A rock and soil structure analysis method and system based on image processing

Abstract

The present invention discloses a rock and soil structure analysis method and system based on image processing, the method comprising: obtaining the first size of a target area in a rock and soil single-layer image corresponding to a rock and soil single-layer sub-image, and using a preset screening rule to screen out a target rock and soil single-layer image that meets preset conditions from other rock and soil single-layer images; obtaining a target single-layer sub-image corresponding to the target rock and soil single-layer image, and correcting the first size of the target area in a rock and soil single-layer image according to the second size of the target area in the target single-layer sub-image and the third size of the target area in a rock and soil single-layer sub-image, to obtain the actual size of the target area in a rock and soil single-layer image, that is, the actual thickness of a rock and soil single layer. The method realizes a relatively accurate identification of the thickness of irregular rock and soil layers, and solves the problem of inaccurate analysis of the thickness of some rock and soil layers caused by the transfer of some rock and soil layers due to settlement or soil erosion at some sampling points.

Description

Technical Field

[0001] The present invention belongs to the technical field of rock and soil image analysis, and in particular relates to a rock and soil structure analysis method and system based on image processing. Background Art

[0002] Natural rock and soil are formed by weathering, transportation and accumulation of rocks. Therefore, the composition of the parent rock, weathering properties, transportation process and accumulation environment are the main factors affecting the composition of soil, and the thickness of different soil layers is the basis for determining the engineering properties of foundation soil.

[0003] The existing soil layer identification method obtains rock and soil core samples by drilling and measures the thickness of each soil layer of the rock and soil core samples. Although this method is simple, when settlement occurs at the sampling point or erosion occurs in the adjacent upper and lower soil layers, causing partial soil layer shift in the area where the sampling point is located, this soil layer identification method will have a significant deviation from the actual soil layer thickness, and the accuracy of soil layer identification is low. Summary of the invention

[0004] The present invention provides a rock and soil structure analysis method and system based on image processing, which are used to solve the technical problem of inaccurate identification of rock and soil layer thickness at some sampling points due to partial rock and soil layer transfer caused by settlement of some sampling points or rock and soil layer erosion.

[0005] In a first aspect, the present invention provides a geotechnical structure analysis method based on image processing, comprising:

[0006] Acquire rock and soil layer images of at least two sampling points, and input each rock and soil layer image into a pre-built image recognition model, the image recognition model outputs a labeled image corresponding to each rock and soil layer image, wherein the rock and soil layer image includes multiple types of rock and soil layers;

[0007] Segmenting a certain marked image corresponding to a certain rock and soil layer image using a preset segmentation strategy to obtain at least one rock and soil single layer image and a rock and soil single layer sub-image corresponding to the at least one rock and soil single layer image;

[0008] Determine whether there is a target area in a rock and soil single layer sub-image, wherein the target area is an area including the rock and soil layer;

[0009] If the target area exists, a first size of the target area in a certain rock and soil single layer image corresponding to the certain rock and soil single layer sub-image is obtained, and a preset screening rule is used to screen out a target rock and soil single layer image that meets the preset conditions from other rock and soil single layer images, wherein the other rock and soil single layer images are rock and soil single layer images obtained by segmenting the rock and soil layer images of other sampling points;

[0010] A target single-layer sub-image corresponding to the target rock and soil single-layer image is obtained, and a first size of the target area in the rock and soil single-layer image is corrected according to a second size of the target area in the target single-layer sub-image and a third size of the target area in the rock and soil single-layer sub-image to obtain an actual size of the target area in the rock and soil single-layer image, that is, an actual thickness of a rock and soil single layer.

