Method, device and equipment for extracting tunnel face structural plane information, medium and product

By using adaptive convolution kernel and skeleton extraction algorithm in the information extraction model, the problem of low accuracy of palm surface image recognition in harsh environments in the tunnel hole is solved, and the accurate extraction and recognition of palm surface structural surfaces is achieved.

CN118982644APending Publication Date: 2024-11-19CHINA RAILWAY 20TH BUREAU GROUP CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410964931.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-18
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

Images of the palm surface taken in harsh environments in the tunnel are susceptible to dust and dim light, resulting in many interference factors and low recognition accuracy.

Method used

The information extraction model is adopted, including feature extraction module, image feature processing module and information recognition module, and image features are extracted through adaptive convolution kernel, semantic segmentation and binarization processing are performed, and the main structural surface of the palm face is extracted by using the skeleton extraction algorithm. Endpoint coordinates.

Benefits of technology

Through semantic segmentation and skeleton extraction algorithms, the mapping area of ​​the palm surface structure surface is accurately identified, reducing interference characteristics and improving the recognition accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118982644A_ABST
    Figure CN118982644A_ABST
Patent Text Reader

Abstract

The invention discloses a tunnel face structural surface information extraction method and device, equipment, a medium and a product, and relates to the technical field of tunnel face structural surface information extraction.The tunnel face structural surface information extraction method comprises the steps that a tunnel face image is obtained; wherein the tunnel face image comprises a mapping area corresponding to a main structure face of the tunnel face; and inputting the tunnel face image into an information extraction model to obtain the main structure face information of the tunnel face output by the information extraction model. The method can improve the recognition accuracy.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of tunnel face structural surface information extraction, and in particular to a tunnel face structural surface information extraction method, device, equipment, medium and product. Background Art

[0002] In the current theory of underground tunnel structure surrounding rock classification, the number of rock volume joints, the number of structural surface groups, and the average spacing of structural surfaces in the face structural surface information are important indicators for the classification of tunnel rock integrity, and the basic classification of tunnel surrounding rock is determined by the rock hardness and rock integrity. It can be seen that the face structural surface information is not only necessary for tunnel construction and tunnel geological advance prediction, but also an important factor that needs to be considered in the tunnel design and construction stages.

[0003] However, when extracting the tunnel face structural surface information from the tunnel face image, due to the poor environment inside the tunnel, the tunnel face image is easily affected by dust and dim lighting environment, resulting in more interference factors in the tunnel face image, resulting in low recognition accuracy. Summary of the invention

[0004] The main purpose of this application is to provide a method, device, equipment, medium and product for extracting information of a tunnel face structure, aiming to solve the technical problem that there are many interference factors in the tunnel face image, resulting in low recognition accuracy.

[0005] To achieve the above objectives, the present application proposes a method for extracting structural surface information of a tunnel face, comprising:

[0006] Acquire a tunnel face image; wherein the tunnel face image includes a mapping area corresponding to a main structural surface of the tunnel face;

[0007] The palm face image is input into the information extraction model to obtain the palm face main structural surface information output by the information extraction model; wherein the information extraction model includes a feature extraction module, an image feature processing module and an information recognition module, the feature extraction module is used to extract features of the palm face image to obtain image features; the image feature processing module is used to perform semantic segmentation on the image features to obtain a mask image containing a mapping area, and binarize the mask image to obtain a binary image; the information recognition module is used to extract the endpoint coordinates of the palm face main structural surface in the binary image using a skeleton extraction algorithm to obtain the palm face main structural surface information.

[0008] In one embodiment, the feature extraction module includes an adaptive convolution kernel, which performs feature extraction on the tunnel face image, and the obtained image features include:

[0009] Adaptive convolution kernel is used to extract features of the tunnel face image to obtain image features.

