A tunnel positioning method, device, storage medium and electronic equipment

Abstract

The application discloses a tunnel positioning method and device, a storage medium and an electronic device, and belongs to the technical field of tunnel engineering measurement and positioning. The method comprises the following steps: calculating a plurality of coordinates based on a transformation matrix to obtain a plurality of registered coordinates, wherein the plurality of registered coordinates comprise the coordinates of a registered vehicle center point, the coordinates of a registered longitudinal axis positive direction and the coordinates of an arbitrary point on a registered transverse axis direction; determining the current position of the vehicle based on the coordinates of the registered vehicle center point; and performing pose solving based on the coordinates of the registered vehicle center point, the coordinates of the registered longitudinal axis positive direction and the coordinates of the arbitrary point on the registered transverse axis direction to obtain the attitude information of the vehicle. The tunnel positioning method can improve the positioning accuracy of tunnel positioning.

Description

Technical Field

[0001] This application belongs to the field of tunnel engineering surveying and positioning technology, and specifically relates to a tunnel positioning method, device, storage medium and electronic equipment. Background Technology

[0002] Precise internal positioning is a key technology for ensuring construction quality, safety, and efficiency during tunnel construction. Currently, tunnel positioning faces the following main technical bottlenecks: 1. Limitations of traditional surveying methods: Traditional surveying equipment such as total stations require frequent station setups for positioning in long tunnels, relying on manual operation, which is inefficient.

[0003] 2. GPS signal loss: GPS signals cannot be received inside the tunnel, causing satellite positioning technology to be completely ineffective inside the tunnel. Pseudo-satellite technology requires the setting up of base stations, which is costly.

[0004] 3. Complex point cloud data processing: Although 3D laser scanning technology can acquire high-precision point cloud data, the real-time registration and processing of large-scale point cloud data requires a large amount of computation, which is difficult to meet the real-time positioning requirements during construction.

[0005] 4. Difficulty in multi-sensor fusion: The positioning accuracy of fusion of multiple sensor data such as laser scanning, inertial navigation, and vision is low and the cumulative error is large, which makes it unsuitable for tunnel construction operations.

[0006] Currently, point cloud registration techniques mainly employ the ICP (Iterative Closest Point) algorithm and its improved versions. However, these methods suffer from slow convergence speed and susceptibility to local optima when processing large-scale point cloud data. While feature extraction and matching methods can improve registration efficiency, the stability and reliability of feature extraction face challenges in environments with relatively simple structural features, such as tunnels.

[0007] In summary, how to provide a tunnel positioning method to improve the positioning accuracy of tunnels is a problem to be solved. Summary of the Invention

[0008] To address the aforementioned problems, this application provides a tunnel positioning method, apparatus, storage medium, and electronic device, which can improve the positioning accuracy of tunnel positioning.

[0009] In a first aspect, embodiments of this application provide a tunnel positioning method, the method comprising: Obtain the basis feature image mapped from the basis data, and obtain the real-time feature image; The base feature image and the real-time feature image are matched to obtain a matching result, which includes: the optimal matching segment determined based on the phase velocity between the base feature image and the real-time feature image; Based on the matching results, the corresponding base point cloud segments are extracted; For the segmented base point cloud, a preset ICP algorithm is used for point cloud registration to obtain a transformation matrix. The preset ICP algorithm includes: point-to-point ICP algorithm, point-to-surface ICP algorithm, and generalized ICP algorithm. Multiple coordinates are obtained, which are coordinates obtained by calibrating the spatial parameters of the vehicle in the original point cloud scene of the LiDAR. The multiple coordinates include: the coordinates of the vehicle center point, the coordinates of the positive direction of the vertical axis, and the coordinates of any point in the horizontal axis direction. Based on the transformation matrix, the multiple coordinates are calculated to obtain multiple registered coordinates, which include: the coordinates of the registered vehicle center point, the coordinates of the registered positive vertical axis, and the coordinates of any point in the registered horizontal axis. The vehicle's current position is determined based on the coordinates of the registered vehicle center point, and the vehicle's attitude information is obtained by performing pose calculation based on the coordinates of the registered vehicle center point, the coordinates of the registered positive longitudinal axis, and the coordinates of any point in the registered transverse axis.

