CN118135141B - Pore three-dimensional reconstruction method and system based on rock image - Google Patents
Pore three-dimensional reconstruction method and system based on rock image Download PDFInfo
- Publication number
- CN118135141B CN118135141B CN202410342396.1A CN202410342396A CN118135141B CN 118135141 B CN118135141 B CN 118135141B CN 202410342396 A CN202410342396 A CN 202410342396A CN 118135141 B CN118135141 B CN 118135141B
- Authority
- CN
- China
- Prior art keywords
- image
- pore
- rock
- pixel
- dimensional reconstruction
- 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
- 239000011148 porous material Substances 0.000 title claims abstract description 80
- 239000011435 rock Substances 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 23
- 238000001514 detection method Methods 0.000 claims abstract description 22
- 230000004044 response Effects 0.000 claims abstract description 14
- 238000010606 normalization Methods 0.000 claims abstract description 10
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000012216 screening Methods 0.000 claims abstract description 7
- 238000010187 selection method Methods 0.000 claims abstract description 7
- 230000001629 suppression Effects 0.000 claims abstract description 7
- 238000012163 sequencing technique Methods 0.000 claims abstract description 4
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000001914 filtration Methods 0.000 claims description 13
- 239000011159 matrix material Substances 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 7
- 239000003086 colorant Substances 0.000 claims description 6
- 238000009499 grossing Methods 0.000 claims description 4
- 239000002245 particle Substances 0.000 claims description 4
- 238000009877 rendering Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 101100001674 Emericella variicolor andI gene Proteins 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 claims description 3
- 230000003993 interaction Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000012800 visualization Methods 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 abstract description 6
- 238000005259 measurement Methods 0.000 abstract description 3
- 238000004590 computer program Methods 0.000 description 6
- 238000000605 extraction Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005481 NMR spectroscopy Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000002591 computed tomography Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 239000013078 crystal Substances 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000004090 dissolution Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 229910052500 inorganic mineral Inorganic materials 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000011707 mineral Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004549 pulsed laser deposition Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004062 sedimentation Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- 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
- G06T17/10—Constructive solid geometry [CSG] using solid primitives, e.g. cylinders, cubes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/001—Texturing; Colouring; Generation of texture or colour
-
- 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
- G06T17/20—Finite element generation, e.g. wire-frame surface description, tesselation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G06T2207/20004—Adaptive image processing
-
- 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
- G06T2207/20112—Image segmentation details
- G06T2207/20164—Salient point detection; Corner detection
-
- 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
- G06T2207/30181—Earth observation
-
- 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
- Y02A90/30—Assessment of water resources
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Graphics (AREA)
- Remote Sensing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a pore three-dimensional reconstruction method and system based on a rock image, relates to the field of rock structure measurement, and aims to solve the problems that a machine learning method is required to reconstruct a rock image pore, high mathematical or computer professional requirements are required, labor and economic cost are high, and the method and system are difficult to be applied to a small rock pore reconstruction project. Comprising the following steps: dividing the acquired slice images of each rock sample into a group, and preprocessing; step two, carrying out graying, histogram equalization and normalization treatment on the image; thirdly, performing corner detection by adopting a Harris corner detection algorithm, sequencing Harris response values, selecting key points by setting the number of key points, and screening the selected key points by adopting a non-maximum suppression method; dividing the boundary of the image pore by a self-adaptive threshold selection method, and extracting pore characteristics; and fifthly, constructing a pore three-dimensional reconstruction model by adopting a movable cube algorithm. The method is used for three-dimensional reconstruction of the rock image pore.
Description
Technical Field
The invention relates to the technical field of rock structure measurement, in particular to a pore three-dimensional reconstruction method and system based on rock images.
Background
Rock porosity refers to pores or voids present in the rock, the formation of which is typically due to a number of factors during rock formation and deterioration, including sedimentation, dissolution, shrinkage of mineral crystals, and the like. The size, shape and distribution of which have a significant impact on the nature and use of the rock.
