Degradation detection method, system and equipment for underground tunnel environment

Abstract

The invention provides a degradation detection method, system and equipment for an underground tunnel environment, and belongs to the technical field of detection and positioning of the underground tunnel environment, and the method comprises the following steps: constructing a cylindrical space adaptive to tunnel structure characteristics by taking an original point of a laser radar coordinate system as a center; performing point cloud partitioning on the cylindrical space to obtain a plurality of block regions; calculating a normal vector of each block region, and establishing a reference normal vector of a local region; correcting a normal vector direction by using a local region reference normal vector; a sphere histogram is established, intervals are divided according to the corrected normal vector azimuth angle and pitch angle, and a normal vector is projected after being subjected to spherical coordinate system conversion; and calculating a degradation judgment factor according to a projection result, and judging whether the underground tunnel environment is degraded or not by utilizing the degradation judgment factor. Based on the degradation detection method for the underground tunnel environment, the invention further provides a degradation detection system and device for the underground tunnel environment. According to the invention, the positioning and mapping precision in a complex environment is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of detection and positioning of underground tunnel environments, and in particular relates to a degradation detection method, system and equipment for underground tunnel environments. Background Art

[0002] With the rapid development of autonomous mobile robots, unmanned driving, and intelligent warehousing, the simultaneous positioning and mapping technology SLAM, as the core module for achieving environmental perception and autonomous navigation, is facing increasingly complex application scenario requirements. The current mainstream SLAM methods can be divided into two categories: vision and laser. The vision solution has the advantages of low cost and lightweight, but it is limited by the physical characteristics of the visual sensor and does not work well in environments with low texture and sudden changes in illumination. LiDAR is widely used in structured environments such as urban roads, indoors, and industrial parks due to its high-precision ranging and strong anti-interference ability. However, the laser SLAM system still faces a challenge that cannot be ignored in practical applications - the degradation problem, that is, when the robot moves in an area with insufficient geometric constraints, the pose estimation produces an accumulation of errors in unobservable directions due to the lack of observation information dimensions, resulting in positioning drift and map distortion. This challenge is further highlighted in extremely complex scenarios such as mine tunnels. As the core transportation channel for underground resource mining, its topological structure is usually narrow, long, low, and multi-branched. In addition, affected by the geological structure and mining process, the tunnel wall often has similar characteristics of local bending, irregular deformation, and cracks. This type of environment poses a dual challenge to the laser SLAM system: on the one hand, the main structure of the tunnel is mostly long and straight or with gently varying curvature. When the laser radar moves axially along the tunnel, it is easy to cause degradation along the forward direction due to insufficient geometric constraint dimensions in the scanning plane; on the other hand, the local irregularity of the tunnel wall will lead to uneven distribution of point cloud density.

[0003] The existing degradation detection methods for underground tunnel environments mainly include impact echo method and laser scanning technology. The impact echo method is a method of detecting structures using ultrasonic and sound waves generated by steel ball impact. The integrity of the structure is analyzed by recording multiple reflected waves through sensors; laser scanning technology can quickly obtain three-dimensional data inside the tunnel, and by comparing data at different time points, changes and degradation of the tunnel structure can be detected. However, they have common disadvantages, such as high cost, complex operation, greater environmental impact, and long data processing time. These disadvantages may limit the widespread use of these two methods in practical applications. Summary of the invention

[0004] In order to solve the above technical problems, the present invention proposes a degradation detection method, system and device for underground tunnel environment, which improves the positioning and mapping accuracy in complex environments.

[0005] To achieve the above object, the present invention adopts the following technical solutions: A degradation detection method for an underground tunnel environment, comprising the following steps: Construct a cylindrical space adapted to the tunnel structure characteristics with the origin of the lidar coordinate system as the center; perform point cloud segmentation on the cylindrical space to obtain a plurality of block regions; Calculate the normal vector of each block region, and establish a local region reference normal vector; use the local region reference normal vector to correct the direction of the normal vector; Establish a spherical histogram, divide the interval according to the azimuth angle and pitch angle of the corrected normal vector, and project the normal vector after spherical coordinate transformation; Calculate the degradation judgment factor according to the projection result, and use the degradation judgment factor to judge whether there is degradation in the underground tunnel environment.