[0011] In a second aspect, the present invention provides a geotechnical structure analysis system based on image processing, comprising:

[0012] an acquisition module, configured to acquire rock and soil layer images of at least two sampling points, and input each rock and soil layer image into a pre-built image recognition model, wherein the image recognition model outputs a labeled image corresponding to each rock and soil layer image, wherein the rock and soil layer image includes multiple types of rock and soil layers;

[0013] A segmentation module is configured to segment a certain marked image corresponding to a certain rock and soil layer image using a preset segmentation strategy to obtain at least one rock and soil single layer image and a rock and soil single layer sub-image corresponding to the at least one rock and soil single layer image;

[0014] A judgment module configured to judge whether there is a target area in a certain rock and soil single layer sub-image, wherein the target area is an area containing a rock and soil layer;

[0015] a screening module configured to obtain, if a target area exists, a first size of the target area in a certain rock and soil single-layer image corresponding to the certain rock and soil single-layer sub-image, and to screen out a target rock and soil single-layer image that meets preset conditions from other rock and soil single-layer images using a preset screening rule, wherein the other rock and soil single-layer images are rock and soil single-layer images obtained by segmenting rock and soil layer images of other sampling points;

[0016] The correction module is configured to obtain a target single-layer sub-image corresponding to the target rock and soil single-layer image, and to correct the first size of the target area in the rock and soil single-layer image according to the second size of the target area in the target single-layer sub-image and the third size of the target area in the rock and soil single-layer sub-image, so as to obtain the actual size of the target area in the rock and soil single-layer image, that is, the actual thickness of a rock and soil single layer.

[0017] According to a third aspect, an electronic device is provided, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein 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 steps of the geotechnical structure analysis method based on image processing according to any embodiment of the present invention.

[0018] In a fourth aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor executes the steps of the geotechnical structure analysis method based on image processing according to any embodiment of the present invention.

[0019] The present application discloses a rock and soil structure analysis method and system based on image processing, which uses preset screening rules to screen out a target rock and soil single-layer image that meets preset conditions from other rock and soil single-layer images, and can relatively accurately find other sampling points with similar distribution structures to the current rock and soil layer of the current sampling point, thereby comparing the current rock and soil layer of the current sampling point with the current rock and soil layer of other sampling points, and can effectively analyze whether a partial rock and soil layer transfer occurs at the current sampling point; and obtain a target single-layer sub-image corresponding to the target rock and soil single-layer image, and correct the first size of the target area in a certain rock and soil single-layer image according to the second size of the target area in the target single-layer sub-image and the third size of the target area in a certain rock and soil single-layer sub-image, thereby achieving relatively accurate identification of the thickness of irregular rock and soil layers, and solving the problem of inaccurate analysis of the thickness of some rock and soil layers at some sampling points due to the transfer of some rock and soil layers caused by settlement or soil erosion at some sampling points. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 A flowchart of a geotechnical structure analysis method based on image processing provided by one embodiment of the present invention;

[0022] Figure 2 A structural block diagram of a geotechnical structure analysis system based on image processing provided by an embodiment of the present invention;

[0023] Figure 3 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] See also Figure 1 , which shows a flow chart of a geotechnical structure analysis method based on image processing of the present application.

[0026] like Figure 1 As shown, the geotechnical structure analysis method based on image processing specifically includes the following steps:

[0027] Step S101, obtaining rock and soil layer images of at least two sampling points, and inputting each rock and soil layer image into a pre-built image recognition model, the image recognition model outputs a labeled image corresponding to each rock and soil layer image, wherein the rock and soil layer image contains multiple types of rock and soil layers.

[0028] In this step, the image recognition model may be a model obtained by iteratively training each rock and soil layer image and the annotations of the rock and soil layer images into a neural network, and the neural network may be a VGGNet network or other convolutional neural networks.

[0029] Step S102, using a preset segmentation strategy to segment a certain marked image corresponding to a certain rock and soil layer image, to obtain at least one rock and soil single layer image, and a rock and soil single layer sub-image corresponding to the at least one rock and soil single layer image.

[0030] In this step, a certain marked image contains at least one rock-soil layer region. For example, the marked image A contains rock-soil layer region a, rock-soil layer region b and rock-soil layer region c from top to bottom.