[0010] In one embodiment, the endpoint coordinates of the main structural surface of the tunnel face in the binary image are extracted using a skeleton extraction algorithm, and the main structural surface information of the tunnel face is obtained, including:

[0011] The binary image is processed using the skeleton extraction algorithm to obtain the contour line of the main structural surface of the tunnel face;

[0012] Determine first pixel coordinate information of an endpoint on one side of the contour line in the tunnel face image and second pixel coordinate information of an endpoint on the other side of the contour line in the tunnel face image;

[0013] Based on the first pixel coordinate information and the second pixel coordinate information, the endpoint coordinates of the main structural surface of the tunnel face are determined.

[0014] In one embodiment, determining the endpoint coordinates of the main structural surface of the tunnel face based on the first pixel coordinate information and the second pixel coordinate information includes:

[0015] Determine third pixel coordinate information of vertices on one side of the mask area in the tunnel face image, and fourth pixel coordinate information of vertices on the other side of the mask area in the tunnel face image;

[0016] The sum of the pixel ordinate value in the first pixel coordinate information and the pixel ordinate value in the third pixel coordinate information is used as the first pixel ordinate value;

[0017] Using the pixel horizontal coordinate value in the first pixel coordinate information as the first pixel horizontal coordinate value;

[0018] Determine first target coordinate information of an end point on one side of the main structural surface of the tunnel face based on the first pixel ordinate value and the first pixel abscissa value;

[0019] taking the sum of the pixel ordinate value in the second pixel coordinate information and the pixel ordinate value in the fourth pixel coordinate information as the second pixel ordinate value;

[0020] Using the pixel horizontal coordinate value in the second pixel coordinate information as the second pixel horizontal coordinate value;

[0021] Determine the second target coordinate information of the other end point of the main structural surface of the tunnel face based on the second pixel ordinate value and the second pixel abscissa value;

[0022] The first target coordinate information and the second target coordinate information are used as endpoint coordinates.

[0023] In one embodiment, after taking the first target coordinate information and the second target coordinate information as the endpoint coordinates, the method further includes:

[0024] Determine the actual height of the tunnel face and the total pixel height of the tunnel face image;

[0025] Using the actual height of the tunnel face, the total pixel height and the first pixel ordinate value, the first actual height of the endpoint on one side is obtained;

[0026] The second actual height of the endpoint on the other side is obtained by using the actual height of the tunnel face, the total pixel height and the second pixel ordinate value.

[0027] In one embodiment, the information extraction model is a SPM-YOLOv8-seg model.

[0028] In addition, to achieve the above-mentioned purpose, the present application also proposes a tunnel face structural surface information extraction device, which includes:

[0029] An acquisition module is used to acquire a tunnel face image; wherein the tunnel face image includes a mapping area corresponding to a main structural surface of the tunnel face;

[0030] An input module is used to input a palm face image into an information extraction model to obtain palm face main structural surface information output by the information extraction model; wherein the information extraction model includes a feature extraction module, an image feature processing module and an information recognition module, wherein the feature extraction module is used to perform feature extraction on the palm face image to obtain image features; the image feature processing module is used to perform semantic segmentation on the image features to obtain a mask image containing a mapping area, and binarize the mask image to obtain a binary image; the information recognition module is used to extract the endpoint coordinates of the palm face main structural surface in the binary image using a skeleton extraction algorithm to obtain palm face main structural surface information.

[0031] In addition, to achieve the above-mentioned purpose, the present application also proposes a tunnel face structural surface information extraction device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the tunnel face structural surface information extraction method as described above.

[0032] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the method for extracting structural surface information of a tunnel face as described above are implemented.

[0033] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps of the method for extracting tunnel face structural surface information as described above are implemented.

