Carbonate rock fracture identification method and system based on image processing

Abstract

The invention discloses a carbonate rock fracture identification method and system based on image processing. The method comprises the steps that a high-definition unmanned aerial vehicle shooting device is adopted to collect a carbonate rock image in real time; according to the method, the high-definition unmanned aerial vehicle shooting equipment can be used for efficiently obtaining the real-time image of the carbonate rock in a large range, basic data are provided for subsequent analysis, the preprocessing step can improve the image quality and remove noise, and the image is segmented into crack areas which are easier to analyze. By analyzing and learning carbonate rock crack information in historical data, a neural network model can be constructed, the model can automatically identify and extract basic information such as the length, depth and width of cracks, on the other hand, understanding of different types of crack features is crucial to accurate identification of crack types, and through feature analysis, the accurate identification of crack types is realized. According to the method, the unique features of each crack type can be extracted to form a feature set, and the crack type in the image can be judged by calculating the similarity.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a carbonate rock fracture identification method and system based on image processing. Background Art

[0002] Carbonate rocks are affected by multiple factors such as lithofacies paleogeography, sedimentary structural evolution or later diagenesis, and have more complex reservoir space and oil and gas seepage and migration rules, which leads to greater risks and difficulties in the development of carbonate reservoirs. Therefore, it is particularly important to determine the type of carbonate reservoirs in order to correctly select the development model and development plan of carbonate rocks.

[0003] In the prior art, carbonate rock images are photographed, but the effect of processing core images is poor. The subsequent determination of carbonate rock fracture types is mainly based on the experience of staff. This method is relatively cumbersome and inaccurate, and it is difficult to meet the needs of staff. Summary of the invention

[0004] In order to solve the above technical problems, a method and system for identifying carbonate rock fractures based on image processing are provided. The technical solution solves the problem that in the prior art proposed in the above background technology, carbonate rock images are photographed, but the effect of processing core images is poor, and the subsequent determination of carbonate rock fracture types is mainly based on the experience of staff. This method is relatively troublesome and has low accuracy.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is: In the first aspect of the present invention, a carbonate rock fracture identification method based on image processing is also provided, comprising: Use high-definition drone photography equipment to collect carbonate rock images in real time; Preprocessing the carbonate rock image to obtain a preprocessed carbonate rock image, wherein the preprocessing includes image denoising, image enhancement and image segmentation; Retrieving historical carbonate rock images from a database and analyzing them to obtain basic information about carbonate rock fractures, wherein the basic information about fractures includes length information, depth information, and width information of the fractures, and using a neural network model to construct a carbonate rock fracture information analysis model; The pre-processed carbonate rock image is input into the carbonate rock fracture information analysis model to output the basic fracture information; Retrieving all existing fracture types from the database, the fracture types including crevice type, solution pore type and matrix type, performing feature analysis on all fracture types, obtaining corresponding features of all fracture types, and forming a fracture type feature set; The cracks in the preprocessed carbonate rock image are subjected to feature analysis to obtain the corresponding crack type feature test data and form a crack type feature test data set. The similarity between the crack type feature test data set and the crack type feature set is calculated to determine the crack type in the carbonate rock image.

[0006] Preferably, the image denoising specifically comprises the following steps: Adaptive wavelet threshold denoising of carbonate rock images; By constructing a probability model of wavelet coefficients, the optimal wavelet threshold is determined using Bayesian estimation. The wavelet coefficients are processed with adaptive threshold and then reconstructed by wavelet to obtain a denoised image.

[0007] Preferably, the image enhancement specifically comprises the following steps: Performing adaptive histogram equalization processing on the denoised image; Determine the cumulative distribution function of the local area by calculating the grayscale histogram of the denoised image; Based on the cumulative distribution function, the grayscale mapping relationship of the local area is adaptively adjusted to obtain an enhanced image.

[0008] Preferably, the image segmentation specifically comprises the following steps: Segmenting the enhanced image into multiple superpixels using a superpixel segmentation algorithm; Determine the similarity matrix between superpixels as the edge weight of the undirected graph, and construct a superpixel graph cut undirected graph; Combined with the pre-set probability distribution of the crack area, the global optimal solution of the superpixel graph cut undirected graph is solved by the maximum flow minimum cut algorithm; The segmentation result of the crack area is obtained to obtain the preprocessed image.