When rock pore related measurements are involved, there are mainly electron microscope scans, nuclear magnetic resonance, CT scans, etc., but the ability to reflect the rock pore conditions is not sufficient. Neural network technology is utilized to process and analyze the data to facilitate extraction of information about pore structure. Machine learning and three-dimensional modeling rendering techniques are typically employed to effect restoration and reconstruction of the pores. The flow of the method often includes cleaning, normalizing and processing the data to ensure data quality and consistency. In preparing a data set for machine learning training, it is necessary to select an appropriate machine learning algorithm, such as a convolutional neural network, a support vector machine, etc., and perform model training using a labeled data set, which requires a lot of costs related to hardware requirements, training time, data acquisition, labeling, etc. Furthermore, the need for operators to have the skilled operations and associated expertise of machine learning makes some small rock pore reconstruction projects burdensome.
Disclosure of Invention
The invention aims to solve the technical problems that:
In the prior art, the rock image pore reconstruction is carried out by a machine learning method, higher mathematical or computer professional requirements are required, the labor and economic cost is higher, and the method and the system are difficult to be applied to small rock pore reconstruction projects, so that the invention provides a rock image-based pore three-dimensional reconstruction method and system.
The invention adopts the technical scheme for solving the technical problems:
the invention provides a pore three-dimensional reconstruction method based on rock images, which comprises the following steps:
Firstly, slicing a rock sample, collecting microscopic images of particles and pores of slicing the rock sample, dividing slice images of each rock sample into a group, and preprocessing image data;
Step two, firstly carrying out gray processing on an image, then removing image noise through median filtering, enhancing details and adaptability of the image through histogram equalization, and finally mapping pixel values of the image to a specific range through normalization processing;
Thirdly, performing corner detection by adopting a Harris corner detection algorithm, sequencing Harris response values, selecting key points by setting the number of the key points, and further screening the selected key points by adopting a non-maximum suppression method;
dividing the boundary of the image aperture by a self-adaptive threshold selection method, extracting aperture characteristics, and giving different colors to the aperture according to different attributes of the aperture to generate a pseudo-color image;
And fifthly, constructing a pore three-dimensional reconstruction model of the grid structure by adopting a moving cube algorithm according to the pseudo-color images of each group of slices.
Further, the preprocessing of the image data in the first step includes clipping and scaling the images, and smoothing each group of images by gaussian filtering to remove high-frequency noise, and the specific calculation method is as follows:
Where I smooth (x, y) is the smoothed intensity at the pixel (x, y) after gaussian filtering, k is the size of the filter, w (I, j) is the weight given to the pixel at the relative position in the filter, x i、xj represents the spatial distance between the pixels, I and j are the pixel distances relative to the center of the filter, σ 0 is the standard deviation of the pixels;
further, the calculation method of histogram equalization in the second step is as follows:
wherein s is the image gray level after histogram equalization, r is the original image gray level, and P (r) is the probability density of random variable r, namely:
Where μ is the mean of the pixels and σ is the standard deviation of the pixels, i.e.:
Where M and N are the height and width of the image and r ij is the gray value at pixel (i, j).
Further, in the histogram equalization process, 50% of pixel values of the image are set to be smaller than 128, 25% of pixel values are set to be smaller than 64, and the gray level of the histogram of the image is scattered from being concentrated on a small part of gray level to having a certain coverage in all gray levels.
Further, the normalization calculation method in the second step is as follows:
Where x' is the normalized pixel value, x is the pixel value before normalization, x max represents the maximum pixel value, and x min represents the minimum pixel value.
Further, the third step comprises the following steps:
Firstly, calculating the gradient of each pixel point of the image obtained in the second step through a first-order gradient operator; then, carrying out corner detection by a Harris corner detection algorithm, wherein the corner detection method specifically comprises the following steps: traversing the pixel gradient matrix image through a local window, and calculating the curvature C of the pixel point by adopting a Hessian matrix, namely:
wherein trace (M) is the trace of the gradient matrix and det (M) is the determinant of the gradient matrix;
For each pixel in the image, calculating a local characteristic response value of the pixel, setting a threshold value of the local characteristic response value, and taking a pixel point higher than the threshold value as a corner point;
finally, sorting the Harris response values, and selecting key points by setting the number of the key points; and further screening the selected key points by adopting a non-maximum suppression method.