[0034] One or more technical solutions proposed in this application have at least the following technical effects:

[0035] In the present application, after extracting the image features, the image features are semantically segmented to obtain a mask image corresponding to the mapping area of ​​the main structural surface of the face, and the mask image is binarized to obtain a binary image, and finally the skeleton extraction algorithm is used to extract the endpoint coordinates of the main structural surface of the face in the binary image. That is, the present application can accurately identify the mapping area of ​​the face structural surface from the image features by semantic segmentation, so as to reduce the interference features in the mask image containing the mapping area, thereby avoiding the interference features from being mistakenly identified as the main structural surface of the face, thereby improving the recognition accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0038] Figure 1 A schematic diagram of a flow chart provided for the first embodiment of the method for extracting structural surface information of a tunnel face of the present application;

[0039] Figure 2 This is a schematic diagram of the process of extracting image features using traditional convolution kernels in this application;

[0040] Figure 3 This is a schematic diagram of the process of extracting image features using adaptive convolution kernels in this application;

[0041] Figure 4 This is a schematic diagram of the principle of the skeleton extraction algorithm of this application;

[0042] Figure 5 This is a schematic diagram of the module structure of the device for extracting structural surface information of a tunnel face according to an embodiment of the present application;

[0043] Figure 6 Schematic diagram of the equipment structure of the hardware operating environment involved in the method for extracting tunnel face structural surface information in the embodiment of the present application.

[0044] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0045] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0046] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0047] The main solution of the embodiment of the present application is: obtaining a palm face image; wherein the palm face image includes a mapping area corresponding to the main structural surface of the palm face; inputting the palm face image into an information extraction model to obtain the palm face main structural surface information output by the information extraction model; wherein the information extraction model includes a feature extraction module, an image feature processing module and an information recognition module, the feature extraction module is used to extract features of the palm face image to obtain image features; the image feature processing module is used to perform semantic segmentation on the image features to obtain a mask image including the mapping area, and binarize the mask image to obtain a binary image; the information recognition module is used to extract the endpoint coordinates of the main structural surface of the palm face in the binary image using a skeleton extraction algorithm to obtain the main structural surface information of the palm face.

[0048] In the current theory of underground tunnel structure surrounding rock classification, the number of rock volume joints, the number of structural surface groups, and the average spacing of structural surfaces in the face structural surface information are important indicators for the classification of tunnel rock integrity, and the basic classification of tunnel surrounding rock is determined by the rock hardness and rock integrity. It can be seen that the face structural surface information is not only necessary for tunnel construction and tunnel geological advance prediction, but also an important factor that needs to be considered in the tunnel design and construction stages.

[0049] However, when extracting the tunnel face structural surface information from the tunnel face image, due to the poor environment inside the tunnel, the tunnel face image is easily affected by dust and dim lighting environment, resulting in more interference factors in the tunnel face image, resulting in low recognition accuracy.

[0050] The present application provides a solution, after extracting the image features, semantically segmenting the image features to obtain a mask image corresponding to the mapping area of ​​the main structural surface of the face, and binarizing the mask image to obtain a binary image, and finally using a skeleton extraction algorithm to extract the endpoint coordinates of the main structural surface of the face in the binary image. That is, the present application can accurately identify the mapping area of ​​the face structural surface from the image features by semantic segmentation, so as to reduce the interference features in the mask image containing the mapping area, thereby avoiding the interference features from being mistakenly identified as the main structural surface of the face, thereby improving the recognition accuracy.

[0051] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a tunnel face structural surface information extraction device, etc. The following takes the tunnel face structural surface information extraction device as an example to illustrate this embodiment and the following embodiments.

[0052] Based on this, the present application embodiment provides a method for extracting structural surface information of a tunnel face, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the method for extracting structural surface information of a tunnel face of the present application.

[0053] In this embodiment, the method for extracting tunnel face structural surface information includes steps S10 to S20:

[0054] Step S10, acquiring a tunnel face image.

[0055] The tunnel face image includes a mapping area corresponding to the main structural surface of the tunnel face.

[0056] Specifically, the user can collect the tunnel face image through the image acquisition device, and after collecting the tunnel face image, transmit the tunnel face image to the tunnel face recognition device by interacting with the virtual keyboard and / or buttons of the tunnel face recognition device.