[0009] Preferably, the use of a neural network model to construct a carbonate rock fracture information analysis model specifically includes the following steps: Based on the feedforward neural network, a carbonate rock fracture information analysis model is constructed; Based on machine learning, multiple historical crack width feature data, multiple historical crack length feature data, and multiple historical crack depth feature data are labeled and divided to obtain training sets, validation sets, and test sets; The training set, validation set and test set are used to perform supervised training, validation and testing on the fracture identification model to obtain the carbonate rock fracture information analysis model whose accuracy meets the preset accuracy requirements.

[0010] Preferably, the step of inputting the preprocessed carbonate rock image into the carbonate rock fracture information analysis model and outputting the fracture information specifically comprises the following steps: Perform feature analysis on the preprocessed carbonate rock image to obtain corresponding fracture width feature data, historical fracture length feature data, and historical fracture depth feature data; Inputting the obtained real-time crack width characteristic data into the crack identification model that meets the preset accuracy requirement to obtain real-time crack width information; Inputting the obtained real-time crack length characteristic data into the crack identification model that meets the preset accuracy requirement to obtain real-time crack length information; Inputting the obtained real-time crack depth characteristic data into the crack identification model that meets the preset accuracy requirement to obtain real-time crack depth information; Based on the real-time crack width information, real-time crack length information and real-time crack depth information, basic crack information is output.

[0011] Preferably, the similarity calculation formula between the crack type feature test data set and the crack type feature set is: simJaccard(A,B) = |A∩B| / |A∪B| Where A is the crack type feature test data set, B is the crack type feature set, |A∩B| is the intersection of the crack type feature test data set and the crack type feature set, and |A∪B| is the union of the crack type feature test data set and the crack type feature set.

[0012] In a second aspect of the present invention, a carbonate rock fracture identification system based on image processing is also provided, comprising: A shooting module, which is used to collect carbonate rock images in real time using a high-definition drone shooting device; A preprocessing module, the preprocessing module is used to preprocess the carbonate rock image to obtain the preprocessed carbonate rock image, and the internal integration of the preprocessing module includes an image denoising unit, an image enhancement unit and an image segmentation unit; A model building module, which is used to retrieve historical carbonate rock images from a database and analyze them to obtain basic information about carbonate rock fractures, wherein the basic information includes length information, depth information, and width information of the fractures, and to build a carbonate rock fracture information analysis model using a neural network model; A fracture basic information confirmation module, wherein the fracture basic information confirmation module is used to input the preprocessed carbonate rock image into the carbonate rock fracture information analysis model and output the fracture basic information; An analysis module, which is used to retrieve all existing fracture types from a database, including fracture types, dissolved pore types, and matrix types, perform feature analysis on all fracture types, obtain corresponding features of all fracture types, and form a fracture type feature set; A fracture type confirmation module, the fracture type confirmation module is used to perform feature analysis on fractures in the preprocessed carbonate rock image, obtain corresponding fracture type feature test data, and form a fracture type feature test data set, perform similarity calculation between the fracture type feature test data set and the fracture type feature set, and determine the fracture type in the carbonate rock image; An image denoising unit, which is used to denoise the carbonate rock image and obtain the denoised carbonate rock image; An image enhancement unit, wherein the image enhancement unit is used to enhance the denoised carbonate rock image to obtain an enhanced carbonate rock image; An image segmentation unit is used to segment the enhanced carbonate rock image to obtain a segmented carbonate rock image.

[0013] In a third aspect of the present invention, an electronic device is further provided. The electronic device comprises at least one processor; and a memory connected to the at least one processor in communication; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the method of the first aspect of the present invention.

