Anchor steel belt installation hole identification device, method, equipment, medium and product

Through binocular visual structured light technology, the spatial virtual model of anchor steel belt is constructed in the underground anchoring operation, which solves the problem of anchor steel belt installation hole positioning in dusty environments, and realizes the unmanned and intelligent underground anchoring operation. Improve precise positioning accuracy.

CN114463617BActive Publication Date: 2024-11-08SANY HEAVY EQUIP CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210114608.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-01-30
Publication Date
2024-11-08
Estimated Expiration
2042-01-30

AI Technical Summary

Technical Problem

In the underground anchor protection operation, due to the dusty environment, point cloud effect is poor, and it is difficult to accurately locate the anchor protection steel belt installation hole. The existing technology is costly and has low accuracy.

Method used

Using binocular vision structured light technology, the spatial virtual model of the anchor steel belt is constructed through the image acquisition part and the attitude adjustment part, and the installation holes are accurately positioned to achieve unmanned and intelligent anchor protection.

Benefits of technology

Generate accurate point cloud maps within a limited range, realize unmanned and intelligent downhole anchoring operations, improve the precise positioning accuracy of installation holes, and provide strong guarantees for subsequent hole drilling and anchoring.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114463617B_ABST
    Figure CN114463617B_ABST
Patent Text Reader

Abstract

The present invention provides an apparatus, method, equipment, medium and product for identifying installation holes of anchor steel belts, the apparatus comprising: an image acquisition unit and a posture adjustment unit; the image acquisition unit is used to acquire image information of underground tunnels after laying the anchor steel belts; the posture adjustment unit is connected to the image acquisition unit, and is used to adjust the acquisition posture of the image acquisition unit; wherein the image acquisition unit comprises at least one projection optical path and two imaging optical paths. The apparatus, method, equipment, medium and product for identifying installation holes of anchor steel belts provided by the present invention can generate an accurate point cloud map within a limited range by using binocular vision structured light to identify the installation holes of anchor steel belts, thereby realizing unmanned and intelligent underground anchoring operations, realizing unmanned and intelligent anchoring, and providing strong guarantees for subsequent drilling and anchoring operations.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel construction, and in particular to an identification device, method, equipment, medium and product for an anchor steel belt installation hole. Background Art

[0002] With the rapid development of artificial intelligence, depth cameras, point cloud data processing and sensor technology, the intelligentization of engineering machinery has been gradually realized. In the process of anchoring and protecting underground tunnels, especially under special geological conditions, the construction difficulty and conditions are particularly harsh and dangerous. At the same time, due to the special working surface underground, the light and dust are relatively large, and the vibration amplitude is relatively large. The current mechanical equipment uses manual excavation and manual anchoring in the process of anchoring and excavation. There are also laser radars for scanning, and then the laser radar point cloud data is processed twice to find the point cloud. On the one hand, this method has a high cost for laser radars, and the point cloud effect is not good in the dusty environment underground. On the other hand, because the holes in the steel belts of the anchor are relatively small, it is difficult to accurately locate the position of the holes. Summary of the invention

[0003] The present invention provides an identification device and an identification method for anchor steel belt installation holes, which are used to solve the defects of poor point cloud effect and difficulty in accurate positioning in the dusty environment underground during the existing anchoring and excavation operations. By adopting binocular vision structured light to identify the anchor steel belt installation holes, accurate point cloud maps can be generated within a limited range, realizing unmanned and intelligent underground anchoring operations, realizing unmanned anchoring and intelligent anchoring, and providing strong guarantees for subsequent drilling and anchoring operations.

[0004] The present invention further provides an electronic device.

[0005] The present invention further provides a non-transitory computer-readable storage medium.

[0006] The present invention also provides a computer program product.

[0007] According to a first aspect of the present invention, a device for identifying installation holes of anchor steel belts in underground tunnels includes: an image acquisition unit and a posture adjustment unit;

[0008] The image acquisition unit is used to collect image information of the underground tunnel after laying the anchor steel belt;

[0009] The posture adjustment unit is connected to the image acquisition unit and is used to adjust the acquisition posture of the image acquisition unit;

[0010] Wherein, the image acquisition unit includes at least one projection light path and two imaging light paths.

[0011] According to an implementation manner of the present invention, the acquisition posture at least includes an acquisition displacement and an acquisition angle of the image acquisition unit.

