CN116645602B - Method, system and storage medium for intelligent identification and three-dimensional reconstruction of grotto weathered cracks - Google Patents
Method, system and storage medium for intelligent identification and three-dimensional reconstruction of grotto weathered cracks Download PDFInfo
- Publication number
- CN116645602B CN116645602B CN202310481025.7A CN202310481025A CN116645602B CN 116645602 B CN116645602 B CN 116645602B CN 202310481025 A CN202310481025 A CN 202310481025A CN 116645602 B CN116645602 B CN 116645602B
- Authority
- CN
- China
- Prior art keywords
- weathered
- fracture
- dimensional
- cracks
- crack
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000003860 storage Methods 0.000 title claims abstract description 9
- 238000009826 distribution Methods 0.000 claims abstract description 49
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 35
- 238000005516 engineering process Methods 0.000 claims abstract description 18
- 238000000638 solvent extraction Methods 0.000 claims abstract description 11
- 230000011218 segmentation Effects 0.000 claims abstract description 5
- 230000006378 damage Effects 0.000 claims description 41
- 238000011161 development Methods 0.000 claims description 31
- 230000018109 developmental process Effects 0.000 claims description 31
- 239000011435 rock Substances 0.000 claims description 24
- 239000007787 solid Substances 0.000 claims description 13
- 238000004806 packaging method and process Methods 0.000 claims description 8
- 239000013598 vector Substances 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000003064 k means clustering Methods 0.000 claims description 4
- 230000009897 systematic effect Effects 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 238000005538 encapsulation Methods 0.000 abstract description 2
- 208000027418 Wounds and injury Diseases 0.000 description 25
- 208000014674 injury Diseases 0.000 description 25
- 238000005259 measurement Methods 0.000 description 9
- 238000001514 detection method Methods 0.000 description 7
- 239000004575 stone Substances 0.000 description 5
- 239000013256 coordination polymer Substances 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 230000000877 morphologic effect Effects 0.000 description 4
- 238000012512 characterization method Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 241000251468 Actinopterygii Species 0.000 description 2
- 238000007792 addition Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000002427 irreversible effect Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000007670 refining Methods 0.000 description 2
- 230000002787 reinforcement Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000000342 Monte Carlo simulation Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000011065 in-situ storage Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 238000002604 ultrasonography 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- 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
- G06V10/20—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
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Probability & Statistics with Applications (AREA)
- Geometry (AREA)
- Computer Graphics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention provides a method, a system and a storage medium for intelligent identification and three-dimensional reconstruction of grotto weathered cracks, wherein the method comprises the following steps: generating dense three-dimensional point cloud data based on a motion restoration structure technology by using an image acquired through close-range photography; clustering the weather cracks by using a dynamic clustering algorithm, dividing the plane where each weather crack surface is located based on a clustering result, and identifying the weather cracks of the damaged area based on the segmentation; characterizing the geometrical characteristic parameters of the weathered fracture through a plane fitting algorithm; counting geometrical characteristic parameters of the weathered fracture to obtain a probability distribution model of the weathered fracture; and encapsulating the dense three-dimensional point cloud data by using geometric topological information to form a three-dimensional entity model, and constructing a rectangular weathered fracture network in the three-dimensional entity model formed by encapsulation in a partitioning manner based on the statistical result and the probability distribution model of the geometric characteristic parameters of each weathered fracture. The invention can truly reflect the geometric shape, scale, quantity and spatial distribution characteristics of the wind-activated fissure in the damaged area.
Description
Technical Field
The invention relates to the technical field of intelligent identification and information characterization of grotto cracks, in particular to an intelligent identification and three-dimensional reconstruction method and system for grotto weathered cracks.
Background
The geologic body attached to the grottoes is subjected to the effects of long natural environment and human activities and faces the risks of complex and various diseases such as crack development, water leakage, weathering erosion, severe environmental change and the like. Wherein, the weathering fracture fundamentally changes the mechanical property of the rock mass and plays an important role in controlling the integrity and stability of the structure of the grotto rock mass. The geometrical characteristics of the weathered cracks in the grotto injury area are obtained, and the spatial injury distribution information of the weathered cracks is explored, so that the long-term safety and stability of the grotto are guaranteed. Therefore, a detailed investigation of the development of weathered fissures in grotto rock is required.
The traditional measurement means comprise the step of acquiring geometric information of the cracks by adopting a manual measurement mode, such as adopting a geological compass, a tape measure, a feeler gauge and the like to collect weathered cracks in a contact manner, and the manual measurement modes are time-consuming and labor-consuming, and researchers in severely damaged areas such as collapse, collapse and the like are directly exposed to disaster risks, so that the personal safety problem is also caused. Traditional measurement means also include the use of geophysical prospecting techniques such as ground penetrating radar, ultrasound, etc. to detect fissures in areas of damage to stone relics. Both the manual measurement mode and the geophysical prospecting technology belong to a contact type acquisition method, so that the requirements on the professional technical capability of operators are high, and irreversible damage and destruction to a grotto injury area can be possibly caused by slight carelessness. In addition, the traditional manual measurement means and geophysical prospecting technology are difficult to truly reflect the distribution characteristics of three-dimensional cracks in a grotto injury area according to the geometric parameters of weathered cracks. The Chinese patent with publication number CN111579646A and the name of "in-situ nondestructive detection method of stone relic crack" discloses a method for detecting stone relic crack length and inclination angle based on different longitudinal wave propagation speeds in different media. The problem that this patent exists is that ultrasonic detection must touch the surface of stone relics, and this kind of detection method probably can cause irreversible destruction to stone relics, and can only obtain two limited parameters of crack length and inclination to and the regional limited of ultrasonic method measuring, can not reflect the three-dimensional spatial distribution information of crack in the damage region.
Because of the irreproducibility and the specificity of grotto cultural relics, non-contact and nondestructive requirements are put on the detection technology of damaged areas, and the conventional contact type measurement method is difficult to meet the requirements. Aiming at the detection of cracks in a grotto damaged area, a method for identifying the geometric information of the weathered cracks in the grotto damaged area and accurately characterizing the morphology and the spatial distribution characteristics of the weathered cracks in the grotto damaged area in a non-contact, rapid and intelligent manner is needed to be searched out so as to reflect the morphology and the spatial distribution characteristics of the weathered cracks in the damaged area in a lossless, rapid and real manner.