[0006] The present invention also proposes a degradation detection system for an underground tunnel environment, comprising: A construction module, configured to construct a cylindrical space adapted to the tunnel structure characteristics with the origin of the lidar coordinate system as the center; perform point cloud segmentation on the cylindrical space to obtain a plurality of block regions; A correction module, configured to calculate the normal vector of each block region, and establish a local region reference normal vector; use the local region reference normal vector to correct the direction of the normal vector; A conversion module, configured to establish a spherical histogram, divide the interval according to the azimuth angle and pitch angle of the corrected normal vector, and project the normal vector after spherical coordinate transformation; A detection module, configured to calculate the degradation judgment factor according to the projection result, and use the degradation judgment factor to judge whether there is degradation in the underground tunnel environment.

[0007] The present invention also proposes a degradation detection device for an underground tunnel environment, comprising: A memory, configured to store a computer program; A processor, configured to implement the steps of the degradation detection method for an underground tunnel environment when executing the computer program.

[0008] The effects provided in the invention content are only the effects of the embodiments, rather than all the effects of the invention. One of the above technical solutions has the following advantages or beneficial effects: The present invention proposes a degradation detection method, system, and device for an underground tunnel environment, belonging to the technical field of detection and positioning of underground tunnel environments, including the following steps: constructing a cylindrical space adapted to the tunnel structure characteristics with the origin of the lidar coordinate system as the center; performing point cloud partitioning on the cylindrical space to obtain multiple block regions; calculating the normal vector of each block region to establish a local region reference normal vector; correcting the normal vector direction using the local region reference normal vector; establishing a spherical histogram, dividing intervals based on the azimuth angle and elevation angle of the corrected normal vector, and projecting the normal vector after spherical coordinate transformation; calculating a degradation judgment factor based on the projection result, and using the degradation judgment factor to determine whether there is degradation in the underground tunnel environment. Based on a degradation detection method for an underground tunnel environment, a degradation detection system and device for an underground tunnel environment are also proposed. The present invention is based on a fast degradation detection factor based on normal vector distribution, realizes real-time discrimination of degradation states by analyzing the statistical characteristics of the normal vector set, reduces the time complexity while realizing information reuse, and can make targeted compensation thereby, improving the positioning and mapping accuracy in complex environments.

[0009] The implementation of the present invention has no special requirements for hardware devices, has a wide application range, and can cope with various complex environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 It is a flowchart of a degradation detection method for an underground tunnel environment proposed in Embodiment 1 of the present invention; Figure 2 It is a schematic diagram of a degradation detection system for an underground tunnel environment proposed in Embodiment 2 of the present invention; Figure 3 It is a schematic diagram of a degradation detection device for an underground tunnel environment proposed in Embodiment 3 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0011] To clearly illustrate the technical characteristics of the present solution, the present invention will be described in detail below through specific embodiments and in conjunction with its accompanying drawings. The following disclosure provides many different embodiments or examples for implementing different structures of the present invention. To simplify the disclosure of the present invention, the components and settings of specific examples are described below. In addition, the present invention may repeat reference numerals and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not in itself indicate the relationship between the various embodiments and / or settings discussed. It should be noted that the components illustrated in the accompanying drawings are not necessarily drawn to scale. The present invention omits the description of well-known components and processing techniques and processes to avoid unnecessarily limiting the present invention.

[0012] Embodiment 1 Embodiment 1 of the present invention proposes a degradation detection method, system, and device for an underground tunnel environment to solve the technical problems existing in degradation detection in a long and straight environment in the prior art. This application utilizes the uneven characteristics in a mine tunnel to perform targeted feature extraction.

[0013] Figure 1 It is a flowchart of a degradation detection method for an underground tunnel environment proposed in Embodiment 1 of the present invention; In step S100, a cylindrical space adapted to the tunnel structure characteristics is constructed with the origin of the lidar coordinate system as the center; the point cloud in the cylindrical space is divided into multiple block regions.