[0010] Optionally, before obtaining the basis feature image mapped from the basis data, the method further includes: Construct base data for tunnel positioning, and update the base data to obtain updated base data; The point cloud is segmented according to the tunnel design station information and the preset segment spacing to obtain multiple point cloud segments; Based on preset rules, any one of the multiple point cloud segments is mapped into a corresponding two-dimensional feature image; and the two-dimensional feature image is used as the base feature image.

[0011] Optionally, the construction of the base data for tunnel positioning, and the updating of the base data to obtain updated base data, include: Point cloud data of the tunnel was obtained by multi-station scanning along the tunnel axis using a 3D laser scanner. The point cloud data is converted to the engineering coordinate system by using target points or control points to obtain the corresponding engineering data in the engineering coordinate system, and the engineering data is used as the base data for tunnel positioning. When tunnel construction extension is detected, the base data is updated to obtain updated base data.

[0012] Optionally, after mapping any one of the multiple point cloud segments into a corresponding two-dimensional feature image based on preset rules, the method further includes: Based on the tunnel design station information, the multiple point cloud segments, and the two-dimensional feature image, a correspondence between the station, point cloud segments, and feature image is established.

[0013] Optionally, before acquiring the real-time feature image, the method further includes: The spatial parameters of the vehicle in the original point cloud scene of the lidar are calibrated to obtain multiple coordinates, including: the coordinates of the vehicle center point, the coordinates of the positive direction of the vertical axis, and the coordinates of any point in the horizontal axis direction. When the construction equipment is determined to be located, the vehicle-mounted lidar is activated to acquire point clouds of multiple surrounding tunnels around the point to be located. Based on preset rules, any one of the surrounding tunnel point clouds is mapped into a corresponding two-dimensional feature image; and this two-dimensional feature image is used as the real-time feature image.

[0014] Secondly, embodiments of this application provide a tunnel positioning device, the device comprising: The first acquisition module is used to acquire the basis feature image mapped from the basis data, and to acquire the real-time feature image; A matching module is used to match the base feature image and the real-time feature image to obtain a matching result, the matching result including: the best matching segment determined based on the phase velocity between the base feature image and the real-time feature image; The extraction module is used to extract based on the matching results to obtain the corresponding base point cloud segments; The registration module is used to perform point cloud registration for the base point cloud segments using a preset ICP algorithm to obtain a transformation matrix. The preset ICP algorithm includes: point-to-point ICP algorithm, point-to-surface ICP algorithm, and generalized ICP algorithm. The second acquisition module is used to acquire multiple coordinates, which are coordinates obtained by calibrating the spatial parameters of the vehicle in the original point cloud scene of the LiDAR. The multiple coordinates include: the coordinates of the vehicle center point, the coordinates in the positive direction of the vertical axis, and the coordinates of any point in the horizontal axis direction. The calculation module is used to calculate the multiple coordinates based on the transformation matrix to obtain the multiple registered coordinates, which include: the coordinates of the registered vehicle center point, the coordinates of the registered positive vertical axis, and the coordinates of any point in the registered horizontal axis. The determination module is used to determine the current position of the vehicle based on the coordinates of the registered vehicle center point; The pose calculation module is used to calculate the pose based on the coordinates of the registered vehicle center point, the coordinates of the registered longitudinal axis in the positive direction, and the coordinates of any point in the registered transverse axis, so as to obtain the vehicle's attitude information.

[0015] Optionally, the device further includes: The data construction and data update module is used for: Before acquiring the base feature image mapped from the base data, base data for tunnel localization is constructed, and the base data is updated to obtain the updated base data. The basis feature image determination module is used for: The point cloud is segmented according to the tunnel design station information and the preset segment spacing to obtain multiple point cloud segments; Based on preset rules, any one of the multiple point cloud segments is mapped into a corresponding two-dimensional feature image; and the two-dimensional feature image is used as the base feature image.

[0016] Optionally, the data construction and data update module is specifically used for: Point cloud data of the tunnel was obtained by multi-station scanning along the tunnel axis using a 3D laser scanner. The point cloud data is converted to the engineering coordinate system by using target points or control points to obtain the corresponding engineering data in the engineering coordinate system, and the engineering data is used as the base data for tunnel positioning. When tunnel construction extension is detected, the base data is updated to obtain updated base data.