Further, the fourth step comprises the following steps:
The boundaries of the image pores are segmented by an adaptive threshold selection method, namely: determining an optimal gray threshold, dividing an image into a foreground and a background, and calculating the inter-class variance of the segmented foreground and background to maximize the variance of the segmented two classes, wherein the specific calculation method comprises the following steps:
Sigma between2 (t ) is the variance after segmentation, t is the threshold, P (t) and The probabilities of foreground and background at the threshold t, μ (t) andIs the average gray value of the foreground and the background;
The shape, size and distribution characteristics of the pores are extracted, and different colors are given to the pores according to different properties of the pores, so that a pseudo-color image is generated.
Further, the fifth step comprises the following steps:
Dividing the generated pseudo-color image into a plurality of grid voxels, converting the voxel grid into a three-dimensional grid with surface information, converting voxel data into vertexes and faces of the grid, and performing surface fitting on the voxels; acquiring density and gray information of each voxel, and drawing a histogram of voxel data through the voxel information to determine a pore scalar value range; and generating an equivalent surface of the three-dimensional structure of the rock pore in the determined pore scalar value range by utilizing a moving cube algorithm, integrating the whole set of pseudo-color images to form a three-dimensional reconstruction model of the pore, and simultaneously presenting the characteristics of shape and color.
Further, the fifth step further comprises: and adopting a VTK rendering window to realize real-time interaction and visualization of the pore three-dimensional reconstruction model.
A rock image-based three-dimensional pore reconstruction system having program modules corresponding to the steps of any one of the above-described aspects, the steps of the rock image-based three-dimensional pore reconstruction method described above being performed at run-time.
Compared with the prior art, the invention has the beneficial effects that:
The invention relates to a pore three-dimensional reconstruction method and a pore three-dimensional reconstruction system based on a rock image, which adopt graying, median filtering, histogram equalization and normalization to improve the image quality and minimize noise; the key features in the image are extracted through operations such as threshold segmentation and corner detection, and the Harris corner detection algorithm is creatively improved, so that feature points can be automatically ordered according to the response degree, and the improved algorithm shows excellent performance in a feature point matching stage, so that the number of custom feature points is efficiently obtained; and finally, introducing a moving cube algorithm to restore the rock pore structure with high precision.
The invention adopts the computer vision technology to process the image, thereby remarkably reducing the cost, saving the training time of the neural network method, reducing the requirement on hardware and realizing the high-efficiency processing of the small rock pore reconstruction project. The invention realizes the reconstruction of the rock image pore in a low-cost mode, does not need higher mathematical or computer professional requirements, greatly reduces the labor and economic cost, and is completely suitable for small rock pore reconstruction projects through verification.
The method can realize high-resolution three-dimensional image reconstruction, provides a new view angle for geological research, and brings great potential to the fields of resource development, environmental protection and the like. The method provided by the invention verifies the technical effect and practicality claimed by the invention through simulation experiments and practical application.
Drawings
FIG. 1 is a flow chart of a method for three-dimensional reconstruction of a pore based on a rock image in an embodiment of the invention;
FIG. 2 is a partial rock image used in the pore identification method according to an embodiment of the present invention;
FIG. 3 is a schematic representation of graying of rock images in an embodiment of the invention;
FIG. 4 is a Harris feature extraction flow chart in an embodiment of the invention;
FIG. 5 is a schematic view of a basic model of a mobile cube in an embodiment of the invention;
FIG. 6 is a histogram equalization chart of a rock image in an embodiment of the invention;
FIG. 7 is a graph of feature extraction using Harris algorithm in an embodiment of the invention;
FIG. 8 is a schematic view of image segmentation in an embodiment of the present invention;
FIG. 9 is a schematic diagram of extraction of pore feature points in an embodiment of the present invention;
FIG. 10 is a schematic representation of the pore results in an embodiment of the present invention.
