation region, the curvature at all points of the deformation region is calculated, and the maximum curvature is set as the concave curvature of the deformation region.
In this embodiment, the initial curvature is a concave curvature of a preset mountain structure model portion corresponding to the position of the deformed region, which is set as the initial curvature.
In this embodiment, the current curvature is a concave curvature of the complete mountain structure model portion corresponding to the deformation region position, which is set as the current curvature.
In this embodiment, the preset value is a value obtained by calculating a large amount of data in advance, and when the difference between the current curvature and the initial curvature is greater than the preset value, the sag of the mine deformation area corresponding to the current curvature is irreversible, the curvature of the mine deformation area is gradually increased, and the deformation area is collapsed.
The beneficial effects of the technology are as follows: whether the deformation area is a mine dangerous area can be predicted by means of the curvature calculation result, prediction efficiency is improved, pre-warning of mine pits is achieved, and more time is reserved for maintenance treatment or early warning prevention treatment of the mine pits.
Example 10: on the basis of embodiment 1, a mine safety risk early warning prediction system, a risk early warning module, includes:
the signal generation sub-module is used for generating a corresponding early warning signal based on the position of the mine dangerous area;
And the signal sending sub-module is used for sending the early warning signal to the monitoring early warning background.
In this embodiment, the warning signal is an alarm signal containing location information.
In the embodiment, the monitoring and early warning background is a monitoring room background of a mine.
The beneficial effects of the technology are as follows: corresponding early warning signals are generated through the positions of the mine dangerous areas, the danger is early warned in time, and the pre-warning of safety risk accidents caused by the possible sinking and deformation of the mine is realized.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. A mine safety risk early warning prediction system, comprising:
the image modeling module is used for carrying out frequency decomposition and fusion on the mine mountain images subjected to plane conversion to obtain fusion images, and constructing a primary mountain structure model based on the fusion images;
the range determining module is used for carrying out unit area decomposition and boundary enhancement on the fusion image to obtain a boundary enhancer image, and determining a region correction range based on a correction value of the boundary enhancer image;
The laser modeling module is used for re-modeling the area correction range to obtain an area correction range model;
the azimuth determining module is used for processing based on the preliminary mountain model and the area correction range model and determining the fusion azimuth of the area correction range model in the preliminary mountain structure model;
the area determining module is used for obtaining a complete mountain structure model based on the fusion azimuth, and determining a deformation area of the mine through the complete mountain structure model and a preset mountain structure model;
the danger prediction module is used for carrying out concave curvature calculation on the deformation area of the mine to obtain the current curvature of the deformation area, and predicting the mine danger area based on the current curvature and the initial curvature corresponding to the deformation area in a preset mountain structure model;
and the danger early warning module is used for sending an early warning signal based on the position of the mine danger area.
2. The mine safety risk early warning prediction system of claim 1, wherein the image modeling module comprises:
the image acquisition sub-module is used for acquiring images of the area where the mine is located based on shooting equipment arranged on the unmanned aerial vehicle, so as to obtain a plurality of mine mountain images;
The image conversion sub-module is used for inputting a plurality of mine mountain images into a preset plane conversion model to obtain corresponding spliced images;
and the graph fusion sub-module is used for carrying out frequency decomposition on all the spliced images, then fusing to obtain a fused image, and carrying out model building based on the fused image to obtain a primary mountain structure model.
3. The mine safety risk early warning prediction system of claim 2, wherein the graphic fusion sub-module comprises:
the image conversion unit is used for carrying out Fourier transform on the spliced image to obtain a spectrogram, and determining the brightness value of each pixel point in the spectrogram as a frequency component representation value in the spliced image;
the region determining unit is used for determining the same frequency component representation value in different spliced images, and taking a region surrounded by pixel points corresponding to all the same frequency component representation values in each two spliced images as a spliced region between the two spliced images;
the image stitching unit is used for stitching all the images which can be stitched in pairs based on all the areas which can be stitched to obtain a fusion image;
the model building unit is used for extracting three-dimensional point clouds from the fusion image, and modeling is carried out based on the three-dimensional point cloud data to obtain a preliminary mountain structure model.
4. A mine safety risk early warning prediction system according to claim 3, characterized in that the image stitching unit comprises:
an image generation subunit, configured to generate a first sub-image corresponding to the image that can be spliced under each frequency component based on the spectrogram;
an image area dividing subunit, configured to determine all first partial sub-images of the low-frequency component and all second partial sub-images of the high-frequency component in the mosaicable area in the two mosaicable images to be fused;
the low-frequency processing subunit is used for determining the average value of the gray values of all the pixel points at the same position in all the first partial sub-images, and giving the average value of the gray values to the pixel points at the corresponding positions in the blank image to obtain a low-frequency fusion image;
the high-frequency processing subunit is used for determining the maximum value of the gray values of all the pixel points at the same position in all the second partial sub-images, and giving the maximum value of the gray values to the pixel points at the corresponding positions in the blank image to obtain a high-frequency fusion image;
and the image splicing subunit is used for superposing and synthesizing the low-frequency fusion image and the high-frequency fusion image to obtain a new spliceable region, and splicing the two spliceable images to be fused based on the new spliceable region to obtain a fusion image.