[0012] Specifically, this embodiment provides an implementation method for collecting postures, which realizes collecting anchor steel belts in the same area or different areas from multiple directions by adjusting the position and angle of the image collection unit, so as to realize the construction of a spatial virtual model of the anchor steel belts through more comprehensive data.

[0013] According to one embodiment of the present invention, the posture adjustment unit is a robotic arm.

[0014] Specifically, this embodiment provides an implementation of a posture adjustment unit, and by setting the posture adjustment unit as a mechanical arm, the adjustment of the acquisition posture of the image acquisition unit is achieved.

[0015] According to the second aspect of the present invention, a recognition method for the above-mentioned underground tunnel anchor steel belt installation hole recognition device includes:

[0016] After laying the anchor steel belt in the underground tunnel, obtaining image parameters of the anchor steel belt;

[0017] Constructing a spatial virtual model of the anchor steel belt according to the image parameters;

[0018] The hole position parameters of the anchor steel belt are extracted according to the spatial virtual model, and a drilling decision is generated according to the hole position parameters.

[0019] According to an embodiment of the present invention, after laying the anchor steel belt in the underground tunnel, the step of acquiring the image parameters of the anchor steel belt specifically includes:

[0020] After the anchor steel belt is laid in the underground tunnel, a first image feature vector and a second image feature vector of the anchor steel belt are obtained, wherein the first image feature vector points to a collection area of ​​the anchor steel belt, and the second image feature vector points to a mounting hole of the anchor steel belt;

[0021] generating image acquisition information according to the first image feature vector and the second image feature vector;

[0022] Adjust the acquisition position and / or acquisition angle, and repeat the above steps N times to obtain N pieces of acquisition information, where N is a positive integer greater than or equal to one;

[0023] The image parameters are generated according to the N pieces of acquisition information.

[0024] Specifically, this embodiment provides an implementation method for obtaining the image parameters of the anchor guard steel belt, by dividing the acquisition elements of the anchor guard steel belt into a first image feature vector and a second image feature vector, so that on the one hand, the acquisition area of ​​the anchor guard steel belt is divided by the first image feature vector, so that the image of the anchor guard steel belt can be acquired in all directions, and the area can be marked to avoid the problem of repeated acquisition. On the other hand, the installation holes of the anchor guard steel belt are identified by the second image feature vector, so that the installation holes can be more accurately located during the subsequent edge extraction. During the acquisition process, the acquisition area and the installation holes are identified and marked, thereby improving the robustness of the algorithm.

[0025] According to an embodiment of the present invention, the step of adjusting the acquisition position and / or acquisition angle and repeating the above steps N times to obtain N pieces of acquisition information specifically includes:

[0026] Randomly obtain coordinate information of a collection area corresponding to the first image feature vector, and use the coordinate information as the original coordinate;

[0027] Obtaining the remaining N first image feature vectors of the collected information, extracting coordinate information of each of the first image feature vectors, and using the coordinate information as a reference coordinate;

[0028] Obtaining the offset between each of the reference coordinates and the original coordinates, and using the N offsets as a set of offset parameters;

[0029] Repeat the above steps M times to obtain M groups of the offset parameters, where M is a positive integer greater than or equal to one.

[0030] Specifically, this embodiment provides an implementation method for obtaining N pieces of acquisition information, using the coordinate information of the acquisition area corresponding to a first image feature vector as the original coordinate, thereby realizing the construction of a spatial virtual model of the anchor steel belt according to the original coordinate.

[0031] Furthermore, by repeating M times, M groups of offset parameters are obtained, and the calculation error can be reduced based on multiple calculations of the offset, making the calculation of the installation hole position more accurate, providing guarantee for subsequent drilling and anchoring.

[0032] According to an implementation manner of the present invention, after the step of repeating the above steps M times to obtain M groups of the offset parameters, the method further includes:

[0033] Performing weighted calculation on the M groups of offset parameters, and obtaining M confidences corresponding to each group of offset parameters;

[0034] Sorting the M confidences from high to low, and outputting the weighted offset corresponding to the confidence ranked first in the sorting;

[0035] Corrected coordinates corresponding to the remaining N first image feature vectors are generated according to the weighted offset and the original coordinates, and the acquisition information is generated according to the original coordinates and the corrected coordinates.

[0036] Specifically, this embodiment provides an implementation method for generating acquisition information based on M groups of offset parameters. By performing weighted calculation on the offset parameters, the confidence of each group of offset parameters is obtained, and a group of weighted offsets with the highest confidence is output according to the confidence ranking. Then, based on the weighted offsets, the corrected coordinates corresponding to the remaining N first image feature vectors are obtained, and then the construction of the spatial virtual model of the anchor steel belt is realized based on the original coordinates and the corrected coordinates.