Detailed Description
In the description of the present invention, it should be noted that the terms "first," "second," and "third" mentioned in the embodiments of the present invention are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first", "a second", or a third "may explicitly or implicitly include one or more such feature.
In order that the above objects, features and advantages of the invention will be readily understood, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings.
The specific embodiment I is as follows: as shown in fig. 1, the invention provides a pore three-dimensional reconstruction method based on rock images, which comprises the following steps:
Firstly, slicing a rock sample, collecting microscopic images of particles and pores of slicing the rock sample, dividing slice images of each rock sample into a group, and preprocessing image data;
Step two, firstly carrying out gray processing on an image, then removing image noise through median filtering, enhancing details and adaptability of the image through histogram equalization, and finally mapping pixel values of the image to a specific range through normalization processing;
Thirdly, performing corner detection by adopting a Harris corner detection algorithm, sequencing Harris response values, selecting key points by setting the number of the key points, and further screening the selected key points by adopting a non-maximum suppression method;
dividing the boundary of the image aperture by a self-adaptive threshold selection method, extracting aperture characteristics, and giving different colors to the aperture according to different attributes of the aperture to generate a pseudo-color image;
And fifthly, constructing a pore three-dimensional reconstruction model of the grid structure by adopting a moving cube algorithm according to the pseudo-color images of each group of slices.
In step one of this embodiment, rock flake images are collected by preparing flakes of different sizes to meet specific requirements; rock flakes were prepared to 10mm x 10mm in size and subsequently scanned across the full field of view using a zeiss EVO15 type scanning electron microscope to obtain microscopic rock images clearly showing rock particles and pores, as shown in figure 2.
In the second step of the present embodiment, the gray scale processing retains the brightness information of the rock sample, and reduces the complexity of the data, and is implemented by using a simple average value calculation, so that the gray scale value of each pixel in the image is equal to the average value of the red, green and blue channel values. The median filtering process replaces the value of each pixel with the median of the pixel values in its neighborhood window, replaces the pixel value with the median of the pixel values, suppresses noise while maintaining detail. The odd number in the window is arranged according to the order of the sizes, and the number at the center is used as a processing result, so that the image is smoothed and the edge information of the image is reserved. The median filtering does not adopt linear weighted average, but directly selects a median, and compared with a linear filter, the median filtering can remove noise and simultaneously can maintain the edge information of an image. So that the pixel values at the edges are not easily affected by smoothing. And it is independent of the statistical properties of the image and therefore appears relatively robust in processing different types of rock images.
And a specific embodiment II: the first step of preprocessing the image data, including clipping and scaling the images, and smoothing each group of images by gaussian filtering to remove high-frequency noise, comprises the following specific calculation steps:
Where I smooth (x, y) is the smoothed intensity at the pixel (x, y) after gaussian filtering, k is the size of the filter, w (I, j) is the weight given to the pixel at the relative position in the filter, x i、xj represents the spatial distance between the pixels, I and j are the pixel distances relative to the center of the filter, and σ 0 is the standard deviation of the pixels. The other embodiments are the same as those of the first embodiment.
And a third specific embodiment: as shown in fig. 6, the histogram equalization calculation method in the second step is as follows:
wherein s is the image gray level after histogram equalization, r is the original image gray level, and P (r) is the probability density of random variable r, namely:
Where μ is the mean of the pixels and σ is the standard deviation of the pixels, i.e.:
Where M and N are the height and width of the image and r ij is the gray value at pixel (i, j). This embodiment is otherwise identical to the second embodiment.