[0057] Step S20, inputting the tunnel face image into the information extraction model to obtain the tunnel face main structural surface information output by the information extraction model.

[0058] Among them, the information extraction model includes a feature extraction module, an image feature processing module and an information recognition module. The feature extraction module is used to extract features of the palm face image to obtain image features; the image feature processing module is used to perform semantic segmentation on the image features to obtain a mask image containing a mapping area, and to binarize the mask image to obtain a binary image; the information recognition module is used to extract the endpoint coordinates of the main structural surface of the palm face in the binary image using a skeleton extraction algorithm to obtain the main structural surface information of the palm face.

[0059] In this embodiment, the information extraction model is a model obtained by optimizing the YOLOv8-seg model, that is, the information extraction model is the SPM-YOLOv8-seg model (YOLOv8 segmentation model).

[0060] It should be noted that when the face image is input into the YOLOv8-seg model and the feature extraction module in the YOLOv8-seg model is used to extract image features, the traditional convolution kernel of the feature extraction module in the YOLOv8-seg model is used to extract features. Figure 2 As shown in the figure, the traditional convolution kernel can only extract features in the form of a sliding window of image sampling with a fixed size and fixed window. Therefore, interference features will be extracted when extracting features, resulting in a decrease in recognition accuracy due to too many interference features in subsequent recognition. In order to reduce the interference features in the image features, the convolution kernel in the feature extraction module can be replaced with AKconv (adaptive convolution kernel), that is, when extracting features, the adaptive convolution kernel is used to extract features from the face image to obtain image features. Figure 3 As shown in the figure, when extracting image features, the adaptive convolution kernel can automatically adjust the shape and size of the collection itself to avoid extracting interfering features during the process of extracting image features.

[0061] In this embodiment, an adaptive convolution kernel is used to replace the traditional convolution kernel in the feature extraction module. The adaptive convolution kernel can change its own size and shape, so that when performing feature extraction, it can avoid extracting interference features, thereby improving the recognition accuracy.

[0062] After the binary image is obtained, when the information recognition module uses the skeleton extraction algorithm to extract the endpoint coordinates of the main structural surface of the tunnel face from the binary image, in order to reduce the preprocessing steps of the image and still be able to extract the endpoint coordinates of the main structural surface of the tunnel face when the image quality is poor, further, as an optional implementation, step S20 specifically includes:

[0063] Step S201, using a skeleton extraction algorithm to process the binary image to obtain the contour line of the main structural surface of the tunnel face.

[0064] Step S202: determining first pixel coordinate information of an endpoint on one side of the contour line in the tunnel face image and second pixel coordinate information of an endpoint on the other side of the contour line in the tunnel face image.

[0065] Step S203: determining the endpoint coordinates of the main structural surface of the tunnel face based on the first pixel coordinate information and the second pixel coordinate information.

[0066] In this embodiment, the skeleton extraction algorithm may be the Zhang-Suen skeleton extraction algorithm, or may be other skeleton extraction algorithms, such as the Guo-Hall algorithm, the Thinning algorithm, etc., which is not limited in this embodiment.

[0067] Specifically, refer to Figure 4 As shown, Figure 4This is the principle of the skeleton extraction algorithm. The principle of the skeleton extraction algorithm is to perform multiple iterations on the area to be extracted, indenting from the edge to the center to form a trace, that is, to use the skeleton extraction algorithm to process the binary image to obtain the contour line of the main structural surface of the face. After obtaining the contour line, the positions of the endpoints on both sides of the contour line can be determined, and the image coordinate system can be constructed with any vertex of the face image as the origin to determine the coordinates of the endpoint on one side of the contour line relative to the origin, and the coordinates of the endpoint on the other side of the contour line relative to the origin, that is, to determine the first pixel coordinate information of the endpoint on one side of the contour line in the face image and the second pixel coordinate information of the endpoint on the other side in the face image.