Disclosure of Invention
In view of the above, the invention provides a method and a system for intelligently identifying and three-dimensionally reconstructing a grotto weathered crack, which are used for identifying the geometric information of the weathered crack of a grotto damaged area in a non-contact, rapid and intelligent manner and accurately characterizing the morphology and the spatial distribution characteristics of the weathered crack.
One aspect of the embodiment of the invention provides a grotto weathering fracture intelligent identification and three-dimensional reconstruction method, which comprises the following steps:
acquiring a plurality of close-range image images which are obtained by close-range photography from a plurality of positions and angles and meet the requirement of picture overlapping rate in a representative rock damage area of a grotto;
Importing the multiple close-range image images into three-dimensional modeling software for processing, and generating dense three-dimensional point cloud data based on a motion restoration structure technology;
clustering the generated dense three-dimensional point cloud data by using a dynamic clustering algorithm, dividing the plane where each weathered crack surface is located based on a clustering result, and identifying the weathered cracks on the rock mass surface in the damaged area based on a dividing result;
Fitting point cloud data of each weathered fracture surface through a plane fitting algorithm, and representing weathered fracture geometric feature parameters based on an analytical geometric theory, wherein the weathered fracture geometric feature parameters comprise: yield, trace length, spacing, and depth of development;
Dividing a representative rock mass damage area into subareas, and counting the geometrical characteristic parameters of the weathered cracks in each subarea to obtain a probability distribution model of the geometrical characteristic parameters of each weathered crack;
and packaging the generated dense three-dimensional point cloud data by using geometric topology information to form a three-dimensional entity model, and constructing a rectangular weathered fracture network in the three-dimensional entity model formed by packaging based on the statistical result and the probability distribution model of the geometric characteristic parameters of each weathered fracture.
In some embodiments of the present invention, the picture overlap rate requirement is that the picture longitudinal overlap rate and the picture lateral overlap rate are greater than the first scale and the second scale, respectively.
In some embodiments of the present invention, the three-dimensional modeling software is Agisoft Metashape software, and the dynamic clustering algorithm is a dynamic DBSCAN algorithm.
In some embodiments of the present invention, clustering the generated dense three-dimensional point cloud data using a dynamic clustering algorithm, and dividing a plane in which each weathered crack surface is located based on a clustering result, including:
determining: determining a neighborhood radius and a minimum inclusion point number;
Core point identification: traversing each point in the point cloud, identifying a core point in the point cloud based on the determined neighborhood radius and the minimum inclusion points, and incorporating the identified core point into a subset of core point clusters;
clustering: randomly taking out a core point which is not clustered from the core point clustering subset, incorporating the neighborhood point within the neighborhood radius range of the core point into the same sub-cluster, traversing all the core points in the sub-cluster, and incorporating the neighborhood point within the neighborhood radius range of the traversed core point into the same sub-cluster;
in some embodiments of the invention, characterizing the weathered fracture geometry parameters based on analytical geometry theory includes:
fitting the point cloud data of the weathered fracture surface through a plane fitting algorithm to obtain a geometric equation of the weathered fracture surface;
Calculating the attitude of the weathered fracture surface based on the conversion relationship between the unit normal vector of the weathered fracture surface and the attitude of the weathered fracture surface;
Extracting and measuring the maximum distance between the vertexes of the polygon representing the weathered fracture surface as the trace length of the weathered fracture;
Calculating the distance between two points which are perpendicular to the trace length and are positioned in the weathered crack surface as the development depth of the weathered crack;
and calculating the vertical distance between two adjacent weathered fracture surfaces to be used as the distance between the two adjacent weathered fractures.
In some embodiments of the present invention, counting the geometric feature parameters of the weathered fracture in each sub-region and obtaining a probability distribution model of the geometric feature parameters of each weathered fracture includes:
Counting the geometrical characteristic parameters of the weathered cracks in each subarea;
Drawing the counted weathered crack occurrence results on an equal density chart, dividing the dominant group number of the weathered crack occurrence according to the density degree of poles of the weathered crack occurrence in the equal density chart distribution and a systematic clustering method, and obtaining the dominant occurrence of the weathered crack occurrence of each subarea of the grotto by adopting a K-means clustering algorithm, so as to count and fit a probability distribution model of geometric characteristic parameters of the weathered crack occurrence.
In some embodiments of the present invention, a rectangular weathered fracture network is built in a three-dimensional solid model partition formed by encapsulation based on a statistical result and a probability distribution model of each weathered fracture geometric feature parameter, including:
Obtaining a statistical result and a probability distribution model of the geometrical characteristic parameters of the weathered slot;
The space position of the weathered cracks is represented by utilizing the occurrence, the length and the width of the weathered cracks are limited by the trace length and the development depth, the quantity of the weathered cracks is limited by the volume density, and a rectangular weathered crack network is constructed in a partitioning manner in a three-dimensional solid model by combining a Monte Carlo technology.
Another aspect of the invention provides a grotto-weathered fracture intelligent identification and three-dimensional reconstruction system comprising a processor and a memory, the memory having stored therein computer instructions for executing the computer instructions stored in the memory, the system implementing the steps of the method of any of the embodiments when the computer instructions are executed by the processor.
Another aspect of the invention provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method of any of the embodiments described above.
According to the intelligent identifying and three-dimensional reconstructing method and system for the grotto weathered cracks, disclosed by the invention, three-dimensional digital spatial distribution information of the grotto weathered cracks is obtained by non-contact, rapid and intelligent identifying of the weathered cracks in the damaged region of the grotto, and a rectangular weathered crack network capable of reflecting the scale and morphological characteristics of the weathered cracks can be lossless, rapid and truly.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention. The objectives and other advantages of the invention may be realized and attained by the structure particularly pointed out in the written description and drawings.
It will be appreciated by those skilled in the art that the objects and advantages that can be achieved with the present invention are not limited to the above-described specific ones, and that the above and other objects that can be achieved with the present invention will be more clearly understood from the following detailed description.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate and together with the description serve to explain the application. In the drawings:
Fig. 1 is a schematic flow chart of a grotto weathered slot intelligent identification and three-dimensional reconstruction method according to an embodiment of the invention.
FIG. 2 is an illustration of weathered fracture surfaces in a three dimensional space coordinate system in accordance with one embodiment of the present invention.