5. The mine safety risk early warning prediction system of claim 1, wherein the range determination module comprises:
the boundary optimization sub-module is used for dividing the fusion image constructing the preliminary mountain structure model into a plurality of second sub-images with unit areas, carrying out image boundary detection on all the second sub-images, determining boundary parts of all the second sub-images, and carrying out boundary enhancement on the boundary parts of all the second sub-images to obtain a boundary enhancement sub-image set;
a correction value calculation sub-module for determining a correction value for each boundary-enhancement sub-image in the set of boundary-enhancement sub-images based on the following formula:
；
in the method, in the process of the invention,a is the ordinate value of the lower boundary of the boundary enhancer image in the plane rectangular coordinate system, b is the ordinate value of the upper boundary of the boundary enhancer image in the plane rectangular coordinate system, c is the abscissa value of the left boundary of the boundary enhancer image in the plane rectangular coordinate system, d is the abscissa value of the right boundary of the boundary enhancer image in the plane rectangular coordinate system, & gt>Coordinates in the boundary enhancer image>Maximum value of pixel difference values between a pixel point at a position and each pixel point in an enhanced boundary in a corresponding boundary enhancer image,/v >Coordinates in the boundary enhancer image>Minimum value of pixel difference values between pixel point at and each pixel point in enhanced boundary in corresponding boundary enhancer image, +.>Is an independent variable derivative;
and the range judging sub-module is used for taking the boundary enhancement sub-images with the correction value larger than the rated correction value in the boundary enhancement sub-image set as the areas to be corrected and taking the area ranges corresponding to all the areas to be corrected in the primary mountain structure model as the area correction ranges.
6. The mine safety risk early warning prediction system of claim 1, wherein the laser modeling module comprises:
the laser sampling sub-module is used for determining a plurality of scanning points in the area correction range, and controlling the unmanned aerial vehicle to scan at the corresponding actual positions of the scanning points in the mine mountain to obtain three-dimensional point cloud data of the corresponding scanning points;
the coincidence ratio calculating submodule is used for calculating the coincidence ratio of the three-dimensional point cloud data of all adjacent scanning points;
the supplementary scanning sub-module is used for inserting a new scanning point between adjacent scanning points with the contact ratio smaller than the minimum contact ratio threshold value, and obtaining three-dimensional point cloud data of the new scanning point in a supplementary mode until the contact ratio between the three-dimensional point cloud data of all the adjacent scanning points which are determined up to the latest is not smaller than the minimum contact ratio threshold value, and obtaining first three-dimensional point cloud data;
The point cloud duplicate removal sub-module is used for randomly removing one group of three-dimensional point cloud data of adjacent scanning points with the coincidence degree exceeding a maximum coincidence degree threshold value in the first three-dimensional point cloud data to obtain second three-dimensional point cloud data;
the registration point sub-module is used for determining the same three-dimensional point cloud in the three-dimensional point cloud data of the adjacent scanning points in the second three-dimensional point cloud data as a registration point corresponding to the adjacent scanning points;
the point cloud synthesis sub-module is used for carrying out point cloud synthesis on the three-dimensional point cloud data corresponding to the adjacent scanning points based on the registration points to obtain the complete point cloud of the area correction range;
the model construction submodule is used for constructing a region correction range model based on the complete point cloud of the region correction range.
7. The mine safety risk early warning prediction system of claim 1, wherein the position determination module comprises:
the dimension unification submodule is used for unifying dimensions of the preliminary mountain structure model and the region correction range model;
and the position determination submodule is used for determining the fusion orientation of the area correction range model in the preliminary mountain structure model.
8. The mine safety risk early warning prediction system of claim 1, wherein the zone determination module comprises:
The fusion sub-module fuses the region correction range model and the preliminary mountain structure model based on the fusion azimuth to obtain a complete mountain structure model;
and the deformation determination submodule is used for comparing the complete mountain structure model with a preset mountain structure model to determine a deformation area.
9. The mine safety risk early warning prediction system of claim 1, wherein the risk prediction module comprises:
the initial curvature calculation sub-module is used for calculating the initial curvature of the corresponding range area of the deformation area in the preset mountain structure model;
the concave curvature submodule is used for calculating the current curvature of the deformation area in the complete mountain structure model;
and the prediction sub-module is used for predicting the deformation area with the corresponding difference value between the current curvature and the initial curvature larger than a preset value as a mine dangerous area.