[0037] Furthermore, by extracting the weighted offset according to the confidence after weighted calculation, the influence of the error on the construction of the system model is reduced, so that any randomly selected position as the original coordinate can obtain a spatial virtual model that is closer to the actual anchoring situation of the anchor steel belt.

[0038] According to an embodiment of the present invention, the step of constructing a spatial virtual model of the anchor steel belt according to the image parameters specifically includes:

[0039] Acquiring anchor protection contour features of the spatial virtual model, wherein the anchor protection contour features at least include contact surface contour information between the anchor protection steel belt and the underground tunnel;

[0040] Matching corresponding preset anchor protection parameters in a preset anchor protection database according to the anchor protection profile features, and extracting a first anchor protection strategy of the preset anchor protection parameters, wherein the first anchor protection strategy includes a drilling strategy after the anchor protection steel belt is laid in the underground tunnel;

[0041] The hole position parameters of the anchor steel belt are extracted according to the spatial virtual model, and a drilling decision is generated according to the first anchor protection strategy and the hole position parameters.

[0042] Specifically, this embodiment provides an implementation method for constructing a spatial virtual model of an anchor steel belt. By extracting the anchor contour features of the spatial virtual model and matching them with a preset anchor database, a first anchor strategy corresponding to the anchor contour features in the preset anchor database is obtained. The first anchor strategy at least includes a drilling strategy corresponding to the anchor contour features.

[0043] It should be noted that due to the complex and changeable conditions in underground tunnels, the first anchor protection strategy is only a reference for similarity to provide support for subsequent drilling and anchor protection.

[0044] According to an embodiment of the present invention, the step of extracting the hole position parameters of the anchor steel belt according to the spatial virtual model specifically includes:

[0045] Extracting point cloud distribution parameters corresponding to the installation holes of the anchor steel belt according to the spatial virtual model;

[0046] Denoising the point cloud distribution parameters according to the first anchoring strategy, and extracting boundary features of the denoised point cloud distribution parameters;

[0047] The center position of the mounting hole is determined according to the boundary feature, and the hole position parameters are generated according to the center position.

[0048] Specifically, this embodiment provides an implementation method for extracting the hole position parameters of the anchor guard steel belt, by extracting the point cloud distribution parameters of the installation hole of the anchor guard steel belt, and denoising it through the first anchor protection strategy, so that the point cloud distribution parameters after denoising are clearer, which facilitates the determination of the center position of the installation hole.

[0049] According to an embodiment of the present invention, the step of determining the center position of the mounting hole according to the boundary feature and generating the hole position parameters according to the center position specifically includes:

[0050] Classifying the installation holes according to the hole position parameters, and obtaining a second anchoring strategy corresponding to at least the size, drilling method and drilling sequence of the installation holes;

[0051] The drilling decision is generated according to the first anchoring strategy and the second anchoring strategy.

[0052] Specifically, this embodiment provides an implementation method for generating hole position parameters based on the center position, by classifying the installation holes according to size, drilling method and drilling order, and then generating a second anchoring strategy, thereby realizing the determination of the drilling and anchoring implementation method according to the specific conditions of the installation holes.

[0053] According to a third aspect of the present invention, an electronic device is provided, comprising: a memory and a processor;

[0054] The memory and the processor communicate with each other via a bus;

[0055] The memory stores computer instructions that can be executed on the processor;

[0056] When the processor calls the computer instructions, it can execute the above-mentioned method for identifying the installation holes of the anchor steel belts in the underground tunnel.

[0057] According to a fourth aspect of the present invention, a non-transitory computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned method for identifying installation holes of anchor steel belts in underground tunnels are implemented.

[0058] According to a fifth aspect of the present invention, a computer program product is provided, which includes a non-transitory machine-readable medium storing a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned method for identifying installation holes of anchor steel belts in underground tunnels are implemented.

[0059] The above one or more technical solutions in the present invention have at least one of the following technical effects: the present invention provides an identification device, method, equipment, medium and product for the installation hole of the anchor steel belt, which can generate accurate point cloud maps within a limited range by adopting binocular vision structured light to identify the installation hole of the anchor steel belt, thereby realizing unmanned and intelligent downhole anchoring operations, realizing unmanned and intelligent anchoring, and providing strong guarantees for subsequent drilling and anchoring operations.