[0017] Thirdly, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed in a computer, causes the computer to perform the method of the first aspect.

[0018] Fourthly, an electronic device is provided, including a memory and a processor, wherein the memory stores executable code, and the processor executes the executable code to implement the method of the first aspect.

[0019] Compared with the prior art, this application has the following advantages: It can improve the positioning accuracy of tunnel positioning.

[0020] Other features and advantages of this application will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the application. The objectives and other advantages of this application may be realized and obtained by means of the structures pointed out in the description, claims and drawings. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 A flowchart of a tunnel positioning method according to an embodiment of this application is shown; Figure 2 A further flowchart of a tunnel positioning method according to an embodiment of this application is shown; Figure 3 Another flowchart of a tunnel positioning method according to an embodiment of this application is shown; Figure 4 A schematic diagram of the structure of a tunnel positioning device 400 according to an embodiment of this application is shown. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0024] This application provides a tunnel positioning method and apparatus, a computer-readable medium, and an electronic device, which will be described below with reference to the accompanying drawings.

[0025] Please refer to Figure 1 It illustrates flowcharts of tunnel positioning methods provided by some embodiments of this application, such as... Figure 1 As shown, the tunnel location method may include the following steps: Step S101: Obtain the basis feature image mapped from the basis data, and obtain the real-time feature image.

[0026] In one example, before obtaining the base feature image mapped from the base data, the tunnel localization method provided in this application embodiment further includes the following steps: Construct the base data for tunnel positioning, and update the base data to obtain the updated base data; The point cloud is segmented according to the tunnel design station information and the preset segment spacing to obtain multiple point cloud segments; Based on preset rules, any one of the multiple point cloud segments is mapped into a corresponding two-dimensional feature image; and this two-dimensional feature image is used as the base feature image.

[0027] In a specific application scenario, the above-mentioned preset rules can be described as follows: The tunnel point cloud is segmented from the bottom centerline and unfolded along the tunnel cross-section. The unfolding method adopts existing methods, and the least squares method is used to fit the most approximate plane of the unfolded point cloud. The distance value d from all points to the fitting plane is calculated, and color value mapping is performed with the range of d values, such as 0-0.1 blue, 0.1~0.2 green, 0.2~0.3 yellow, etc. A feature image is formed based on the fitting plane and color values.

[0028] Alternatively, the radius of curvature value r of all points can be calculated, and color value mapping can be performed within the range of r values ​​to form a feature image based on the fitting plane and color values.

[0029] The above preset rules are just examples. Different preset rules can be configured for different application scenarios. Here, no specific limitations are made on the preset rules.

[0030] The tunnel positioning method provided in the application embodiment maps any one of the multiple point cloud segments into a corresponding two-dimensional feature image to achieve structured data management.

[0031] In a specific application scenario, the preset segment interval is set to 10 meters. This is just an example. The preset segment interval can be adjusted according to the needs of different application scenarios, which will not be elaborated here.

[0032] In practical applications, the tunnel point cloud is segmented according to the station number to form multiple point cloud segments. The preset segment interval can be 0.2 to 4 times the tunnel diameter.

[0033] Based on preset rules, each point cloud segment is mapped into a two-dimensional feature image, or unfolded and mapped into a two-dimensional image. The image can be mapped according to the flatness value or curvature information of the points.

[0034] In a specific application scenario, the above-mentioned preset rules can be described as follows: The tunnel point cloud is segmented from the bottom centerline and unfolded along the tunnel cross-section. The unfolding method adopts existing methods, and the least squares method is used to fit the most approximate plane of the unfolded point cloud. The distance value d from all points to the fitting plane is calculated, and color value mapping is performed with the range of d values, such as 0-0.1 blue, 0.1~0.2 green, 0.2~0.3 yellow, etc. A feature image is formed based on the fitting plane and color values.

[0035] Alternatively, the radius of curvature value r of all points can be calculated, and color value mapping can be performed within the range of r values ​​to form a feature image based on the fitting plane and color values.

[0036] The above preset rules are just examples. Different preset rules can be configured for different application scenarios. Here, no specific limitations are made on the preset rules.