[0068] After obtaining the first pixel coordinate information and the second pixel coordinate information, since the ordinate pixel value in the first pixel coordinate information and the second pixel coordinate information is the height of the skeleton or the central part of the main structural surface of the tunnel face, in order to better cover the entire range of the main structural surface of the tunnel face, further, as an optional implementation, step S203 specifically includes:

[0069] Step A10, determining third pixel coordinate information of vertices on one side of the mask area in the tunnel face image, and fourth pixel coordinate information of vertices on the other side of the mask area in the tunnel face image.

[0070] Step A20: taking the sum of the pixel vertical coordinate value in the first pixel coordinate information and the pixel vertical coordinate value in the third pixel coordinate information as the first pixel vertical coordinate value.

[0071] Step A30: Use the pixel horizontal coordinate value in the first pixel coordinate information as the first pixel horizontal coordinate value.

[0072] Step A40: determining first target coordinate information of an end point on one side of the main structural surface of the tunnel face based on the first pixel ordinate value and the first pixel abscissa value.

[0073] Step A50: taking the sum of the pixel ordinate value in the second pixel coordinate information and the pixel ordinate value in the fourth pixel coordinate information as the second pixel ordinate value.

[0074] Step A60: Use the pixel horizontal coordinate value in the second pixel coordinate information as the second pixel horizontal coordinate value.

[0075] Step A70: determining the second target coordinate information of the other end point of the main structural surface of the tunnel face based on the second pixel ordinate value and the second pixel abscissa value.

[0076] Step A80: Use the first target coordinate information and the second target coordinate information as endpoint coordinates.

[0077] In this embodiment, the directions of the vertices on one side of the mask region and the endpoints on one side of the contour line are consistent, and the directions of the vertices on the other side of the mask region and the endpoints on the other side of the contour line are consistent.

[0078] Specifically, after the mask area is determined, the coordinates of the vertices on one side of the mask area relative to the origin, i.e., the third pixel coordinate information, and the coordinates of the vertices on the other side of the mask area relative to the origin, i.e., the fourth pixel coordinate information, can be determined with reference to the aforementioned image coordinate system. After the third pixel coordinate information and the fourth pixel coordinate information are determined, the sum of the pixel ordinate value in the first pixel coordinate information and the pixel ordinate value in the third pixel coordinate information can be used as the first pixel ordinate value, the pixel abscissa value in the first pixel coordinate information can be used as the first pixel abscissa value, and finally the first pixel ordinate value and the first pixel abscissa value can be used to determine the first target coordinate information of the endpoint on one side of the main structural surface of the face. Correspondingly, the sum of the pixel ordinate value in the second pixel coordinate information and the pixel ordinate value in the fourth pixel coordinate information can be used as the second pixel ordinate value, the pixel abscissa value in the second pixel coordinate information can be used as the second pixel abscissa value, and the second pixel ordinate value and the second pixel abscissa value can be used to determine the second target coordinate information of the endpoint on the other side of the main structural surface of the face, and finally the first target coordinate information and the second target coordinate information can be used as the endpoint coordinates.

[0079] In this embodiment, when extracting the endpoint coordinate information of the main structural surface of the face from the binary image, the skeleton extraction algorithm is used to process the binary image to obtain the contour line of the main structural surface of the face, which can reduce the preprocessing steps of the binary image, and the endpoint coordinates of the main structural surface of the face can still be extracted when the quality of the binary image is poor. At the same time, after determining the coordinate information of the endpoints on both sides of the contour line, since the ordinates in the coordinate information of the endpoints on both sides of the contour line mainly represent the height of the skeleton or the central part of the main structural surface of the face, in order to better describe the overall height of the main structural surface of the face, after determining the coordinate information of the vertices on both sides of the mask area, the pixel ordinate values ​​of the vertices of the mask area and the pixel ordinate values ​​of the endpoints of the contour line are used as the first pixel ordinate. Since the pixel ordinate values ​​in the vertex coordinates of the mask area can reflect the edge or outer contour of the main structural surface of the face, adding them can better cover the overall range of the main structural surface, thereby providing more information about the shape and size of the main structural surface of the face.

