Sandstone pore type identification method and device, equipment and medium

Abstract

The invention belongs to the technical field of oil-gas exploration, and particularly relates to a sandstone pore type identification method and device, equipment and a medium. The method comprises the steps of obtaining a casting body slice image of target sandstone; determining a component segmentation image, component identification information, a pore segmentation image and pore identification information of the target sandstone according to the casting body sheet image; determining a fusion image according to the component segmentation image and the pore segmentation image; and determining a pore type identification result according to the fused image, the component identification information and the pore identification information. According to the method, accurate and objective identification of sandstone pore types is realized, more accurate judgment can be made for reservoir characteristics and diagenesis understanding, and more effective technical support is provided for oil-gas exploration and development.

Description

Technical Field

[0001] The invention belongs to the technical field of oil and gas exploration, and specifically relates to a sandstone pore type identification method, device, equipment and medium. Background Art

[0002] The reservoir space of clastic rocks is mainly composed of various types of pores. The distribution and dependence of oil and gas in porous media depend on the pore structure characteristics of the reservoir. Therefore, it is of practical significance to study the pore characteristics of sandstone reservoirs, identify the pore types of sandstone reservoirs, understand reservoir characteristics and diagenesis, comprehensively evaluate reservoirs, predict the production capacity of oil and gas layers, the movement of oil and water in oil layers, water drive efficiency and improve oil recovery.

[0003] The study of pore types of clastic rocks needs to start from the microscopic level, which is usually completed by the casting thin section method. The specific steps are: 1) Sample selection and pretreatment, select suitable rock samples for oil washing treatment; 2) Rock pore casting die casting, inject dyed resin or liquid glue into the pore space of the rock under vacuum, and solidify the resin or liquid glue at a certain temperature and pressure (the internationally common resin or liquid glue is blue, and the actual colors used are blue, red, green, and yellow); 3) Casting thin section preparation, the die-cast rock sample is made into a 30μM thick thin section according to the required orientation; 4) Observation under a polarizing microscope, because the pore space in the casting thin section has been injected with dyed resin or liquid glue, it is possible to conveniently and directly observe the type, shape, size and other characteristics of the pores under a polarizing microscope, avoiding the interference of artificially induced pores or cracks.

[0004] There are many classification schemes for pore types in clastic reservoirs. Some divide pores into primary pores, secondary pores, and mixed pores based on their genesis; some divide pores into intergranular pores, intragranular pores, micropores, and fracture pores based on their occurrence; and some divide pores into supercapillary pores (pore diameter > 500 ΜM), capillary pores (pore diameter 0.2-500 ΜM), and microcapillary pores (pore diameter < 0.2 ΜM) based on their size. Based on the size classification scheme, manual estimation or image analysis can be used to extract the dyed pore space in the cast thin section and calculate the pore size. The definitions of different pore types based on the classification scheme of genesis and occurrence are all abstract natural language. For example, primary pores refer to pores formed simultaneously with sedimentation, and secondary pores refer to pores formed by dissolution, fracture and other actions during diagenesis. Therefore, the current classification of pore types is mainly based on the observation of thin section identification personnel under a polarizing microscope. The classification results of pore types are completely dependent on the identification personnel's observation of diagenetic phenomena in thin sections and their understanding of pore characteristics. It is highly subjective, lacks a unified cognitive standard, and has obvious limitations. Summary of the invention

[0005] In view of the above technical problems, the present invention proposes a method, device, equipment and medium for identifying the pore type of sandstone. The present application obtains a cast thin section image of the target sandstone; determines the component segmentation image, component identification information and pore segmentation image, pore identification information of the target sandstone according to the cast thin section image; determines a fused image according to the component segmentation image and the pore segmentation image; and determines the pore type identification result according to the fused image, the component identification information and the pore identification information. Accurate and objective identification of sandstone pore types is achieved, and more accurate judgments can be made on reservoir characteristics and diagenesis, providing more effective technical support for oil and gas exploration and development.

[0006] To solve the above technical problems, the technical solution adopted by the present invention includes four aspects.

[0007] In a first aspect, a method for identifying pore types of sandstone is provided, comprising: obtaining a cast thin section image of a target sandstone; determining a component segmentation image, component identification information and a pore segmentation image, and pore identification information of the target sandstone according to the cast thin section image; determining a fused image according to the component segmentation image and the pore segmentation image; and determining a pore type identification result according to the fused image, the component identification information and the pore identification information.