[0014] Compared with the prior art, the present invention provides a carbonate rock fracture identification method and system based on image processing, which has the following beneficial effects: The present invention utilizes high-definition drone photography equipment to efficiently and widely acquire real-time images of carbonate rocks, providing basic data for subsequent analysis. The preprocessing steps (image denoising, image enhancement, and image segmentation) can improve image quality, remove noise, enhance useful information, and segment the image into fracture areas that are easier to analyze. By analyzing and learning carbonate rock fracture information in historical data, a neural network model can be constructed, which can automatically identify and extract basic information such as the length, depth, and width of the fracture. On the other hand, understanding the characteristics of different types of fractures is crucial for accurately identifying the fracture type. Through feature analysis, the unique characteristics of each fracture type can be extracted to form a feature set, which provides a basis for subsequent classification. By calculating similarity, the present invention can also determine the fracture type in the image. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A schematic diagram of a carbonate rock fracture identification method based on image processing in the present invention; Figure 2 A schematic diagram of the method for image denoising in the present invention; Figure 3 Schematic diagram of the image enhancement method in the present invention; Figure 4 It is a schematic diagram of the image segmentation method in the present invention; Figure 5 A schematic diagram of a method for constructing a carbonate rock fracture information analysis model using a neural network model in the present invention; Figure 6 A schematic diagram of a method for inputting a pre-processed carbonate rock image into a carbonate rock fracture information analysis model to output fracture information in the present invention; Figure 7 A block diagram of an exemplary electronic device capable of implementing embodiments of the present invention is shown; Among them, 700 is an electronic device, 701 is a computing unit, 702 is a ROM, 703 is a RAM, 704 is a bus, 705 is an I / O interface, 706 is an input unit, 707 is an output unit, 708 is a storage unit, and 709 is a communication unit. DETAILED DESCRIPTION

[0016] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0017] Example 1 Please refer to Figure 1 As shown, in the first aspect of the present invention, a carbonate rock fracture identification method based on image processing is also provided, comprising: S101, using high-definition drone photography equipment to collect carbonate rock images in real time; S102, preprocessing the carbonate rock image to obtain a preprocessed carbonate rock image, wherein the preprocessing includes image denoising, image enhancement and image segmentation; S103, retrieving historical carbonate rock images from a database and analyzing them to obtain basic information about carbonate rock fractures, where the basic information includes length information, depth information, and width information of the fractures, and constructing a carbonate rock fracture information analysis model using a neural network model; S104, inputting the preprocessed carbonate rock image into a carbonate rock fracture information analysis model, and outputting basic fracture information; S105, retrieving all existing fracture types from the database, the fracture types including crevice type, dissolved pore type and matrix type, performing feature analysis on all fracture types, obtaining corresponding features of all fracture types, and forming a fracture type feature set; S106, performing feature analysis on the cracks in the preprocessed carbonate rock image, obtaining corresponding crack type feature test data, and forming a crack type feature test data set, performing similarity calculation between the crack type feature test data set and the crack type feature set, and determining the crack type in the carbonate rock image.

[0018] It is understood by those skilled in the art that the use of high-definition drone photography equipment can efficiently and widely obtain real-time images of carbonate rocks, providing basic data for subsequent analysis. Drone photography not only improves work efficiency, but also covers a wider area and captures more details. The preprocessing steps (image denoising, image enhancement, and image segmentation) can improve image quality, remove noise, enhance useful information, and segment the image into parts that are easier to analyze. This helps to improve the accuracy and efficiency of subsequent analysis. By analyzing and learning the carbonate rock fracture information in historical data, a neural network model can be constructed that can automatically identify and extract basic information such as the length, depth, and width of the fracture. By inputting the preprocessed image into the trained model, basic information such as length, depth, and width of the fracture can be automatically and quickly obtained. Understanding the characteristics of different types of fractures is crucial to accurately identify the fracture type. Through feature analysis, the unique features of each fracture type can be extracted to form a feature set to provide a basis for subsequent classification. By calculating the similarity, we can determine which type of fractures in the image are (fracture type, solution pore type or matrix type), which is of great significance for understanding the formation mechanism of fractures and evaluating the reservoir performance and permeability of reservoirs.

[0019] Please refer to Figure 2 As shown, image denoising specifically includes the following steps: S201, performing adaptive wavelet threshold denoising on the carbonate rock image; S202, by constructing a probability model of wavelet coefficients, and using Bayesian estimation to determine the optimal wavelet threshold; S203, performing adaptive threshold processing on the wavelet coefficients and performing wavelet reconstruction to obtain a denoised image.