Fig. 3 is an example of vertical grid multi-position and angle shots in an embodiment of the invention.
Fig. 4 shows an example of division of subregions of a grotto roof according to an embodiment of the invention.
FIG. 5 is a statistical example of fracture geometry parameters for the stroke in accordance with one embodiment of the present invention.
FIG. 6 is an example of a three-dimensional rectangular weathered fracture network in an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the following embodiments and the accompanying drawings, in order to make the objects, technical solutions and advantages of the present invention more apparent. The exemplary embodiments of the present invention and the descriptions thereof are used herein to explain the present invention, but are not intended to limit the invention.
It should be noted here that, in order to avoid obscuring the present invention due to unnecessary details, only structures and/or processing steps closely related to the solution according to the present invention are shown in the drawings, while other details not greatly related to the present invention are omitted.
It should be emphasized that the term "comprises/comprising" when used herein is taken to specify the presence of stated features, elements, steps or components, but does not preclude the presence or addition of one or more other features, elements, steps or components.
Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. In the drawings, the same reference numerals represent the same or similar components, or the same or similar steps.
And the geometrical characteristic parameters of the weathered fissures in the grotto injury area are obtained, and the spatial distribution of the weathered fissures is explored, so that the long-term safety and stability of the grotto rock mass are guaranteed. However, the existing grotto fracture detection, identification and characterization technology mainly relies on the traditional manual measurement or geophysical prospecting technology to obtain fracture geometric features, so that the requirements of non-contact and nondestructive are difficult to meet, and the distribution characteristics of the weathered fractures in the grotto damaged area cannot be truly reflected according to fracture geometric feature parameters. In addition, the prior art research is limited to performing discoidal simulation on rock cracks, however, the weathered cracks are in a rectangular shape, so that the prior art is difficult to truly reflect the morphology features of the weathered cracks with small dimensions and shallow development depth, and a three-dimensional rectangular weathered crack network cannot be constructed.
Based on the method, the embodiment of the invention provides the intelligent identification and three-dimensional reconstruction method for the grotto weathered cracks, the high-definition picture of the damaged region of the grotto can be obtained in a non-contact mode through a close-range photogrammetry technology, then a three-dimensional point cloud model is built based on the high-definition picture, the weathered cracks on the surface of the damaged region are identified and characterized intelligently, and the morphology and the spatial distribution characteristics of the weathered cracks of the damaged region are reflected truly.
Fig. 1 is a schematic flow chart of a grotto weathered slot intelligent identification and three-dimensional reconstruction method according to an embodiment of the invention. As shown in FIG. 1, the method may specifically include steps S110-S160.
Step S110: and acquiring a plurality of close-range image images which are obtained by close-range photographing from a plurality of positions and angles and meet the requirement of the picture overlapping rate.
As an example, a region where cracks develop and the rock mass is broken is selected as a representative rock mass damaged region of the grotto, and a global high-definition picture of the damaged region is taken and acquired from different positions by a camera.
After a grotto representative rock mass damage area is selected, a proper photographing camera point is erected, high-definition photos covering the whole area of the damage area can be photographed and obtained from a plurality of positions and angles, and the photographed high-definition photos can be used for constructing a refined three-dimensional point cloud model.
In some embodiments of the present invention, the picture overlap rate requirement is that the picture longitudinal overlap rate and the picture lateral overlap rate should be greater than the first scale and the second scale, respectively. The invention provides the requirement of picture overlapping rate to ensure the quality of image matching when the image matching is carried out in the later step.
In some embodiments of the present invention, when taking a picture of a damaged region of a grotto, the surrounding boundaries of the damaged region of the grotto may be taken together and processed together, so that the weathered fissure overall recognition of the damaged region of the grotto may be more comprehensive.
For simplicity of description, unless otherwise specified, the cracks appearing hereinafter are all referred to as weathered cracks.
Step S120: and importing a plurality of close-range image images into three-dimensional modeling software for processing, and generating dense three-dimensional point cloud data based on a motion restoration structure technology.
As an example, the three-dimensional modeling software is Agisoft Metashape software. And importing Agisoft Metashape shot high-definition photos into software for fusion matching treatment, namely performing image matching, acquiring the position information of matched features in the photos, and performing image fusion based on the acquired position information. Further, based on a motion restoration structure technology (Structure from motion, sfM), processing the image in Agisoft Metashape software to obtain dense three-dimensional point cloud data, or to obtain a three-dimensional point cloud model containing the three-dimensional point cloud data, wherein the three-dimensional point cloud model is used for refining and restoring morphological features of a damaged area.
The motion restoration structure algorithm combines a series of two-dimensional images obtained from a plurality of positions and angles, and reconstructs a three-dimensional structure of a static scene by performing a motion estimation state by a camera corresponding to each two-dimensional image. Assuming that the imaging point of the spatial point CP i is CP i-n, the corresponding homogeneous coordinate is CP i＝(xw,yw,zw,1)T and CP i-n＝(u,v,1)T, i represents the number of spatial points, n represents the number of imaging points corresponding to the spatial points, and T represents the transpose of the matrix, then the solution mathematical model of the motion restoration structure algorithm is:
Wherein lambda is the projection depth and is a non-zero scale factor; r and l are extrinsic parameter matrices representing the transformation relationship of the camera coordinate system and the world coordinate system. Wherein the rotation matrix R is composed of R 1～r9 and the translation vector l is composed of lx, ly and lz. S is a matrix composed of focal length f, principal point coordinates (u 0,v0), physical dimensions dx, dy, and other parameters inside the camera, and p=s (Rl) is a projection matrix.
Step S130: and clustering the generated dense three-dimensional point cloud data by using a dynamic clustering algorithm, dividing the plane where each weathered crack surface is located based on a clustering result, and identifying the weathered cracks on the rock mass surface in the damaged area based on a dividing result.
In some embodiments, the dynamic clustering algorithm is a dynamic DBSCAN (Density-Based Spatial Clustering of Applications with Noise, density-based noise application spatial clustering) algorithm, and the clustering segmentation of the three-dimensional point cloud data can be realized by adopting the dynamic DBSCAN algorithm in Matlab software.
The dynamic DBSCAN algorithm is a density-based clustering algorithm that is capable of dividing a region with sufficient density into clusters, and finding arbitrarily shaped clusters in noisy spatial data, which defines the clusters as the largest set of density-connected points. The algorithm uses two parameters: the determined neighborhood radius eps and minimum inclusion point minPts.