[0008] In some embodiments, determining the component segmentation image and component identification information of the target sandstone based on the cast thin section image includes: extracting component features from the cast thin section image; performing region segmentation on the cast thin section image based on the component features to obtain a component region segmentation image, wherein the component region segmentation image includes a plurality of component regions; annotating multi-level component labels on each of the component regions in the component region segmentation image based on the component features to obtain the component segmentation image; determining component identification information of the component segmentation image based on the multi-level component labels of each of the component regions, wherein the component identification information corresponds to the multi-level component labels.

[0009] In some embodiments, the determining of the pore segmentation image and pore identification information of the target sandstone according to the cast thin section image includes: extracting pore features from the cast thin section image; determining the grayscale histogram of the cast thin section image according to the pore features; performing region segmentation on the cast thin section image according to the grayscale histogram using an iterative image threshold segmentation algorithm to obtain a pore region segmentation image, wherein the pore region segmentation image includes a plurality of pore regions; annotating multi-level pore labels on each of the pore regions in the pore region segmentation image according to the pore features to obtain the pore segmentation image; and determining the pore identification information of the pore segmentation image according to the multi-level pore labels of each of the pore regions, wherein the pore identification information corresponds to the multi-level pore labels.

[0010] In some embodiments, determining the fused image based on the component segmentation image and the pore segmentation image includes: fusing each of the pore regions of the pore segmentation image with each of the component regions of the component segmentation image to obtain the fused image.

[0011] In some embodiments, determining the pore type identification result based on the fused image, the component identification information and the pore identification information includes: extracting fusion features of each of the component regions and each of the pore regions from the fused image, wherein the fusion features can characterize the overlapping areas of each of the component regions and each of the pore regions; fusing the pore identification information and the component identification information into fusion identification information according to the fusion features; and determining the pore type identification result of the target sandstone according to the fusion features and the fusion identification information.

[0012] In some embodiments, the pore identification information and the component identification information are fused into fused identification information according to the fusion feature, including: extracting target identification information corresponding to the fusion feature from the component identification information; fusing the multi-level component labels corresponding to the target identification information and the multi-level pore labels corresponding to the pore identification information step by step according to the fusion feature to obtain the fused identification information, wherein the target fusion information records the pore type identification results corresponding to each area of ​​the target sandstone.

[0013] In some embodiments, determining the component segmentation image, component identification information and pore segmentation image, pore identification information of the target sandstone based on the cast thin section image also includes: inputting the cast thin section image into a pre-trained sandstone component segmentation and identification model to obtain the component segmentation image and the component identification information of the target sandstone; inputting the cast thin section image into a pre-trained sandstone pore segmentation and identification model to obtain the pore segmentation image and the pore identification information of the target sandstone.

[0014] In the second aspect, the present application proposes a pore type identification device for sandstone, comprising: a first acquisition module, used to acquire a cast thin section image of the target sandstone; a first execution module, used to determine a component segmentation image, component identification information and a pore segmentation image, pore identification information of the target sandstone based on the cast thin section image; a first determination module, used to determine a fused image based on the component segmentation image and the pore segmentation image; and a second determination module, used to determine a pore type identification result based on the fused image, the component identification information and the pore identification information.

[0015] In a third aspect, the present application proposes an electronic device, comprising: a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the method described in the first aspect is performed.

[0016] In a fourth aspect, the present application proposes a storage medium, which stores a computer program that can be executed by one or more processors, and the computer program can be used to implement the method described in the first aspect.

[0017] Beneficial effects of the invention: The invention obtains a cast thin section image of the target sandstone; determines the component segmentation image, component identification information and pore segmentation image, pore identification information of the target sandstone according to the cast thin section image; determines a fused image according to the component segmentation image and the pore segmentation image; and determines a pore type identification result according to the fused image, the component identification information and the pore identification information. This realizes accurate and objective identification of the sandstone pore type, can make more accurate judgments on reservoir characteristics and diagenesis, and provide more effective technical support for oil and gas exploration and development. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The scope of the present disclosure may be better understood by reading the following detailed description of exemplary embodiments in conjunction with the accompanying drawings. The drawings included are:

[0019] Figure 1 An overall flow chart of a method for identifying pore types of sandstone provided in an embodiment of the present application;