[0020] It is understood by those skilled in the art that carbonate rock images may be interfered by various noises during the acquisition and transmission process, such as sensor noise, environmental noise, etc. The adaptive wavelet threshold denoising method utilizes the multi-scale characteristics of wavelet transform to decompose the image into different frequency scales and perform threshold processing for the noise characteristics at each scale. By setting a suitable threshold, the wavelet coefficients less than the threshold can be regarded as noise and removed, while the wavelet coefficients greater than the threshold are retained, which mainly contain useful information of the image. This method can effectively remove noise while retaining the details and edge information of the image. Further optimization of the adaptive wavelet threshold denoising method. Traditional threshold selection methods may be too simple or fixed to adapt to different images and different noise levels. By constructing a probability model of wavelet coefficients and using Bayesian estimation to determine the optimal wavelet threshold, the characteristics of noise and signal in the image can be more accurately reflected. The Bayesian estimation method considers the relationship between prior information and observed data and obtains the optimal threshold by maximizing the posterior probability. This method can adaptively adjust the threshold to adapt to different images and noise conditions, thereby improving the denoising effect. After determining the optimal wavelet threshold, the wavelet coefficients are processed by adaptive threshold, that is, the wavelet coefficients are divided into two categories according to the size of the threshold: coefficients greater than the threshold are retained, and coefficients less than the threshold are set to zero or processed in other ways. Then, the processed wavelet coefficients are reconstructed back to the image space using the wavelet reconstruction algorithm to obtain the denoised carbonate rock image. This step is to achieve the ultimate goal of image denoising, that is, to obtain a clear, noise-free image, which provides a basis for subsequent image analysis and processing.

[0021] Please refer to Figure 3 As shown, image enhancement specifically includes the following steps: S301, performing adaptive histogram equalization processing on the denoised image; S302, determining the cumulative distribution function of the local area by calculating the grayscale histogram of the denoised image; S303: Based on the cumulative distribution function, adaptively adjust the grayscale mapping relationship of the local area to obtain an enhanced image.

[0022] It can be understood by those skilled in the art that adaptive histogram equalization (AHE) is a local contrast enhancement method, which improves the local contrast of an image by performing histogram equalization on a local area of ​​the image. Applying AHE processing on the denoised carbonate rock image can further enhance the visual effect of the image, making the details of the image clearer and the contrast more uniform. This is very beneficial for subsequent image analysis and processing, such as crack detection and feature extraction. The grayscale histogram reflects the number of pixels at each grayscale level in the image, while the cumulative distribution function (CDF) is obtained by accumulating the grayscale histogram, which represents the proportion of the number of pixels less than or equal to a certain grayscale level to the total number of pixels. By calculating the grayscale histogram of the denoised image and the cumulative distribution function of the local area, basic data can be provided for the subsequent grayscale mapping relationship adjustment. This helps to ensure that the enhanced image achieves a uniform distribution of contrast while maintaining the original grayscale arrangement order. This step is the core step to achieve image enhancement. Based on the cumulative distribution function, the grayscale mapping relationship of the local area of ​​the denoised image can be adaptively adjusted. Specifically, a mapping function is used to map the grayscale value of the original image to a new grayscale value, so that the enhanced image has a more uniform grayscale distribution and higher contrast in the local area. This adaptive adjustment method can avoid the over-enhancement or distortion problems that may be caused by global equalization, thereby obtaining a more natural and clear enhanced image.

[0023] Please refer to Figure 4 As shown, image segmentation specifically includes the following steps: S401, segmenting the enhanced image into multiple superpixels using a superpixel segmentation algorithm; S402, determining the similarity matrix between superpixels as the edge weight of the undirected graph, and constructing a superpixel graph cut undirected graph; S403, combining the pre-set probability distribution of the crack area, solving the global optimal solution of the superpixel graph cut undirected graph through the maximum flow minimum cut algorithm; S404: Obtain the segmentation result of the crack area and obtain a preprocessed image.