In some embodiments, clustering the generated dense three-dimensional point cloud data using a dynamic clustering algorithm may specifically include the steps of:
step S131, determining a neighborhood radius eps and a minimum inclusion point minPts.
The neighborhood radius acts to determine core points in the point cloud. The neighborhood radius may be set empirically or calculated based on minimum inclusion points minPts. Under the condition that the neighborhood radius is obtained through calculation, a certain point in the three-dimensional cloud can be randomly selected, and the neighborhood radius corresponding to the selected point when the selected point has a preset number of neighborhood points (the minimum number of points minPts) is calculated through a nearest neighbor algorithm.
Step S132, traversing each point in the point cloud, identifying a core point in the point cloud based on the determined neighborhood radius and the least-included point number, and incorporating the identified core point into a core point cluster subset.
The core points are points with the number of the neighborhood points in the neighborhood radius range in the high-density area being larger than or equal to the minimum containing points.
More specifically, each point in the point cloud is traversed, the number of neighborhood points in the neighborhood radius range of each point in the three-dimensional point cloud selected randomly is calculated, if the number of the neighborhood points is larger than or equal to the minimum containing point number, the current point is used as a core point, the neighborhood points are included in the core point clustering subset, if the number of the neighborhood points is smaller than the minimum containing point number, one point which is not traversed in the point cloud and is not traversed in the point cloud is skipped and selected randomly again, and until each point in the point cloud is traversed. At this time, the subset of core point clusters is grouped into a single large cluster.
Step S133, randomly selecting one core point in the core point clustering subset, incorporating the neighborhood point in the neighborhood radius range of the core point into the same sub-cluster, traversing all the core points in the sub-cluster, incorporating the neighborhood point in the neighborhood radius range of the traversed core point into the same sub-cluster, and thus dividing the clusters.
And repeating the step until all the core points in the core point clustering subset are incorporated into the sub-clusters, thereby completing the cluster segmentation, namely, the plane where each weathered crack surface is located is segmented one by one.
Step S140: and fitting point cloud data of each weathered fracture surface by a plane fitting algorithm, and representing the geometric characteristic parameters of the weathered fracture based on an analytical geometric theory.
The geometric characteristic parameters of the weathered slot include: yield, trace length, spacing, and depth of development.
By way of example, the point cloud data of the weathered fracture surface may be fitted by a RANSAC (Random Sample Consensus ) plane fitting algorithm to obtain the following geometric equation of the weathered fracture surface:
ax+by+cz+d＝0；
wherein (a, b, c) is a unit normal vector of the fracture surface; d is an amount used to determine the specific location of the fracture surface in the spatial coordinates, and the weathered fracture surface is shown in FIG. 2 in the three-dimensional spatial coordinate system.
And calculating the occurrence of the fracture surface based on the conversion relation between the unit normal vector of the weathered fracture surface and the occurrence of the weathered fracture surface.
The attitude of the fracture surface refers to the general term for the state and orientation of formation production at the fracture surface. In addition to the horizontal fracture surface producing horizontally, the production of an inclined fracture surface is expressed in terms of its strike, dip and dip angle, the dip being 90 ° or 270 ° different from the strike. There are two representation methods for the occurrence of fissured surfaces: azimuth and quadrant angle representations. The invention is illustrated by way of example only in terms of azimuth notation. Azimuth expressions are generally recording trends and dip angles. In fig. 2, α represents the tendency of the weathered fracture surface; beta represents the dip angle of the weathered fracture face.
In the embodiment of the invention, the unit normal vector is obtained based on the geometric equation of the weathered fracture surface, and the inclination angle and the tendency of the weathered fracture surface can be calculated based on the conversion relation between the unit normal vector and the weathered fracture surface.
The shape of the rock cracks is mainly disc-shaped, and the development characteristics of the weathered cracks are obviously not consistent with the disc-shaped. The development depth of the weathered crack is controlled by the horizontal layer arrangement, the trace is relatively long, the upper layer surface and the lower layer surface determine the upper side and the lower side of the crack, the left side and the right side are approximately vertical layer surfaces and are approximately rectangular, and the length and the width of the weathered crack can be respectively determined as the trace length and the development depth of the crack. Therefore, in the embodiment of the invention, the shape of the simulated weathering fracture is rectangular, and the trace length l, the depth g and the normal distance s of the weathering fracture can be calculated by using the analytical geometry theory.
More specifically, the maximum distance between vertices of the polygon representing the weathered fracture surface is extracted and measured as the trace length l of the weathered fracture. The method comprises the steps of obtaining point cloud data of a weathered fracture surface by utilizing a weathered fracture surface identified by a dynamic DBSCAN algorithm, connecting edge points in the point cloud data of the fracture surface to generate a weathered fracture surface polygon, selecting two vertexes Q 1(x1,y1,z1),Q2(x1,y1,z1 of the polygon), reading coordinates of the two points by Matlab software for processing the point cloud, calculating Euclidean distance of the two points, and obtaining the farthest distance as trace length l of the weathered fracture surface. The calculation formula is as follows:
the distance of two points perpendicular to the trace length and located within the weathered slot plane was calculated as the depth of development g of the weathered slot.
Calculating the vertical distance between two adjacent fracture surfaces as the distance s between the two adjacent fractures:
Wherein, The average value of the unit normal vectors of the same group of fracture surfaces in each direction is respectively shown, and d 1 and d 2 are respectively the position parameters of the two fracture surfaces.
Step S150: and dividing the representative rock mass damage area into subareas, and counting the fracture geometric feature parameters in each subarea to obtain a probability distribution model of each fracture geometric feature parameter.
In some embodiments, the present step may specifically include the steps of:
In step S151, the grotto damaged area to be identified may be divided into a plurality of sub-areas, such as 3 sub-areas (the number is merely an example, and the present invention is not limited thereto), according to the number of development cracks, and the different sub-areas represent different weathering levels.
As an example, the subareas are divided according to different distribution situations of the cracks in the grotto injury area, for example, the cracks with denser distribution are divided into the same subareas, and the cracks with sparser distribution are divided into the same subareas.