[0080] After obtaining the endpoint coordinates of the main structural surface of the tunnel face, in order to determine the actual height of the main structural surface of the tunnel face, further, as an optional implementation, after step A80, the following is further included:

[0081] Step A81, determining the actual height of the tunnel face and the total pixel height of the tunnel face image.

[0082] Step A82, using the actual height of the tunnel face, the total pixel height and the first pixel ordinate value, obtain the first actual height of the endpoint on one side.

[0083] Step A83, using the actual height of the face, the total pixel height and the second pixel ordinate value, obtain the second actual height of the other end point.

[0084] In this embodiment, the actual height of the face can be collected by using a height measuring device. After collecting the actual height of the face, the relevant personnel can transmit the actual height of the face to the face structure information extraction device by interacting with the virtual keyboard and / or buttons in the face structure information extraction device. After receiving the actual height of each face, the face structure information extraction device can store the actual height of the face in the local or cloud of the face structure information extraction device, so that when executing step A81, the actual height of the face can be directly called from the local or cloud of the face structure information extraction device.

[0085] Specifically, based on the above, after constructing the image coordinate system with any vertex of the face image as the origin, determine another vertex on the same vertical line as the origin in the Y-axis direction of the image coordinate system, and use the pixel distance between the origin and the other vertex as the total pixel height. After determining the actual face height and the total pixel height, the first actual height of the endpoint on one side can be obtained based on the actual face height, the total pixel height and the first pixel ordinate value, that is, Y 1 Indicates the first actual height of the endpoint on one side, y 1 represents the first pixel ordinate value, H represents the actual height of the face, and h represents the total pixel height. Correspondingly, the second actual height of the other end point can be obtained according to the actual face height, the total pixel height and the second pixel ordinate value, that is, Y 2 Indicates the second actual height of the other end point, y 2 Indicates the second pixel vertical coordinate value.

[0086] In this embodiment, after obtaining the endpoint coordinates of the main structural surface of the tunnel face, the actual height of the endpoints on both sides of the tunnel face main structural surface is calculated using the actual height of the tunnel face, the total pixel height and the endpoint coordinates, which helps to determine the actual position of the main structural surface of the tunnel face in the tunnel face, so as to better determine the position information of the main structure of the tunnel face.

[0087] In this embodiment, after extracting the image features, semantic segmentation is performed on the image features to obtain a mask image corresponding to the mapping area of ​​the main structural surface of the face, and the mask image is binarized to obtain a binary image, and finally the skeleton extraction algorithm is used to extract the endpoint coordinates of the main structural surface of the face in the binary image. That is, the present application can accurately identify the mapping area of ​​the face structural surface from the image features by semantic segmentation, so as to reduce the interference features in the mask image containing the mapping area, thereby avoiding the interference features from being mistakenly identified as the main structural surface of the face, thereby improving the recognition accuracy.

[0088] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the method for extracting structural surface information of the tunnel face of the present application. More simple transformations based on this technical concept are all within the protection scope of the present application.

[0089] This application also provides a device for extracting information from a tunnel face structure surface. Figure 5 , the tunnel face structural surface information extraction device comprises:

[0090] An acquisition module is used to acquire a tunnel face image; wherein the tunnel face image includes a mapping area corresponding to a main structural surface of the tunnel face;

[0091] An input module is used to input a palm face image into an information extraction model to obtain palm face main structural surface information output by the information extraction model; wherein the information extraction model includes a feature extraction module, an image feature processing module and an information recognition module, wherein the feature extraction module is used to perform feature extraction on the palm face image to obtain image features; the image feature processing module is used to perform semantic segmentation on the image features to obtain a mask image containing a mapping area, and binarize the mask image to obtain a binary image; the information recognition module is used to extract the endpoint coordinates of the palm face main structural surface in the binary image using a skeleton extraction algorithm to obtain palm face main structural surface information.