[0060] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 paying creative work.

[0062] Figure 1 This is one of the structural schematic diagrams of the identification device for the installation hole of the anchor guard steel belt provided by the present invention;

[0063] Figure 2 This is the second structural schematic diagram of the identification device for the installation hole of the anchor guard steel belt provided by the present invention;

[0064] Figure 3 It is a schematic diagram of the flow of the method for identifying the installation hole of the anchor guard steel belt provided by the present invention;

[0065] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention.

[0066] Reference numerals:

[0067] 10. Image acquisition unit; 11. Projection optical path; 12. Imaging optical path;

[0068] 20. Posture adjustment unit;

[0069] 810, processor; 820, communication interface; 830, memory; 840, communication bus. DETAILED DESCRIPTION

[0070] 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.

[0071] The present invention is described in detail below in conjunction with the accompanying drawings of the specification. The specific operating method in the method embodiment can also be applied to the device embodiment or the system embodiment. In the description of the present invention, unless otherwise specified, "at least one" includes one or more. "Multiple" refers to two or more. For example, at least one of A, B and C includes: A exists alone, B exists alone, A and B exist at the same time, A and C exist at the same time, B and C exist at the same time, and A, B and C exist at the same time. In the present invention, " / " means or, for example, A / B can mean A or B; "and / or" in this article is only a kind of association relationship that describes the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0072] The present invention will be described in detail below in conjunction with specific implementation modes.

[0073] In some specific embodiments of the present invention, Figure 1 and Figure 2 As shown, the present solution provides an identification device for installation holes of anchor steel belts in underground tunnels, comprising: an image acquisition unit 10 and a posture adjustment unit 20; the image acquisition unit 10 is used to acquire image information of the underground tunnel after laying the anchor steel belts; the posture adjustment unit 20 is connected to the image acquisition unit 10, and is used to adjust the acquisition posture of the image acquisition unit 10; wherein the image acquisition unit 10 includes at least one projection optical path 11 and two imaging optical paths 12.

[0074] In detail, the present invention provides an identification device for anchor steel belt installation holes, which is used to solve the defects of poor point cloud effect and difficulty in accurate positioning in the dusty environment underground during the existing anchoring and excavation operations. By adopting binocular vision structured light, the anchor steel belt installation holes are identified, and accurate point cloud maps can be generated within a limited range, thereby realizing unmanned and intelligent underground anchoring operations, realizing unmanned anchoring and intelligent anchoring, and providing strong guarantees for subsequent drilling and anchoring operations.

[0075] In some possible embodiments of the present invention, the acquisition posture at least includes the acquisition displacement and acquisition angle of the image acquisition unit 10 .

[0076] Specifically, this embodiment provides an implementation method for collecting postures. By adjusting the position and angle of the image acquisition unit 10, it is possible to collect anchor steel belts in the same area or different areas from multiple directions, so as to construct a spatial virtual model of the anchor steel belts through more comprehensive data.

[0077] In a possible implementation manner, an image acquisition unit 10 and a posture adjustment unit 20 are included, and the image acquisition unit 10 is disposed in the posture adjustment unit 20 .

[0078] In a possible implementation manner, at least two image acquisition units 10 and a posture adjustment unit 20 corresponding to each of the image acquisition units 10 are included.

[0079] In a possible implementation, at least two image acquisition units 10 and one posture adjustment unit 20 are included, and one posture adjustment unit 20 has adjustment stations corresponding to the number of image acquisition units 10 to achieve independent adjustment of the posture of each image acquisition unit 10 .

[0080] In some possible embodiments of the present invention, the posture adjustment unit 20 is a robotic arm.

[0081] Specifically, this embodiment provides an implementation of a posture adjustment unit 20 , and by setting the posture adjustment unit 20 as a mechanical arm, the adjustment of the acquisition posture of the image acquisition unit 10 is achieved.

[0082] In a possible implementation manner, the posture adjustment unit 20 is a six-axis robotic arm.

[0083] In a possible implementation manner, the posture adjustment unit 20 is disposed on a mobile device to achieve movement in an underground tunnel.

[0084] In a possible implementation manner, the posture adjustment unit 20 is arranged on the tunnel excavation equipment to meet the requirements of excavation, collection and anchoring at the same time.

[0085] In a possible implementation manner, an industrial computer is further included, and the industrial computer is connected to the posture adjustment unit 20 and the image acquisition unit 10 respectively to control the posture adjustment unit 20 and the image acquisition unit 10 .