[0031] Specifically, a marked image is segmented according to the distribution of at least one rock and soil layer area to obtain a marked sub-image corresponding to at least one rock and soil layer area; the maximum inscribed rectangular area is intercepted in a marked sub-image to obtain a rock and soil single-layer image containing the maximum inscribed rectangular area, and a rock and soil single-layer sub-image not containing the maximum inscribed rectangular area, wherein the maximum inscribed rectangular area is the maximum rectangular area in a marked sub-image that only contains the rock and soil layer area.

[0032] For example, the marked image A is divided from top to bottom into a first marked sub-image, a second marked sub-image and a third marked sub-image according to the rock-soil layer region a, the rock-soil layer region b and the rock-soil layer region c.

[0033] The maximum rectangular area is intercepted in the first marked sub-image, the second marked sub-image and the third marked sub-image respectively, that is, the first marked sub-image is divided into the first rock and soil single layer image and the first rock and soil single layer sub-image, the second marked sub-image is divided into the second rock and soil single layer image and the second rock and soil single layer sub-image, and the third marked sub-image is divided into the third rock and soil single layer image and the third rock and soil single layer sub-image.

[0034] Step S103, determining whether there is a target area in a certain rock and soil single layer sub-image, wherein the target area is an area including the rock and soil layer.

[0035] In a specific embodiment, if the target area does not exist in a certain rock and soil single layer sub-image, it means that the actual rock and soil layer corresponding to the certain rock and soil single layer image is relatively flat, and there is no settlement, or partial rock and soil layers are transferred to each other, or the terrain is uneven. Therefore, the first size of the target area in a certain rock and soil single layer image can be directly used as the actual size of the target area in a certain rock and soil single layer image, that is, the actual thickness of a certain rock and soil single layer. In this way, the thickness of the rock and soil layer corresponding to the current sampling point and a certain rock and soil single layer image can be determined more accurately and quickly.

[0036] Step S104, if there is a target area, obtain the first size of the target area in a certain rock and soil single layer image corresponding to the certain rock and soil single layer sub-image, and use the preset screening rules to screen out the target rock and soil single layer image that meets the preset conditions from other rock and soil single layer images, wherein the other rock and soil single layer images are rock and soil single layer images obtained after segmenting the rock and soil layer images of other sampling points.

[0037] In this step, the preset condition is that the difference between the fourth size of the target area in the target rock and soil single layer image and the first size of the target area in a certain rock and soil single layer image is less than a first preset threshold.

[0038] It should be noted that the location information of each sampling point on the electronic map is obtained, and other rock and soil single-layer images are obtained in sequence according to the rule from far to near for a certain position point of the sampling point corresponding to a certain rock and soil single-layer image, and the target rock and soil single-layer image that meets the preset conditions is screened out from other rock and soil single-layer images. In this way, by sequentially obtaining and screening other rock and soil single-layer images according to the rule from far to near, it is possible to avoid the problem of inaccurate subsequent analysis when adjacent sampling points or sampling points with a small interval also sink or part of the rock and soil layers are transferred to each other.

[0039] For example, for the rock and soil single layer image A of the current sampling point, other rock and soil single layer images are obtained in sequence from far to near. Among them, according to the order of position distance from large to small, it is found that the rock and soil single layer image B, rock and soil single layer image C and rock and soil single layer image D meet the preset conditions. Since the sampling point corresponding to the rock and soil single layer image B is farthest from the sampling point corresponding to the rock and soil single layer image A, the rock and soil single layer image B is used as the target rock and soil single layer image.

[0040] Step S105, obtaining a target single-layer sub-image corresponding to the target rock and soil single-layer image, and correcting the first size of the target area in the rock and soil single-layer image according to the second size of the target area in the target single-layer sub-image and the third size of the target area in the rock and soil single-layer sub-image, to obtain the actual size of the target area in the rock and soil single-layer image, that is, the actual thickness of a rock and soil single layer.