[0092] The device for extracting the structural surface information of the face provided by the present application adopts the method for extracting the structural surface information of the face in the above embodiment, and can solve the technical problem that the recognition accuracy is low due to many interference factors in the face image. Compared with the related art, the beneficial effect of the device for extracting the structural surface information of the face provided by the present application is the same as the beneficial effect of the method for extracting the structural surface information of the face provided by the above embodiment, and the other technical features in the device for extracting the structural surface information of the face are the same as the features disclosed in the above embodiment method, and will not be repeated here.

[0093] The present application provides a device for extracting structural surface information of a tunnel face, the device comprising: 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 execute the method for extracting structural surface information of the tunnel face in the first embodiment.

[0094] Reference below Figure 6 , which shows a schematic diagram of the structure of a tunnel face structural surface information extraction device suitable for implementing the embodiment of the present application. The tunnel face structural surface information extraction device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The illustrated equipment for extracting structural surface information of a tunnel face is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0095] like Figure 6As shown, the equipment for extracting structural surface information of a tunnel face may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM) 1004. Various programs and data required for the operation of the equipment for extracting structural surface information of a tunnel face are also stored in the RAM 1004. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 may allow the tunnel face structural surface information extraction device to communicate wirelessly or by wire with other devices to exchange data. Although the tunnel face structural surface information extraction device having various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have instead.

[0096] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0097] The tunnel face structural surface information extraction device provided by the present application adopts the tunnel face structural surface information extraction method in the above embodiment, which can solve the technical problem that the tunnel face image has many interference factors and leads to low recognition accuracy. Compared with the related art, the beneficial effects of the tunnel face structural surface information extraction device provided by the present application are the same as the beneficial effects of the tunnel face structural surface information extraction method provided by the above embodiment, and other technical features in the tunnel face structural surface information extraction device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0098] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0099] The above is only a specific implementation 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.

[0100] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the method for extracting structural surface information of a tunnel face in the above-mentioned embodiment.

[0101] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0102] The computer-readable storage medium may be included in the tunnel face structural surface information extraction device; or may exist independently without being assembled into the tunnel face structural surface information extraction device.

[0103] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by a face structure surface information extraction device, the face structure surface information extraction device: obtains a face image; wherein the face image includes a mapping area corresponding to a face main structure surface; inputs the face image into an information extraction model to obtain face main structure surface information output by the information extraction model; wherein the information extraction model includes a feature extraction module, an image feature processing module and an information recognition module, wherein the feature extraction module is used to perform feature extraction on the face image to obtain image features; the image feature processing module is used to perform semantic segmentation on the image features to obtain a mask image including the mapping area, and binarize the mask image to obtain a binarized image; and the information recognition module is used to extract the endpoint coordinates of the face main structure surface in the binarized image using a skeleton extraction algorithm to obtain face main structure surface information.

[0104] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0105] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0106] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0107] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned method for extracting the structural surface information of the tunnel face, and can solve the technical problem that the tunnel face image has many interference factors and leads to low recognition accuracy. Compared with the related art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the method for extracting the structural surface information of the tunnel face provided in the above-mentioned embodiment, and will not be repeated here.

[0108] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned method for extracting tunnel face structural surface information when executed by a processor.

[0109] The computer program product provided by the present application can solve the technical problem that the recognition accuracy is low due to many interference factors in the tunnel face image. Compared with the related art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the tunnel face structural surface information extraction method provided by the above embodiment, which will not be repeated here.

[0110] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for extracting structural surface information of a tunnel face, characterized in that: The method comprises: Acquire a tunnel face image; wherein the tunnel face image includes a mapping area corresponding to a main structural surface of the tunnel face; The palm face image is input into an information extraction model to obtain the palm face main structural surface information output by the information extraction model; wherein the information extraction model includes a feature extraction module, an image feature processing module and an information recognition module, wherein the feature extraction module is used to perform feature extraction on the palm face image to obtain image features; the image feature processing module is used to perform semantic segmentation on the image features to obtain a mask image containing the mapping area, and binarize the mask image to obtain a binarized image; the information recognition module is used to extract the endpoint coordinates of the palm face main structural surface in the binarized image using a skeleton extraction algorithm to obtain the palm face main structural surface information.

