A 3D modeling method and system based on original geological cataloging

Abstract

The present application discloses a three-dimensional modeling method and system based on an original geological catalog. The method comprises: scanning the original geological catalog to obtain a scanned image, cropping the scanned image to obtain a geological catalog map; performing image processing on the geological catalog map; extracting boundaries from the image-processed geological catalog map and vectorizing the extracted boundaries; constructing the vectorized boundaries into three-dimensional geological catalog boundaries based on the spatial position relationship of the three walls in the original geological catalog; performing surface processing on the three-dimensional geological catalog boundaries to obtain a three-dimensional model, wherein the surface processing is used to add a surface to the three-dimensional geological catalog boundaries. The present application solves the problem of poor effect of three-dimensional mine geological models caused by the failure to perform corresponding processing on the original geological maps in the prior art, thereby improving the quality of geological catalog modeling.

Description

Technical Field

[0001] The present application relates to the field of mine geological cataloging, and more specifically, to a three-dimensional modeling method and system based on original geological cataloging. Background Art

[0002] Mine geological cataloging is the process of observing, recording, and sketching geological phenomena in mine exploration projects and shaft and tunnel engineering through text, charts, and other information. This work provides a strong basis for determining the spatial distribution of ore bodies, the boundary between ore and rock, and the distribution of mine grades.

[0003] Traditional geological cataloging methods often rely on original geological drawings. This is labor-intensive, with limited feature recognition speed, low accuracy, and difficulty in storage, making it difficult to achieve modern, efficient work. Subsequently, two-dimensional CAD mapping technology was developed to visualize the spatial structural relationships of ore bodies. However, this method is significantly influenced by the subjective factors of the draftsman, making it difficult to effectively guarantee the accuracy and timeliness of the drawings.

[0004] With the development of digital mining technology, the use of 3D modeling for batch processing of raw geological catalogs has matured. In actual geological cataloging, 3D geological modeling can significantly reduce the concealment of underground engineering, intuitively reflect the spatial distribution of geological bodies, and effectively manage geological spatial information. For example, Zhang Haitao et al. eliminated intrusive non-mining rock masses, ensuring that the boundaries of geologically cataloged ore bodies more closely aligned with actual ore bodies. Sun Huanying et al., through comparative analysis of existing geological exploration software, summarized the main theories and methods of digital geological cataloging. Wu Yongping et al., based on close-range photogrammetry, used a geological cataloger to display the cataloging process and results, significantly improving cataloging efficiency. Yang Jianhua et al. utilized digital image geological cataloging methods, implementing computer-assisted cataloging through a series of methods such as cross-section calculation and image distortion correction. Zhao Jiechen conducted in-depth research on geological vectorization technology and grid deformation techniques used in geological structure modeling, establishing a geological interpretation platform system to serve mine geological cataloging.

[0005] The aforementioned studies provide detailed analysis and application of mine geological cataloging. While all of these techniques require the use of original geological maps, they lack appropriate processing. For example, they fail to consider the impact of contamination and noise in the original maps during the cataloging process. This makes it difficult to achieve ideal vectorization results and ore-rock boundaries, and to share and connect the collected data. These factors hinder industrial mining operations such as ore body delineation, mining design, and calculation of dilution losses. Summary of the Invention

[0006] The embodiments of the present application provide a three-dimensional modeling method and system based on original geological cataloging, so as to at least solve the problem in the prior art of poor effect of mine geological three-dimensional modeling caused by failure to perform corresponding processing on original geological maps.

[0007] According to one aspect of the present application, a three-dimensional modeling method based on an original geological catalog is provided, characterized in that it includes: scanning the original geological catalog to obtain a scanned image, cropping the scanned image to obtain a geological catalog map, wherein the cropping is used to obtain a graphic portion in the scanned image; performing image processing on the geological catalog map, wherein the image processing is used to perform noise reduction and refinement processing on the geological catalog map, and the refinement processing is used to adjust the pixel width of the lines of the geological catalog map; extracting boundaries from the image-processed geological catalog map, and vectorizing the extracted boundaries; constructing the vectorized boundaries into three-dimensional geological catalog boundaries according to the spatial position relationship of the three walls in the original geological catalog, wherein the three-dimensional geological catalog boundaries are used to display the real form of the three-dimensional space; performing surface processing on the three-dimensional geological catalog boundaries to obtain a three-dimensional model, wherein the surface processing is used to add a surface to the three-dimensional geological catalog boundaries.