[0041] In this step, the first change amount between the third size and the second size, and the second change amount between the first size and the fourth size are obtained; it is determined whether the difference between the first size change amount and the second size change amount is greater than the second preset threshold value; if the difference between the first size change amount and the second size change amount is greater than the second preset threshold value, it means that the rock layer corresponding to a certain rock and soil single layer image may have partially shifted at the sampling point, and the partial shift of the soil layer may be caused by settlement or soil erosion, so the thickness of the rock and soil layer corresponding to a certain rock and soil single layer image is not corrected, that is, the first size is directly used as the actual size of the target area in a certain rock and soil single layer image. If the difference between the first size change amount and the second size change amount is not greater than the second preset threshold value, it means that the soil layer corresponding to a certain rock and soil single layer image is relatively stable at the sampling point, and no partial shift of the soil layer occurs. The situation that the target area exists in a certain rock and soil single layer sub-image may be caused by the uneven distribution of the rock and soil layers, which is a normal situation. Therefore, half of the third size is superimposed with the first size of the target area in a certain rock and soil single layer image to obtain the corrected actual size of the target area in a certain rock and soil single layer image.

[0042] In summary, the method of the present application firstly adopts a preset segmentation strategy to segment a certain marked image corresponding to a certain rock and soil layer image, and obtains at least one rock and soil single-layer image, and a rock and soil single-layer sub-image corresponding to at least one rock and soil single-layer image, which can facilitate the subsequent analysis of the rock and soil layer conditions of each current sampling point, and then determines whether there is a target area in a certain rock and soil single-layer sub-image. If there is a target area, the first size of the target area in a certain rock and soil single-layer image corresponding to the certain rock and soil single-layer sub-image is obtained, and a preset screening rule is used to screen out the target rock and soil single-layer image that meets the preset conditions from other rock and soil single-layer images, so that the current rock and soil layer sub-image corresponding to the current sampling point can be found more accurately. Other sampling points with similar distribution structures are selected, so as to compare the current rock and soil layer of the current sampling point with the current rock and soil layers of other sampling points, so as to effectively analyze whether part of the rock and soil layer transfer occurs at the current sampling point. Finally, a target single-layer sub-image corresponding to the target rock and soil single-layer image is obtained, and the first size of the target area in a certain rock and soil single-layer image is corrected according to the second size of the target area in the target single-layer sub-image and the third size of the target area in a certain rock and soil single-layer sub-image, so as to realize more accurate recognition of the thickness of irregular rock and soil layers, and solve the problem of inaccurate analysis of the thickness of some rock and soil layers at some sampling points caused by the transfer of some rock and soil layers due to settlement or soil erosion at some sampling points.

[0043] See also Figure 2 , which shows a structural block diagram of a geotechnical structure analysis system based on image processing of the present application.

[0044] like Figure 2 As shown, the geotechnical structure analysis system 200 includes an acquisition module 210 , a segmentation module 220 , a judgment module 230 , a screening module 240 and a correction module 250 .

[0045] Among them, the acquisition module 210 is configured to acquire rock and soil layer images of at least two sampling points, and input each rock and soil layer image into a pre-constructed image recognition model, and the image recognition model outputs a labeled image corresponding to each rock and soil layer image, wherein the rock and soil layer image contains multiple types of rock and soil layers; the segmentation module 220 is configured to segment a labeled image corresponding to a certain rock and soil layer image using a preset segmentation strategy to obtain at least one rock and soil single layer image, and a rock and soil single layer sub-image corresponding to the at least one rock and soil single layer image; the judgment module 230 is configured to judge whether there is a target area in a certain rock and soil single layer sub-image, and the target area is an area containing rock and soil layers; the screening module 240 is configured to, if the target area exists, Then, a first size of a target area in a certain rock and soil single layer image corresponding to the certain rock and soil single layer sub-image is obtained, and a preset screening rule is used to screen out a target rock and soil single layer image that meets the preset conditions from other rock and soil single layer images, wherein the other rock and soil single layer images are rock and soil single layer images obtained after segmenting the rock and soil layer images of other sampling points; a correction module 250 is configured to obtain a target single layer sub-image corresponding to the target rock and soil single layer image, and correct the first size of the target area in the certain rock and soil single layer image according to the second size of the target area in the target single layer sub-image and the third size of the target area in the certain rock and soil single layer sub-image, so as to obtain the actual size of the target area in the certain rock and soil single layer image, that is, the actual thickness of a certain rock and soil single layer.