[0037] In one example, constructing baseline data for tunnel positioning and updating the baseline data to obtain updated baseline data includes the following steps: Point cloud data of the tunnel was obtained by multi-station scanning along the tunnel axis using a 3D laser scanner. Point cloud data is converted to the engineering coordinate system by target points or control points to obtain the corresponding engineering data in the engineering coordinate system, and the engineering data is used as the base data for tunnel positioning. When tunnel construction extension is detected, the base data is updated to obtain updated base data.

[0038] In the tunnel positioning method provided in this application embodiment, a complete point cloud model of the tunnel can be established as the positioning base to ensure the accuracy of the positioning reference.

[0039] In one example, after mapping any one of the multiple point cloud segments into a corresponding two-dimensional feature image based on preset rules, the tunnel localization method provided in this application embodiment further includes the following steps: Based on tunnel design station information, multiple point cloud segments, and two-dimensional feature images, a correspondence between station numbers, point cloud segments, and feature images is established.

[0040] In a specific application scenario, the above-mentioned preset rules can be described as follows: The tunnel point cloud is segmented from the bottom centerline and unfolded along the tunnel cross-section. The unfolding method adopts existing methods, and the least squares method is used to fit the most approximate plane of the unfolded point cloud. The distance value d from all points to the fitting plane is calculated, and color value mapping is performed with the range of d values, such as 0-0.1 blue, 0.1~0.2 green, 0.2~0.3 yellow, etc. A feature image is formed based on the fitting plane and color values.

[0041] Alternatively, the radius of curvature value r of all points can be calculated, and color value mapping can be performed within the range of r values ​​to form a feature image based on the fitting plane and color values.

[0042] The above preset rules are just examples. Different preset rules can be configured for different application scenarios. Here, no specific limitations are made on the preset rules.

[0043] In one example, before acquiring the real-time feature image, the tunnel localization method provided in this application embodiment further includes the following steps: The spatial parameters of the vehicle in the original point cloud scene of the LiDAR are calibrated to obtain multiple coordinates, including: the coordinates of the vehicle center point, the coordinates of the positive direction of the vertical axis, and the coordinates of any point in the horizontal axis. When the construction equipment is determined to be located, the vehicle-mounted lidar is activated to acquire point clouds of multiple surrounding tunnels around the point to be located. Based on preset rules, any one of the surrounding tunnel point clouds is mapped into a corresponding two-dimensional feature image; and this two-dimensional feature image is used as a real-time feature image.

[0044] In a specific application scenario, the above-mentioned preset rules can be described as follows: The tunnel point cloud is segmented from the bottom centerline and unfolded along the tunnel cross-section. The unfolding method adopts existing methods, and the least squares method is used to fit the most approximate plane of the unfolded point cloud. The distance value d from all points to the fitting plane is calculated, and color value mapping is performed with the range of d values, such as 0-0.1 blue, 0.1~0.2 green, 0.2~0.3 yellow, etc. A feature image is formed based on the fitting plane and color values.

[0045] Alternatively, the radius of curvature value r of all points can be calculated, and color value mapping can be performed within the range of r values ​​to form a feature image based on the fitting plane and color values.

[0046] The above preset rules are just examples. Different preset rules can be configured for different application scenarios. Here, no specific limitations are made on the preset rules.

[0047] Step S102: Match the base feature image and the real-time feature image to obtain the matching result, which includes the best matching segment determined based on the phase velocity between the base feature image and the real-time feature image.

[0048] In practical applications, real-time feature images can be quickly matched with basis feature images using algorithms such as SIFT (Scale Invariant Feature Transform), SURF (Speeded Up Robust Features), and ORB (Oriented FAST and Rotated BRIEF).

[0049] In the tunnel positioning method provided in this application embodiment, rapid coarse positioning is achieved through feature image matching, which greatly reduces the registration search range.

[0050] Step S103: Extract based on the matching results to obtain the corresponding base point cloud segments.

[0051] Step S104: For the segmentation of the base point cloud, the point cloud is registered using a preset ICP algorithm to obtain the transformation matrix. The preset ICP algorithms include: point-to-point ICP algorithm, point-to-surface ICP algorithm, and generalized ICP algorithm.

[0052] In the tunnel positioning method provided in this application embodiment, the improved ICP algorithm achieves sub-centimeter level registration accuracy, ensuring the reliability of the positioning results.