[0008] Furthermore, the image processing of the geological log map includes: binarizing the geological log map; corroding the image obtained after the binarization process using a 3×3 matrix, and then dilating the image using a 3×3 matrix; and refining the image after the corrosion and dilation processes.

[0009] Furthermore, performing thinning processing on the image that has undergone the erosion and dilation processing includes: first performing thinning processing on the image that has undergone the erosion and dilation processing by using a table lookup method, and then performing thinning processing on the image that has undergone the erosion and dilation processing by using a Rosenfeld method.

[0010] Furthermore, extracting boundaries from the image-processed geological catalog map and vectorizing the extracted boundaries includes: obtaining a first boundary from the image-processed geological catalog map by sketching, and vectorizing the first boundary; and thinning the vectorized first boundary to obtain the boundary.

[0011] Furthermore, the boundaries include: top and bottom plate boundaries, two wall boundaries and geological logging boundaries.

[0012] According to another aspect of the present application, a three-dimensional modeling system based on the original geological catalog is also provided, including: a cropping module, used to scan the original geological catalog to obtain a scanned image, and crop the scanned image to obtain a geological catalog map, wherein the cropping is used to obtain the graphic part of the scanned image; an image processing module, used to perform image processing on the geological catalog map, wherein the image processing is used to reduce noise and refine the geological catalog map, and the refinement is used to adjust the pixel width of the lines of the geological catalog map; a vectorization module, used to extract boundaries from the geological catalog map after image processing and vectorize the extracted boundaries; a construction module, used to construct the vectorized boundaries into three-dimensional geological catalog boundaries according to the spatial position relationship of the three walls in the original geological catalog, wherein the three-dimensional geological catalog boundaries are used to display the real shape of the three-dimensional space; a surface processing module, used to perform surface processing on the three-dimensional geological catalog boundaries to obtain a three-dimensional model, wherein the surface processing is used to add a surface to the three-dimensional geological catalog boundaries.

[0013] Furthermore, the image processing module is used to: binarize the geological catalog map; corrode the image obtained after the binarization using a 3×3 matrix, and then dilate it using a 3×3 matrix; and refine the image after the corrosion and dilation processing.

[0014] Furthermore, the image processing module is used to: subject the image after the erosion and dilation processing to a table lookup thinning process first, and then to a Rosenfeld method to a thinning process.

[0015] Furthermore, the vectorization module is used to: obtain a first boundary line from the geological catalog map after image processing by sketch extraction, and vectorize the first boundary line; and perform thinning processing on the vectorized first boundary line to obtain the boundary line.

[0016] Furthermore, the boundaries include: top and bottom plate boundaries, two wall boundaries and geological logging boundaries.

[0017] In an embodiment of the present application, the original geological catalog is scanned to obtain a scanned image, and the scanned image is cropped to obtain a geological catalog map, wherein the cropping is used to obtain the graphic portion of the scanned image; the geological catalog map is image processed, wherein the image processing is used to reduce noise and refine the geological catalog map, and the refinement is used to adjust the pixel width of the lines of the geological catalog map; boundaries are extracted from the image-processed geological catalog map, and the extracted boundaries are vectorized; based on the spatial position relationship of the three walls in the original geological catalog, the vectorized boundaries are constructed into three-dimensional geological catalog boundaries, wherein the three-dimensional geological catalog boundaries are used to display the true form of the three-dimensional space; surface processing is performed on the three-dimensional geological catalog boundaries to obtain a three-dimensional model, wherein the surface processing is used to add a surface to the three-dimensional geological catalog boundaries. This application solves the problem of poor effect of the three-dimensional model of mine geology caused by the failure to perform corresponding processing on the original geological map in the prior art, thereby improving the quality of geological catalog modeling. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings, which constitute part of this application, are intended to provide a further understanding of this application. The exemplary embodiments and descriptions of this application are intended to explain this application and do not constitute an improper limitation on this application. In the accompanying drawings:

[0019] Figure 1 is a schematic diagram of a method for vectorizing 3D modeling of original geological records based on image recognition according to an embodiment of the present application;