[0046] It should be understood that Figure 2 Modules and references documented in Figure 1 Therefore, the operations and features described above for the method and the corresponding technical effects are also applicable to Figure 2 The modules in it will not be described in detail here.

[0047] In some other embodiments, the embodiments of the present invention further provide a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor is caused to execute the geotechnical structure analysis method based on image processing in any of the above method embodiments;

[0048] As an implementation mode, the computer-readable storage medium of the present invention stores computer-executable instructions, and the computer-executable instructions are configured as follows:

[0049] Acquire rock and soil layer images of at least two sampling points, and input each rock and soil layer image into a pre-built image recognition model, the image recognition model outputs a labeled image corresponding to each rock and soil layer image, wherein the rock and soil layer image includes multiple types of rock and soil layers;

[0050] Segmenting a certain marked image corresponding to a certain rock and soil layer image using a preset segmentation strategy to obtain at least one rock and soil single layer image and a rock and soil single layer sub-image corresponding to the at least one rock and soil single layer image;

[0051] Determine whether there is a target area in a rock and soil single layer sub-image, wherein the target area is an area including the rock and soil layer;

[0052] If the target area exists, a first size of the target area in a certain rock and soil single layer image corresponding to the certain rock and soil single layer sub-image is obtained, and a preset screening rule is used to screen out a target rock and soil single layer image that meets the preset conditions from other rock and soil single layer images, wherein the other rock and soil single layer images are rock and soil single layer images obtained by segmenting the rock and soil layer images of other sampling points;

[0053] A target single-layer sub-image corresponding to the target rock and soil single-layer image is obtained, and a first size of the target area in the rock and soil single-layer image is corrected according to a second size of the target area in the target single-layer sub-image and a third size of the target area in the rock and soil single-layer sub-image to obtain an actual size of the target area in the rock and soil single-layer image, that is, an actual thickness of a rock and soil single layer.

[0054] The computer-readable storage medium may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the geotechnical structure analysis system based on image processing, etc. In addition, the computer-readable storage medium may include a high-speed random access memory, and may also include a memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the computer-readable storage medium may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the geotechnical structure analysis system based on image processing via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0055] Figure 3 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 3 As shown, the device includes: a processor 310 and a memory 320. The electronic device may also include: an input device 330 and an output device 340. The processor 310, the memory 320, the input device 330 and the output device 340 may be connected via a bus or other means. Figure 3In the example, the bus connection is used. The memory 320 is the above-mentioned computer-readable storage medium. The processor 310 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 320, that is, the geotechnical structure analysis method based on image processing of the above-mentioned method embodiment is realized. The input device 330 can receive input digital or character information, and generate key signal input related to user settings and function control of the geotechnical structure analysis system based on image processing. The output device 340 may include display devices such as display screens.

[0056] The electronic device can execute the method provided by the embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not described in detail in this embodiment, please refer to the method provided by the embodiment of the present invention.

[0057] As an implementation mode, the electronic device is applied to a geotechnical structure analysis system based on image processing, and is used for a client, and includes: at least one processor; and a memory connected to the at least one processor in communication; wherein 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:

[0058] Acquire rock and soil layer images of at least two sampling points, and input each rock and soil layer image into a pre-built image recognition model, the image recognition model outputs a labeled image corresponding to each rock and soil layer image, wherein the rock and soil layer image includes multiple types of rock and soil layers;

[0059] Segmenting a certain marked image corresponding to a certain rock and soil layer image using a preset segmentation strategy to obtain at least one rock and soil single layer image and a rock and soil single layer sub-image corresponding to the at least one rock and soil single layer image;

[0060] Determine whether there is a target area in a rock and soil single layer sub-image, wherein the target area is an area including the rock and soil layer;

[0061] If the target area exists, a first size of the target area in a certain rock and soil single layer image corresponding to the certain rock and soil single layer sub-image is obtained, and a preset screening rule is used to screen out a target rock and soil single layer image that meets the preset conditions from other rock and soil single layer images, wherein the other rock and soil single layer images are rock and soil single layer images obtained by segmenting the rock and soil layer images of other sampling points;

[0062] A target single-layer sub-image corresponding to the target rock and soil single-layer image is obtained, and a first size of the target area in the rock and soil single-layer image is corrected according to a second size of the target area in the target single-layer sub-image and a third size of the target area in the rock and soil single-layer sub-image to obtain an actual size of the target area in the rock and soil single-layer image, that is, an actual thickness of a rock and soil single layer.