Step S152, the geometric characteristic parameters such as the occurrence, trace length, spacing, depth and the like of the fracture surface in each sub-area are respectively counted and summarized. Drawing the counted weathered fracture occurrence results on an isopycnic chart, dividing the dominant group number of the fracture surface according to the density degree of poles of the fracture surface occurrence in the isopycnic chart distribution and a systematic clustering method, then adopting a K-means clustering algorithm to obtain the dominant occurrence of the fracture surface of each subarea of the grotto, and further counting and fitting a probability distribution model of the weathered fracture occurrence length, the interval and the development depth.
Further, the linear density λ and the bulk density λ v for each fracture group may be derived based on the weathered fracture spacing information:
The average pitch, average trace length, and average development depth of the weathered fissures of each fissure group are shown, and λ, λ v are the linear density and the volumetric density of the corresponding fissure group, respectively. Bulk density can be used to define the number of weathered cracks.
Step S160: and packaging the generated dense three-dimensional point cloud data by using geometric topology information to form a three-dimensional entity model, and constructing a rectangular weathered fracture network in the three-dimensional entity model formed by packaging based on the statistical result and the probability distribution model of the geometric characteristic parameters of each weathered fracture.
This step may more particularly comprise the steps of:
The dense three-dimensional point cloud data may be processed using point cloud data processing software (e.g., geomatic Studio software) to fit the dense three-dimensional point cloud data to a three-dimensional solid model.
In the step, the three-dimensional solid model can be obtained from the curved polygon by carrying out noise reduction and repair on the three-dimensional point cloud data to reconstruct the triangular curved patch, and further carrying out a series of software operations of repairing grid errors, model parameterization curved patch processing and rasterization through a grid doctor.
Further, a model which comprehensively reflects the spatial distribution of weathered cracks in a grotto injury zone can be generated in a three-dimensional solid model by combining three-dimensional modeling and simulation software (such as 3DEC (three-dimensional discrete unit method) software) with Monte Carlo (Monte Carlo) technology.
In some embodiments of the invention, a rectangular weathered fracture network model can be constructed in a three-dimensional entity model of a grotto injury region by developing a fish language in 3DEC software in a partitioning way, so that the geometric shape, the scale, the number and the spatial distribution characteristics of the weathered fracture in the injury region are truly reflected. The step of constructing a weathered fracture network model may include the steps of:
(1) And realizing the file format conversion of the three-dimensional entity model by developing an interface program.
For example, the.inp file exported by the geomic Studio software is converted into a.3 ddat format file that can be read by the 3DEC software using a development interface program.
(2) The method comprises the steps of obtaining statistical results and a probability distribution model of geometrical characteristic parameters of the weathered cracks, expressing the space positions of the weathered cracks by utilizing the occurrence, limiting the length and the width of the weathered cracks by utilizing the trace length and the development depth, limiting the number of the weathered cracks by utilizing the volume density, and constructing a rectangular weathered crack network model in a three-dimensional entity model in a partitioning mode by adopting 3DEC software and Monte Carlo technology.
The following describes a method for intelligent identification and three-dimensional reconstruction of grotto weathered cracks by taking a specific example, and the method comprises the following steps S01 to S06:
step S01: selecting a grotto top plate with very developed weathered fissures, erecting a Canon RP photographic camera, erecting the camera to a point position which is about 5-7m away from the surface of the top plate, and taking high-definition pictures covering a damaged area from a plurality of positions and angles by adopting a vertical grid mode, wherein the pictures are shown in figure 3. The longitudinal and transverse overlap rates of the taken photographs may be greater than 60% (first scale) and 40% (second scale), respectively. Close-range photogrammetry comprehensively acquires 292 high-resolution pictures. Here, the values of the camera position, the first ratio, and the second ratio are only examples, and the present invention is not limited thereto, and the first ratio may be equal to the second ratio.
Step S02: and importing Agisoft Metashape the shot high-resolution pictures into software to obtain the position information of the matching features in the plurality of pictures. Based on the motion restoration structure technology, the image is processed in Agisoft Metashape software to obtain dense three-dimensional point cloud data.
Three-dimensional point cloud data of about 46 ten thousand points are finally generated and used for refining and restoring the morphological characteristics of the damaged area.
Step S03: and clustering the generated dense three-dimensional point cloud data by utilizing a dynamic DBSCAN algorithm based on the generated three-dimensional point cloud data, and automatically identifying the weathered cracks on the rock mass surface of the damaged area based on a clustering result.
More specifically, the generated dense three-dimensional point cloud data is clustered in Matlab software by using a dynamic DBSCAN algorithm, and the planes of each weathered fracture surface are segmented one by one (namely, the clusters are segmented) based on the clustering result.
Step S04: fitting point cloud data of each weathered fracture surface through a plane fitting algorithm, and representing weathered fracture geometric feature parameters based on an analytical geometric theory, wherein the weathered fracture geometric feature parameters comprise: yield, trace length, spacing, and depth of development.
The process of obtaining the geometric characteristic parameters of the weathered slot specifically can refer to the previous description, and will not be repeated here.
Step S05: and dividing the representative rock mass damage area into subareas, characterizing and counting geometrical characteristic parameters such as the occurrence, trace length, spacing, depth and the like of each group of weathered cracks in the damage area in a partitioning manner, and deducing the volume density of the weathered cracks according to a corresponding probability distribution model.
Because the weathered cracks are unevenly distributed in the area, the grotto top plate is divided into three areas of north, middle and south according to the type and development quantity of the observed rock mass structure, as shown in fig. 4, geometric characteristic parameters such as the occurrence, trace length, spacing, development depth and the like of the rock mass crack surfaces in the divided areas are respectively counted and summarized, and the results are shown in (a) - (d) in fig. 5 and table 1. As shown in fig. 5 (a), the statistical fracture surface occurrence result is drawn on an isopycnic chart through Dips software, the dominant groups of the fracture surface are divided according to the density degree of poles of the fracture surface occurrence in the isopycnic chart distribution and a systematic clustering method, the north, middle and south fracture surfaces of the grotto roof can be respectively divided into 3, 2 and 1 dominant groups, namely, north 1-3#, middle 1-2#, south 1#, and the volume density lambda v of each fracture group is derived based on fracture space information. And then obtaining dominant zones of fracture surfaces of all subregions of the grotto by adopting a K-means clustering algorithm, wherein the dominant zones are subjected to Fisher distribution. The trace length and spacing of the fracture surface, as shown in (b) - (c) in fig. 5, mainly obey the negative index and logarithmic normal distribution, the development depth ranges from 0-9.2cm, and is mainly concentrated in 0-2.3cm, and the distribution situation is shown in (d) in fig. 5.