[0086] In a possible implementation manner, the image acquisition unit 10 is a structured light device based on binocular vision, including a structured light camera, a projector, a lens, and the like.

[0087] In some specific embodiments of the present invention, Figures 1 to 3 As shown, this solution provides an identification method for the above-mentioned underground tunnel anchor steel belt installation hole identification device, comprising:

[0088] After laying the anchor steel belt to the underground tunnel, obtain the image parameters of the anchor steel belt;

[0089] Construct a spatial virtual model of the anchor steel belt according to the image parameters;

[0090] The hole position parameters of the anchor steel belt are extracted according to the spatial virtual model, and the drilling decision is generated based on the hole position parameters.

[0091] In some possible embodiments of the present invention, after laying the anchor steel belt in the underground tunnel, the step of obtaining the image parameters of the anchor steel belt specifically includes:

[0092] After the anchor steel belt is laid in the underground tunnel, a first image feature vector and a second image feature vector of the anchor steel belt are obtained, wherein the first image feature vector points to the acquisition area of ​​the anchor steel belt, and the second image feature vector points to the installation hole of the anchor steel belt;

[0093] generating image acquisition information according to the first image feature vector and the second image feature vector;

[0094] Adjust the acquisition position and / or acquisition angle, and repeat the above steps N times to obtain N acquisition information, where N is a positive integer greater than or equal to one;

[0095] Image parameters are generated according to the N pieces of acquisition information.

[0096] Specifically, this embodiment provides an implementation method for obtaining the image parameters of the anchor guard steel belt, by dividing the acquisition elements of the anchor guard steel belt into a first image feature vector and a second image feature vector, so that on the one hand, the acquisition area of ​​the anchor guard steel belt is divided by the first image feature vector, so that all-round image acquisition of the anchor guard steel belt can be achieved, and the area can be marked to avoid the problem of repeated acquisition. On the other hand, the installation holes of the anchor guard steel belt are identified by the second image feature vector, so that the installation holes can be more accurately located during subsequent edge extraction. During the acquisition process, the acquisition area and the installation holes are identified and marked, thereby improving the robustness of the algorithm.

[0097] In a possible implementation, by setting the first image feature vector, after multiple acquisitions, the surface morphology features of the anchor steel belt laid in the underground tunnel are identified.

[0098] In a possible implementation, during the acquisition process, there is an intersection between the acquisition areas corresponding to the two first image feature vectors. Therefore, after the anchor steel belt is laid in the underground tunnel, in the step of obtaining the first image feature vector and the second image feature vector of the anchor steel belt, it is also necessary to perform noise reduction processing on the overlapping acquisition areas to achieve accurate reconstruction of the surface morphology of the anchor steel belt and avoid the problem of repeated calculation in the process of morphology stitching, which in turn leads to deviations in the count of the installation holes pointed to by the second image feature vector.

[0099] In a possible implementation, by pre-acquiring the number of mounting holes on the surface of the anchor guard steel belt, a preset reference condition for constructing a spatial virtual model of the anchor guard steel belt is achieved. By calculating the mounting holes pointed to by the second image feature vector, if the preset reference condition is met, the completeness of the construction of the spatial virtual model of the anchor guard steel belt is determined.

[0100] In a possible implementation, the acquisition area pointed to by the first image feature vector includes the plane information of the surface area division of the anchor steel belt, and also includes the depth information of the anchor steel belt after it is laid in the underground tunnel, wherein the depth information includes the change of the three-dimensional coordinates of the installation hole after the anchor steel belt is deformed.

[0101] In some possible embodiments of the present invention, adjusting the acquisition position and / or acquisition angle, and repeating the above steps N times to obtain N acquisition information specifically includes:

[0102] Randomly obtain coordinate information of a collection area corresponding to a first image feature vector, and use the coordinate information as the original coordinate;

[0103] Obtain the first image feature vectors of the remaining N pieces of collected information, extract the coordinate information of each first image feature vector, and use the coordinate information as the reference coordinate;

[0104] Obtain the offset between each reference coordinate and the original coordinate, and use the N offsets as a set of offset parameters;

[0105] Repeat the above steps M times to obtain M groups of offset parameters, where M is a positive integer greater than or equal to one.

[0106] Specifically, this embodiment provides an implementation method for obtaining N pieces of acquisition information, using the coordinate information of the acquisition area corresponding to a first image feature vector as the original coordinate, thereby realizing the construction of a spatial virtual model of the anchor steel belt according to the original coordinate.