[0020] Figure 2 A schematic diagram of a component segmentation image of sandstone provided in an embodiment of the present application;

[0021] Figure 3 A schematic diagram of a pore segmentation image of sandstone provided in an embodiment of the present application;

[0022] Figure 4 A schematic diagram of a fused image of sandstone provided in an embodiment of the present application;

[0023] Figure 5 A structural block diagram of an amplitude determination device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0025] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0026] If similar descriptions of "first\second\third" appear in the application documents, the following instructions will be added. In the following description, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged in a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0027] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0028] Embodiment 1:

[0029] At present, the classification of pore types is mainly based on the observation of thin section identification personnel under a polarizing microscope. The classification results of pore types are completely dependent on the identification personnel's observation of diagenetic phenomena in thin sections and their understanding of pore characteristics. It is highly subjective, lacks a unified cognitive standard, and has obvious limitations.

[0030] In view of the problems existing in the prior art, such as Figure 1 As shown, the present application provides a method for identifying the pore type of sandstone, and the method is applied to an electronic device, and the electronic device can be a server, a mobile terminal, a computer, a cloud platform, etc. The function implemented by the device data processing provided in the embodiment of the present application can be implemented by calling a program code by a processor of the electronic device, wherein the program code can be stored in a computer storage medium, and the method for identifying the pore type of sandstone includes:

[0031] Step S1: Acquire a thin section image of a target sandstone casting.

[0032] The sandstone casting thin section refers to the process of injecting dyed resin or liquid glue into the pores of the rock treated with oil washing, and then making the rock into a 30μm thick thin section after the resin or liquid glue solidifies. The target sandstone casting thin section image refers to the image obtained by observing and photographing the target sandstone casting thin section through a microscope. The obtained casting thin section image includes at least one single polarized image and one orthogonal polarized image.

[0033] Step S2: determining the component segmentation image, component identification information, pore segmentation image, and pore identification information of the target sandstone according to the cast thin section image.

[0034] In this step, two processes are performed on the cast thin section image at the same time, one is the component region segmentation process, and the other is the pore region segmentation process. The component segmentation image can represent the region where multiple components are located in the cast thin section image, and the component identification information records the component information corresponding to each region in the component segmentation image. Similarly, the pore component segmentation image can represent the region where various types of pores are located in the cast thin section image, and the pore identification information records the pore type corresponding to each pore region in the pore segmentation image. In order to better explain the means used in step S2, the two processes in step S2 are explained separately.

[0035] In some embodiments, step S2 of “determining the component segmentation image and component identification information of the target sandstone according to the cast thin section image” includes:

[0036] Step S21: extracting component features from the casting thin section image.

[0037] Step S22: performing region segmentation on the casting thin slice image according to the component characteristics to obtain a component region segmentation image, wherein the component region segmentation image includes a plurality of component regions.

[0038] There are obvious differences between different components in the cast thin section image, and the present application can extract component features from the cast thin section image. After the component features are extracted, in order to make the distinction between the component features more obvious and comparable, the extracted component features need to be normalized, and then the cast thin section image is segmented according to the normalized processing results, so that each area has only sandstone components, and a component region segmentation image consisting of multiple component regions is obtained.

[0039] Step S23: annotating each of the component regions in the component region segmentation image with a multi-level component label according to the component features to obtain the component segmentation image.

[0040] Step S24: determining component identification information of the component segmentation image according to the multi-level component labels of each of the component regions, wherein the component identification information corresponds to the multi-level component labels.

[0041] After obtaining the component region segmentation image, the components of each region in the component region segmentation image can be labeled. In order to obtain more accurate and objective pore type identification results in the present application, a multi-level labeling method is used for labeling. For example, the component labels of the target sandstone are divided into three levels. The first-level component labels include particles and fillings. The second-level labels include particles of different subtypes such as quartz, feldspar, and rock fragments, as well as fillings of different subtypes such as siliceous cement, feldspar cement, autogenous clay cement, carbonate cement, sulfate cement, and matrix. The third level is the segmentation area and identification information of particles of different subtypes such as igneous rock fragments, metamorphic rock fragments, and sedimentary rock fragments, as well as the segmentation area of ​​fillings of different subtypes, and the hierarchical labels of component types can continue to be decomposed downward. For example, further labeling can be performed by dissolution layer degree. After completing the labeling of each region in the component segmentation image, the component identification information can be obtained by sorting the labeling results. The component segmentation image is as follows: Figure 2 As shown in Table 1, the component identification results are shown in Table 1. Figure 2 is the component segmentation result of a cast thin section image on a target sandstone in a certain place, and Table 1 is the group identification information corresponding to the component segmentation result.