[0014] In this application, with the origin of the lidar coordinate system as the center of the cylindrical space, the point cloud is divided into multiple non-uniform block regions based on the azimuth angle and height. The specific implementation process is as follows: ; ; Among them, is the interval coordinate in the cylindrical coordinate system; is the azimuth angle span of the interval; represents the number of azimuth angle intervals for cylindrical interval division; represents the number of height intervals for cylindrical interval division; represents the th azimuth angle interval; represents the th height interval; represents the bottom span of the interval; represents the middle span of the interval; represents the top span of the interval; is the highest point among the scanned points; is the lowest point among the scanned points; ; Obtain the direction angle of any point ; ; Among them, represents the axis coordinate of any point in the cylindrical interval; represents the axis coordinate of any point in the cylindrical interval; represents the axis coordinate of any point in the cylindrical interval; represents the corresponding direction angle of any point

[0015] Since the top (vault) and bottom (ground) have dense point clouds due to obvious planar features, and the point cloud in the middle area (side wall) is relatively sparse. In this application, non-uniform height stratification is adopted to adapt to the tunnel structure characteristics, which is specifically reflected in: ; .

[0016] The azimuth angle is divided to achieve full 360° coverage (value range [-180°, 180°]) through the atan2 function, avoiding the angle jump problem of the traditional arctan function when x < 0.

[0017] Example of dynamic partitioning: When , the height is divided into , ,..., , where .

[0018] In step S110, calculate the normal vector of each block area, establish the local area reference normal vector; use the local area reference normal vector to correct the normal vector direction.

[0019] Determine the set of local neighborhood points of any point in the point cloud, specifically: ; Among them, is the preprocessed current scanned point cloud set; is the search radius; is in 's neighborhood points; Construct the local neighborhood covariance matrix using the local neighborhood points: ; Among them, represents 's average value; Perform eigenvalue decomposition on the local neighborhood covariance matrix, and the eigenvector corresponding to the smallest eigenvalue obtained is the normal vector of any point; ; Among them, is the local neighborhood covariance matrix 's first eigenvalue; is the local neighborhood covariance matrix 's second eigenvalue; is the local neighborhood covariance matrix 's third eigenvalue; and ; is the eigenvector corresponding to the first eigenvalue; is the eigenvector corresponding to the second eigenvalue; is the eigenvector corresponding to the third eigenvalue; the minimum eigenvalue The corresponding eigenvector is the normal vector of point , that is .

[0020] When is located in the cylindrical interval , the normal vector of the corrected point cloud is: ; where is the reference normal vector of each cylindrical interval.

[0021] Neighborhood search uses a spherical query with a radius . Numerical stability is ensured by SVD during the eigen-decomposition of the covariance matrix.

[0022] Normal vector correction is judged by the dot product sign to ensure that all normal vectors point to the origin of the lidar coordinate system, solving the problem of the direction ambiguity of the normal vectors on both sides of the plane.

[0023] In step S120, a spherical histogram is established, and the intervals are divided according to the azimuth angle and elevation angle of the corrected normal vector, and the normal vector is projected after being transformed into the spherical coordinate system.

[0024] Establish a spherical histogram and divide the intervals according to the azimuth angle and elevation angle of the corrected normal vector; specifically: The spherical histogram divides the spherical region with an azimuth angle span and an elevation angle span to obtain the interval coordinates of the spherical histogram which are expressed as:[[]]END]]

[0025] where represents the number of azimuth angle intervals for the spherical region division; represents the number of elevation angle intervals for the spherical region division; represents the th azimuth angle interval; represents the th elevation angle interval; represents the azimuth angle span; represents the elevation angle span; and respectively represent the first interval coordinate and the second interval coordinate passing through the center of the sphere; For the corrected normal vector , the elevation angle Calculated as: ; Wherein, is the axis coordinate of the spherical region of the corrected normal vector; is the axis coordinate of the spherical region of the corrected normal vector; is the axis coordinate of the spherical region of the corrected normal vector.

[0026] This application adopts a dual - interval design to achieve seamless spherical coverage and avoid distortion in the pole regions.

[0027] After classifying the set of normal vectors into the corresponding spherical histograms, the number of normal vectors corresponding to each pair of intervals is counted. There may be a problem with histogram projection: when a cluster of normal vectors with roughly the same direction is exactly on the boundary of the divided intervals, it may be projected into multiple adjacent intervals. To solve this problem, the following screening mechanism is proposed in this paper: First, only retain the intervals where the number of normal vectors is in the top one - third of the entire interval as candidates; Second, the number of normal vectors in the neighborhood of the candidate interval is less than its own number; Finally, the ratio of the number of normal vectors in the surrounding neighborhood intervals to the candidate interval needs to be higher than a set threshold, and the qualified neighborhood statistics are merged into the candidate interval. The axial symmetry of the tunnel determines that the degenerate direction is basically orthogonal to the direction of the dense distribution of normal vectors, and the interval corresponding to the degenerate direction will not appear in the interval with the largest number of normal vectors and its neighborhood intervals. Therefore, such a screening mechanism will not affect the degenerate judgment.