[0063] Through the description of the above implementation modes, those skilled in the art can clearly understand that each implementation mode can be implemented by means of software plus a necessary general hardware platform, or of course by hardware. Based on such an understanding, the above technical solution can essentially or in other words be embodied in the form of a software product that contributes to the prior art. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment.

[0064] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A geotechnical structure analysis method based on image processing, characterized in that: include: Acquire rock and soil layer images of at least two sampling points, and input each rock and soil layer image into a pre-built image recognition model, the image recognition model outputs a labeled image corresponding to each rock and soil layer image, wherein the rock and soil layer image includes multiple types of rock and soil layers; Segmenting a certain marked image corresponding to a certain rock and soil layer image using a preset segmentation strategy to obtain at least one rock and soil single layer image and a rock and soil single layer sub-image corresponding to the at least one rock and soil single layer image; Determine whether there is a target area in a rock and soil single layer sub-image, wherein the target area is an area including the rock and soil layer; If there is a target area, a first size of the target area in a certain rock and soil single-layer image corresponding to the certain rock and soil single-layer sub-image is obtained, and a preset screening rule is used to screen out a target rock and soil single-layer image that meets a preset condition from other rock and soil single-layer images, wherein the other rock and soil single-layer images are rock and soil single-layer images obtained by segmenting rock and soil layer images of other sampling points, and the preset condition is that a difference between a fourth size of the target area in the target rock and soil single-layer image and a first size of the target area in the certain rock and soil single-layer image is less than a first preset threshold value; The method of using a preset screening rule to screen out a target rock and soil single layer image that meets the preset conditions from other rock and soil single layer images includes: Obtaining the location information of each sampling point on the electronic map, and sequentially obtaining other rock and soil single-layer images according to the rule from far to near of a certain location point of the sampling point corresponding to the said rock and soil single-layer image, and screening out the target rock and soil single-layer image that meets the preset conditions from the other rock and soil single-layer images; A target single-layer sub-image corresponding to the target rock and soil single-layer image is obtained, and a first size of the target area in the rock and soil single-layer image is corrected according to a second size of the target area in the target single-layer sub-image and a third size of the target area in the rock and soil single-layer sub-image to obtain an actual size of the target area in the rock and soil single-layer image, that is, an actual thickness of a rock and soil single layer, wherein the first size of the target area in the rock and soil single-layer image is corrected according to the second size of the target area in the target single-layer sub-image and the third size of the target area in the rock and soil single-layer sub-image to obtain the actual size of the target area in the rock and soil single-layer image includes: Acquire a first change amount between the third size and the second size, and a second change amount between the first size and the fourth size; Determine whether the difference between the first size change and the second size change is greater than a second preset threshold; If the difference between the first size change and the second size change is greater than a second preset threshold, the first size is directly used as the actual size of the target area in a certain rock and soil single layer image, that is, the actual thickness of a certain rock and soil single layer; If the difference between the first size change and the second size change is not greater than the second preset threshold, half of the third size is superimposed on the first size of the target area in the rock and soil single layer image to obtain the actual size of the target area in the corrected rock and soil single layer image.