Further, the volumetric density λ v of each fracture group may be inferred from the fracture spacing information:
Wherein, The average pitch, average trace length, and average development depth of the weathered fissures of each fissure group are respectively, and λ, λ v are respectively the linear density and the volumetric density of the corresponding fissure group.
The results are shown in Table 1.
TABLE 1 probability distribution and numerical summary tables for geometric parameters of rock mass structures
Step S06: and carrying out optimization treatment on the constructed three-dimensional point cloud model, encapsulating by utilizing geometric topological information to form a three-dimensional solid model of the grotto injury area, and constructing a rectangular weathered crack network model in the three-dimensional solid model in a partitioning manner so as to truly reflect the geometric shape, scale, quantity and spatial distribution characteristics of the weathered cracks in the injury area.
Firstly, reducing noise and repairing dense three-dimensional point cloud data by using geomatic Studio software, reconstructing a triangular curved surface sheet, repairing grid errors by a grid doctor, performing model parameterization curved surface segmentation and rasterization, and packaging a corresponding curved surface into a three-dimensional solid model, wherein the dimensions of length, width and height are as follows: 10 m.times.6 m.times.5 m, this size being merely an example.
And then, utilizing 3DEC software to develop a fish language partition in a three-dimensional entity model of the grotto injury area to construct a rectangular weathered fracture network model. More specifically, the development interface program converts a file exported by the geomic Studio software (e.g., an inp format file) into a 3ddat format file that can be read by the 3DEC software; the regional range of the weathered fracture simulation in the three-dimensional solid model is defined through 3DEC software, and statistical results and probability distribution models of parameters such as the occurrence, trace length, depth and interval of the weathered fracture of the rock mass are input; random variables which obey the occurrence, trace length and development depth of the weathered cracks are generated by a Monte Carlo simulation method, and the development degree of the number of the cracks in the three-dimensional space can be measured due to the volume density lambda v of the cracks, and the volume density of the weathered cracks is used as a termination condition for generating the number in the three-dimensional solid model; a three-dimensional rectangular weathered fracture network is constructed in a grotto roof sub-area by combining 3DEC software with Monte Carlo technology, namely, the three horizontal areas are divided into three horizontal areas of north, middle and south sides along the roof plane, a model which comprehensively reflects spatial distribution information of the weathered fracture of the grotto roof is generated, and the geometric shape of the fracture surface is a rectangular shape controlled by trace length and depth, as shown in figure 6.
Based on the intelligent identification and three-dimensional reconstruction method of the grotto weathered cracks, aiming at the specificity of nondestructive detection of the grotto cultural relics, the method comprehensively acquires weathered crack pictures of a research damage area based on a non-contact photogrammetry mode, then fuses and matches the global pictures to construct a three-dimensional point cloud model, quickly and intelligently identifies the weathered cracks of the damage area on the basis, characterizes and counts geometric characteristic parameters of the weathered cracks, and finally constructs a three-dimensional entity model and generates a rectangular weathered crack network in a partitioning mode. Unlike traditional contact method, the invention mainly adopts photogrammetry technology, can finely capture the weathering fissure in the whole region of the grotto injury area, not only avoids the contact damage to the grotto cultural relics, but also realizes the rapid automatic acquisition of fissure geometric parameters; according to the characteristic that the weathering fracture in the grotto injury area is small in scale and rectangular, the three-dimensional weathering fracture network truly reflecting the grotto injury area is constructed in a partitioning mode on the basis of rapidly and intelligently acquiring and counting geometric characteristic parameters such as the occurrence, the trace length, the development depth and the interval of the weathering fracture.
According to the method, the refined representation of the weathered cracks in the grotto injury area is realized, the three-dimensional real visual effect of the cracks in the grotto injury area is realized in a statistical sense, the three-dimensional digital distribution information of the weathered cracks in the grotto injury area is obtained, and a powerful basis is provided for analysis of key blocks and overall stability of the grotto injury area and establishment of a reinforcement scheme. Through verification of field results, the technical method greatly improves the efficiency and accuracy of field rock mass structure identification and interpretation, the time for acquiring data in a 60m 2 area is less than 0.5 hour, and compared with the traditional manual measurement time, the method saves approximately 20 times; the relative error of trace length and interval interpretation is less than 1%, the error of attitude angle interpretation is less than 3 degrees, and the accuracy of the method is improved by nearly 3 times compared with that of the traditional manual measurement.
According to the feature that the weathering fracture in the grotto injury area is small in scale and rectangular, the three-dimensional weathering fracture network truly reflecting the grotto injury area is reconstructed in a partitioning mode on the basis of rapidly and intelligently acquiring and counting geometric feature parameters such as the occurrence, the trace length, the development depth and the interval of the weathering fracture. The three-dimensional fracture network model constructed in the past is often simulated into a disc shape, the scale and the morphological characteristics of the weathered fracture are difficult to truly reflect, and the rectangular weathered fracture with small scale and shallow development depth cannot be reconstructed. According to the method, the fine characterization of the weathered cracks in the grotto injury area is realized, the three-dimensional real visual effect of the cracks on the surface and in the grotto injury area is realized in a statistical sense, the three-dimensional digital distribution information of the weathered cracks in the grotto injury area is obtained, and a powerful basis is provided for analysis of key blocks and overall stability of the grotto injury area and establishment of a reinforcement scheme.
Correspondingly, the embodiment of the invention also provides a grotto weathering fracture intelligent identification and three-dimensional reconstruction system, which comprises computer equipment, wherein the computer equipment comprises a processor and a memory, the memory is stored with computer instructions, the processor is used for executing the computer instructions stored in the memory, and the system realizes the steps of the method in any embodiment when the computer instructions are executed by the processor.
The embodiment of the invention also provides a computer readable storage medium, on which a computer program is stored, which when being executed by a processor, realizes the steps of the edge computing server deployment method. The computer readable storage medium may be a tangible storage medium such as Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, floppy disks, hard disk, a removable memory disk, a CD-ROM, or any other form of storage medium known in the art.