[0028] In step S130, a degenerate judgment factor is calculated according to the projection result, and the degenerate judgment factor is used to judge whether there is degradation in the underground tunnel environment.

[0029] Count the sum of the number of normal vectors in the two intervals with the largest number in the histogram , and the sum of the number of normal vectors in the remaining intervals , calculate the degenerate judgment factor as: ; When the degenerate judgment factor is less than the preset threshold, it is considered that the environment is degraded, and the cross - product result of the main directions of the two intervals with the largest number of normal vectors is the degenerate direction; the degenerate factor reflects the degree of environmental anisotropy: when the tunnel is non - degenerate (such as at intersections), the normal vectors are evenly distributed; is larger; when it is degenerate (long straight tunnel), the normal vectors are concentrated in the side - wall direction tends to 0.

[0030] Tunnel main direction and the direction of the maximum normal - vector aggregation ( , ) satisfies the right - hand rule and physically corresponds to the cross - direction of the side - wall normal vector (i.e., the tunnel extension direction); the degradation direction The calculation method is as follows: ; Among them, represents the number of normal vectors in the interval with the largest number of normal vectors in the histogram; represents the number of normal vectors in the interval with the second - largest number of normal vectors in the histogram; represents the normal vectors in the first interval; represents the normal vectors in the second interval; represents the main direction obtained by fitting the normal vectors in the first interval; represents the main direction obtained by fitting the normal vectors in the second interval.

[0031] In this application, the parameter setting suggestions are as follows: Columnar partition: (15° interval), ; Spherical histogram: (30° interval), (30° interval) Threshold selection: , and the measured data shows that when, the positioning error increases significantly.

[0032] The scope of protection of the present invention is not limited to the specific data listed in Embodiment 1, and those skilled in the art can make reasonable selections according to the actual situation.

[0033] A degradation detection method for an underground tunnel environment proposed in Embodiment 1 of the present invention, based on a fast degradation detection factor of normal vector distribution, realizes real - time discrimination of the degradation state by analyzing the statistical characteristics of the normal vector set, reduces the time complexity while realizing information reuse, and can make targeted compensations thereby, improving the positioning and mapping accuracy in complex environments. At the same time, the present invention has no special requirements for hardware devices, has a wide application range, and can cope with various complex environments.

[0034] A degradation detection method for an underground tunnel environment proposed in Embodiment 1 of the present invention, its core advantage is to transform the complex geometric degradation problem into quantifiable statistical distribution characteristics, which not only retains physical interpretability but also meets the real - time requirement.

[0035] Embodiment 2 Based on the degradation detection method for an underground tunnel environment proposed in Embodiment 1 of the present invention, Embodiment 2 of the present invention also proposes a degradation detection system for an underground tunnel environment, Figure 2Schematic diagram of a degradation detection system for an underground tunnel environment proposed in Embodiment 2 of the present invention. The system includes: A construction module for constructing a cylindrical space adapted to the tunnel structure characteristics with the origin of the lidar coordinate system as the center; and dividing the point cloud in the cylindrical space to obtain a plurality of block regions; A calibration module for calculating the normal vector of each block region and establishing a local region reference normal vector; and correcting the direction of the normal vector by using the local region reference normal vector; A conversion module for establishing a spherical histogram, dividing intervals based on the azimuth angle and pitch angle of the calibrated normal vector, and projecting the normal vector after spherical coordinate conversion; A detection module for calculating a degradation judgment factor based on the projection result and using the degradation judgment factor to determine whether there is degradation in the underground tunnel environment.

[0036] In the construction module: dividing the point cloud in the cylindrical space to obtain block regions. The specific process is as follows: taking the origin of the lidar coordinate system as the center of the cylindrical space, and dividing the point cloud into a plurality of non-uniform block regions based on the azimuth angle and height.