In this embodiment, the histogram equalization firstly stretches and compresses the brightness level of the image, and controls the gray value of the pixel point according to the histogram to change the pixel between black and white, so that the more concentrated gray level distribution is wider. Belonging to the point operation range, the normalized original image gray level and the image gray level after histogram equalization are respectively represented by r and s, namely, any r in the [0,1] interval can generate a corresponding s through a transformation function T (r), wherein the formula is s=T (r)
And a specific embodiment IV: in the histogram equalization process, 50% of pixel values of an image are set to be smaller than 128, 25% of pixel values are set to be smaller than 64, and the gray level of the histogram of the image is scattered from being concentrated on a small part of gray level to having a certain coverage in all gray levels. The resolution of the brightness level is improved, which helps to more accurately represent the brightness variation in the image. This embodiment is otherwise identical to the third embodiment.
Fifth embodiment: the normalization calculation method in the second step is as follows:
Where x' is the normalized pixel value, x is the pixel value before normalization, x max represents the maximum pixel value, and x min represents the minimum pixel value. This embodiment is otherwise identical to the fourth embodiment.
The embodiment ensures that the pixel values of the images are in the same range, ensures the consistency of the scales and improves the generalization capability.
Specific embodiment six: as shown in fig. 4 and 7, step three includes the following processes:
Firstly, calculating the gradient of each pixel point of the image obtained in the second step through a first-order gradient operator; then, carrying out corner detection by a Harris corner detection algorithm, wherein the corner detection method specifically comprises the following steps: traversing the pixel gradient matrix image through a local window, and calculating the curvature C of the pixel point by adopting a Hessian matrix, namely:
wherein trace (M) is the trace of the gradient matrix and det (M) is the determinant of the gradient matrix;
For each pixel in the image, calculating a local characteristic response value of the pixel, setting a threshold value of the local characteristic response value, and taking a pixel point higher than the threshold value as a corner point;
finally, the Harris response values are sorted, and the key points are selected by setting the number of key points, and the result is shown in fig. 9. And further screening the selected key points by adopting a non-maximum suppression method. This embodiment is otherwise identical to embodiment five.
In this embodiment, the local window is used to move over the image, and it is determined whether the gradation has changed significantly. If there is a large variation in the gray values (on the gradient map) within a window, then corner points are present in the region where this window is located. By establishing a model, the center of a window is located at a position (x, y) of the gray image, the gray value of a pixel at the position is I (x, y), if the window moves by small displacements u and v in the x and y directions respectively to a new position (x+u, y+v), the I (x+u, y+v) -I (x, y) is the gray value change caused by the window movement, namely the feature to be extracted.
The implementation effect of the Harris corner detection algorithm is evaluated by adopting recall rate, accuracy and F1 score:
wherein True Positives denotes the number of correctly detected corner points, FALSE NEGATIVES denotes the number of actually present but not detected corner points.
In the embodiment, the gradient of each pixel point of the image is calculated through a first-order gradient operator, and then the corner detection is carried out through a Harris corner detection algorithm, so that higher accuracy and recall rate can be realized.
Specific embodiment seven: as shown in fig. 8, step four includes the following procedure:
The boundaries of the image pores are segmented by an adaptive threshold selection method, namely: determining an optimal gray threshold, dividing an image into a foreground and a background, and calculating the inter-class variance of the segmented foreground and background to maximize the variance of the segmented two classes, wherein the specific calculation method comprises the following steps:
sigma between2(t) is the variance after segmentation, t is the threshold, P (t) and The probabilities of foreground and background at the threshold t, μ (t) andIs the average gray value of the foreground and the background;
The shape, size and distribution characteristics of the pores are extracted, and different colors are given to the pores according to different properties of the pores, so that a pseudo-color image is generated. This embodiment is otherwise identical to the sixth embodiment.
Specific embodiment eight: as shown in fig. 5, the fifth step includes the following procedure:
Dividing the generated pseudo-color image into a plurality of grid voxels, converting the voxel grid into a three-dimensional grid with surface information, converting voxel data into vertexes and faces of the grid, and performing surface fitting on the voxels; acquiring density and gray information of each voxel, and drawing a histogram of voxel data through the voxel information to determine a pore scalar value range; and generating an equivalent surface of the three-dimensional structure of the rock pore in the determined pore scalar value range by utilizing a moving cube algorithm, integrating the whole set of pseudo-color images to form a three-dimensional reconstruction model of the pore, and simultaneously presenting the characteristics of shape and color. This embodiment is otherwise identical to embodiment seven.