[0020] Figure 2 is an original geological log map according to an embodiment of the present application;

[0021] Figure 3 is a cropped geological logging map according to an embodiment of the present application;

[0022] Figure 4 This is a geological log map after noise reduction and refinement according to an embodiment of the present application;

[0023] Figure 5 is a schematic diagram of geological boundary sketch extraction and thinning separation according to an embodiment of the present application;

[0024] Figure 6 is a schematic diagram of a three-dimensional geological logging boundary according to an embodiment of the present application;

[0025] Figure 7 is a schematic diagram of a Coons surface according to an embodiment of the present application;

[0026] Figure 8a is a schematic diagram of geological logging curve modeling according to an embodiment of the present application;

[0027] Figure 8b This is a schematic diagram of a folded coil calibration model according to an embodiment of the present application;

[0028] Figure 9 This is a flow chart of a three-dimensional modeling method based on original geological cataloging according to an embodiment of the present application. DETAILED DESCRIPTION

[0029] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0030] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0031] In this embodiment, a 3D modeling method based on original geological records is provided. Figure 9 is a flow chart of a three-dimensional modeling method based on original geological cataloging according to an embodiment of the present application, such as Figure 9 As shown, the process includes the following steps:

[0032] Step S902, scanning the original geological catalog to obtain a scanned map, and cropping the scanned map to obtain a geological catalog map, wherein the cropping is used to obtain a graphic portion of the scanned map;

[0033] Step S904, performing image processing on the geological log map, wherein the image processing is used to perform noise reduction and thinning processing on the geological log map, and the thinning processing is used to adjust the pixel width of the lines of the geological log map;

[0034] In this step, there are many ways to perform image processing, such as binarizing the geological map; corroding the binarized image using a 3×3 matrix, and then dilating it using a 3×3 matrix; and thinning the image after the corroded and dilated processes. In this embodiment, an optimized thinning process is also used, whereby the image after the corroded and dilated processes is first thinned using a table lookup, and then thinned using the Rosenfeld method.

[0035] Step S906, extracting boundaries from the geological log map after image processing, and vectorizing the extracted boundaries;

[0036] There are many ways to perform vectorization. In one optional method, a first boundary can be extracted from an image-processed geological catalog map through sketching, and the first boundary can be vectorized; the vectorized first boundary can be thinned out to obtain the boundary.

[0037] Step S908: constructing the vectorized boundaries into three-dimensional geological record boundaries according to the spatial position relationship of the three walls in the original geological record, wherein the three-dimensional geological record boundaries are used to display the true form of the three-dimensional space;

[0038] Step S910 , performing surface processing according to the three-dimensional geological record boundary to obtain a three-dimensional model, wherein the surface processing is used to add a surface to the three-dimensional geological record boundary.

[0039] The above steps solve the problem in the prior art that the original geological maps are not processed accordingly, resulting in poor results of the three-dimensional mine geological model, thereby improving the quality of geological cataloging modeling.

[0040] An optional embodiment is described below with reference to the accompanying drawings. Figure 1 This is a schematic diagram of a method for vectorizing 3D modeling of original geological records based on image recognition according to an embodiment of the present application. Figure 1 This method is described below. Figure 1 As can be seen from the figure, the original geological catalog vectorization 3D modeling method based on image recognition can be divided into five steps: (1) reading and cropping the original geological catalog drawings; (2) denoising and refining the graphics, in which the Rosenfeld algorithm can be used; (3) extracting and thinning the geological sketch boundaries, in which the Douglas-Peucker algorithm can be used; (4) 3Dizing the geological catalog boundaries; (5) constructing a 3D geological body model using a surface, in which the Coons surface can be used.

[0041] The above five steps are described below.

[0042] (1) Geological catalog reading and cropping. In this step, a scanned image is formed through indoor comprehensive organization. The catalog can then be read using the OpenCV tool, compressed using a compression tool, and finally non-graphic information is cropped using an interactive solution. The interactive solution can provide an interface for user input, through which the user can adjust cropping parameters, such as cropping position. The OpenCV tool is an open source image processing tool. Scanned images can be uniformly processed and saved using OpenCV. Of course, other tools can also be used for processing.