[0107] Furthermore, by repeating M times, M groups of offset parameters are obtained, and the calculation error can be reduced based on multiple calculations of the offset, making the calculation of the installation hole position more accurate, providing guarantee for subsequent drilling and anchoring.

[0108] In some possible embodiments of the present invention, after repeating the above steps M times to obtain M groups of offset parameters, the following further includes:

[0109] Perform weighted calculation on M groups of offset parameters, and obtain M confidences corresponding to each group of offset parameters;

[0110] Sort the M confidences from high to low, and output the weighted offset corresponding to the confidence that ranks first in the sorting;

[0111] Corrected coordinates corresponding to the remaining N first image feature vectors are generated according to the weighted offset and the original coordinates, and acquisition information is generated according to the original coordinates and the corrected coordinates.

[0112] Specifically, this embodiment provides an implementation method for generating acquisition information based on M groups of offset parameters. By performing weighted calculation on the offset parameters, the confidence of each group of offset parameters is obtained, and a group of weighted offsets with the highest confidence is output according to the confidence ranking. Then, based on the weighted offsets, the corrected coordinates corresponding to the remaining N first image feature vectors are obtained, and then the construction of the spatial virtual model of the anchor steel belt is realized based on the original coordinates and the corrected coordinates.

[0113] Furthermore, by extracting the weighted offset according to the confidence after weighted calculation, the influence of the error on the construction of the system model is reduced, so that any randomly selected position as the original coordinate can obtain a spatial virtual model that is closer to the actual anchoring situation of the anchor steel belt.

[0114] In some possible embodiments of the present invention, the step of constructing a spatial virtual model of the anchor steel belt according to the image parameters specifically includes:

[0115] Acquire anchor protection contour features of the spatial virtual model, wherein the anchor protection contour features at least include contact surface contour information between the anchor protection steel belt and the underground tunnel;

[0116] Matching corresponding preset anchor protection parameters in a preset anchor protection database according to the anchor protection profile features, and extracting a first anchor protection strategy of the preset anchor protection parameters, wherein the first anchor protection strategy includes a drilling strategy after the anchor protection steel belt is laid in the underground tunnel;

[0117] The hole position parameters of the anchor steel belt are extracted according to the spatial virtual model, and the drilling decision is generated according to the first anchor protection strategy and the hole position parameters.

[0118] Specifically, this embodiment provides an implementation method for constructing a spatial virtual model of an anchor steel belt. By extracting the anchor contour features of the spatial virtual model and matching them with a preset anchor database, a first anchor strategy corresponding to the anchor contour features in the preset anchor database is obtained. The first anchor strategy at least includes a drilling strategy corresponding to the anchor contour features.

[0119] It should be noted that due to the complex and changeable conditions in underground tunnels, the first anchor protection strategy is only a reference for similarity to provide support for subsequent drilling and anchor protection.

[0120] In a possible implementation, operations corresponding to similar hole positions in the first anchoring strategy are extracted according to hole position parameters, such as drilling, anchoring, and the like, and the operations are used as recommended operations to generate drilling decisions.

[0121] In some possible embodiments of the present invention, the step of extracting the hole position parameters of the anchor steel belt according to the spatial virtual model specifically includes:

[0122] Extract the point cloud distribution parameters of the installation holes corresponding to the anchor steel belts according to the spatial virtual model;

[0123] Denoising the point cloud distribution parameters according to the first anchor protection strategy, and extracting boundary features of the denoised point cloud distribution parameters;

[0124] The center position of the mounting hole is determined according to the boundary features, and the hole position parameters are generated according to the center position.

[0125] Specifically, this embodiment provides an implementation method for extracting the hole position parameters of the anchor guard steel belt, by extracting the point cloud distribution parameters of the installation hole of the anchor guard steel belt, and denoising it through the first anchor protection strategy, so that the point cloud distribution parameters after denoising are clearer, which facilitates the determination of the center position of the installation hole.

[0126] In a possible implementation, the point cloud distribution parameters after denoising remove the sparse point cloud, retain the external form of the point cloud, and retain the installation holes corresponding to the first anchor protection strategy, so as to improve the subsequent calculation speed.

[0127] In a possible implementation, the distribution parameters of the denoised point cloud are clustered and segmented. The cluster segmentation is mainly based on the distance information between the point clouds, and the most concentrated point clouds are segmented and those secondary clustered point clouds are eliminated. This method can be used to exclude other point cloud information in a practical environment.