10. The mine safety risk early warning prediction system of claim 1, wherein the risk early warning module comprises:
the signal generation sub-module is used for generating a corresponding early warning signal based on the position of the mine dangerous area;
and the signal sending sub-module is used for sending the early warning signal to the monitoring early warning background.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310962424.5A CN116739183B (en) | 2023-08-02 | 2023-08-02 | Mine safety risk early warning prediction system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310962424.5A CN116739183B (en) | 2023-08-02 | 2023-08-02 | Mine safety risk early warning prediction system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116739183A true CN116739183A (en) | 2023-09-12 |
| CN116739183B CN116739183B (en) | 2023-10-20 |
Family
ID=87901418
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310962424.5A Active CN116739183B (en) | 2023-08-02 | 2023-08-02 | Mine safety risk early warning prediction system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116739183B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117078749A (en) * | 2023-10-16 | 2023-11-17 | 吉林省思极科技有限公司 | Mountain falling stone on-line early warning and monitoring system |
| CN117782226A (en) * | 2024-02-23 | 2024-03-29 | 四川省能源地质调查研究所 | Mine safety early warning system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050052556A1 (en) * | 2003-02-17 | 2005-03-10 | Silverbrook Research Pty Ltd | Image processor |
| CN102622526A (en) * | 2012-04-06 | 2012-08-01 | 中国矿业大学(北京) | Digital mine tunneling search prediction method |
| CN107464046A (en) * | 2017-07-21 | 2017-12-12 | 广东容祺智能科技有限公司 | A kind of Geological Hazards Monitoring assessment system based on unmanned plane |
| CN107729582A (en) * | 2016-08-11 | 2018-02-23 | 张家港江苏科技大学产业技术研究院 | Component defect inspection and forecasting system based on TLS |
| CN107764192A (en) * | 2017-11-30 | 2018-03-06 | 中国地质调查局水文地质环境地质调查中心 | One kind landslide multi-point displacement intelligent monitoring device and monitoring method |
-
2023
- 2023-08-02 CN CN202310962424.5A patent/CN116739183B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050052556A1 (en) * | 2003-02-17 | 2005-03-10 | Silverbrook Research Pty Ltd | Image processor |
| CN102622526A (en) * | 2012-04-06 | 2012-08-01 | 中国矿业大学(北京) | Digital mine tunneling search prediction method |
| CN107729582A (en) * | 2016-08-11 | 2018-02-23 | 张家港江苏科技大学产业技术研究院 | Component defect inspection and forecasting system based on TLS |
| CN107464046A (en) * | 2017-07-21 | 2017-12-12 | 广东容祺智能科技有限公司 | A kind of Geological Hazards Monitoring assessment system based on unmanned plane |
| CN107764192A (en) * | 2017-11-30 | 2018-03-06 | 中国地质调查局水文地质环境地质调查中心 | One kind landslide multi-point displacement intelligent monitoring device and monitoring method |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117078749A (en) * | 2023-10-16 | 2023-11-17 | 吉林省思极科技有限公司 | Mountain falling stone on-line early warning and monitoring system |
| CN117078749B (en) * | 2023-10-16 | 2024-01-05 | 吉林省思极科技有限公司 | Mountain falling stone on-line early warning and monitoring system |
| CN117782226A (en) * | 2024-02-23 | 2024-03-29 | 四川省能源地质调查研究所 | Mine safety early warning system |
| CN117782226B (en) * | 2024-02-23 | 2024-05-14 | 四川省能源地质调查研究所 | Mine safety early warning system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116739183B (en) | 2023-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116739183B (en) | Mine safety risk early warning prediction system | |
| Riveiro et al. | Automated processing of large point clouds for structural health monitoring of masonry arch bridges | |
| Zhang et al. | Automatic construction of building footprints from airborne LIDAR data | |
| US8116530B2 (en) | Map change detection device, map change detection method, and program | |
| EP2120009B1 (en) | Measuring device and measuring method | |
| US20170004345A1 (en) | Survey data processing device, survey data processing method, and survey data processing program | |
| Chen et al. | Building reconstruction from LIDAR data and aerial imagery | |
| US7376513B2 (en) | Geospatial modeling system for separating foliage data from building data based upon noise filtering operations and related methods | |
| Tarsha Kurdi et al. | Efficiency of terrestrial laser scanning in survey works: Assessment, modelling, and monitoring | |
| CN116524017B (en) | Underground detection, identification and positioning system for mine | |
| US7292941B1 (en) | Geospatial modeling system for separating foliage data from building data based upon loose and strict tolerance noise filtering operations and related methods | |
| US7487046B2 (en) | Geospatial modeling system for performing filtering operations based upon a sum of differences of a given and neighboring location points and related methods | |
| JP4941420B2 (en) | Target detection system | |
| CN112802307B (en) | Geological monitoring and early warning method and system for geological investigation | |
| CN114140707A (en) | Power grid fault inspection method | |
| Kim et al. | Automatic generation of digital building models for complex structures from LiDAR data | |
| Bool et al. | Automated building detection using RANSAC from classified LiDAr point cloud data | |
| CN114581615B (en) | Data processing method, device, equipment and storage medium | |
| Yu et al. | A cue line based method for building modeling from LiDAR and satellite imagery | |
| Kashani et al. | 3D data collection and automated damage assessment for near real-time tornado loss estimation | |
| JP2020086471A (en) | Top end face step extraction system and top end face step extraction method | |
| Lavigne et al. | Automatic building detection and 3D shape recovery from single monocular electro-optic imagery | |
| CN117036611B (en) | Three-dimensional scene construction method and system of non-mine safety monitoring platform | |
| CN114155508B (en) | Road change detection method, device, equipment and storage medium | |
| CN116629809B (en) | Intelligent mine management method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |