CN115546116A - Method and system for extracting and calculating spacing of discontinuous surface of fully-covered rock mass - Google Patents
Method and system for extracting and calculating spacing of discontinuous surface of fully-covered rock mass Download PDFInfo
- Publication number
- CN115546116A CN115546116A CN202211132823.0A CN202211132823A CN115546116A CN 115546116 A CN115546116 A CN 115546116A CN 202211132823 A CN202211132823 A CN 202211132823A CN 115546116 A CN115546116 A CN 115546116A
- Authority
- CN
- China
- Prior art keywords
- discontinuous
- discontinuous surface
- rock mass
- crack
- planar
- 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
- 239000011435 rock Substances 0.000 title claims abstract description 82
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 32
- 238000000605 extraction Methods 0.000 claims description 33
- 238000004364 calculation method Methods 0.000 claims description 27
- 230000004927 fusion Effects 0.000 claims description 19
- 239000013598 vector Substances 0.000 claims description 13
- 238000005457 optimization Methods 0.000 claims description 12
- 230000011218 segmentation Effects 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 7
- 238000007689 inspection Methods 0.000 claims description 6
- 238000003062 neural network model Methods 0.000 claims description 6
- 230000001174 ascending effect Effects 0.000 claims description 5
- 238000000354 decomposition reaction Methods 0.000 claims description 5
- 238000009826 distribution Methods 0.000 abstract description 5
- 239000000284 extract Substances 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 10
- 238000004590 computer program Methods 0.000 description 8
- 238000000513 principal component analysis Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 238000012512 characterization method Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005211 surface analysis Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000009916 joint effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- 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
- G06T17/05—Geographic models
-
- 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
- G06T17/30—Polynomial surface description
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- 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
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
- G06V10/763—Non-hierarchical techniques, e.g. based on statistics of modelling distributions
-
- 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
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video 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
- G06V10/70—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
- G06V10/7715—Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods
-
- 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
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/70—Labelling scene content, e.g. deriving syntactic or semantic representations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30132—Masonry; Concrete
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Geometry (AREA)
- Computer Graphics (AREA)
- Algebra (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Computational Linguistics (AREA)
- Remote Sensing (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a method and a system for extracting discontinuous surfaces and calculating intervals of a fully-covered rock mass, which are used for acquiring fracture image data exposed in a linear form and fracture image data exposed in a planar form; obtaining a fitted linear discontinuous surface according to the crack image data exposed in a linear form; obtaining a planar discontinuous surface according to the crack image data exposed in a planar form; obtaining a discontinuous surface interval according to the obtained linear discontinuous surface and the planar discontinuous surface; the invention divides the discontinuous surface of the rock mass into two discontinuous surfaces which are exposed in a surface shape and exposed in a trace line, extracts the fracture through intelligent identification and reconstruction, converts the image into fracture characteristic points, extracts the discontinuous surface through an algorithm, and calculates the distance between the discontinuous surfaces, thereby realizing the representation of discontinuous distribution.
Description
Technical Field
The invention relates to the technical field of rock mass discontinuous surface analysis, in particular to a full-coverage rock mass discontinuous surface extraction and interval calculation method and system.
Background
The statements in this section merely provide background information related to the present disclosure and may not constitute prior art.
Rock mass joints include joints, faults, bedding, etc., and the presence of joint properties (i.e., spacing, durability, roughness, filling, weathering and the presence of water) has a significant effect on the mechanical behavior and permeability of the rock mass. At present, the research on extracting the discontinuous surface distance of the rock mass is less, but the discontinuous surface distance has great influence on the discontinuous property of the rock mass, and the influence degrees of different distribution states on engineering construction are different due to the same discontinuous surface size. According to the traditional method, the representations of the measuring tape compass and the like on the joint surfaces of the rock mass, particularly the acquisition of the joint space consumes huge time and energy, the efficiency is low, and the manual measurement of discontinuous surfaces is limited by more and more conditions along with the excavation of the ultra-buried tunnel.
The inventor finds that most of the existing schemes acquire the rock mass discontinuous surface through three-dimensional point cloud, but the method needs large data volume and has higher requirement on resolving equipment, and the three-dimensional point cloud lacks RGB numerical values and has poorer characterization degree on rock mass fractures; on the other hand, the discontinuity surface of the tunnel face or the slope rock body is characterized by not only the crack exposed in the trace form but also the crack exposed in the surface form, and only one crack is used, so that the adaptability of the model is poor, and the accuracy of the characterization result is poor.
Disclosure of Invention
In order to solve the defects of the prior art, the invention provides a full-coverage type method and a system for extracting discontinuous surfaces of a rock mass and calculating the distance between the discontinuous surfaces, wherein the discontinuous surfaces of the rock mass are divided into two discontinuous surfaces which are exposed in a surface shape and exposed in a trace line, a fracture is extracted through intelligent identification and reconstruction, an image is converted into fracture characteristic points, the discontinuous surfaces are extracted through an algorithm, the distance between the discontinuous surfaces is calculated, and the characterization of discontinuous distribution is realized.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention provides a method for extracting discontinuous surfaces of a full-coverage rock mass and calculating distances between the discontinuous surfaces of the full-coverage rock mass.
A full-coverage rock mass discontinuous surface extraction and interval calculation method comprises the following steps:
acquiring fracture image data exposed in a linear form and fracture image data exposed in a planar form;
according to crack image data exposed in a linear form, combining a semantic segmentation model to obtain a rock mass crack identification result graph, replacing crack pixels in the rock mass crack identification result graph with pixels corresponding to an original image to obtain a crack identification result fusion graph, performing rock mass crack three-dimensional reconstruction according to the crack identification result fusion graph, extracting three-dimensional coordinates of crack points according to a three-dimensional reconstruction result, and fitting crack characteristic points by using a random convex polygon fitting algorithm to obtain a fitted linear discontinuous surface;
according to fracture image data exposed in a planar form, utilizing a neural network model to perform fracture identification results, obtaining characteristic points of exposed discontinuous surfaces through a reconstruction algorithm, and sequentially performing coplanarity parameter calculation, plane fitting, plane generation and coplanarity inspection to obtain planar discontinuous surfaces;
the discontinuous surface pitch is obtained from the obtained linear discontinuous surface and planar discontinuous surface.
As an optional implementation mode, the fracture recognition result fusion graph is used as input of a three-dimensional reconstruction algorithm, sparse modeling is performed after feature point extraction, feature point matching, matching optimization, triangulation, pose estimation and BA optimization are sequentially performed, and a three-dimensional reconstruction result of dense modeling is obtained through depth map estimation and optimization.
As an optional implementation mode, fracture characteristic points are extracted by utilizing different RGB values of the fracture characteristic points in the fusion map, and three-dimensional coordinates of the fracture characteristic points are obtained.
As an optional implementation manner, a point on the discontinuous surface is locked, and a nearby feature point is searched according to a search function and an Euclidean distance by a KNN algorithm, and is named as Q i After k adjacent characteristic points are obtained, detecting the clustering plane by utilizing a PCA algorithm to obtain plane normal vectors (a, b and c) and characteristic values (lambda) 1 ,λ 2 ,λ 3 ) Defining deviation parameters
When eta is smaller than the maximum allowable maximum deviation parameter, the coplanarity condition is met, and a clustering discontinuous plane equation is obtained through SVD singular value algorithm decomposition fitting;
and obtaining a plane normal vector of each cluster by the PCA algorithm, converting the plane normal vector into a stereoscopic projection, observing the density of the characteristic points, obtaining a local maximum value of the density, taking the normal vector at the local maximum value of the density as the main polar direction of the discontinuous surface, determining the discontinuous surface as the main plane of the discontinuous surface of the cluster, and further obtaining a main equation of the discontinuous surface.
As an alternative implementation manner, obtaining the discontinuous surface pitch according to the obtained linear discontinuous surface and planar discontinuous surface includes:
the clustering characteristic point of the linear discontinuous surface and the planar discontinuous surface is P, and the D values of all the points are named as D p Define its clustering attribute as D c ；
Obtaining a cluster list by ascending the P points according to the D value, and randomly selecting a discontinuous surfaceIs defined as cl 1 Removing cl from 1 Creating a characteristic point data set R externally, searching the cluster in R, and obtaining the distance cl 1 The discontinuous plane where the nearest feature point is located is cl j ；
To obtain cl j Then, cl is removed j All the included characteristic points are defined as Q, and the value of the equation D of the discontinuous surface in which the characteristic points are located is D 1 Creating another data set R (except cl) j And cl 1 Outer), retrieve the nearest point of M to Q plane, whose cluster is defined as cl i The value of the equation D of the discontinuous surface is D 2 Output cl j 、cl i 、D 1 、D 2 、D 1 -D 2 Calculate cl j 、cl i And (4) repeating the processes of the other discontinuous surfaces according to the distance between the two discontinuous surfaces until all the discontinuous feature point retrieval is completed.
Further, the rock mass fracture density is calculated according to the areas of the linear discontinuous surface and the planar discontinuous surface.
The invention provides a fully-covered rock mass discontinuous surface extraction and distance calculation system.