[0053] Step S105: Obtain multiple coordinates. The multiple coordinates are obtained by calibrating the spatial parameters of the vehicle in the original point cloud scene of the LiDAR. The multiple coordinates include: the coordinates of the vehicle center point, the coordinates of the positive direction of the vertical axis, and the coordinates of any point in the horizontal axis direction.

[0054] Step S106: Based on the transformation matrix, calculate multiple coordinates to obtain multiple registered coordinates. The multiple registered coordinates include: the coordinates of the registered vehicle center point, the coordinates of the registered positive vertical axis, and the coordinates of any point in the registered horizontal axis.

[0055] Step S107: Determine the current position of the vehicle based on the coordinates of the registered vehicle center point, and perform pose calculation based on the coordinates of the registered vehicle center point, the coordinates of the registered longitudinal axis in the positive direction, and the coordinates of any point in the registered transverse axis to obtain the vehicle's attitude information.

[0056] In the tunnel positioning method provided in this application embodiment, the vehicle-mounted positioning device integrates a lidar, a computing unit, and a communication module for collecting and processing point cloud data and updating base data. Thus, by integrating the lidar and computing unit, real-time and precise positioning of the construction equipment is achieved.

[0057] like Figure 2As shown, another flowchart of a tunnel positioning method according to an embodiment of this application is illustrated; as Figure 3 As shown, another flowchart of a tunnel positioning method according to an embodiment of this application is illustrated.

[0058] against Figure 2 and Figure 3 The following explanation is provided: The tunnel positioning method in this application embodiment may include the following steps: Step 1: Complete point cloud acquisition and update.

[0059] A high-precision 3D laser scanner was used to perform multi-station scanning along the tunnel axis; Unify the cloud data of each site into the engineering coordinate system by using target points or control points; Generate complete point cloud model data of the tunnel; When tunnel construction extends, the base data should be updated in a timely manner to ensure the integrity and timeliness of the positioning benchmark.

[0060] Step 2: Segment cutting based on station number.

[0061] Based on the tunnel design station information, the point cloud is segmented at fixed intervals (e.g., 10 meters). Each segment contains complete tunnel cross-sectional information; Establish the correspondence between station numbers and point cloud segments, that is, the tunnel station number interval represented by each point cloud segment.

[0062] Step 3: Feature image mapping.

[0063] For each point cloud segment, a cylindrical projection method is used to map it onto a two-dimensional plane.

[0064] Based on the curvature information of all points, a grayscale image is generated according to features such as curvature distribution, and the standard size of the generated feature image is 512×512 pixels.

[0065] Step 4: Onboard data acquisition and calibration.

[0066] The relative position of the vehicle and the lidar is calibrated, a precise coordinate transformation relationship is established, and the coordinates of the vehicle's center point O, the positive longitudinal axis direction P, and a point Q in the transverse axis direction are obtained.

[0067] When the construction equipment is started and positioned, the vehicle-mounted lidar scans the surrounding environment.

[0068] Collect point cloud data of the tunnels surrounding the current vehicle location.

[0069] Data preprocessing includes denoising, filtering, and downsampling.

[0070] Step 5: Feature image generation.

[0071] Feature images are generated according to the same rules as the base data to ensure that the image features are comparable to the base images.

[0072] Feature images of the same size and format are generated by segmenting according to the same segmentation rules.

[0073] Step 6: Quick image matching.

[0074] An improved template matching algorithm is used for feature image matching.

[0075] Calculate similarity scores to determine the best-matching segment.

[0076] This achieves coarse localization, narrowing the search range for subsequent registration.

[0077] It should be noted that the above calculation of similarity scores uses a conventional method, which will not be elaborated upon here.

[0078] Step 6: Point cloud fine registration.

[0079] Based on the image matching results, the corresponding base point cloud segments are extracted.

[0080] An improved ICP algorithm was used for precise point cloud registration.

[0081] Optional algorithms include: point-to-point ICP, point-to-area ICP, generalized ICP, etc.

[0082] By combining feature constraints and normal vector information, the registration accuracy can be improved.

[0083] A multi-scale strategy and adaptive thresholding are employed to optimize convergence performance.

[0084] Introducing normal vector constraints and distance thresholds improves registration accuracy.

[0085] Step 7: Pose information calculation.

[0086] The vehicle's position in the global coordinate system is calculated using the registration transformation matrix.