[0042]

[0043] Table 1

[0044] In some embodiments, step S2 of "determining the pore segmentation image and pore identification information of the target sandstone according to the cast thin section image" includes:

[0045] Step S25: extracting pore features from the casting thin section image.

[0046] Step S26: determining a grayscale histogram of the casting thin slice image according to the pore characteristics.

[0047] Step S27: using an iterative image threshold segmentation algorithm to perform region segmentation on the cast thin slice image according to the grayscale histogram to obtain a pore region segmentation image, wherein the pore region segmentation image includes a plurality of pore regions.

[0048] Step S28: annotating each pore region in the pore region segmentation image with a multi-level pore label according to the pore features to obtain the pore segmentation image.

[0049] Step S29: determining pore identification information of the pore segmentation image according to the multi-level pore labels of each of the pore regions, wherein the pore identification information corresponds to the multi-level pore labels.

[0050] The main principles of step S25-step S29 are the same as those of step S21-step S24, except that in step S26-step S27, it is proposed to use an iterative threshold segmentation algorithm to segment the cast thin film image. The optional threshold segmentation algorithm includes Otsu algorithm, adaptive threshold segmentation algorithm, maximum entropy threshold segmentation algorithm, iterative threshold segmentation algorithm, etc. For the multi-level label of pores, it can be divided into at least two levels, the first level is pores, and the second level is binary primary pores and secondary pores. The pore segmentation image is as follows Figure 3 As shown in , the pore identification information corresponding to the pore segmentation image is shown in Table 2. Figure 3 for Figure 2 The pore segmentation image of the corresponding casting thin section image.

[0051] Table 2

[0052] The above steps S21 to S29 are the principles of obtaining component segmentation images, component identification information, pore segmentation images, and pore component identification based on the cast thin section image. Those skilled in the art can achieve the purpose of step S2 based on the principles recorded in steps S21 to S29. Similarly, the principles in steps S21 to S29 can also be combined with the neural network, and the purpose of step S2 can be achieved by using a pre-trained neural network model. Therefore, in some embodiments, step S2 "determine the component segmentation image, component identification information, pore segmentation image, and pore identification information of the target sandstone based on the cast thin section image" also includes:

[0053] Step S201: inputting the casting thin section image into a pre-trained sandstone component segmentation and recognition model to obtain a component segmentation image of the target sandstone and the component recognition information.

[0054] Step S202: inputting the casting thin section image into a pre-trained sandstone pore segmentation and recognition model to obtain the pore segmentation image of the target sandstone and the pore recognition information.

[0055] The training process of the neural network is a conventional technical method, so it will not be described in detail in this application.

[0056] Step S3: determining a fused image according to the component segmentation image and the pore segmentation image.

[0057] Since the component segmentation image and the pore segmentation image are two images, it is impossible to directly obtain the pore type recognition result. Therefore, in some embodiments, step S3 "determine a fused image according to the component segmentation image and the pore segmentation image" includes:

[0058] Step S31: fusing the pore regions of the pore segmentation image and the component regions of the component segmentation image to obtain the fused image.

[0059] The component segmentation image includes multiple component regions, and the pore segmentation image also has multiple pore regions. Therefore, after the two images are fused, the pore region of the pore segmentation image overlaps with the component region of the component segmentation image, thereby obtaining a fused image that includes both component regions and pore regions.

[0060] Step S4: determining a pore type identification result according to the fused image, the component identification information and the pore identification information.

[0061] Since the component identification information records the multi-level component labels of each component area, and the pore identification information records the multi-level pore labels of each pore area, after obtaining the fused image, the pore type identification result of the target sandstone can be obtained by combining the component identification information and the pore identification information according to the overlap between the component area and the rest of the pores in the fused image. Figure 4 shown.

[0062] Therefore, in some embodiments, step S4 "fusing the pore identification information and the component identification information into fused identification information according to the fusion feature" includes:

[0063] Step S41: extracting fusion features of each of the component regions and each of the pore regions from the fused image, wherein the fusion features can characterize the overlapping areas of each of the component regions and each of the pore regions.