Embodiment nine: the fifth step also comprises: adopting a VTK rendering window to realize real-time interaction and visualization of the pore three-dimensional reconstruction model; the results are shown in FIG. 10. This embodiment is otherwise identical to embodiment eight.
Specific embodiment ten: a rock image-based three-dimensional pore reconstruction system having program modules corresponding to the steps of any of the embodiments described above, the steps of the rock image-based three-dimensional pore reconstruction method described above being performed at run-time.
The pore three-dimensional reconstruction method (algorithm) based on the rock image is a technical kernel of the bottom layer, and various products can be derived based on the algorithm.
The method provided by the invention is used for developing a pore three-dimensional reconstruction system based on the rock image by using a program language, the system is provided with a program module corresponding to the steps of the technical scheme, and the steps in the pore three-dimensional reconstruction method based on the rock image are executed during operation.
A computer program of a developed system (software) is stored on a computer readable storage medium, which computer program is configured to implement the steps of the above-described rock image-based pore three-dimensional reconstruction method when called by a processor. I.e. the invention is embodied on a carrier as a computer program product.
Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASIC (application specific integrated circuit), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
The computing programs (also referred to as programs, software applications, or code) in the present invention include machine instructions for a programmable processor, and can be implemented in a high-level procedural and/or object-oriented programming language, and/or in assembly/machine language. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, programmable logic devices, PLDs) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.
Although the present disclosure is disclosed above, the scope of the present disclosure is not limited thereto. Various changes and modifications may be made by one skilled in the art without departing from the spirit and scope of the disclosure, and such changes and modifications would be within the scope of the disclosure.
Claims (8)
1. The pore three-dimensional reconstruction method based on the rock image is characterized by comprising the following steps of:
Firstly, slicing a rock sample, collecting microscopic images of particles and pores of slicing the rock sample, dividing slice images of each rock sample into a group, and preprocessing image data;
Step two, firstly carrying out gray processing on an image, then removing image noise through median filtering, enhancing details and adaptability of the image through histogram equalization, and finally mapping pixel values of the image to a specific range through normalization processing;
the calculation method of the histogram equalization comprises the following steps:
wherein s is the image gray level after histogram equalization, r is the original image gray level, and P (r) is the probability density of random variable r, namely:
Where μ is the mean of the pixels and σ is the standard deviation of the pixels, i.e.:
Where M and N are the height and width of the image, and r ij is the gray value at pixel (i, j);
Thirdly, performing corner detection by adopting a Harris corner detection algorithm, sequencing Harris response values, selecting key points by setting the number of the key points, and further screening the selected key points by adopting a non-maximum suppression method; the method comprises the following steps:
Firstly, calculating the gradient of each pixel point of the image obtained in the second step through a first-order gradient operator; then, carrying out corner detection by a Harris corner detection algorithm, wherein the corner detection method specifically comprises the following steps: traversing the pixel gradient matrix image through a local window, and calculating the curvature C of the pixel point by adopting a Hessian matrix, namely:
Wherein trace (H) is the trace of the gradient matrix and det (H) is the determinant of the gradient matrix;
For each pixel in the image, calculating a local characteristic response value of the pixel, setting a threshold value of the local characteristic response value, and taking a pixel point higher than the threshold value as a corner point;
Finally, sorting the Harris response values, and selecting key points by setting the number of the key points; further screening the selected key points by adopting a non-maximum suppression method;
dividing the boundary of the image aperture by a self-adaptive threshold selection method, extracting aperture characteristics, and giving different colors to the aperture according to different attributes of the aperture to generate a pseudo-color image;
And fifthly, constructing a pore three-dimensional reconstruction model of the grid structure by adopting a moving cube algorithm according to the pseudo-color images of each group of slices.