[0087] Calculate the vehicle's attitude information (pitch angle, roll angle, yaw angle).

[0088] Outputs positioning accuracy results at the sub-centimeter level.

[0089] The tunnel positioning method provided in this application embodiment can improve the positioning accuracy of tunnels. Furthermore, the tunnel positioning method provided in this application embodiment achieves rapid coarse positioning through image matching and high-precision positioning by combining point cloud fine registration. It has advantages such as high positioning accuracy, strong real-time performance, and wide applicability, and can be widely used in the precise navigation and positioning of tunnel engineering construction equipment. In addition, the tunnel positioning method provided in this application embodiment can perform high-precision positioning: through multimodal data fusion and fine registration algorithms, it achieves sub-centimeter-level positioning accuracy. Moreover, the tunnel positioning method provided in this application embodiment has high registration efficiency: feature image mapping and matching algorithms significantly improve registration efficiency, meeting the real-time positioning needs of construction. Further, the tunnel positioning method provided in this application embodiment has strong adaptability: it is suitable for positioning needs of different geological conditions and tunnel structures. In addition, the tunnel positioning method provided in this application embodiment has high system integration: the hardware device integrates multiple sensors, and the software system achieves fully automated processing. Furthermore, the tunnel positioning method provided in this application embodiment is cost-effective: compared with traditional measurement methods, it significantly improves work efficiency and reduces labor costs.

[0090] In the above embodiments, a tunnel positioning method is provided. Correspondingly, this application also provides a tunnel positioning device. The tunnel positioning device provided in this application can implement the above-described tunnel positioning method. The tunnel positioning device can be implemented by software, hardware, or a combination of both. For example, the tunnel positioning device may include integrated or separate functional modules or units to perform the corresponding steps in the above methods.

[0091] Please refer to Figure 4 This illustration shows a schematic diagram of a tunnel positioning device provided by some embodiments of this application. Since the device embodiments are basically similar to the method embodiments, the description is relatively simple; relevant details can be found in the description of the method embodiments. The device embodiments described below are merely illustrative.

[0092] like Figure 4 As shown, the tunnel positioning device 400 may include: The first acquisition module 401 is used to acquire a base feature image mapped from the base data, and to acquire a real-time feature image; Matching module 402 is used to match the base feature image and the real-time feature image to obtain a matching result. The matching result includes: the segmentation of the best match determined based on the phase velocity between the base feature image and the real-time feature image. Extraction module 403 is used to extract based on the matching results to obtain the corresponding base point cloud segments; The registration module 404 is used to perform point cloud registration for the base point cloud segmentation using a preset ICP algorithm to obtain a transformation matrix. The preset ICP algorithms include: point-to-point ICP algorithm, point-to-surface ICP algorithm, and generalized ICP algorithm. The second acquisition module 405 is used to acquire multiple coordinates. The multiple coordinates are the coordinates obtained by calibrating the spatial parameters of the vehicle in the original point cloud scene of the LiDAR. The multiple coordinates include: the coordinates of the vehicle center point, the coordinates in the positive direction of the vertical axis, and the coordinates of any point in the horizontal axis direction. The calculation module 406 is used to calculate multiple coordinates based on the transformation matrix to obtain multiple registered coordinates. The multiple registered coordinates include: the coordinates of the registered vehicle center point, the coordinates of the registered positive vertical axis, and the coordinates of any point in the registered horizontal axis. The determination module 407 is used to determine the current position of the vehicle based on the coordinates of the registered vehicle center point; The pose calculation module 408 is used to calculate the pose based on the coordinates of the registered vehicle center point, the coordinates of the registered longitudinal axis in the positive direction, and the coordinates of any point in the registered transverse axis, so as to obtain the vehicle's attitude information.

[0093] In some embodiments of this application, the tunnel positioning device 400 may further include: Data construction and data update modules (in Figure 4 (not shown in the image), used for: Before acquiring the base feature image mapped from the base data, base data for tunnel localization is constructed, and the base data is updated to obtain the updated base data. The basis feature image determination module is used for: The point cloud is segmented according to the tunnel design station information and the preset segment spacing to obtain multiple point cloud segments; Based on preset rules, any one of the multiple point cloud segments is mapped into a corresponding two-dimensional feature image; and this two-dimensional feature image is used as the base feature image.