[0037] ; ; Among them, is the interval coordinate in the cylindrical coordinate system; is the azimuth angle span of the interval; represents the number of azimuth angle intervals for cylindrical interval division; represents the number of height intervals for cylindrical interval division; represents the th azimuth angle interval; represents the th height interval; represents the bottom span of the interval; represents the middle span of the interval; represents the top span of the interval; is the highest point in the scanned points; is the lowest point in the scanned points; ; Obtain the direction angle of any point ; ; Among them, represents the axis coordinate of any point in the cylindrical interval; represents the axis coordinate of any point in the cylindrical interval; represents the In the cylindrical interval axis coordinates; representing an arbitrary point corresponding direction angle.

[0038] In the calibration module: calculate the normal vector of each block area, and establish a local area reference normal vector; use the local area reference normal vector to calibrate the direction of the normal vector; specifically: determine the local neighborhood points of an arbitrary point in the point cloud; Construct a local neighborhood covariance matrix using the local neighborhood points; perform eigenvalue decomposition on the local neighborhood covariance matrix, and the eigenvector corresponding to the minimum eigenvalue is the normal vector of the arbitrary point; place the scanned point cloud into the cylindrical space according to the azimuth angle and height to calibrate the direction of the normal vector.

[0039] Determine the set of local neighborhood points of an arbitrary point in the point cloud, specifically: ; where, is the set of currently scanned point clouds after preprocessing; is the search radius; is in the neighborhood points; Construct a local neighborhood covariance matrix using the local neighborhood points : ; where, represents the average value of; Perform eigenvalue decomposition on the local neighborhood covariance matrix, and the eigenvector corresponding to the minimum eigenvalue is the normal vector of the arbitrary point;

[0040] where, is the local neighborhood covariance matrix corresponding first eigenvalue; is the local neighborhood covariance matrix corresponding second eigenvalue; is the local neighborhood covariance matrix corresponding third eigenvalue; and ; is the eigenvector corresponding to the first eigenvalue; is the eigenvector corresponding to the second eigenvalue; is the eigenvector corresponding to the third eigenvalue; the eigenvector corresponding to the minimum eigenvalue is the normal vector of the point i.e., ; When Located in the cylindrical interval When the corrected point cloud normal vector is: Among them, is the reference normal vector of each cylindrical interval.

[0041] In the conversion module, a spherical histogram is established, and the azimuth and elevation angles of the corrected normal vector are used to divide the intervals; the specific process is as follows: the spherical histogram is divided into spherical regions with an azimuth span and an elevation span to obtain the interval coordinates of the spherical histogram which is expressed as:

[0042] Among them, represents the number of azimuth intervals for the spherical region division; represents the number of elevation intervals for the spherical region division; represents the th azimuth interval; represents the th elevation interval; and respectively represent the first and second interval coordinates passing through the center of the sphere; represents the azimuth span; represents the elevation span; For the corrected normal vector , the elevation angle is calculated as: ; Among them, is the axis coordinate of the spherical region of the corrected normal vector; is the axis coordinate of the spherical region of the corrected normal vector; is the axis coordinate of the spherical region of the corrected normal vector.

[0043] The process of projecting the normal vector after spherical coordinate transformation is specifically as follows: retain the intervals with the normal vector quantity in the front preset ratio of the full interval as candidate intervals; among them, the number of neighboring normal vectors in the candidate interval is less than its own quantity; the ratio of the number of normal vectors in the surrounding neighboring intervals to the candidate interval is higher than the set threshold; merge the qualified neighborhood statistics into the candidate interval.

[0044] In the detection module, a degradation judgment factor is calculated based on the projection result, and the degradation judgment factor is used to determine whether there is degradation in the underground tunnel environment. Specifically: the sum of the normal vector quantities in the two intervals with the largest number in the statistical histogram , the sum of the normal vector quantities in the remaining intervals , and the degradation judgment factor is calculated as: ; Among them, is the degradation judgment factor; When the degradation judgment factor is less than the preset threshold, it is considered that the environment has degradation, and the cross product result of the main directions of the two intervals with the most normal vectors is the degradation direction; the degradation direction The calculation method is: ; Among them, represents the normal vector quantity of the interval ranked first in the normal vector quantity in the histogram; represents the normal vector quantity of the interval ranked second in the normal vector quantity in the histogram; represents the normal vector of the first interval; represents the normal vector of the second interval; represents the main direction obtained by fitting the normal vectors of the first interval; represents the main direction obtained by fitting the normal vectors of the second interval.