[0043] The first step in the vector modeling of geological records is to read and cut the original geological records. The original geological records are comprehensively sorted and scanned indoors to form scanned images, such as Figure 2 As shown in the figure, we use OpenCV to quickly read the catalog file and compress it with the corresponding compression tool. This step will fully prepare for the improvement of the calculation speed of subsequent modeling work.

[0044] The extracted catalog files are often not usable directly and require file processing. Since the original geological catalog contains a large amount of non-graphic information such as text, labels, coordinates, and sampling, an interactive solution is often used to crop the catalog file by specifying the catalog part that needs to be vectorized, such as Figure 3 The interactive solution here refers to allowing users to input and adjust the cropping area to crop the catalog file.

[0045] As another optional embodiment, a first machine learning model can be trained using multiple sets of training data, each of which includes input data and output data. The input data is a scanned image of the original geological catalog that has been cropped, and the output data is a manually cropped image of the scanned image. After training, the machine learning model can be used. By inputting the catalog file into the first machine learning model, the cropped catalog file can be obtained from the first machine learning model.

[0046] (2) Image denoising and refinement. In this step, the image is effectively cleaned up by grayscale conversion, background blurring, watermark fading, and noise removal. The steps used for image denoising are explained below.

[0047] (2-1) Binarization. Decompose the multi-channel color image into a three-channel RGB grayscale image. This article uses the B-channel image. After bilateral filtering, the grayscale image is subjected to bimodal binarization. The median of the bimodal image is generally around 130 grayscale. Alternatively, the grayscale threshold can be manually specified interactively. Pixels with values ​​below 130 are reset to 255 (white), and pixels with values ​​equal to or above 130 are reset to 0 (black).

[0048] (2-2) Erosion and Dilation. Both erosion and dilation use a 3×3 matrix, with erosion performed first and then dilation performed. Image erosion and dilation are morphological operations, a series of shape-based image processing operations. The basic idea of ​​digital morphology is to use structural elements with a certain shape to measure and extract corresponding shapes in an image to achieve image analysis and recognition. Image erosion and dilation operate on highlights (white). Dilation expands the highlights, similar to "domain expansion," while erosion erodes the highlights, similar to "domain erosion." Applications of dilation and erosion are primarily reflected in noise removal, segmenting independent elements or connecting adjacent elements, finding significant maximum and minimum regions in an image, and calculating image gradients. Image erosion shrinks the target image, and the effect of the operation depends on the size, content, and logical properties of the structural element. Image erosion shrinks the target image, and the effect of the operation depends on the size, content, and logical properties of the structural element. Erosion can be represented as detecting an image using a structural element to find areas within the image where the structural element can fit. Erosion is the process of eliminating boundary points and causing them to shrink. It can be used to eliminate small and meaningless targets. The function of image dilation is to enlarge the target image.

[0049] (2-3) The cleaned graphics need to be refined to ensure the accuracy of the geological catalog map. Image refinement refers to the skeletonization of the binary image, which is an operation to refine the image lines from the width of multiple pixels to the width of a unit pixel. Usually, the pixel width occupied by the geological sketch boundary is relatively fixed. Therefore, the image is refined by considering the use of table refinement preprocessing and Rosenfeld method post-processing mode, such as Figure 4As shown. In this step, the table lookup refinement preprocessing can pre-acquire the pixel widths of different types of lines configured in the table, and then process the lines in the image into the corresponding pixel widths according to their types. In the Rosenfeld algorithm, the background pixel value is defined as 0 and the foreground pixel value is defined as 1. For a certain pixel P1, there are eight adjacent pixels (P2 to P9) around it. According to the arrangement of north at the top, south at the bottom, west at the left, and east at the right, P2 is directly above P1, P6 is directly below P1, P8 is to the left of P1, P4 is to the right of P1, P9 is to the upper left of P1, P3 is to the upper right of P1, P5 is to the lower right of P1, and P7 is to the lower left of P1. For the foreground pixel p1, if p2 = 0, then p1 is called the northern boundary point. If p6 = 0, p1 is called the southern boundary point, p4 = 0, p1 is called the eastern boundary point, and p8 = 0, p1 is called the western boundary point. If the values ​​of the eight pixels surrounding point P1 are all 0, then point P1 is an isolated point. If only one of the eight surrounding pixels has a value of 1, then point P1 is called an endpoint. Another important concept to understand is 8simple, which means that setting the value of P1 to 0 does not change the 8-connectivity of the surrounding eight pixels.