[0094] In some embodiments of this application, Data construction and data update modules (in Figure 4 (not shown in the image), specifically used for: Point cloud data of the tunnel was obtained by multi-station scanning along the tunnel axis using a 3D laser scanner. Point cloud data is converted to the engineering coordinate system by target points or control points to obtain the corresponding engineering data in the engineering coordinate system, and the engineering data is used as the base data for tunnel positioning. When tunnel construction extension is detected, the base data is updated to obtain updated base data.

[0095] In some embodiments of this application, the tunnel positioning device 400 may further include: Create a module (in) Figure 4 (Not shown in the image) is used to: after mapping any one of the multiple point cloud segments into a corresponding two-dimensional feature image based on preset rules, establish the correspondence between the station number, point cloud segment, and feature image based on the tunnel design station number information, multiple point cloud segments, and two-dimensional feature image.

[0096] In some embodiments of this application, the tunnel positioning device 400 may further include: Calibration module (in) Figure 4 (Not shown in the image) is used to: calibrate the spatial parameters of the vehicle in the original point cloud scene of the LiDAR before acquiring the real-time feature image, and obtain multiple coordinates, including: the coordinates of the vehicle center point, the coordinates of the positive direction of the vertical axis, and the coordinates of any point in the horizontal axis. The third acquisition module (in) Figure 4 (not shown in the image) is used to: when it is determined that construction equipment needs to be positioned, activate the vehicle-mounted lidar to acquire multiple surrounding tunnel point clouds around the point to be positioned; Real-time feature image determination module (in) Figure 4 (Not shown in the image), used for: mapping any one of the surrounding tunnel point clouds into a corresponding two-dimensional feature image based on preset rules; and using the two-dimensional feature image as a real-time feature image.

[0097] According to another embodiment, a computer-readable storage medium is also provided, on which a computer program is stored, which, when executed in a computer, causes the computer to perform the above-described tunnel positioning method.

[0098] According to another embodiment, an electronic device is also provided, including a memory and a processor, wherein the memory stores executable code, and the processor executes the executable code to implement the above-described tunnel positioning method.

[0099] Those skilled in the art will recognize that, in one or more of the examples above, the functions described in this application can be implemented using hardware, software, firmware, or any combination thereof. When implemented in software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or code on a computer-readable medium.

[0100] Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A tunnel positioning method, characterized in that, The method includes: Obtain the basis feature image mapped from the basis data, and obtain the real-time feature image; The base feature image and the real-time feature image are matched to obtain a matching result, which includes: the optimal matching segment determined based on the phase velocity between the base feature image and the real-time feature image; Based on the matching results, the corresponding base point cloud segments are extracted; For the segmented base point cloud, a preset ICP algorithm is used for point cloud registration to obtain a transformation matrix. The preset ICP algorithm includes: point-to-point ICP algorithm, point-to-surface ICP algorithm, and generalized ICP algorithm. Multiple coordinates are obtained, which are coordinates obtained by calibrating the spatial parameters of the vehicle in the original point cloud scene of the LiDAR. The multiple coordinates include: the coordinates of the vehicle center point, the coordinates of the positive direction of the vertical axis, and the coordinates of any point in the horizontal axis direction. Based on the transformation matrix, the multiple coordinates are calculated to obtain multiple registered coordinates, which include: the coordinates of the registered vehicle center point, the coordinates of the registered positive vertical axis, and the coordinates of any point in the registered horizontal axis. The vehicle's current position is determined based on the coordinates of the registered vehicle center point, and the vehicle's attitude information is obtained by performing pose calculation based on the coordinates of the registered vehicle center point, the coordinates of the registered positive longitudinal axis, and the coordinates of any point in the registered transverse axis.

2. The tunnel positioning method according to claim 1, characterized in that, Before obtaining the basis feature image mapped from the basis data, the method further includes: Construct base data for tunnel positioning, and update the base data to obtain updated base data; The point cloud is segmented according to the tunnel design station information and the preset segment spacing to obtain multiple point cloud segments; Based on preset rules, any one of the multiple point cloud segments is mapped into a corresponding two-dimensional feature image; and the two-dimensional feature image is used as the base feature image.