[0045] A degradation detection system for the underground tunnel environment proposed in Embodiment 2 of the present invention, based on the fast degradation detection factor of the normal vector distribution, realizes the real-time discrimination of the degradation state by analyzing the statistical characteristics of the normal vector set, reduces the time complexity while realizing information reuse, and can make targeted compensation thereby, improving the positioning and mapping accuracy in complex environments. At the same time, the implementation of the present invention has no special requirements for hardware devices, has a wide application range, and can cope with various complex environments.

[0046] The core advantage of the degradation detection system for the underground tunnel environment proposed in Embodiment 2 of the present invention is to transform the complex geometric degradation problem into a quantifiable statistical distribution feature, which not only retains the physical interpretability but also meets the real-time requirement.

[0047] Embodiment 3 The present invention also proposes a device, Figure 3 which is a schematic diagram of a degradation detection device for the underground tunnel environment proposed in Embodiment 3 of the present invention, including: A memory for storing a computer program; A processor for implementing the method steps as follows when executing the computer program: In step S100, a cylindrical space adapted to the tunnel structure characteristics is constructed with the origin of the lidar coordinate system as the center; the point cloud is segmented in the cylindrical space to obtain multiple block regions.

[0048] In step S110, the normal vector of each block region is calculated to establish a local region reference normal vector; the direction of the normal vector is corrected using the local region reference normal vector.

[0049] In step S120, a spherical histogram is established, intervals are divided according to the azimuth angle and pitch angle of the corrected normal vector, and the normal vector is projected after being transformed into the spherical coordinate system.

[0050] In step S130, a degradation judgment factor is calculated based on the projection result, and the degradation judgment factor is used to determine whether there is degradation in the underground tunnel environment.

[0051] An underground tunnel environment degradation detection device proposed in Embodiment 3 of the present invention, based on a fast degradation detection factor of normal vector distribution, realizes real-time discrimination of the degradation state by analyzing the statistical characteristics of the normal vector set, reduces the time complexity while realizing information reuse, and can make targeted compensation thereby to improve the positioning and mapping accuracy in complex environments. At the same time, the present invention has no special requirements for hardware devices, has a wide application range, and can cope with various complex environments.

[0052] An underground tunnel environment degradation detection device proposed in Embodiment 3 of the present invention, its core advantage is to transform the complex geometric degradation problem into a quantifiable statistical distribution feature, which not only retains physical interpretability but also meets the real-time requirement.

[0053] It should be noted that the technical solution of the present invention also provides an electronic device, including: a communication interface capable of interacting with other devices such as network devices; a processor connected to the communication interface to achieve information interaction with other devices, and when running a computer program, executing a degradation detection method for an underground tunnel environment provided by one or more of the above technical solutions, and the computer program is stored on a memory. Of course, in actual application, each component in the electronic device is coupled together through a bus system. It can be understood that the bus system is used to realize the connection and communication between these components. The bus system includes, in addition to a data bus, a power bus, a control bus, and a status signal bus. The memory in the embodiment of the present application is used to store various types of data to support the operation of the electronic device. Examples of these data include: any computer program for operating on the electronic device. It can be understood that the memory can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM, Read Only Memory), a programmable read-only memory (PROM, Programmable Read-Only Memory), an erasable programmable read-only memory (EPROM, Erasable Programmable Read-Only Memory), an electrically erasable programmable read-only memory (EEPROM, Electrically Erasable Programmable Read-Only Memory), a ferromagnetic random access memory (FRAM, ferromagnetic random access memory), a flash memory (FlashMemory), a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM, Compact Disc Read-Only Memory); the magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM, Random AccessMemory), which is used as an external cache.By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), sync link dynamic random access memory (SLDRAM), direct rambus random access memory (DRRAM). The memories described in the embodiments of the present application are intended to include but not limited to these and any other suitable types of memories. The methods disclosed in the embodiments of the present application above can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with the ability to process signals. In the implementation process, the steps of the above methods can be completed by the integrated logic circuit of the hardware in the processor or the instructions in the form of software. The above processor may be a general-purpose processor, a DSP (Digital Signal Processing, that is, a chip capable of implementing digital signal processing technology), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or any conventional processor, etc. Combining the steps of the methods disclosed in the embodiments of the present application, it can be directly embodied as being executed and completed by the hardware decoding processor, or executed and completed by the combination of the hardware and software modules in the decoding processor. The software module may be located in a storage medium, and the storage medium is located in the memory. The processor reads the program in the memory and combines its hardware to complete the steps of the foregoing methods. When the processor executes the program, the corresponding processes in the various methods of the embodiments of the present application are implemented. For the sake of brevity, it will not be elaborated here.