A full-coverage rock mass discontinuity surface extraction and interval calculation system comprises:
a data acquisition module configured to: acquiring fracture image data exposed in a linear form and fracture image data exposed in a planar form;
a linear discontinuity extraction module configured to: according to crack image data exposed in a linear form, combining a semantic segmentation model to obtain a rock mass crack identification result graph, replacing crack pixels in the rock mass crack identification result graph with pixels corresponding to an original graph to obtain a crack identification result fusion graph, performing rock mass crack three-dimensional reconstruction according to the crack identification result fusion graph, extracting three-dimensional coordinates of crack points according to the three-dimensional reconstruction result, and fitting crack characteristic points by using a random convex polygon fitting algorithm to obtain a fitted linear discontinuous surface;
a planar discontinuous surface extraction module configured to: according to the crack image data exposed in a planar form, utilizing a neural network model to perform crack identification results, obtaining characteristic points of the exposed discontinuous surface through a reconstruction algorithm, and sequentially performing coplanarity parameter calculation, plane fitting, plane generation and coplanarity inspection to obtain a planar discontinuous surface;
a discontinuity pitch calculation module configured to: a discontinuous surface pitch is obtained from the obtained linear discontinuous surface and planar discontinuous surface.
As an optional implementation manner, obtaining a discontinuous surface pitch according to the obtained linear discontinuous surface and planar discontinuous surface includes:
the clustering characteristic point of the linear discontinuous surface and the planar discontinuous surface is P, and the D values of all the points are named as D p Define its clustering attribute as D c ；
Obtaining a clustering list by ascending the P points according to the D value, and randomly selecting a discontinuous surface to define as cl 1 Removing cl from 1 Creating a characteristic point data set R externally, searching the cluster in R, and obtaining the distance cl 1 The discontinuous plane where the nearest feature point is located is cl j ；
To obtain cl j Then, cl is added j All the included characteristic points are defined as Q, and the value of the equation D of the discontinuous surface in which the characteristic points are located is D 1 Creating another data set R (except cl) j And cl 1 Outer), search M to the nearest point of Q plane, its clustering is defined as cl i The value of the equation D of the discontinuous surface is D 2 Output cl j 、cl i 、D 1 、D 2 、D 1 -D 2 Calculate cl j 、cl i The distance between two discontinuous surfaces and other discontinuous surfaces are repeated until all the discontinuous characteristic points are searched
A third aspect of the invention provides a computer readable storage medium having a program stored thereon, which when executed by a processor, performs the steps in the method of fully-covered rock mass discontinuity extraction and spacing calculation according to the first aspect of the invention.
A fourth aspect of the present invention provides an electronic device, which includes a memory, a processor and a program stored in the memory and executable on the processor, and the processor executes the program to implement the steps of the method for extracting the discontinuity surface and calculating the distance between the fully-covered rock mass according to the first aspect of the present invention.
Compared with the prior art, the invention has the beneficial effects that:
1. the invention relates to a method and a system for extracting and calculating spacing of discontinuous surfaces of a fully-covered rock mass.
2. The invention provides a method and a system for extracting and calculating a distance between discontinuous surfaces of a fully-covered rock mass, which are used for automatically extracting the discontinuous surfaces of the rock mass based on an image combined deep learning technology aiming at the completely exposed discontinuous surfaces of the rock mass, can realize the automatic extraction of the discontinuous surfaces of the surface of the rock mass, and are favorable for directly analyzing the discontinuity of the rock mass.
3. According to the fully-covered rock mass discontinuous surface extraction and interval calculation method and system, intelligent identification of the rock mass is realized by combining a deep learning technology aiming at the incompletely exposed rock mass discontinuous surface, a convex polygon fitting algorithm is provided, fitting of the rock mass discontinuous surface is realized, and finally extraction of the rock mass discontinuous surface and three-dimensional parameter acquisition are realized.
4. According to the method and the system for extracting the discontinuous surface of the fully-covered rock mass and calculating the distance between the discontinuous surfaces, the distance between the discontinuous surfaces is calculated according to the equation D value of the discontinuous surface and the properties of the discontinuous surface, and the automatic representation of the distribution state of the discontinuous surfaces is realized.
Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
Fig. 1 is a schematic flow chart of a method for intelligently and automatically extracting a rock mass discontinuity surface and calculating a distance according to embodiment 1 of the present invention.
Fig. 2 is a schematic flow chart of a discontinuous plane pitch calculation system according to embodiment 1 of the present invention.
Fig. 3 is a schematic diagram of a fitting method of a random convex polygon provided in embodiment 1 of the present invention.
Detailed Description
The invention is further described with reference to the following figures and examples.
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an", and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
Example 1:
as shown in fig. 1 and 2, embodiment 1 of the present invention provides a full-coverage rock mass discontinuous surface extraction and interval calculation method, which includes four processes of linear discontinuous surface extraction, planar discontinuous surface extraction, discontinuous surface interval calculation and rock mass discontinuity analysis.
The linear discontinuous surface extraction comprises fracture identification, rock three-dimensional reconstruction, random convex polygon fitting, DBSCAN geometric detection and denoising, and more specifically comprises the following steps:
intelligently identifying rock mass fractures through a semantic segmentation model, marking the fractures in a fracture map as targets by using a marking tool, dividing other rocks and the like into backgrounds, inputting a rock mass fracture image data set into the semantic segmentation model according to the proportion of 9;
replacing crack pixels in the rock mass crack recognition result graph with pixels corresponding to the original graph to obtain a crack recognition result fusion graph, inputting the fusion graph as a three-dimensional reconstruction algorithm, sequentially performing feature point extraction, feature point matching, matching optimization, triangulation, pose estimation, BA optimization and the like to realize sparse modeling, and performing depth map estimation and depth map optimization after sparse modeling to obtain dense modeling;
extracting fracture characteristic points by using different RGB values of the fracture characteristic points in the fusion map, obtaining three-dimensional coordinates of the fracture characteristic points, and fitting the fracture characteristic points by using a random convex polygon fitting algorithm.
The random convex polygon fitting algorithm comprises the following steps:
assume that the normal point subset of the fracture points is M i The discrete point subset is M 0 Then, the fracture fitting surface can be defined as
Tend to be
Wherein a, b and c are the intercept of the plane on three coordinate axes respectively. The distance of each point of the dataset to the fracture plane is defined by the intercept parameter as the euclidean distance:
wherein x is i Representing any one crack point, the crack detection can be simplified into an optimization problem with optimized parameters, and can be expressed as
The target fracture surface is shown in the formula because randomly drawn samples of each fracture surface candidate generated by regression cannot be directly used by M i And (6) verifying. Therefore, the present implementation provides a specific parameter for verification, assuming that the support degree is s and the distance threshold is τ, the parameter can be expressed as:
if the support quantity exceeds a predefined threshold value within the maximum iteration step length, an iteration termination criterion is met, and the crack candidate is determined to be an optimal solution. And deleting the points of the fitting plane in the corresponding data set after each detection, and then iterating to find the next optimal crack until the whole data set is small enough. Assuming that q is the probability of accurately estimating the fracture parameters through the data set, the probability of selecting a sample with at least one outlier is 1-q. Therefore, the minimum number of iterations to obtain an accurate fracture surface satisfies the relationship:
As shown in fig. 3, a fitted polygon can be obtained, and a plane equation of the plane can be obtained.
The planar discontinuous surface extraction system firstly utilizes a neural network model to identify a crack surface exposed in a planar form, further obtains characteristic points of the exposed discontinuous surface through a reconstruction algorithm, and sequentially performs coplanarity parameter calculation, plane fitting, plane generation and coplanarity inspection to extract the planar discontinuous surface.
First, a point P on the discontinuous surface is locked i By Knn (K-nea)rest neighbor distances) algorithm searches nearby feature points according to a search function and Euclidean distances, and is named as Q i After k adjacent feature points are obtained, detecting the clustering plane by using a Principal Component Analysis (PCA) algorithm to obtain plane normal vectors (a, b, c) and feature values (lambda) 1 ,λ 2 ,λ 3 ) Defining a deviation parameter η:
setting a maximum allowable maximum deviation parameter eta max Empirically, when η<η max And according with the coplanarity condition, further decomposing and fitting by using an SVD singular value decomposition (singular value decomposition) algorithm to obtain a clustering discontinuity plane equation ax + by + cz + d =0.
The PCA algorithm can obtain a plane normal vector of each cluster, the plane normal vector is converted into a stereo projection, the density of the feature points can be observed, a local maximum value of the density is obtained, the normal vector at the position can be used as a principal pole direction of the discontinuous surface, the discontinuous surface is determined to be a principal plane of the discontinuous surface of the cluster, and a principal equation Ax + By + Cz + D =0 of the discontinuous surface can be obtained.
The discontinuous surface interval calculation system is shown in the figure, the clustering characteristic points of the linear discontinuous surface and the planar discontinuous surface are P, and the D values of all the points are named as D p Define its clustering attribute as D c Obtaining a clustering list by ascending the P points according to the D value, and randomly selecting a discontinuous surface to define as cl 1 Removing cl 1 Creating a characteristic point data set R externally, searching the cluster in R, and obtaining the distance cl 1 The discontinuous plane where the nearest feature point is located is cl j To obtain cl j Then, cl is added j All the included characteristic points are defined as Q, and the value of the equation D of the discontinuous surface in which the characteristic points are located is D 1 Creating another data set R (except cl) j And cl 1 Outer), retrieve the nearest point of M to Q plane, whose cluster is defined as cl i The value of the equation D of the discontinuous surface is D 2 Output cl j 、cl i 、D 1 、D 2 、D 1 -D 2 I.e. calculate cl j 、cl i And (4) repeating the processes of the other discontinuous surfaces according to the distance between the two discontinuous surfaces until all the discontinuous feature point retrieval is completed.
Calculating to obtain rock mass crack density P through the discontinuous surface distance obtained by the discontinuous surface distance calculation system and the discontinuous surface area obtained by the discontinuous surface extraction system 32 (m/m 2 )。
The method is applied to realize intelligent automatic extraction and interval calculation of the discontinuous surface of the rock mass, and the operation method comprises the following steps:
1) Firstly, a linear discontinuous surface extraction system shoots a rock fracture image by using a camera or a mobile phone, a rock fracture image data set is established, an image fracture is marked by using a marking tool, the data set is expanded by preprocessing such as segmentation, rotation, mirror image and the like, and the method comprises the following steps of: 1, inputting the proportion into a semantic segmentation model to intelligently distinguish rock fractures, and outputting an identification result diagram;
2) Matrix replacement is carried out on the rock mass fracture identification result graph and fracture pixel points corresponding to the original graph, fracture identification result fusion is achieved, feature point extraction, feature point matching, matching optimization, triangulation, pose estimation, BA optimization and depth map estimation are carried out in sequence, rock mass three-dimensional reconstruction is completed, two-dimensional to three-dimensional conversion of all feature points is achieved, and three-dimensional coordinates of the feature points are obtained;
3) The linear discontinuous surface extraction system extracts fracture characteristic points according to different RGB values in the fracture recognition result fusion graph, obtains three-dimensional coordinates of the fracture characteristic points, and fits the discontinuous surface through a random convex polygon fitting algorithm to further obtain a discontinuous surface optimal equation;
4) The planar discontinuous surface extraction system repeats the steps 1) and 2), identifies the planar discontinuous surface and realizes the three-dimensional conversion of the characteristic points of the planar discontinuous surface;
5) The planar discontinuous surface extraction system calculates point curvature calculation and point normal vectors, extracts clustering discontinuous surfaces according to SVD singular value decomposition, further calculates density distribution, extracts plane main polar directions according to a density maximum value, generates main discontinuous surfaces and obtains a discontinuous surface equation and attributes;
6) And inputting the equation and the attribute of the discontinuous surface into a discontinuous surface distance calculation system, dividing the discontinuous surface according to the D value, and iteratively calculating the distance between every two discontinuous surfaces according to the method until all the discontinuous characteristic points are searched.
7) Calculating unit volume density P by discontinuous surface analysis system 32 (m/m 2 )。
Example 2:
the embodiment 2 of the invention provides a full-coverage rock mass discontinuity surface extraction and interval calculation system, which comprises:
a data acquisition module configured to: acquiring fracture image data exposed in a linear form and fracture image data exposed in a planar form;
a linear discontinuity extraction module configured to: according to crack image data exposed in a linear form, combining a semantic segmentation model to obtain a rock mass crack identification result graph, replacing crack pixels in the rock mass crack identification result graph with pixels corresponding to an original image to obtain a crack identification result fusion graph, performing rock mass crack three-dimensional reconstruction according to the crack identification result fusion graph, extracting three-dimensional coordinates of crack points according to a three-dimensional reconstruction result, and fitting crack characteristic points by using a random convex polygon fitting algorithm to obtain a fitted linear discontinuous surface;
a planar discontinuous surface extraction module configured to: according to the crack image data exposed in a planar form, utilizing a neural network model to perform crack identification results, obtaining characteristic points of the exposed discontinuous surface through a reconstruction algorithm, and sequentially performing coplanarity parameter calculation, plane fitting, plane generation and coplanarity inspection to obtain a planar discontinuous surface;
a discontinuity pitch calculation module configured to: a discontinuous surface pitch is obtained from the obtained linear discontinuous surface and planar discontinuous surface.
The working method of the system is the same as the method for extracting the discontinuity surface of the fully-covered rock mass and calculating the distance between the discontinuity surface of the fully-covered rock mass and the distance, which is provided in embodiment 1 and is not described again here.
Example 3:
embodiment 3 of the present invention provides a computer readable storage medium, on which a program is stored, which when executed by a processor, implements the steps in the method for extracting and calculating the distance between discontinuities of a fully-covered rock mass according to embodiment 1 of the present invention.
Example 4:
embodiment 4 of the present invention provides electronic equipment, which includes a memory, a processor, and a program stored in the memory and capable of running on the processor, and when the processor executes the program, the steps in the method for extracting and calculating the distance between the discontinuities of the fully-covered rock mass according to embodiment 1 of the present invention are implemented.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by a computer program, which may be stored in a computer readable storage medium and executed by a computer to implement the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A full-coverage rock mass discontinuous surface extraction and interval calculation method is characterized by comprising the following steps:
the method comprises the following steps:
acquiring crack image data exposed in a linear form and crack image data exposed in a planar form;
according to crack image data exposed in a linear form, combining a semantic segmentation model to obtain a rock mass crack identification result graph, replacing crack pixels in the rock mass crack identification result graph with pixels corresponding to an original graph to obtain a crack identification result fusion graph, performing rock mass crack three-dimensional reconstruction according to the crack identification result fusion graph, extracting three-dimensional coordinates of crack points according to the three-dimensional reconstruction result, and fitting crack characteristic points by using a random convex polygon fitting algorithm to obtain a fitted linear discontinuous surface;
according to fracture image data exposed in a planar form, utilizing a neural network model to perform fracture identification results, obtaining characteristic points of exposed discontinuous surfaces through a reconstruction algorithm, and sequentially performing coplanarity parameter calculation, plane fitting, plane generation and coplanarity inspection to obtain planar discontinuous surfaces;
the discontinuous surface pitch is obtained from the obtained linear discontinuous surface and planar discontinuous surface.
2. The method for extracting the discontinuity surface and calculating the distance of the fully-covered rock mass according to claim 1, characterized in that:
and taking the fracture recognition result fusion graph as the input of a three-dimensional reconstruction algorithm, carrying out sparse modeling after feature point extraction, feature point matching, matching optimization, triangulation, pose estimation and BA optimization in sequence, and obtaining a three-dimensional reconstruction result of dense modeling through depth map estimation and optimization.
3. The method for extracting the discontinuity surface and calculating the distance of the fully-covered rock mass according to claim 1, characterized in that:
and extracting fracture characteristic points by utilizing different RGB values of the fracture characteristic points in the fusion map to obtain three-dimensional coordinates of the fracture characteristic points.
4. The method for extracting the discontinuity surface and calculating the distance of the fully-covered rock mass according to claim 1, characterized in that:
locking a point on the discontinuous surface, searching nearby characteristic points according to a search function and Euclidean distance by a KNN algorithm, and naming the characteristic points as Q i After k adjacent feature points are obtained, detecting the clustering plane by using a PCA algorithm to obtain plane normal vectors (a, b, c) and feature values (lambda) 1 ,λ 2 ,λ 3 ) Defining deviation parameters
When eta is smaller than the maximum allowable maximum deviation parameter, the coplanarity condition is met, and a clustering discontinuous plane equation is obtained through SVD singular value algorithm decomposition fitting;
and the PCA algorithm obtains a plane normal vector of each cluster, converts the plane normal vector into a stereoscopic projection, observes the density of the characteristic points, obtains a local maximum of the density, takes the normal vector at the local maximum of the density as the main polar direction of the discontinuous surface, determines the discontinuous surface as the main plane of the discontinuous surface of the cluster, and further obtains a main equation of the discontinuous surface.
5. The method for extracting the discontinuity surface and calculating the distance of the fully-covered rock mass according to claim 1, characterized in that:
obtaining a discontinuous surface pitch from the obtained linear discontinuous surface and planar discontinuous surface, the method comprising:
the clustering characteristic point of the linear discontinuous surface and the planar discontinuous surface is P, and the D values of all the points are named as D p Define its clustering attribute as D c ；
Obtaining a clustering list by ascending the P points according to the D value, and randomly selecting a discontinuous surface to define as cl 1 Removing cl 1 Creating a characteristic point data set R outside, searching clusters in the R by a distance cl 1 The discontinuous plane where the nearest feature point is located is cl j ；
To obtain cl j Then, cl is removed j All the included characteristic points are defined as Q, and the value of the equation D of the discontinuous surface in which the characteristic points are located is D 1 Creating another data set R (except cl) j And cl 1 Outer), search M to the nearest point of Q plane, its clustering is defined as cl i The value of the equation D of the discontinuous surface is D 2 Output cl j 、cl i 、D 1 、D 2 、D 1 -D 2 Calculate cl j 、cl i Two are not connectedAnd (4) repeating the process for other discontinuous surfaces according to the distance between the continuous surfaces until all the discontinuous feature points are searched.
6. The method for extracting the discontinuity surface and calculating the distance of the fully-covered rock mass according to claim 5, is characterized in that:
and calculating the rock mass fracture density according to the areas of the linear discontinuous surface and the planar discontinuous surface.
7. The utility model provides a full coverage formula rock mass discontinuity surface draws and interval computational system which characterized in that:
the method comprises the following steps:
a data acquisition module configured to: acquiring fracture image data exposed in a linear form and fracture image data exposed in a planar form;
a linear discontinuity extraction module configured to: according to crack image data exposed in a linear form, combining a semantic segmentation model to obtain a rock mass crack identification result graph, replacing crack pixels in the rock mass crack identification result graph with pixels corresponding to an original graph to obtain a crack identification result fusion graph, performing rock mass crack three-dimensional reconstruction according to the crack identification result fusion graph, extracting three-dimensional coordinates of crack points according to the three-dimensional reconstruction result, and fitting crack characteristic points by using a random convex polygon fitting algorithm to obtain a fitted linear discontinuous surface;
a planar discontinuous surface extraction module configured to: according to fracture image data exposed in a planar form, utilizing a neural network model to perform fracture identification results, obtaining characteristic points of an exposed discontinuous surface through a reconstruction algorithm, and sequentially performing coplanarity parameter calculation, plane fitting, plane generation and coplanarity inspection to obtain a planar discontinuous surface;
a discontinuity-surface pitch calculation module configured to: a discontinuous surface pitch is obtained from the obtained linear discontinuous surface and planar discontinuous surface.
8. The system for extracting and calculating the distance between discontinuous surfaces of the fully-covered rock mass according to claim 7, wherein:
obtaining a discontinuous surface pitch from the obtained linear discontinuous surface and planar discontinuous surface, the method comprising:
the clustering characteristic point of the linear discontinuous surface and the planar discontinuous surface is P, and the D values of all the points are named as D p Define its clustering attribute as D c ；
Obtaining a clustering list by ascending the P points according to the D value, and randomly selecting a discontinuous surface to define as cl 1 Removing cl from 1 Creating a characteristic point data set R externally, searching the cluster in R, and obtaining the distance cl 1 The discontinuous plane where the nearest feature point is located is cl j ；
To obtain cl j Then, cl is removed j All the included characteristic points are defined as Q, and the value of the equation D of the discontinuous surface in which the characteristic points are located is D 1 Creating another data set R (except cl) j And cl 1 Outer), retrieve the nearest point of M to Q plane, whose cluster is defined as cl i The value of the equation D of the discontinuous surface is D 2 Output cl j 、cl i 、D 1 、D 2 、D 1 -D 2 Calculate cl j 、cl i And (4) repeating the processes of the other discontinuous surfaces according to the distance between the two discontinuous surfaces until all the discontinuous feature point retrieval is completed.
9. A computer readable storage medium having a program stored thereon, wherein the program when executed by a processor implements the steps in the method of full coverage rock mass discontinuity extraction and distance calculation according to any one of claims 1 to 6.
10. An electronic device comprising a memory, a processor and a program stored on the memory and operable on the processor, wherein the processor when executing the program implements the steps in the method of fully-covered rock mass discontinuity extraction and distance calculation according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211132823.0A CN115546116B (en) | 2022-09-15 | 2022-09-15 | Full-coverage type rock mass discontinuous surface extraction and interval calculation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211132823.0A CN115546116B (en) | 2022-09-15 | 2022-09-15 | Full-coverage type rock mass discontinuous surface extraction and interval calculation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115546116A true CN115546116A (en) | 2022-12-30 |
| CN115546116B CN115546116B (en) | 2024-08-16 |
Family
ID=84727717
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211132823.0A Active CN115546116B (en) | 2022-09-15 | 2022-09-15 | Full-coverage type rock mass discontinuous surface extraction and interval calculation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115546116B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116645602A (en) * | 2023-04-28 | 2023-08-25 | 长安大学 | Method, system and storage medium for intelligent identification and three-dimensional reconstruction of grotto weathered cracks |
| CN117854060A (en) * | 2024-03-07 | 2024-04-09 | 山东大学 | Tunnel rock body planar crack identification method and system based on deep learning |
| CN118172406A (en) * | 2024-03-07 | 2024-06-11 | 山东大学 | Method and system for extracting discontinuous surface inside rock mass based on borehole fracture image |
| CN118196618A (en) * | 2024-03-07 | 2024-06-14 | 山东大学 | Method and system for correlation analysis of rock mass cracks in tunnel |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW202001615A (en) * | 2018-06-14 | 2020-01-01 | 國立臺北科技大學 | Method for using point cloud to determine rock discontinuity attitude which includes acquiring proper point cloud; and determining an attitude of rock discontinuity by using the point cloud according to geomagnetism and geographic directions |
| CN113838005A (en) * | 2021-09-01 | 2021-12-24 | 山东大学 | Intelligent rock fracture identification and three-dimensional reconstruction method and system based on dimension conversion |
| KR20220111428A (en) * | 2021-02-02 | 2022-08-09 | 한국해양대학교 산학협력단 | Method and apparatus for calculating a rating value of bedrock based on digital images |
-
2022
- 2022-09-15 CN CN202211132823.0A patent/CN115546116B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW202001615A (en) * | 2018-06-14 | 2020-01-01 | 國立臺北科技大學 | Method for using point cloud to determine rock discontinuity attitude which includes acquiring proper point cloud; and determining an attitude of rock discontinuity by using the point cloud according to geomagnetism and geographic directions |
| KR20220111428A (en) * | 2021-02-02 | 2022-08-09 | 한국해양대학교 산학협력단 | Method and apparatus for calculating a rating value of bedrock based on digital images |
| CN113838005A (en) * | 2021-09-01 | 2021-12-24 | 山东大学 | Intelligent rock fracture identification and three-dimensional reconstruction method and system based on dimension conversion |
Non-Patent Citations (3)
| Title |
|---|
| HASSAN MOOMIVAND ET AL.: "A new approach to improve the assessment of rock mass discontinuity spacing using image analysis technique", INTERNATIONAL JOURNAL OF ROCK MECHANICS AND MINING SCIENCES, vol. 143, 31 July 2021 (2021-07-31) * |
| MOHAMMAD AZARAFZA ET AL.: "Spacing and blockvolume estimation in discontinuous rock masses using image processing technique:a case study", ENVIRONMENTAL EARTH SCIENCES, vol. 80, 9 July 2021 (2021-07-09), XP037514451, DOI: 10.1007/s12665-021-09768-3 * |
| 王培涛 等: "基于立体成像技术的矿山岩体质量快速分级方法研究", 黄金, vol. 43, no. 3, 31 March 2022 (2022-03-31) * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116645602A (en) * | 2023-04-28 | 2023-08-25 | 长安大学 | Method, system and storage medium for intelligent identification and three-dimensional reconstruction of grotto weathered cracks |
| CN116645602B (en) * | 2023-04-28 | 2024-05-07 | 长安大学 | Method, system and storage medium for intelligent identification and three-dimensional reconstruction of grotto weathered cracks |
| CN117854060A (en) * | 2024-03-07 | 2024-04-09 | 山东大学 | Tunnel rock body planar crack identification method and system based on deep learning |
| CN117854060B (en) * | 2024-03-07 | 2024-05-03 | 山东大学 | Tunnel rock body planar crack identification method and system based on deep learning |
| CN118172406A (en) * | 2024-03-07 | 2024-06-11 | 山东大学 | Method and system for extracting discontinuous surface inside rock mass based on borehole fracture image |
| CN118196618A (en) * | 2024-03-07 | 2024-06-14 | 山东大学 | Method and system for correlation analysis of rock mass cracks in tunnel |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115546116B (en) | 2024-08-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Czerniawski et al. | Pipe spool recognition in cluttered point clouds using a curvature-based shape descriptor | |
| CN107038717B (en) | A method of 3D point cloud registration error is automatically analyzed based on three-dimensional grid | |
| CN115546116B (en) | Full-coverage type rock mass discontinuous surface extraction and interval calculation method and system | |
| CN109658445A (en) | Network training method, increment build drawing method, localization method, device and equipment | |
| Ückermann et al. | Real-time 3D segmentation of cluttered scenes for robot grasping | |
| Liu et al. | Automatic buildings extraction from LiDAR data in urban area by neural oscillator network of visual cortex | |
| CN115546113B (en) | Method and system for predicting fracture image and front three-dimensional structure parameters of tunnel face | |
| Galvanin et al. | Extraction of building roof contours from LiDAR data using a Markov-random-field-based approach | |
| Hu et al. | Efficient and automatic plane detection approach for 3-D rock mass point clouds | |
| Kim et al. | Urban scene understanding from aerial and ground LIDAR data | |
| CN109685821A (en) | Region growing 3D rock mass point cloud plane extracting method based on high quality voxel | |
| CN113838005A (en) | Intelligent rock fracture identification and three-dimensional reconstruction method and system based on dimension conversion | |
| CN113033248B (en) | Image recognition method and device and computer readable storage medium | |
| CN112241676A (en) | Method for automatically identifying terrain sundries | |
| Kyriakaki-Grammatikaki et al. | Geometric primitive extraction from semantically enriched point clouds | |
| Sun et al. | Rock mass discontinuity extraction method based on multiresolution supervoxel segmentation of point cloud | |
| CN107452003A (en) | A kind of method and device of the image segmentation containing depth information | |
| CN117994484A (en) | Device and method for splicing three-dimensional images of prefabricated parts of large building | |
| Demir | Automated detection of 3D roof planes from Lidar data | |
| CN112634447B (en) | Outcrop stratum layering method, device, equipment and storage medium | |
| Buldo et al. | A scan-to-BIM workflow proposal for cultural heritage. Automatic point cloud segmentation and parametric-adaptive modelling of vaulted systems | |
| Wang et al. | A segmentation method for point cloud based on local sample and statistic inference | |
| Harshit et al. | Geometric features interpretation of photogrammetric point cloud from Unmanned Aerial Vehicle | |
| Ward et al. | A model-based approach to recovering the structure of a plant from images | |
| CN114782689A (en) | Point cloud plane segmentation method based on multi-frame data fusion |
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 |