Those of ordinary skill in the art will appreciate that the various illustrative components, systems, and methods described in connection with the embodiments disclosed herein can be implemented as hardware, software, or a combination of both. The particular implementation is hardware or software dependent on the specific application of the solution and the design constraints. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, a plug-in, a function card, or the like. When implemented in software, the elements of the invention are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine readable medium or transmitted over transmission media or communication links by a data signal carried in a carrier wave.
It should be understood that the invention is not limited to the particular arrangements and instrumentality described above and shown in the drawings. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and shown as examples. The method processes of the present invention are not limited to the specific steps described and shown, but various changes, modifications and additions, or the order between steps may be made by those skilled in the art after appreciating the spirit of the present invention.
In this disclosure, features that are described and/or illustrated with respect to one embodiment may be used in the same way or in a similar way in one or more other embodiments and/or in combination with or instead of the features of the other embodiments.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, and various modifications and variations can be made to the embodiments of the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. The intelligent identifying and three-dimensional reconstructing method for the grotto weathered cracks is characterized by comprising the following steps of:
Acquiring a plurality of close-range image images meeting the requirement of the picture overlapping rate, wherein the close-range image is acquired from a plurality of positions and angles of a representative rock damage area of a grotto by close-range shooting;
Importing the multiple close-range image images into three-dimensional modeling software for processing, and generating dense three-dimensional point cloud data based on a motion restoration structure technology;
clustering the generated dense three-dimensional point cloud data by using a dynamic clustering algorithm, dividing the plane where each weathered crack surface is located based on a clustering result, and identifying the weathered cracks on the rock mass surface in the damaged area based on a dividing result;
Fitting point cloud data of each weathered fracture surface through a plane fitting algorithm, and representing weathered fracture geometric feature parameters based on an analytical geometric theory, wherein the weathered fracture geometric feature parameters comprise: yield, trace length, spacing, and depth of development; the distance between two points which are perpendicular to the trace length and are positioned in the weathered crack surface is calculated and used as the development depth of the weathered crack;
Dividing a representative rock mass damaged area into subareas according to the quantity distribution density degree of the weathered cracks, and counting the geometric characteristic parameters of the weathered cracks in each subarea to obtain a probability distribution model of the geometric characteristic parameters of each weathered crack;
packaging the generated dense three-dimensional point cloud data by utilizing geometric topological information to form a three-dimensional entity model, and constructing a rectangular weathered fracture network in the three-dimensional entity model formed by packaging based on the statistical result and the probability distribution model of the geometric characteristic parameters of each weathered fracture;
The rectangular weathered fracture network is constructed by partitioning a three-dimensional solid model formed by packaging on the basis of the statistical result and the probability distribution model of the geometric characteristic parameters of each weathered fracture, and comprises the following steps:
Obtaining a statistical result and a probability distribution model of the geometrical characteristic parameters of the weathered slot;
The method comprises the steps of representing the space position of a weathered crack by utilizing a yield, defining the length and the width of the weathered crack by trace length and development depth, defining the number of the weathered crack by volume density and serving as a termination condition for generating the number in a three-dimensional solid model, and constructing a rectangular weathered crack network in a three-dimensional solid model by adopting a three-dimensional discrete unit method and combining a Monte Carlo technology in a partitioning way;
wherein, the linear density and the volume density of each weathered crack group are obtained based on the average interval and the average trace length of the weathered cracks of each weathered crack group according to the following formula:
Wherein s is, The average distance, average trace length and average development depth of the weathered cracks of each weathered crack group are respectively shown, and lambda v are respectively the linear density and the volume density of the corresponding weathered crack group.
2. The intelligent identifying and three-dimensional reconstructing method for the grotto weathered cracks according to claim 1, wherein the picture overlapping rate is required to be that the picture longitudinal overlapping rate and the picture transverse overlapping rate are respectively larger than a first proportion and a second proportion.
3. The intelligent grotto weathering fracture identification and three-dimensional reconstruction method according to claim 1, wherein the three-dimensional modeling software is Agisoft Metashape software and the dynamic clustering algorithm is a dynamic DBSCAN algorithm.
4. The intelligent grotto weathered slot identification and three-dimensional reconstruction method according to claim 1, wherein the clustering of the generated dense three-dimensional point cloud data by using a dynamic clustering algorithm and the segmentation of the plane in which each weathered slot surface is located based on the clustering result comprises:
determining: determining a neighborhood radius and a minimum inclusion point number;
Core point identification: traversing each point in the point cloud, identifying a core point in the point cloud based on the determined neighborhood radius and the minimum inclusion points, and incorporating the identified core point into a subset of core point clusters;
clustering: randomly taking out a core point which is not clustered from the core point clustering subset, incorporating the neighborhood point within the neighborhood radius range of the core point into the same sub-cluster, traversing all the core points in the sub-cluster, and incorporating the neighborhood point within the neighborhood radius range of the traversed core point into the same sub-cluster;
And repeating the clustering step until all core points are clustered, so as to divide the plane where each weathered crack surface is located.
5. The grotto weathered slot intelligent identification and three-dimensional reconstruction method according to claim 1, wherein the characterizing the weathered slot geometric feature parameters based on analytical geometry theory comprises:
fitting the point cloud data of the weathered fracture surface through a plane fitting algorithm to obtain a geometric equation of the weathered fracture surface;
Calculating the attitude of the weathered fracture surface based on the conversion relationship between the unit normal vector of the weathered fracture surface and the attitude of the weathered fracture surface;
Extracting and measuring the maximum distance between the vertexes of the polygon representing the weathered fracture surface as the trace length of the weathered fracture;
and calculating the vertical distance between two adjacent weathered fracture surfaces to be used as the distance between the two adjacent weathered fractures.
6. The intelligent identifying and three-dimensional reconstructing method for grotto weathered cracks according to claim 1, wherein the calculating the geometric feature parameters of the weathered cracks in each sub-area and obtaining the probability distribution model of the geometric feature parameters of each weathered crack comprises:
Counting the geometrical characteristic parameters of the weathered cracks in each subarea;
Drawing the counted weathered crack occurrence results on an equal density chart, dividing the dominant group number of the weathered crack occurrence according to the density degree of poles of the weathered crack occurrence in the equal density chart distribution and a systematic clustering method, and obtaining the dominant occurrence of the weathered crack occurrence of each subarea of the grotto by adopting a K-means clustering algorithm, so as to count and fit a probability distribution model of geometric characteristic parameters of the weathered crack occurrence.