[0128] In a possible implementation, the point cloud distribution parameters are mainly used to extract the boundary of the point cloud based on the normal of the point cloud. The outline of the point cloud can be roughly seen from the extracted boundary. At the same time, the number of point clouds becomes relatively small. The boundary extraction involves the radius parameter of the neighboring search, which has relatively high requirements on the calculation speed and boundary accuracy, and needs to be set according to actual requirements.

[0129] In some possible embodiments of the present invention, the steps of determining the center position of the mounting hole according to the boundary features and generating the hole position parameters according to the center position specifically include:

[0130] Classifying the installation holes according to the hole position parameters, and obtaining a second anchoring strategy corresponding to at least the size, drilling method and drilling sequence of the installation holes;

[0131] A drilling decision is generated based on the first anchoring strategy and the second anchoring strategy.

[0132] Specifically, this embodiment provides an implementation method for generating hole position parameters based on the center position, by classifying the installation holes according to size, drilling method and drilling order, and then generating a second anchoring strategy, thereby realizing the determination of the drilling and anchoring implementation method according to the specific conditions of the installation holes.

[0133] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4 As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830 and a communication bus 840, wherein the processor 810, the communication interface 820 and the memory 830 communicate with each other through the communication bus 840. The processor 810 may call the logic instructions in the memory 830 to execute the method for identifying the installation hole of the anchor guard steel belt.

[0134] It should be noted that the electronic device in this embodiment can be a server, a PC, or other devices in specific implementation, as long as its structure includes the following: Figure 4 The processor 810, communication interface 820, memory 830 and communication bus 840 shown in the figure, wherein the processor 810, communication interface 820, memory 830 communicate with each other through the communication bus 840, and the processor 810 can call the logic instructions in the memory 830 to execute the above method. This embodiment does not limit the specific implementation form of the electronic device.

[0135] Among them, the server can be a single server or a server group. The server group can be centralized or distributed (for example, the server can be a distributed system). In some embodiments, the server can be local or remote relative to the terminal. For example, the server can access information stored in a user terminal, a database, or any combination thereof via a network. As another example, the server can be directly connected to at least one of the user terminal and the database to access the information and / or data stored therein. In some embodiments, the server can be implemented on a cloud platform; as an example only, the cloud platform can include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an inter-cloud, a multi-cloud, etc., or any combination thereof. In some embodiments, the server and the user terminal can be implemented on an electronic device having one or more components in an embodiment of the present invention.

[0136] Further, the network can be used for the exchange of information and / or data. In some embodiments, one or more components in the interactive scene (e.g., a server, a user terminal, and a database) can send information and / or data to other components. In some embodiments, the network can be any type of wired or wireless network, or a combination thereof. As an example only, the network can include a wired network, a wireless network, a fiber optic network, a telecommunications network, an intranet, the Internet, a local area network (LAN), a wide area network (WAN), a wireless local area network (WLAN), a metropolitan area network (MAN), a wide area network (WAN), a public switched telephone network (PSTN), a Bluetooth network, a ZigBee network, or a near field communication (NFC) network, etc., or any combination thereof. In some embodiments, the network can include one or more network access points. For example, the network can include a wired or wireless network access point, such as a base station and / or a network switching node, through which one or more components of the interactive scene can be connected to the network to exchange data and / or information.

[0137] In addition, the logic instructions in the above-mentioned memory 830 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0138] In a possible implementation, an embodiment of the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to execute the method for identifying the installation hole of the anchor guard steel belt provided in the above embodiments.

[0139] In a possible implementation, an embodiment of the present invention further provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the methods provided by the above-mentioned method embodiments.

[0140] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative effort.

[0141] 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.