[0050] The Rosenfeld thinning algorithm is described as follows:

[0051] Step 1. Scan all pixels. If the pixel is a northern boundary point and is 8simple, but not an isolated point or endpoint, delete the pixel.

[0052] Step 2. Scan all pixels. If the pixel is a southern boundary point and is 8simple, but not an isolated point or endpoint, delete the pixel.

[0053] Step 3. Scan all pixels. If the pixel is an eastern boundary point and is 8simple, but not an isolated point or endpoint, delete the pixel.

[0054] Step 4. Scan all pixels. If the pixel is a western boundary point and is 8simple, but not an isolated point or endpoint, delete the pixel.

[0055] After executing the above four steps, one iteration is completed. Repeat the above iterative process until there are no more points that can be deleted in the image. Then exit the iterative loop and complete the image refinement.

[0056] (3) Geological boundary sketch extraction and thinning separation

[0057] The geological record after noise reduction and refinement is extracted by sketching to separate geological boundaries. The sketch extraction follows the following steps. Starting from an initial pixel point with a non-zero gray value, search in one direction. If the gray value of the pixel point is greater than 0, record the coordinate value of the pixel point and reset the gray value of the pixel point to 0; if the gray value is equal to 0, search in the other direction of the starting pixel point, with the same rule. Until the gray values of all pixel points are all 0, exit the loop.

[0058] The separated geological boundaries need to be thinned to filter out redundant data information. The classic Douglas-Peucker algorithm can be used for image thinning. While maintaining the basic geometric features of the geological record line unchanged, the number of line composition points is significantly reduced. Through image thinning, the key points of the geological boundary sketch are obtained.

[0059] Minimizing the number of data points to the greatest extent while ensuring the shape of the vector curve remains unchanged, this process is called thinning. The Douglas–Peucker algorithm is an algorithm that approximately represents a curve as a series of points and reduces the number of points. Its advantage is that it has translational and rotational invariance. Given a curve and a threshold, the sampling result is certain. The basic idea of the algorithm is: Virtually connect a straight line between the first and last points of each curve, find the distances from all points to the straight line, and find the maximum distance value dmax. Compare dmax with the tolerance D: If dmax < D, all intermediate points on this curve are discarded; If dmax ≥ D, retain the coordinate point corresponding to dmax, and take this point as the boundary, divide the curve into two parts, and repeat this method for these two parts until the thinning is completed.

[0060] In addition, during the vectorization process, some geological record boundaries are often connected to the roof line, resulting in incorrect graphic interpretation. According to the characteristic that there is a large angle between the geological record boundary and the roof line, consider breaking at the turning point of the line (the included angle at the turning point is greater than the predetermined angle) to separate the two. After the geological boundary sketch extraction and thinning separation, as Figure 5 shown.

[0061] (4) Three-dimensionalization of geological record boundaries

[0062] Based on the spatial position relationship of the three-wall expansion in the original geological record, according to the true coordinates of the engineering measurement points and the engineering section parameters, the top and bottom plate side lines, the two-wall side lines, and the geological record boundaries are restored to their true three-dimensional forms through three-dimensional coordinate transformations of translation, scaling, rotation, and projection, providing three-dimensional geological record boundaries for the subsequent establishment of geological models, as Figure 6 shown.

[0063] (5) Coons surface modeling

[0064] In a 3D visualization environment, a bicubic Coons surface is constructed based on the 3D geological logging boundaries obtained in the above steps. Figure 7 As shown in Figure 8, a complex 3D geological model is then precisely constructed. Because Coons surfaces are based on the concept of piecewise splicing, when key point information at a local location changes, only the associated surface needs to be adjusted, eliminating the need to rebuild the entire 3D geological model. This also ensures smooth splicing between surfaces. Compared to traditional drilling engineering zigzag coil ore modeling, the geological model created using 3D geological logging curve modeling is more realistic, the ore body model is more accurate, and the model is more consistent with the on-site exposure.

[0065] A Coons surface, also known as a Kunz surface, is composed of many patches generated by welding four boundary curves. Automatic concatenation can be used to define surface patches: this method uses three boundary curves to define a patch; these three boundary curves are the two upper-left curves and the one lower-right curve. The minimum branching angle is used by the system to analyze boundary curves for concatenation. If the intersection angle of the boundary curves is greater than the minimum branching angle, the system cannot concatenate the boundary curves.