[0024] It can be understood by those skilled in the art that the pixel segmentation algorithm is a technique for dividing an image into several regions with similar attributes (such as color, texture, etc.). These regions are called superpixels, which usually contain more information than a single pixel, and help simplify the subsequent processing and analysis process. Segmenting the enhanced image into multiple superpixels can make the crack area more prominent, while reducing the amount of data to be processed and improving processing efficiency. The similarity matrix reflects the degree of similarity between superpixels, which can be obtained by calculating the color histogram, texture features, etc. between superpixels. Using these similarities as the edge weights of the undirected graph, a superpixel graph cut undirected graph can be constructed. This graph cut undirected graph provides the basis for the subsequent maximum flow minimum cut algorithm, so that the algorithm can find the optimal segmentation path while maintaining the similarity between superpixels. The maximum flow minimum cut algorithm is a classic algorithm in graph theory, which can find the minimum cut set in the graph while maintaining certain properties of the graph (such as the weight sum of the edges). In this step, combined with the pre-set probability distribution of the crack area, the algorithm can locate the crack area more accurately. By solving the global optimal solution of the superpixel graph cut undirected graph, an optimal segmentation path can be obtained, which can segment the crack area from the image. After the previous steps, the segmentation result of the crack area can be finally obtained. This segmentation result is a binary image, in which the crack area is marked as white (or other colors) and the rest is marked as black (or other colors). This preprocessed image provides a basis for subsequent image analysis and processing, allowing researchers to more accurately extract and analyze the features of the crack area.

[0025] Please refer to Figure 5 As shown in FIG. 1 , the neural network model is used to construct a carbonate rock fracture information analysis model, which specifically includes the following steps: S501. Constructing a carbonate rock fracture information analysis model based on a feedforward neural network; S502, based on machine learning, annotating and dividing a plurality of historical crack width feature data, a plurality of historical crack length feature data, and a plurality of historical crack depth feature data to obtain a training set, a validation set, and a test set; S503, using the training set, the validation set and the test set to perform supervised training, validation and testing on the fracture identification model, to obtain a carbonate rock fracture information analysis model whose accuracy meets the preset accuracy requirements.

[0026] Please refer to Figure 6 As shown, the preprocessed carbonate rock image is input into the carbonate rock fracture information analysis model, and the fracture information output specifically includes the following steps: S601, performing feature analysis on the preprocessed carbonate rock image to obtain corresponding fracture width feature data, historical fracture length feature data, and historical fracture depth feature data; S602, inputting the obtained real-time crack width characteristic data into a crack recognition model that meets the preset accuracy requirement to obtain real-time crack width information; S603, inputting the obtained real-time crack length characteristic data into a crack recognition model that meets the preset accuracy requirement to obtain real-time crack length information; S604, inputting the obtained real-time crack depth feature data into a crack recognition model that meets the preset accuracy requirement to obtain real-time crack depth information; S605: Output basic crack information based on the real-time crack width information, the real-time crack length information, and the real-time crack depth information.

[0027] The similarity calculation formula between the crack type feature test data set and the crack type feature set is: simJaccard(A,B) = |A∩B| / |A∪B| Where A is the crack type feature test data set, B is the crack type feature set, |A∩B| is the intersection of the crack type feature test data set and the crack type feature set, and |A∪B| is the union of the crack type feature test data set and the crack type feature set.

[0028] In a second aspect of the present invention, a carbonate rock fracture identification system based on image processing is also provided, comprising: A shooting module, which is used to collect carbonate rock images in real time using high-definition drone shooting equipment; A preprocessing module, which is used to preprocess the carbonate rock image to obtain the preprocessed carbonate rock image, and the internal integration of the preprocessing module includes an image denoising unit, an image enhancement unit and an image segmentation unit; The model building module is used to retrieve historical carbonate rock images from the database and analyze them to obtain basic information about carbonate rock fractures. The basic information about fractures includes length information, depth information, and width information of the fractures. A neural network model is used to build a carbonate rock fracture information analysis model. A fracture basic information confirmation module is used to input the preprocessed carbonate rock image into the carbonate rock fracture information analysis model and output the fracture basic information; The analysis module is used to retrieve all existing fracture types from the database, including fracture types, dissolution pore types and matrix types, perform feature analysis on all fracture types, obtain all corresponding fracture type features, and form a fracture type feature set; A fracture type confirmation module is used to perform feature analysis on fractures in the preprocessed carbonate rock image, obtain corresponding fracture type feature test data, and form a fracture type feature test data set, perform similarity calculation between the fracture type feature test data set and the fracture type feature set, and determine the fracture type in the carbonate rock image; An image denoising unit, which is used to denoise a carbonate rock image to obtain a denoised carbonate rock image; An image enhancement unit, the image enhancement unit is used to enhance the denoised carbonate rock image to obtain an enhanced carbonate rock image; The image segmentation unit is used to segment the enhanced carbonate rock image to obtain the segmented carbonate rock image.