[0064] Step S42: fusing the pore identification information and the component identification information into fused identification information according to the fusion feature.

[0065] In some embodiments, step S42 “fusing the pore identification information and the component identification information into fused identification information according to the fusion feature” includes:

[0066] Step S421: extracting target identification information corresponding to the fusion feature from the component identification information.

[0067] Since the pore area and part of the fusion area are in an overlapping state in the fusion image, and the purpose of this application is to obtain the pore type identification result, in order to reduce the amount of calculation, it is necessary to extract the fusion feature from the fusion image. The fusion feature expresses the fusion of each pore area and each component area. Since there are not pores in every component area on the target sandstone, the component identification information can be screened according to the fusion feature, and the multi-level component labels corresponding to the component areas that overlap with the pore area are sorted as target identification information.

[0068] Step S422: According to the fusion feature, the multi-level component labels corresponding to the target identification information and the multi-level pore labels corresponding to the pore identification information are fused step by step to obtain the fused identification information, wherein the target fusion information records the pore type identification results corresponding to each area of ​​the target sandstone.

[0069] After obtaining the target identification information, the target identification information and the pore identification information can be fused according to the fusion feature, that is, the coincidence and overlap between the pore area and the component area. During the fusion, the fused identification information is obtained in a step-by-step fusion manner.

[0070] For example, the first-level component labels are: particles and fillers, and the first-level pore label is pores. We know that the pores in the particles are intragranular pores, and the pores in the fillers are intergranular pores. Therefore, we mark the first-level fusion label where the pore area and the particle area overlap as intragranular pores, and the first-level fusion label where the pore area and the filler area overlap as intergranular pores. At this time, the second-level component label and the second-level pore label are further fused on the basis of the first-level fusion label, and then the fusion labels of each level are sorted to obtain the fusion identification information. The final fusion identification information is shown in Table 3.

[0071] Table 3

[0072] Step S43: determining the pore type identification result of the target sandstone according to the fusion feature and the fusion identification information.

[0073] After obtaining the fused identification information shown in Table 3, we can obtain the pore type identification results of the target sandstone by fusing the identification information. The pore type identification results are shown in Table 4.

[0074] Pore ​​number Final identification result of pore type K1 Pores in primary igneous rock K2 Pores in primary igneous rock K3 Pores in secondary plagioclase grains K4 Pores in secondary plagioclase grains K5 Pores in secondary plagioclase grains K6 Intergranular pores in secondary calcite cement K7 Pores in secondary plagioclase grains K8 Secondary intergranular pores K9 Primary intergranular pores K10 Primary intergranular pores K11 Intergranular pores in secondary calcite cement K12 Pores in secondary granite rock fragments

[0075] Table 4

[0076] The present application obtains a cast thin section image of the target sandstone; determines the component segmentation image, component identification information, pore segmentation image, and pore identification information of the target sandstone according to the cast thin section image; determines a fused image according to the component segmentation image and the pore segmentation image; and determines a pore type identification result according to the fused image, the component identification information, and the pore identification information. This achieves accurate and objective identification of the sandstone pore type, can make more accurate judgments on reservoir characteristics and diagenesis, and provide more effective technical support for oil and gas exploration and development.

[0077] This application can identify sandstone pore types based on image methods without human intervention. Compared with traditional manual methods, it eliminates subjective influences and has more objective results. Sandstone component segmentation and identification, as well as pore segmentation and identification, are completed based on machine learning methods. Big data is fully utilized to summarize the trends and patterns of human identification of sandstone and pores, and used to deduce the prediction of unknown sandstone and pores. Multi-level labels are set for sandstone components and pores, and the final identification results of pore types are obtained through hierarchical cross-matching of component analysis results and pore analysis results. It has strong operability and high universality.

[0078] Embodiment 2:

[0079] Based on the foregoing embodiments, an embodiment of the present application provides a device for identifying the pore type of sandstone. The modules included in the device and the units included in each module can be implemented by a processor in a computer device; of course, they can also be implemented by a specific logic circuit; in the implementation process, the processor can be a central processing unit (CPU, Central Processing Unit), a microprocessor (MPU, Microprocessor Unit), a digital signal processor (DSP, Digital Signal Processing) or a field programmable gate array (FPGA, Field Programmable Gate Array), etc.

[0080] like Figure 5 As shown, a device for identifying pore types of sandstone includes: a first acquisition module 1, a first execution module 2, a first determination module 3 and a second determination module 4.