2. The method for analyzing rock and soil structures based on image processing according to claim 1, characterized in that: The certain marked image contains at least one rock and soil layer area; The method of using a preset segmentation strategy to segment a certain marked image corresponding to a certain rock and soil layer image to obtain at least one rock and soil single layer image, and the rock and soil single layer sub-image corresponding to the at least one rock and soil single layer image includes: Segmenting the certain marked image according to the distribution of the at least one rock and soil layer area to obtain a marked sub-image corresponding to the at least one rock and soil layer area; The maximum inscribed rectangular area is intercepted in a certain marked sub-image to obtain a certain rock and soil single-layer image containing the maximum inscribed rectangular area, and a certain rock and soil single-layer sub-image not containing the maximum inscribed rectangular area, wherein the maximum inscribed rectangular area is the maximum rectangular area that only contains the rock and soil layer area in the certain marked sub-image.

3. The method for analyzing rock and soil structures based on image processing according to claim 1, characterized in that: After determining whether there is a target area in a rock and soil single layer sub-image, the target area being an area including a rock and soil layer, the method further includes: If the target area does not exist, the first size of the target area in a certain rock and soil single layer image corresponding to the certain rock and soil single layer sub-image is obtained, and the first size is directly used as the actual size of the target area in the certain rock and soil single layer image, that is, the actual thickness of a certain rock and soil single layer.

4. A geotechnical structure analysis system based on image processing, characterized in that: include: an acquisition module, configured to acquire rock and soil layer images of at least two sampling points, and input each rock and soil layer image into a pre-built image recognition model, wherein the image recognition model outputs a labeled image corresponding to each rock and soil layer image, wherein the rock and soil layer image includes multiple types of rock and soil layers; A segmentation module is configured to segment a certain marked image corresponding to a certain rock and soil layer image using a preset segmentation strategy to obtain at least one rock and soil single layer image and a rock and soil single layer sub-image corresponding to the at least one rock and soil single layer image; A judgment module configured to judge whether there is a target area in a certain rock and soil single layer sub-image, wherein the target area is an area containing a rock and soil layer; a screening module configured to obtain, if a target area exists, a first size of the target area in a certain rock and soil single-layer image corresponding to the certain rock and soil single-layer sub-image, and to screen out a target rock and soil single-layer image that meets a preset condition from other rock and soil single-layer images using a preset screening rule, wherein the other rock and soil single-layer images are rock and soil single-layer images obtained by segmenting rock and soil layer images of other sampling points, and the preset condition is that a difference between a fourth size of the target area in the target rock and soil single-layer image and a first size of the target area in the certain rock and soil single-layer image is less than a first preset threshold; The method of using a preset screening rule to screen out a target rock and soil single layer image that meets the preset conditions from other rock and soil single layer images includes: Obtaining the location information of each sampling point on the electronic map, and sequentially obtaining other rock and soil single-layer images according to the rule from far to near of a certain location point of the sampling point corresponding to the said rock and soil single-layer image, and screening out the target rock and soil single-layer image that meets the preset conditions from the other rock and soil single-layer images; The correction module is configured to obtain a target single-layer sub-image corresponding to the target rock and soil single-layer image, and correct the first size of the target area in the rock and soil single-layer image according to the second size of the target area in the target single-layer sub-image and the third size of the target area in the rock and soil single-layer sub-image to obtain the actual size of the target area in the rock and soil single-layer image, that is, the actual thickness of a rock and soil single layer, wherein the correction of the first size of the target area in the rock and soil single-layer image according to the second size of the target area in the target single-layer sub-image and the third size of the target area in the rock and soil single-layer sub-image to obtain the actual size of the target area in the rock and soil single-layer image includes: Acquire a first change amount between the third size and the second size, and a second change amount between the first size and the fourth size; Determine whether the difference between the first size change and the second size change is greater than a second preset threshold; If the difference between the first size change and the second size change is greater than a second preset threshold, the first size is directly used as the actual size of the target area in a certain rock and soil single layer image, that is, the actual thickness of a certain rock and soil single layer; If the difference between the first size change and the second size change is not greater than the second preset threshold, half of the third size is superimposed on the first size of the target area in the rock and soil single layer image to obtain the actual size of the target area in the corrected rock and soil single layer image.

5. An electronic device, characterized in that: include: At least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable 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 execute the method described in any one of claims 1 to 3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 3 is implemented.

Images