[0066] Through the above embodiments, in order to solve the problems of traditional original geological catalog modeling, such as the lack of consideration of map pollution, low vectorization efficiency, and low model accuracy, this paper proposes a method for vectorizing original geological catalog 3D modeling based on image recognition. The method mainly includes the following steps: (1) reading and clipping original geological catalog drawings, (2) using the Rosenfeld algorithm to reduce noise and refine the graphics, (3) using the Douglas-Peucker algorithm to extract and thin out geological sketch boundaries, (4) three-dimensionalizing geological catalog boundaries, and (5) using Coons surfaces to accurately construct a 3D geological body model. The results of numerical simulation experiments show that compared with traditional original geological catalog 3D modeling, the modeling results using this method can more realistically reflect the changes in ore body morphology, and the modeling speed is shortened from 20 minutes to within 30 seconds, which greatly improves the efficiency of geological catalog modeling and thus reduces the risks of underground production exploration and mining operations.

[0067] The above embodiment is suitable for processing original geological catalog drawings. Compared with traditional three-dimensional broken line modeling, the effect of vectorized three-dimensional modeling based on image recognition is significantly improved. By applying this method, the degree of automation is greatly improved, and the modeling speed is shortened from minutes to seconds. The above embodiment can effectively serve the calculation of mine preparation-level reserves, high-precision design and refined mining operations. For areas where the local occurrence of the ore body changes dramatically, the use of this method for refined surface modeling can effectively assist in design modifications and reduce conflicts between the model and the actual situation on site.

[0068] In this embodiment, an electronic device is provided, including a memory and a processor. The memory stores a computer program, and the processor is configured to run the computer program to execute the method in the above embodiment.

[0069] The above program can be executed in a processor or stored in a memory (or computer-readable medium), which includes permanent and non-permanent, removable and non-removable media that can implement information storage by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape, disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media such as modulated data signals and carrier waves.

[0070] These computer programs can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable device to implement the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps of the functions specified in one or more blocks can be implemented by different modules corresponding to different steps.

[0071] This embodiment provides such a device or system. The system is referred to as a 3D modeling system based on an original geological catalog, and includes: a cropping module for scanning the original geological catalog to obtain a scanned image, cropping the scanned image to obtain a geological catalog map, wherein the cropping is used to obtain a graphic portion of the scanned image; an image processing module for performing image processing on the geological catalog map, wherein the image processing is used to reduce noise and refine the geological catalog map, and wherein the refinement is used to adjust the pixel width of lines in the geological catalog map; a vectorization module for extracting boundaries from the image-processed geological catalog map and vectorizing the extracted boundaries; a construction module for constructing the vectorized boundaries into 3D geological catalog boundaries based on the spatial positional relationship of the three walls in the original geological catalog, wherein the 3D geological catalog boundaries are used to display the true form of the 3D space; and a surface processing module for performing surface processing on the 3D geological catalog boundaries to obtain a 3D model, wherein the surface processing is used to add a surface to the 3D geological catalog boundaries.

[0072] The system or device is used to implement the functions of the method in the above-mentioned embodiment. Each module in the system or device corresponds to each step in the method, which has been explained in the method and will not be repeated here.

[0073] For example, the image processing module is used to: binarize the geological catalog map; corrode the binarized image using a 3×3 matrix, and then dilate it using a 3×3 matrix; and refine the image after corrosion and dilation.

[0074] Optionally, the image processing module is used to: first perform table lookup thinning processing on the image after the erosion processing and the dilation processing, and then perform thinning processing on the image by Rosenfeld method.

[0075] For another example, the vectorization module is used to: extract a first boundary from a geological catalog map that has undergone image processing through sketching, and vectorize the first boundary; and perform thinning processing on the vectorized first boundary to obtain the boundary.

[0076] The original geological catalog vectorization 3D modeling scheme based on image recognition proposed in the above embodiment is able to more realistically reflect the changes in ore body morphology than traditional original geological catalog 3D modeling. It overcomes the problems of traditional original geological catalog modeling that do not consider map pollution, low vectorization efficiency, and low model accuracy. The modeling speed is shortened from 20 minutes to 30 seconds, thereby improving the efficiency of geological catalog modeling and reducing the risks of underground production exploration and mining operations.