2. The method according to claim 1, characterized in that The feature extraction module includes an adaptive convolution kernel, and the feature extraction of the tunnel face image to obtain image features includes: The adaptive convolution kernel is used to extract features from the tunnel face image to obtain the image features.

3. The method according to claim 1, characterized in that The method of extracting the endpoint coordinates of the main structural surface of the tunnel face in the binary image by using a skeleton extraction algorithm to obtain the main structural surface information of the tunnel face includes: The binary image is processed by using the skeleton extraction algorithm to obtain the contour line of the main structural surface of the tunnel face; Determine first pixel coordinate information of an endpoint on one side of the contour line in the tunnel face image and second pixel coordinate information of an endpoint on the other side of the contour line in the tunnel face image; Based on the first pixel coordinate information and the second pixel coordinate information, the endpoint coordinates of the main structural surface of the tunnel face are determined.

4. The method according to claim 3, characterized in that The determining the endpoint coordinates of the main structural surface of the tunnel face based on the first pixel coordinate information and the second pixel coordinate information includes: Determine third pixel coordinate information of vertices on one side of the mask area in the tunnel face image, and fourth pixel coordinate information of vertices on the other side of the mask area in the tunnel face image; taking the sum of the pixel ordinate value in the first pixel coordinate information and the pixel ordinate value in the third pixel coordinate information as the first pixel ordinate value; Using the pixel horizontal coordinate value in the first pixel coordinate information as the first pixel horizontal coordinate value; Determine first target coordinate information of an end point on one side of the main structural surface of the tunnel face based on the first pixel ordinate value and the first pixel abscissa value; taking the sum of the pixel ordinate value in the second pixel coordinate information and the pixel ordinate value in the fourth pixel coordinate information as the second pixel ordinate value; Using the pixel horizontal coordinate value in the second pixel coordinate information as the second pixel horizontal coordinate value; Determine the second target coordinate information of the other end point of the main structural surface of the tunnel face based on the second pixel ordinate value and the second pixel abscissa value; The first target coordinate information and the second target coordinate information are used as the endpoint coordinates.

5. The method according to claim 4, characterized in that After the first target coordinate information and the second target coordinate information are used as the endpoint coordinates, the method further includes: Determining an actual height of the tunnel face and a total pixel height of the tunnel face image; Using the actual height of the tunnel face, the total pixel height and the first pixel ordinate value, a first actual height of an endpoint on one side is obtained; The second actual height of the endpoint on the other side is obtained by using the actual height of the tunnel face, the total pixel height and the second pixel ordinate value.

6. The method according to claim 1, characterized in that The information extraction model is the SPM-YOLOv8-seg model.

7. A device for extracting information from a tunnel face structure, characterized in that: The device comprises: An acquisition module, used for acquiring a tunnel face image; wherein the tunnel face image includes a mapping area corresponding to a main structural surface of the tunnel face; An input module is used to input the palm face image into an information extraction model to obtain the palm face main structural surface information output by the information extraction model; wherein the information extraction model includes a feature extraction module, an image feature processing module and an information recognition module, the feature extraction module is used to perform feature extraction on the palm face image to obtain image features; the image feature processing module is used to perform semantic segmentation on the image features to obtain a mask image containing the mapping area, and binarize the mask image to obtain a binarized image; the information recognition module is used to extract the endpoint coordinates of the palm face main structural surface in the binarized image using a skeleton extraction algorithm to obtain the palm face main structural surface information.

8. A device for extracting information from a tunnel face structure, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the method for extracting structural surface information of a tunnel face according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the method for extracting tunnel face structural surface information according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the method for extracting tunnel face structural surface information according to any one of claims 1 to 6 are implemented.