2. The method of claim 1, wherein the preprocessing the image data in the first step includes clipping and scaling the images, and smoothing each group of images by gaussian filtering to remove high frequency noise, and the specific calculation method is as follows:
Where I smooth (x, y) is the smoothed intensity at the pixel (x, y) after gaussian filtering, k is the size of the filter, w (I, j) is the weight given to the pixel at the relative position in the filter, x i、yj represents the spatial distance between the pixels, I and j are the pixel distances relative to the center of the filter, and σ 0 is the standard deviation of the pixels.
3. The method according to claim 2, wherein 50% of the pixels of the image are set to be less than 128 and 25% of the pixels are set to be less than 64 in the histogram equalization process, so that the gray level of the histogram of the image is dispersed from being concentrated in a small part of the gray level to having a certain coverage in all gray levels.
4. A method for three-dimensional reconstruction of a pore based on a rock image according to claim 3, wherein in the second step, the normalized calculation method is as follows:
Where x' is the normalized pixel value, x is the pixel value before normalization, x max represents the maximum pixel value, and x min represents the minimum pixel value.
5. The method of three-dimensional reconstruction of a pore based on a rock image according to claim 4, wherein step four comprises the following steps:
The boundaries of the image pores are segmented by an adaptive threshold selection method, namely: determining an optimal gray threshold, dividing an image into a foreground and a background, and calculating the inter-class variance of the segmented foreground and background to maximize the variance of the segmented two classes, wherein the specific calculation method comprises the following steps:
σ between2(t) is the variance after segmentation, t is the threshold, P (t) and Probability of foreground and background at threshold t, respectively, μ (t) andIs the average gray value of the foreground and the background;
The shape, size and distribution characteristics of the pores are extracted, and different colors are given to the pores according to different properties of the pores, so that a pseudo-color image is generated.
6. The method of three-dimensional reconstruction of a pore based on a rock image according to claim 5, wherein step five comprises the following steps:
Dividing the generated pseudo-color image into a plurality of grid voxels, converting the voxel grid into a three-dimensional grid with surface information, converting voxel data into vertexes and faces of the grid, and performing surface fitting on the voxels; acquiring density and gray information of each voxel, and drawing a histogram of voxel data through the voxel information to determine a pore scalar value range; and generating an equivalent surface of the three-dimensional structure of the rock pore in the determined pore scalar value range by utilizing a moving cube algorithm, integrating the whole set of pseudo-color images to form a three-dimensional reconstruction model of the pore, and simultaneously presenting the characteristics of shape and color.
7. The method of three-dimensional reconstruction of a pore based on a rock image of claim 6, wherein step five further comprises: and adopting a VTK rendering window to realize real-time interaction and visualization of the pore three-dimensional reconstruction model.
8. A rock image-based pore three-dimensional reconstruction system, characterized in that the system has program modules corresponding to the steps of any one of the preceding claims 1 to 7, which, in operation, perform the steps of the above-mentioned rock image-based pore three-dimensional reconstruction method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410342396.1A CN118135141B (en) | 2024-03-25 | 2024-03-25 | Pore three-dimensional reconstruction method and system based on rock image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410342396.1A CN118135141B (en) | 2024-03-25 | 2024-03-25 | Pore three-dimensional reconstruction method and system based on rock image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118135141A CN118135141A (en) | 2024-06-04 |
| CN118135141B true CN118135141B (en) | 2024-10-29 |
Family
ID=91237442
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410342396.1A Active CN118135141B (en) | 2024-03-25 | 2024-03-25 | Pore three-dimensional reconstruction method and system based on rock image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118135141B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111815757A (en) * | 2019-06-29 | 2020-10-23 | 浙江大学山东工业技术研究院 | Three-dimensional reconstruction method for large component based on image sequence |