[0029] In a third aspect of the present invention, an electronic device is further provided. The electronic device comprises at least one processor; and a memory connected to the at least one processor in communication; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the method of the first aspect of the present invention.

[0030] Electronic devices are intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the invention described and / or claimed herein.

[0031] The electronic device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the electronic device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0032] Multiple components in the electronic device 700 are connected to the I / O interface 705, including: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the electronic device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0033] The computing unit 701 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 701 performs the various methods and processes described above, such as methods S100~S600. For example, in some embodiments, methods S101~S106 may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the methods S101~S106 described above may be executed. Alternatively, in other embodiments, the computing unit 701 may be configured to execute methods S101 to S106 in any other appropriate manner (eg, by means of firmware).

[0034] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0035] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0036] In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0037] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0038] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0039] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0040] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0041] In summary, the use of high-definition drone photography equipment can efficiently and widely obtain real-time images of carbonate rocks, providing basic data for subsequent analysis. The preprocessing steps (image denoising, image enhancement, and image segmentation) can improve image quality, remove noise, enhance useful information, and segment the image into fracture areas that are easier to analyze. By analyzing and learning the carbonate rock fracture information in historical data, a neural network model can be constructed, which can automatically identify and extract basic information such as the length, depth, and width of the fracture. On the other hand, understanding the characteristics of different types of fractures is crucial for accurately identifying the fracture type. Through feature analysis, the unique characteristics of each fracture type can be extracted to form a feature set to provide a basis for subsequent classification. By calculating the similarity, the present invention can also determine the fracture type in the image.

[0042] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A carbonate rock fracture identification method based on image processing, characterized in that: include: Use high-definition drone photography equipment to collect carbonate rock images in real time; Preprocessing the carbonate rock image to obtain a preprocessed carbonate rock image, wherein the preprocessing includes image denoising, image enhancement and image segmentation; Retrieving historical carbonate rock images from a database and analyzing them to obtain basic information about carbonate rock fractures, wherein the basic information about fractures includes length information, depth information, and width information of the fractures, and using a neural network model to construct a carbonate rock fracture information analysis model; The pre-processed carbonate rock image is input into the carbonate rock fracture information analysis model to output the basic fracture information; Retrieving all existing fracture types from the database, the fracture types including crevice type, solution pore type and matrix type, performing feature analysis on all fracture types, obtaining corresponding features of all fracture types, and forming a fracture type feature set; The cracks in the preprocessed carbonate rock image are subjected to feature analysis to obtain the corresponding crack type feature test data and form a crack type feature test data set. The similarity between the crack type feature test data set and the crack type feature set is calculated to determine the crack type in the carbonate rock image.

2. The method for identifying carbonate rock fractures based on image processing according to claim 1, characterized in that: The image denoising specifically comprises the following steps: Adaptive wavelet threshold denoising of carbonate rock images; By constructing a probability model of wavelet coefficients, the optimal wavelet threshold is determined using Bayesian estimation. The wavelet coefficients are processed with adaptive threshold and then reconstructed by wavelet to obtain a denoised image.

3. The method for identifying carbonate rock fractures based on image processing according to claim 2, characterized in that: The image enhancement specifically comprises the following steps: Performing adaptive histogram equalization processing on the denoised image; Determine the cumulative distribution function of the local area by calculating the grayscale histogram of the denoised image; Based on the cumulative distribution function, the grayscale mapping relationship of the local area is adaptively adjusted to obtain an enhanced image.