[0054] For the description of the relevant parts of a degradation detection device for an underground tunnel environment provided in Embodiment 3 of the present application, reference can be made to the detailed description of the corresponding parts in a degradation detection method for an underground tunnel environment provided in Embodiment 1 of the present application, which will not be elaborated here.

[0055] It should be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that the elements inherent in a process, method, article or device including a series of elements. Without further limitation, the element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, article or device including the said element. In addition, the parts of the above technical solutions provided in the embodiments of the present application that are consistent with the corresponding technical solutions in the prior art are not described in detail to avoid excessive elaboration.

[0056] Although the specific implementation manners of the present invention have been described above in conjunction with the accompanying drawings, it is not a limitation on the protection scope of the present invention. For those skilled in the art, other different forms of modification or variation can be made on the basis of the above description. It is not necessary and impossible to enumerate all the implementation manners here. Various modifications or variations that can be made by those skilled in the art without creative efforts on the basis of the technical solutions of the present invention are still within the protection scope of the present invention.

Claims

1. A degradation detection method for the underground tunnel environment, characterized in that, It includes the following steps: Construct a cylindrical space centered at the origin of the lidar coordinate system to adapt to the tunnel structure characteristics; Perform point cloud segmentation on the cylindrical space to obtain multiple block regions; Calculate the normal vector of each block region and establish a local region reference normal vector; Use the local region reference normal vector to correct the direction of the normal vector; Establish a spherical histogram, divide the intervals according to the azimuth and elevation angles of the corrected normal vector, and project the normal vector after spherical coordinate transformation; Calculate the degradation judgment factor based on the projection result, and use the degradation judgment factor to determine whether there is degradation in the underground tunnel environment.

2. The degradation detection method for the underground tunnel environment according to claim 1, characterized in that Perform point cloud segmentation on the cylindrical space to obtain segmented regions, specifically: Taking the origin of the lidar coordinate system as the center of the cylindrical space, divide the point cloud into multiple non-uniform segmented regions based on the azimuth and height.

3. The degradation detection method for the underground tunnel environment according to claim 2, characterized in that Calculate the normal vector of each block region and establish a local region reference normal vector; use the local region reference normal vector to correct the direction of the normal vector; specifically: Determine the local neighborhood points of any point in the point cloud; Construct a local neighborhood covariance matrix using the local neighborhood points; Perform eigenvalue decomposition on the local neighborhood covariance matrix, and the eigenvector corresponding to the minimum eigenvalue is the normal vector of any point; Put the scanned point cloud into the cylindrical space according to the azimuth and height to correct the direction of the normal vector.

4. The degradation detection method for the underground tunnel environment according to claim 3, characterized in that Taking the origin of the lidar coordinate system as the center of the cylindrical space, divide the point cloud into multiple non-uniform segmented regions based on the azimuth and height, specifically: ； ； Among them, is the interval coordinate in the cylindrical coordinate system; is the azimuth angle span of the interval; represents the number of azimuth angle intervals for the cylindrical interval division; represents the number of height intervals for the cylindrical interval division; represents the th azimuth angle interval; represents the th height interval; represents the bottom span of the interval; represents the middle span of the interval; represents the top span of the interval; is the highest point among the scanning points; is the lowest point among the scanning points; ； Obtain the direction angle of any point ; ; Among them, represents an arbitrary point on the axis coordinate of the cylindrical interval ; represents an arbitrary point on the axis coordinate of the cylindrical interval ; represents an arbitrary point on the axis coordinate of the cylindrical interval ; represents an arbitrary point and the corresponding direction angle.