| CN112150456A (en) * | 2020-09-30 | 2020-12-29 | 内蒙古科技大学 | Key point detection method based on four-point detection |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014003596A1 (en) * | 2012-06-26 | 2014-01-03 | Schlumberger, Holdings Limited | A method for building a 3d model of a rock sample |
| CN106373168A (en) * | 2016-11-24 | 2017-02-01 | 北京三体高创科技有限公司 | Medical image based segmentation and 3D reconstruction method and 3D printing system |
| CN108335319A (en) * | 2018-02-06 | 2018-07-27 | 中南林业科技大学 | A kind of image angle point matching process based on adaptive threshold and RANSAC |
| CN110490924B (en) * | 2019-07-16 | 2022-07-01 | 西安理工大学 | Light field image feature point detection method based on multi-scale Harris |
| CN111047555B (en) * | 2019-11-13 | 2023-10-17 | 鞍钢集团矿业有限公司 | Ore image granularity detection algorithm based on image processing technology |
| CN111161252B (en) * | 2019-12-31 | 2022-03-25 | 山东大学 | Rock mass structure detection and dangerous stone detection system and method |
| CN112614167A (en) * | 2020-12-17 | 2021-04-06 | 西南石油大学 | Rock slice image alignment method combining single-polarization and orthogonal-polarization images |
| CN117611485B (en) * | 2024-01-24 | 2024-04-02 | 西南石油大学 | Three-dimensional core permeability prediction method based on space-time diagram neural network |
-
2024
- 2024-03-25 CN CN202410342396.1A patent/CN118135141B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111815757A (en) * | 2019-06-29 | 2020-10-23 | 浙江大学山东工业技术研究院 | Three-dimensional reconstruction method for large component based on image sequence |
| CN112150456A (en) * | 2020-09-30 | 2020-12-29 | 内蒙古科技大学 | Key point detection method based on four-point detection |
Non-Patent Citations (1)
| Title |
|---|
| 基于Marching Cubes算法的数字岩心建模方法研究;赵玲等;石油机械;20181031;第46卷(第10期);第97-102页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118135141A (en) | 2024-06-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113781402B (en) | Method and device for detecting scratch defects on chip surface and computer equipment | |
| CN109978839B (en) | Method for detecting wafer low-texture defects | |
| CN107833220B (en) | Fabric defect detection method based on deep convolutional neural network and visual saliency | |
| CN103632361B (en) | An image segmentation method and a system | |
| CN106296653A (en) | Brain CT image hemorrhagic areas dividing method based on semi-supervised learning and system | |
| CN105335972B (en) | Knitted fabric defect detection method based on small echo contourlet transform and vision significance | |
| CN110570440A (en) | Image automatic segmentation method and device based on deep learning edge detection | |
| EP1789920A1 (en) | Feature weighted medical object contouring using distance coordinates | |
| CN110675464A (en) | Medical image processing method and device, server and storage medium | |
| CN112614062A (en) | Bacterial colony counting method and device and computer storage medium | |
| CN106327451A (en) | Image restorative method of ancient animal fossils | |
| Srinivas et al. | Remote sensing image segmentation using OTSU algorithm | |
| CN106599891A (en) | Remote sensing image region-of-interest rapid extraction method based on scale phase spectrum saliency | |
| CN110070545B (en) | Method for automatically extracting urban built-up area by urban texture feature density | |
| CN114862889A (en) | Road edge extraction method and device based on remote sensing image | |
| CN108830883B (en) | Visual attention SAR image target detection method based on super-pixel structure | |
| CN110310263B (en) | SAR image residential area detection method based on significance analysis and background prior | |
| Sofou et al. | Generalized flooding and multicue PDE-based image segmentation | |
| CN107945164B (en) | Textile flaw detection method based on peak threshold, rotational alignment and composite character | |
| CN117635615B (en) | Defect detection method and system for realizing punching die based on deep learning | |
| CN118135141B (en) | Pore three-dimensional reconstruction method and system based on rock image | |
| CN117830623A (en) | Image positioning area selection method, device, equipment and storage medium | |
| CN114241150B (en) | Water area data preprocessing method in oblique photography modeling | |
| CN113592829B (en) | Deep learning sediment particle identification method and device based on segmentation and recombination | |
| CN110378354B (en) | Jacquard fabric picture color extraction method based on tissue filtering algorithm |
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 |