3. The tunnel positioning method according to claim 2, characterized in that, The construction of the base data for tunnel positioning, and the updating of the base data to obtain the updated base data, include: Point cloud data of the tunnel was obtained by multi-station scanning along the tunnel axis using a 3D laser scanner. The point cloud data is converted to the engineering coordinate system by using target points or control points to obtain the corresponding engineering data in the engineering coordinate system, and the engineering data is used as the base data for tunnel positioning. When tunnel construction extension is detected, the base data is updated to obtain updated base data.

4. The tunnel positioning method according to claim 2, characterized in that, After mapping any one of the multiple point cloud segments into a corresponding two-dimensional feature image based on preset rules, the method further includes: Based on the tunnel design station information, the multiple point cloud segments, and the two-dimensional feature image, a correspondence between the station, point cloud segments, and feature image is established.

5. The tunnel positioning method according to claim 1, characterized in that, Prior to acquiring the real-time feature image, the method further includes: The spatial parameters of the vehicle in the original point cloud scene of the lidar are calibrated to obtain multiple coordinates, including: the coordinates of the vehicle center point, the coordinates of the positive direction of the vertical axis, and the coordinates of any point in the horizontal axis direction. When the construction equipment is determined to be located, the vehicle-mounted lidar is activated to acquire point clouds of multiple surrounding tunnels around the point to be located. Based on preset rules, any one of the surrounding tunnel point clouds is mapped into a corresponding two-dimensional feature image; and this two-dimensional feature image is used as the real-time feature image.

6. A tunnel positioning device, characterized in that, The device includes: The first acquisition module is used to acquire the basis feature image mapped from the basis data, and to acquire the real-time feature image; A matching module is used to match the base feature image and the real-time feature image to obtain a matching result, the matching result including: the best matching segment determined based on the phase velocity between the base feature image and the real-time feature image; The extraction module is used to extract based on the matching results to obtain the corresponding base point cloud segments; The registration module is used to perform point cloud registration for the base point cloud segments using a preset ICP algorithm to obtain a transformation matrix. The preset ICP algorithm includes: point-to-point ICP algorithm, point-to-surface ICP algorithm, and generalized ICP algorithm. The second acquisition module is used to acquire multiple coordinates, which are coordinates obtained by calibrating the spatial parameters of the vehicle in the original point cloud scene of the LiDAR. The multiple coordinates include: the coordinates of the vehicle center point, the coordinates in the positive direction of the vertical axis, and the coordinates of any point in the horizontal axis direction. The calculation module is used to calculate the multiple coordinates based on the transformation matrix to obtain the multiple registered coordinates, which include: the coordinates of the registered vehicle center point, the coordinates of the registered positive vertical axis, and the coordinates of any point in the registered horizontal axis. The determination module is used to determine the current position of the vehicle based on the coordinates of the registered vehicle center point; The pose calculation module is used to calculate the pose based on the coordinates of the registered vehicle center point, the coordinates of the registered longitudinal axis in the positive direction, and the coordinates of any point in the registered transverse axis, so as to obtain the vehicle's attitude information.

7. The tunnel positioning device according to claim 6, characterized in that, The device further includes: The data construction and data update module is used for: Before acquiring the base feature image mapped from the base data, base data for tunnel localization is constructed, and the base data is updated to obtain the updated base data. The basis feature image determination module is used for: The point cloud is segmented according to the tunnel design station information and the preset segment spacing to obtain multiple point cloud segments; Based on preset rules, any one of the multiple point cloud segments is mapped into a corresponding two-dimensional feature image; and the two-dimensional feature image is used as the base feature image.

8. The tunnel positioning device according to claim 7, characterized in that, The data construction and data update module is specifically used for: Point cloud data of the tunnel was obtained by multi-station scanning along the tunnel axis using a 3D laser scanner. The point cloud data is converted to the engineering coordinate system by using target points or control points to obtain the corresponding engineering data in the engineering coordinate system, and the engineering data is used as the base data for tunnel positioning. When tunnel construction extension is detected, the base data is updated to obtain updated base data.

9. A computer-readable storage medium, characterized in that, It contains a computer program that, when executed in a computer, causes the computer to perform the method described in any one of claims 1 to 5.

10. An electronic device, characterized in that, The method includes a memory and a processor, wherein the memory stores executable code, and the processor executes the executable code to implement the method according to any one of claims 1 to 5.

Images