[0142] 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 recognition method for an underground tunnel anchor steel belt installation hole recognition device, characterized in that: The device comprises: an image acquisition unit (10) and a posture adjustment unit (20); The image acquisition unit (10) is used to acquire image information of the underground tunnel after laying the anchor steel belt; the posture adjustment unit (20) is connected to the image acquisition unit (10) and is used to adjust the acquisition posture of the image acquisition unit (10); wherein the image acquisition unit (10) comprises at least one projection optical path (11) and two imaging optical paths (12); The method comprises: After the anchor steel belt is laid in the underground tunnel, the first image feature vector and the second image feature vector of the anchor steel belt are obtained, wherein the first image feature vector points to the acquisition area of ​​the anchor steel belt, and the second image feature vector points to the installation hole of the anchor steel belt; image acquisition information is generated according to the first image feature vector and the second image feature vector; the acquisition position and / or acquisition angle are adjusted, and the above steps are repeated N times to obtain N+1 acquisition information, wherein N is a positive integer greater than or equal to one; image parameters are generated according to the N+1 acquisition information; Constructing a spatial virtual model of the anchor steel belt according to the image parameters; Acquiring anchor protection contour features of the spatial virtual model, wherein the anchor protection contour features at least include contact surface contour information between the anchor protection steel belt and the underground tunnel; Matching corresponding preset anchor protection parameters in a preset anchor protection database according to the anchor protection profile features, and extracting a first anchor protection strategy of the preset anchor protection parameters, wherein the first anchor protection strategy includes a drilling strategy after the anchor protection steel belt is laid in the underground tunnel; Extracting hole position parameters of the anchor steel belt according to the spatial virtual model, and generating a drilling decision according to the first anchor protection strategy and the hole position parameters; The step of adjusting the acquisition position and / or acquisition angle, and repeating the above steps N times to obtain N+1 pieces of acquisition information specifically includes: Randomly obtain the coordinate information of the acquisition area corresponding to one of the first image feature vectors, and use the coordinate information as the original coordinate; obtain the first image feature vectors of the remaining N acquisition information, and extract the coordinate information of each of the first image feature vectors, and use the coordinate information as the reference coordinate; obtain the offset between each of the reference coordinates and the original coordinate, and use the N+1 offsets as a group of offset parameters; repeat the above steps M times to obtain M+1 groups of offset parameters, where M is a positive integer greater than or equal to one; After repeating the above steps M times to obtain M+1 groups of the offset parameters, the method further includes: Performing weighted calculation on the M+1 groups of offset parameters, and obtaining M+1 confidence levels corresponding to each group of offset parameters; Sorting the M+1 confidence levels from high to low, and outputting the weighted offset corresponding to the confidence level ranked first in the sorting; According to the weighted offset and any one of the original coordinates, the revised coordinates corresponding to the remaining N first image feature vectors under the same original coordinate are generated, and according to the original coordinates and the N revised coordinates, N+1 pieces of the acquisition information are generated.

2. The identification method of the device for identifying the installation hole of the anchor steel belt in the underground tunnel according to claim 1 is characterized in that: The acquisition posture at least includes the acquisition displacement and acquisition angle of the image acquisition unit (10).

3. The identification method of the device for identifying the installation hole of the anchor steel belt in the underground tunnel according to claim 1 is characterized in that: The posture adjustment unit (20) is a mechanical arm.

4. A recognition method for an identification device for an installation hole of an anchor steel belt in an underground tunnel according to any one of claims 1 to 3, characterized in that: The step of extracting the hole position parameters of the anchor steel belt according to the spatial virtual model specifically includes: Extracting point cloud distribution parameters corresponding to the installation holes of the anchor steel belt according to the spatial virtual model; Denoising the point cloud distribution parameters according to the first anchoring strategy, and extracting boundary features of the denoised point cloud distribution parameters; The center position of the mounting hole is determined according to the boundary feature, and the hole position parameters are generated according to the center position.

5. The identification method of the device for identifying the installation hole of the anchor steel belt in the underground tunnel according to claim 4 is characterized in that: The step of determining the center position of the mounting hole according to the boundary feature and generating the hole position parameters according to the center position specifically includes: Classifying the installation holes according to the hole position parameters, and obtaining a second anchoring strategy corresponding to at least the size, drilling method and drilling sequence of the installation holes; The drilling decision is generated according to the first anchoring strategy and the second anchoring strategy.

6. An electronic device, characterized in that: include: Memory (830) and processor (810); The memory (830) and the processor (810) communicate with each other via a bus; The memory (830) stores computer instructions that can be executed on the processor (810); When the processor (810) calls the computer instruction, it is capable of executing the identification method of the device for identifying the installation hole of the anchor steel belt in the underground tunnel as described in any one of claims 1 to 5.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor (810), the steps of the identification method of the device for identifying the installation hole of the anchor steel belt in the underground tunnel described in any one of claims 1 to 5 are implemented.

8. A computer program product comprising a non-transitory machine-readable medium storing a computer program, characterized in that: When the computer program is executed by the processor (810), the steps of the identification method of the device for identifying the installation hole of the anchor steel belt in the underground tunnel described in any one of claims 1 to 5 are implemented.