4. The method for identifying carbonate rock fractures based on image processing according to claim 3, characterized in that: The image segmentation specifically comprises the following steps: Segmenting the enhanced image into multiple superpixels using a superpixel segmentation algorithm; Determine the similarity matrix between superpixels as the edge weight of the undirected graph, and construct a superpixel graph cut undirected graph; Combined with the pre-set probability distribution of the crack area, the global optimal solution of the superpixel graph cut undirected graph is solved by the maximum flow minimum cut algorithm; The segmentation result of the crack area is obtained to obtain the preprocessed image.

5. The method for identifying carbonate rock fractures based on image processing according to claim 4, characterized in that: The use of a neural network model to construct a carbonate rock fracture information analysis model specifically includes the following steps: Based on the feedforward neural network, a carbonate rock fracture information analysis model is constructed; Based on machine learning, multiple historical crack width feature data, multiple historical crack length feature data, and multiple historical crack depth feature data are labeled and divided to obtain training sets, validation sets, and test sets; The training set, validation set and test set are used to perform supervised training, validation and testing on the fracture identification model to obtain the carbonate rock fracture information analysis model whose accuracy meets the preset accuracy requirements.

6. The method for identifying carbonate rock fractures based on image processing according to claim 5, characterized in that: The step of inputting the preprocessed carbonate rock image into the carbonate rock fracture information analysis model and outputting fracture information specifically includes the following steps: Perform feature analysis on the preprocessed carbonate rock image to obtain corresponding fracture width feature data, historical fracture length feature data, and historical fracture depth feature data; Inputting the obtained real-time crack width characteristic data into the crack identification model that meets the preset accuracy requirement to obtain real-time crack width information; Inputting the obtained real-time crack length characteristic data into the crack identification model that meets the preset accuracy requirement to obtain real-time crack length information; Inputting the obtained real-time crack depth characteristic data into the crack identification model that meets the preset accuracy requirement to obtain real-time crack depth information; Based on the real-time crack width information, real-time crack length information and real-time crack depth information, basic crack information is output.

7. The method for identifying carbonate rock fractures based on image processing according to claim 6, characterized in that: The similarity calculation formula between the crack type feature test data set and the crack type feature set is: simJaccard(A,B) = |A∩B| / |A∪B| Where A is the crack type feature test data set, B is the crack type feature set, |A∩B| is the intersection of the crack type feature test data set and the crack type feature set, and |A∪B| is the union of the crack type feature test data set and the crack type feature set.

8. A carbonate rock fracture identification system based on image processing, used to implement a carbonate rock fracture identification method based on image processing as claimed in claims 1-7, characterized in that: include: A shooting module, which is used to collect carbonate rock images in real time using a high-definition drone shooting device; A preprocessing module, the preprocessing module is used to preprocess the carbonate rock image to obtain the preprocessed carbonate rock image, and the internal integration of the preprocessing module includes an image denoising unit, an image enhancement unit and an image segmentation unit; A model building module, which is used to retrieve historical carbonate rock images from a database and analyze them to obtain basic information about carbonate rock fractures, wherein the basic information includes length information, depth information, and width information of the fractures, and to build a carbonate rock fracture information analysis model using a neural network model; A fracture basic information confirmation module, wherein the fracture basic information confirmation module is used to input the preprocessed carbonate rock image into the carbonate rock fracture information analysis model and output the fracture basic information; An analysis module, which is used to retrieve all existing fracture types from a database, including fracture types, dissolved pore types, and matrix types, perform feature analysis on all fracture types, obtain corresponding features of all fracture types, and form a fracture type feature set; A fracture type confirmation module is used to perform feature analysis on fractures in the preprocessed carbonate rock image, obtain corresponding fracture type feature test data, and form a fracture type feature test data set, perform similarity calculation between the fracture type feature test data set and the fracture type feature set, and determine the fracture type in the carbonate rock image.

9. The carbonate rock fracture identification system based on image processing according to claim 8, characterized in that: Also includes: An image denoising unit, which is used to denoise the carbonate rock image and obtain the denoised carbonate rock image; An image enhancement unit, wherein the image enhancement unit is used to enhance the denoised carbonate rock image to obtain an enhanced carbonate rock image; An image segmentation unit is used to segment the enhanced carbonate rock image to obtain a segmented carbonate rock image.

10. An electronic device comprising at least one processor; and a memory connected to the at least one processor in communication; characterized in that: The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

Images