[0077] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A three-dimensional modeling method based on original geological records, characterized in that: include: Scanning the original geological catalog to obtain a scanned map, and cropping the scanned map to obtain a geological catalog map, wherein the cropping is used to obtain a graphic portion in the scanned map; Performing image processing on the geological log map, wherein the image processing is used to perform noise reduction and thinning processing on the geological log map, and the thinning processing is used to adjust the pixel width of the lines of the geological log map; wherein the geological log map is binarized; the image obtained after the binarization processing is corroded using a 3×3 matrix, and then dilated using a 3×3 matrix; and the image after the corrosion and dilation processing is thinned; Extract boundaries from the image-processed geological map and vectorize the extracted boundaries. Starting from a starting pixel with a non-zero grayscale value, search toward one side. If the pixel grayscale value is greater than 0, record the pixel coordinates and reset the pixel grayscale value to 0. If the grayscale value is 0, search toward the other side of the starting pixel using the same rules as above. Exit the loop until all pixel grayscale values ​​are 0. The separated geological boundaries need to be thinned out to filter out redundant data information. constructing a three-dimensional geological record boundary from the vectorized boundary according to the spatial position relationship of the three walls in the original geological record, wherein the three-dimensional geological record boundary is used to display the true form of the three-dimensional space; Surface processing is performed according to the three-dimensional geological record boundary to obtain a three-dimensional model, wherein the surface processing is used to add a surface on the three-dimensional geological record boundary.

2. The method according to claim 1, characterized in that Thinning the image after erosion and dilation includes: The image after erosion and dilation is first thinned by table lookup and then thinned by Rosenfeld method.

3. The method according to claim 1, characterized in that Extracting boundaries from a geological log map after image processing and vectorizing the extracted boundaries includes: extracting a first boundary line from the geological log map after image processing by sketching, and vectorizing the first boundary line; The vectorized first boundary is subjected to thinning processing to obtain the boundary.

4. The method according to claim 3, characterized in that The boundaries include: top and bottom plate boundaries, two wall boundaries and geological logging boundaries.

5. A 3D modeling system based on original geological records, characterized in that: include: A cropping module, configured to scan the original geological catalog to obtain a scanned image, and crop the scanned image to obtain a geological catalog map, wherein the cropping is used to obtain a graphic portion of the scanned image; an image processing module, configured to perform image processing on the geological log map, wherein the image processing is used to perform noise reduction and thinning processing on the geological log map, and the thinning processing is used to adjust the pixel width of the lines of the geological log map; wherein the geological log map is binarized; the image obtained after the binarization processing is eroded using a 3×3 matrix, and then dilated using a 3×3 matrix; and the image after the erosion and dilation processing is thinned; The vectorization module is used to extract boundaries from the geological catalog map after image processing and vectorize the extracted boundaries. The module starts from a starting pixel with a non-zero grayscale value and searches to one side. If the grayscale value of the pixel is greater than 0, the coordinate value of the pixel is recorded and the grayscale value of the pixel is reset to 0. If the grayscale value is equal to 0, the module searches to the other side of the starting pixel using the same rules as above. The cycle ends when the grayscale values ​​of all pixels are 0. The separated geological boundaries need to be thinned out to filter out redundant data information. A construction module is used to construct the vectorized boundary into a three-dimensional geological record boundary according to the spatial position relationship of the three walls in the original geological record, wherein the three-dimensional geological record boundary is used to display the true form of the three-dimensional space; The surface processing module is used to perform surface processing according to the three-dimensional geological catalog boundary to obtain a three-dimensional model, wherein the surface processing is used to add a surface to the three-dimensional geological catalog boundary.

6. The system according to claim 5, characterized in that The image processing module is used for: The image after erosion and dilation is first thinned by table lookup and then thinned by Rosenfeld method.

7. The system according to claim 5, characterized in that The vectorization module is used to: extracting a first boundary line from the geological log map after image processing by sketching, and vectorizing the first boundary line; The vectorized first boundary is subjected to thinning processing to obtain the boundary.

8. The system according to claim 7, characterized in that The boundaries include: top and bottom plate boundaries, two wall boundaries and geological logging boundaries.

Images