[0081] The first acquisition module 1 is used to acquire a cast thin section image of the target sandstone. The first execution module 2 is used to determine the component segmentation image, component identification information, pore segmentation image, and pore identification information of the target sandstone according to the cast thin section image. The first determination module 3 is used to determine a fused image according to the component segmentation image and the pore segmentation image. The second determination module 4 is used to determine a pore type identification result according to the fused image, the component identification information, and the pore identification information.

[0082] In some embodiments, the first execution module 2 includes: a second execution module, a third execution module, a fourth execution module and a third determination module.

[0083] The second execution module is used to extract component features from the cast thin section image. The third execution module is used to perform region segmentation on the cast thin section image according to the component features to obtain a component region segmentation image, wherein the component region segmentation image includes a plurality of component regions. The fourth execution module is used to annotate multi-level component labels on each of the component regions in the component region segmentation image according to the component features to obtain the component segmentation image. The third determination module is used to determine the component identification information of the component segmentation image according to the multi-level component labels of each of the component regions, wherein the component identification information corresponds to the multi-level component labels.

[0084] In some embodiments, the first execution module 2 further includes: a fifth execution module, a sixth execution module, a seventh execution module, an eighth execution module and a fourth determination module.

[0085] The fifth execution module is used to extract pore features from the cast thin section image. The sixth execution module is used to determine the grayscale histogram of the cast thin section image according to the pore features. The seventh execution module is used to perform regional segmentation on the cast thin section image according to the grayscale histogram using an iterative image threshold segmentation algorithm to obtain a pore region segmentation image, wherein the pore region segmentation image includes multiple pore regions. The eighth execution module is used to annotate multi-level pore labels on each of the pore regions in the pore region segmentation image according to the pore features to obtain the pore segmentation image. The fourth determination module is used to determine the pore identification information of the pore segmentation image according to the multi-level pore labels of each of the pore regions, wherein the pore identification information corresponds to the multi-level pore labels.

[0086] In some embodiments, the first determination module 3 includes: a ninth execution module.

[0087] The ninth execution module is used to fuse the pore regions of the pore segmentation image and the component regions of the component segmentation image to obtain the fused image.

[0088] In some embodiments, the second determination module 4 includes: a tenth execution module, an eleventh execution module and a fifth determination module.

[0089] The tenth execution module is used to extract the fusion features of each component region and each pore region from the fusion image, wherein the fusion features can characterize the overlapping areas of each component region and each pore region. The eleventh execution module is used to fuse the pore identification information and the component identification information into fusion identification information according to the fusion features. The fifth determination module is used to determine the pore type identification result of the target sandstone according to the fusion features and the fusion identification information.

[0090] In some embodiments, the eleventh execution module includes: a twelfth execution module and a thirteenth execution module.

[0091] The twelfth execution module is used to extract the target identification information corresponding to the fusion feature from the component identification information. The thirteenth execution module is used to fuse the multi-level component labels corresponding to the target identification information and the multi-level pore labels corresponding to the pore identification information step by step according to the fusion feature to obtain the fusion identification information, wherein the target fusion information records the pore type identification results corresponding to each area of ​​the target sandstone.

[0092] In some embodiments, the first execution module 2 further includes: a fourteenth execution module and a fifteenth execution module.

[0093] The fourteenth execution module is used to input the cast thin section image into a pre-trained sandstone component segmentation and recognition model to obtain the component segmentation image of the target sandstone and the component identification information. The fifteenth execution module is used to input the cast thin section image into a pre-trained sandstone pore segmentation and recognition model to obtain the pore segmentation image of the target sandstone and the pore identification information.

[0094] Each module in the above-mentioned sandstone pore type identification device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the device in the form of hardware, or can be stored in the memory in the processing device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0095] Embodiment 3:

[0096] A third aspect provides an electronic device, including a storage device and a processor, wherein the storage device stores a computer program, and when the processor executes the computer program, steps of a method for identifying the pore type of sandstone are implemented.

[0097] Embodiment 4:

[0098] A fourth aspect provides a storage medium, wherein a computer program stored in the storage medium can be executed by one or more processors, and the computer program can be used to implement the steps of any one of the sandstone pore type identification methods in the first aspect.