7. A grotto weathered fracture intelligent identification and three-dimensional reconstruction system comprising a processor and a memory, wherein the memory has stored therein computer instructions for executing the computer instructions stored in the memory, which when executed by the processor, implement the steps of the method of any one of claims 1 to 6.
8. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the steps of the method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310481025.7A CN116645602B (en) | 2023-04-28 | 2023-04-28 | Method, system and storage medium for intelligent identification and three-dimensional reconstruction of grotto weathered cracks |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310481025.7A CN116645602B (en) | 2023-04-28 | 2023-04-28 | Method, system and storage medium for intelligent identification and three-dimensional reconstruction of grotto weathered cracks |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116645602A CN116645602A (en) | 2023-08-25 |
| CN116645602B true CN116645602B (en) | 2024-05-07 |
Family
ID=87622143
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310481025.7A Active CN116645602B (en) | 2023-04-28 | 2023-04-28 | Method, system and storage medium for intelligent identification and three-dimensional reconstruction of grotto weathered cracks |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116645602B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108763650A (en) * | 2018-04-28 | 2018-11-06 | 湘潭大学 | A kind of overlying strata mining induced fissure network model construction method |
| CN112784403A (en) * | 2020-12-31 | 2021-05-11 | 东北大学 | Numerical simulation method for establishing jointed rock mass discrete element model based on point cloud data |
| CN112965135A (en) * | 2021-01-28 | 2021-06-15 | 长安大学 | Nondestructive detection comprehensive method for spatial heterogeneous distribution of grotto cliff body fractures |
| 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 |
| CN114187423A (en) * | 2021-12-10 | 2022-03-15 | 国家能源投资集团有限责任公司 | Surrounding rock fracture reconstruction method, electronic equipment and storage medium for three-dimensional simulation test |
| CN115546116A (en) * | 2022-09-15 | 2022-12-30 | 山东大学 | Method and system for extracting and calculating spacing of discontinuous surface of fully-covered rock mass |
-
2023
- 2023-04-28 CN CN202310481025.7A patent/CN116645602B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108763650A (en) * | 2018-04-28 | 2018-11-06 | 湘潭大学 | A kind of overlying strata mining induced fissure network model construction method |
| CN112784403A (en) * | 2020-12-31 | 2021-05-11 | 东北大学 | Numerical simulation method for establishing jointed rock mass discrete element model based on point cloud data |
| CN112965135A (en) * | 2021-01-28 | 2021-06-15 | 长安大学 | Nondestructive detection comprehensive method for spatial heterogeneous distribution of grotto cliff body fractures |
| 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 |
| CN114187423A (en) * | 2021-12-10 | 2022-03-15 | 国家能源投资集团有限责任公司 | Surrounding rock fracture reconstruction method, electronic equipment and storage medium for three-dimensional simulation test |
| CN115546116A (en) * | 2022-09-15 | 2022-12-30 | 山东大学 | Method and system for extracting and calculating spacing of discontinuous surface of fully-covered rock mass |
Non-Patent Citations (6)
| Title |
|---|
| The Planar Shape of Rock Joints;Lianyang Zhang etc.;Rock Mech Rock Eng;第6节 * |
| 基于小型无人机遥感的单体地质灾害应急调查方法与实践;黄海峰，等;工程地质学报;第3节 * |
| 岩体节理几何特征研究及三维网络模拟;雷光伟;中国博士学位论文全文数据库（工程科技II辑）(第1期);摘要、第3章、第6章 * |
| 沙鹏，等.高陡边坡岩体结构信息无人机识别与离散元数值模拟.工程地质学报.2022,第2-4节. * |
| 艾小伟.Python程序设计-从基础开发到数据分析.机械工业出版社,2021,全文. * |
| 高陡边坡岩体结构信息无人机识别与离散元数值模拟;沙鹏，等;工程地质学报;第2-4节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116645602A (en) | 2023-08-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Berger et al. | State of the art in surface reconstruction from point clouds | |
| US9189862B2 (en) | Outline approximation for point cloud of building | |
| Campos et al. | A surface reconstruction method for in-detail underwater 3D optical mapping | |
| Wang et al. | Modeling indoor spaces using decomposition and reconstruction of structural elements | |
| GB2559157A (en) | Apparatus, method and system for alignment of 3D datasets | |
| CN113066162B (en) | Urban environment rapid modeling method for electromagnetic calculation | |
| Zhang et al. | A modified method of discontinuity trace mapping using three-dimensional point clouds of rock mass surfaces | |
| CN109242862A (en) | A kind of real-time digital surface model generation method | |
| Seers et al. | Extraction of three-dimensional fracture trace maps from calibrated image sequences | |
| CN110945568A (en) | System and method for evaluating 3D models | |
| Daghigh et al. | A critical review of discontinuity plane extraction from 3D point cloud data of rock mass surfaces | |
| Silvestre et al. | High-resolution digital 3D models of Algar do Penico Chamber: limitations, challenges, and potential | |
| Özdemir et al. | A multi-purpose benchmark for photogrammetric urban 3D reconstruction in a controlled environment | |
| Herráez et al. | Optimal modelling of buildings through simultaneous automatic simplifications of point clouds obtained with a laser scanner | |
| CN113345072A (en) | Multi-view remote sensing topographic image point cloud reconstruction method and system | |
| Palma et al. | Detection of geometric temporal changes in point clouds | |
| CN117706577A (en) | Ship size measurement method based on laser radar three-dimensional point cloud algorithm | |
| Elkhrachy | Feature extraction of laser scan data based on geometric properties | |
| Ni et al. | Applications of 3d-edge detection for als point cloud | |
| CN116645602B (en) | Method, system and storage medium for intelligent identification and three-dimensional reconstruction of grotto weathered cracks | |
| Budianti et al. | Background blurring and removal for 3d modelling of cultural heritage objects | |
| CN116051980A (en) | Building identification method, system, electronic equipment and medium based on oblique photography | |
| CN115375875A (en) | Grain pile concave-convex shape feature recognition method, equipment and medium based on three-dimensional shape | |
| Chen et al. | Intelligent interpretation of the geometric properties of rock mass discontinuities based on an unmanned aerial vehicle | |
| CN114187423A (en) | Surrounding rock fracture reconstruction method, electronic equipment and storage medium for three-dimensional simulation test |
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 |