5. The degradation detection method for the underground tunnel environment according to claim 4, characterized in that, Determine the set of local neighborhood points of any point in the point cloud, specifically: ； Among them, is the set of currently scanned point clouds after preprocessing; is the search radius; is in the neighboring points of; Constructing a local neighborhood covariance matrix using local neighborhood points : ； Among them, represents the average value of Perform eigenvalue decomposition on the local neighborhood covariance matrix, and the eigenvector corresponding to the minimum eigenvalue is the normal vector of any point; Among them, is the local neighborhood covariance matrix corresponding to the first eigenvalue; is the local neighborhood covariance matrix corresponding to the second eigenvalue; is the local neighborhood covariance matrix corresponding to the third eigenvalue; and ; is the eigenvector corresponding to the first eigenvalue; is the eigenvector corresponding to the second eigenvalue; is the eigenvector corresponding to the third eigenvalue; the eigenvector corresponding to the minimum eigenvalue is the normal vector of the point , that is, ; When is located in the column interval the corrected point cloud normal vector is as follows: ； Among them, is the reference normal vector for each bar interval.

6. The degradation detection method for the underground tunnel environment according to claim 5, characterized in that, Establish a spherical histogram and divide the intervals according to the azimuth and elevation angles of the corrected normal vector; specifically: The spherical histogram spans by azimuth angle and pitch angle to divide the sphere region and obtain the interval coordinates of the spherical histogram which is expressed as: Among them, represents the number of azimuth angle intervals for sphere region division; represents the number of elevation angle intervals for sphere region division; represents the th azimuth angle interval; represents the th elevation angle interval; and respectively represent the first interval coordinates and the second interval coordinates passing through the center of the sphere; Represents the azimuth angle span; Represents the elevation angle span; For the corrected normal vector , the pitch angle is calculated as: ； Among them, is the axis coordinate of the spherical region of the corrected normal vector; is the axis coordinate of the spherical region of the corrected normal vector; is the axis coordinate of the spherical region of the corrected normal vector.

7. The degradation detection method for the underground tunnel environment according to claim 6, wherein Project the normal vector after spherical coordinate transformation; specifically: Retain the intervals where the number of normal vectors is in the top preset ratio of the full interval as candidate intervals; among them, the number of normal vectors in the neighborhood of the candidate interval is less than its own number; The ratio of the number of normal vectors in the surrounding neighborhood interval to the candidate interval is higher than the set threshold; merge the eligible neighborhood statistics into the candidate interval.

8. The degradation detection method for the underground tunnel environment according to claim 7, characterized in that Calculate the degradation judgment factor based on the projection result, and use the degradation judgment factor to determine whether there is degradation in the underground tunnel environment; specifically: The sum of the number of normal vectors in the two intervals with the largest number in the statistical histogram , and the sum of the number of normal vectors in the remaining intervals , calculate the degradation judgment factor as: ； Among them, is the degradation judgment factor; When the degradation judgment factor is less than the preset threshold, it is considered that the environment has degradation, and the cross product result of the main directions of the two intervals with the most normal vectors is the degradation direction; Degradation direction The calculation method is as follows: ； Among them, represents the number of normal vectors in the interval with the largest number of normal vectors in the histogram; represents the number of normal vectors in the interval with the second largest number of normal vectors in the histogram; represents the normal vectors in the first interval; represents the normal vectors in the second interval; represents the main direction obtained by fitting the normal vectors in the first interval; represents the main direction obtained by fitting the normal vectors in the second interval.

9. A degradation detection system for an underground tunnel environment, characterized in that, It includes: A construction module for constructing a cylindrical space centered at the origin of the lidar coordinate system to adapt to the tunnel structure characteristics; Perform point cloud segmentation on the cylindrical space to obtain multiple block regions; A correction module for calculating the normal vector of each block region and establishing a local region reference normal vector; Use the local region reference normal vector to correct the direction of the normal vector; A conversion module for establishing a spherical histogram, dividing the intervals according to the azimuth and elevation angles of the corrected normal vector, and projecting the normal vector after spherical coordinate transformation; A detection module, configured to calculate a degradation judgment factor according to the projection result, and use the degradation judgment factor to determine whether there is degradation in the underground tunnel environment.

10. A degradation detection device for an underground tunnel environment, characterized in that, It includes: A memory, configured to store a computer program; A processor, configured to implement the steps of a degradation detection method for an underground tunnel environment according to any one of claims 1 to 8 when executing the computer program.

Images