[0099] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0100] It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the size of the sequence number of the above-mentioned processes does not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The above-mentioned sequence numbers of the embodiments of the present application are only for description and do not represent the advantages and disadvantages of the embodiments.

[0101] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0102] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0103] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0104] In addition, all functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may be a separate unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0105] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read Only Memory), disks or optical disks, etc. Various media that can store program codes.

[0106] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application can essentially or in other words, the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for a controller to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0107] The above is only an implementation method of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for identifying pore types of sandstone, characterized in that: include: Obtain cast thin-section images of target sandstone; Determining a component segmentation image, component identification information, a pore segmentation image, and pore identification information of the target sandstone according to the cast thin section image; Determine a fused image according to the component segmentation image and the pore segmentation image; A pore type identification result is determined according to the fused image, the component identification information and the pore identification information.

2. The method according to claim 1, characterized in that The step of determining the component segmentation image and component identification information of the target sandstone according to the cast thin section image comprises: extracting component features from the casting thin section image; Performing regional segmentation on the casting thin slice image according to the component characteristics to obtain a component regional segmentation image, wherein the component regional segmentation image includes a plurality of component regions; According to the component features, each of the component regions in the component region segmentation image is annotated with a multi-level component label to obtain the component segmentation image; The component identification information of the component segmentation image is determined according to the multi-level component labels of each of the component regions, wherein the component identification information corresponds to the multi-level component labels.

3. The method according to claim 2, characterized in that The step of determining the pore segmentation image and pore identification information of the target sandstone according to the cast thin section image comprises: extracting pore features from the casting thin section image; Determining a grayscale histogram of the casting thin section image according to the pore characteristics; Using an iterative image threshold segmentation algorithm to perform regional segmentation on the cast thin slice image according to the grayscale histogram to obtain a pore region segmentation image, wherein the pore region segmentation image includes a plurality of pore regions; annotating each pore region in the pore region segmentation image with a multi-level pore label according to the pore characteristics to obtain the pore segmentation image; The pore identification information of the pore segmentation image is determined according to the multi-level pore labels of each of the pore regions, wherein the pore identification information corresponds to the multi-level pore labels.

4. The method according to claim 3, characterized in that: The determining of the fused image according to the component segmentation image and the pore segmentation image comprises: The pore regions of the pore segmentation image and the component regions of the component segmentation image are fused to obtain the fused image.

5. The method according to claim 4, characterized in that The determining of the pore type identification result according to the fused image, the component identification information and the pore identification information comprises: Extracting fusion features of each of the component regions and each of the pore regions from the fused image, wherein the fusion features can characterize the overlapping areas of each of the component regions and each of the pore regions; fusing the pore identification information and the component identification information into fused identification information according to the fusion feature; The pore type identification result of the target sandstone is determined according to the fusion feature and the fusion identification information.

6. The method according to claim 5, characterized in that The step of fusing the pore identification information and the component identification information into fused identification information according to the fusion feature comprises: Extracting target identification information corresponding to the fusion feature from the component identification information; According to the fusion feature, the multi-level component labels corresponding to the target identification information and the multi-level pore labels corresponding to the pore identification information are fused step by step to obtain the fused identification information, wherein the target fusion information records the pore type identification results corresponding to each area of ​​the target sandstone.

7. The method according to claim 1, characterized in that The method of determining the component segmentation image, component identification information and pore segmentation image, pore identification information of the target sandstone according to the cast thin section image also includes: Inputting the cast thin section image into a pre-trained sandstone component segmentation and recognition model to obtain a component segmentation image of the target sandstone and the component recognition information; The cast thin section image is input into a pre-trained sandstone pore segmentation and recognition model to obtain the pore segmentation image of the target sandstone and the pore recognition information.

8. A device for identifying pore types of sandstone, characterized in that: include: A first acquisition module is used to acquire a cast thin section image of the target sandstone; A first execution module is used to determine a component segmentation image, component identification information, a pore segmentation image, and pore identification information of the target sandstone according to the cast thin section image; A first determination module, configured to determine a fused image according to the component segmentation image and the pore segmentation image; The second determination module is used to determine the pore type identification result according to the fused image, the component identification information and the pore identification information.

9. An electronic device, characterized in that: include: A memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the method according to any one of claims 1 to 7 is executed.

10. A storage medium, characterized in that: The computer program stored in the storage medium can be executed by one or more processors, and the computer program can be used to implement the method according to any one of claims 1 to 7.

Images