Shield tail gap image correction method, system and device based on segment wedge amount

Abstract

A shield tail gap image correction method, system and device based on segment wedge amount, comprising: acquiring the physical distance of two lasers; acquiring an original shield tail gap image; extracting the laser center coordinates of the two lasers and the straight line equation of the lower edge of the segment side end face from the original shield tail gap image; calculating the segment wedge amount of the shield machine; calculating the angle between the camera plane and the shooting plane through the wedge amount; according to the angle between the camera plane and the shooting plane, the physical distance of the two lasers, the laser center coordinates of the two lasers and the straight line equation of the lower edge of the segment side end face extracted from the original shield tail gap image, performing coordinate correction on the four points of the laser center coordinates of the two lasers and the lower edge of the segment side end face; substituting the coordinates of the four points before and after correction into the image transformation matrix to calculate the correction parameters; and restoring the original shield tail gap image by using the image transformation matrix with the solved correction parameters. The present application restores the distorted image, and improves the accuracy of the shield tail gap monitoring result.

Description

Technical Field

[0001] This invention belongs to the field of shield tunneling technology, and relates to shield tunneling monitoring instruments and meters, and in particular to a method, system and device for correcting shield tail gap images based on segment wedge measurement. Background Technology

[0002] With the need for large-scale construction of urban subway tunnels and other underground projects, tunnel boring machine (TBM) technology and equipment have rapidly developed and been applied worldwide. The tail clearance is a key technical parameter that requires precise measurement and real-time monitoring during TBM tunneling, playing a crucial role in controlling the TBM's attitude and ensuring efficient and safe TBM construction. Specifically, the tail clearance refers to the distance between the outer diameter of the tunnel segment and the inner diameter of the TBM shell. When the tail clearance varies beyond the set range, excessive compression will occur between the tail and the tunnel segment, accelerating the wear of the tail seal brush, slowing down the tunneling speed, and even causing segment misalignment or damage, leading to serious consequences such as tunnel leakage and surface subsidence. Therefore, it is necessary to measure the tail clearance in real-time, continuously, and periodically to ensure the efficiency and safety of TBM construction.

[0003] Manually measuring the shield tail gap is not only labor-intensive but also inaccurate. Some scholars have proposed machine vision-based methods for measuring the shield tail gap. These methods monitor the shield tail gap value by converting pixel distance into physical distance; therefore, they all rely on an important prerequisite: the camera imaging plane must remain parallel to the side end face of the tunnel segment at all times. (See [link to relevant documentation]). Figure 1 .

[0004] During the tunnel excavation process of a tunnel boring machine (TBM), specific reinforced concrete segments are selected as the lining. During this process, due to the need for curved sections and serpentine corrections, wedge-shaped turning rings are required for tunnel steering. Because of the wedge shape, the length of the turning rings varies, inevitably causing an angle between the camera's imaging plane and the side face of the segment, resulting in distortion in the images acquired by the monitoring equipment. Current machine vision-based methods for monitoring the shield tail gap neglect this image distortion, thus introducing systematic errors in the monitoring of the shield tail gap during the turning rings. Summary of the Invention

[0005] To address the issue that existing machine vision-based shield tail gap measurement methods do not consider the influence of segment wedge shape on monitoring images, this invention proposes a shield tail gap image correction method, system, and device based on segment wedge shape. By restoring the distorted image during turning ring monitoring, the accuracy of machine vision-based shield tail gap monitoring results is improved, eliminating the systematic errors present in existing methods.

[0006] Firstly, a method for correcting shield tail gap images based on segment wedge shape is provided. The shield tail gap is measured by a shield tail gap monitoring device, which includes two lasers providing distance calibration for shield tail gap measurement, and a camera capturing images of the shield tail gap under the calibration of the two lasers. The method includes: acquiring the physical distance between the two lasers; acquiring an original shield tail gap image; extracting the laser center coordinates of the two lasers and the linear equation of the lower edge of the segment side face from the original shield tail gap image; calculating the wedge shape of the shield machine segment; calculating the angle between the camera plane and the shooting plane and the actual distance between the two lasers captured using the wedge shape; correcting the coordinates of four points (the laser center coordinates of the two lasers and the two ends of the lower edge of the segment side face) based on the angle between the camera plane and the shooting plane, the physical distance between the two lasers, the laser center coordinates of the two lasers extracted from the original shield tail gap image, and the linear equation of the lower edge of the segment side face; substituting the coordinates of the four points before and after correction into an image transformation matrix to calculate the correction parameters; and restoring the original shield tail gap image using the image transformation matrix with the corrected correction parameters.

[0007] Secondly, a shield tail gap image correction system based on segment wedge shape is provided. The shield tail gap is measured by a shield tail gap monitoring device, which includes dual lasers for distance calibration of the shield tail gap measurement, and a camera for capturing images of the shield tail gap under dual laser calibration. The system includes: a first acquisition module configured to acquire the physical distance between the two lasers; a second acquisition module configured to acquire the original shield tail gap image; a feature extraction module configured to extract the laser center coordinates of the two lasers and the equation of the straight line of the lower edge of the side end face of the segment from the original shield tail gap image; and a first calculation module configured to calculate the shield machine segment wedge shape. The system comprises the following modules: a second calculation module, configured to calculate the angle between the camera plane and the shooting plane using a wedge measurement; a perspective transformation module, configured to correct the coordinates of four points (the laser center coordinates of the two lasers and the lower edge of the tube side face) based on the angle between the camera plane and the shooting plane, the physical distance between the two lasers, the original shield tail gap image, the laser center coordinates of the two lasers, and the equation of the straight line of the lower edge of the tube side face obtained from the original shield tail gap image; a correction parameter calculation module, configured to substitute the coordinates of the four points before and after correction into the image transformation matrix to calculate the correction parameters; and an image restoration module, configured to restore the original shield tail gap image using the image transformation matrix obtained from the correction parameters.

[0008] Thirdly, a shield tail gap image correction device based on segment wedge amount is provided, comprising: a processor; a memory including one or more program modules; wherein the one or more program modules are stored in the memory and configured to be executed by the processor, and the one or more program modules include instructions for implementing the shield tail gap image correction method based on segment wedge amount.

[0009] Fourthly, a storage medium is provided for storing non-transitory instructions that, when executed by a processor, enable the shield tail gap image correction method based on segment wedge amount. Attached Figure Description

[0010] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings of the embodiments will be briefly described below.

[0011] Figure 1 This is a schematic diagram of shield tail gap measurement based on machine vision, provided as an embodiment of the present invention.

[0012] Figure 2 This is a schematic diagram of laser irradiation on the side end face of a tube segment provided by two cross lasers according to an embodiment of the present invention.

[0013] Figure 3 This is a flowchart of a shield tail gap image correction method based on segment wedge measurement, provided in an embodiment of the present invention.

[0014] Figure 4 This is a schematic diagram for calculating the wedge shape of tunnel boring machine segments according to an embodiment of the present invention. Detailed Implementation

[0015] like Figure 1 The shield tail gap image correction based on the segment wedge measurement of this invention is achieved through a shield tail gap monitoring device, which includes two crosshair calibration lasers (hereinafter also referred to as "two lasers") and a zoom industrial camera. The two lasers provide distance calibration for the shield tail gap, and the center of the laser crosshairs of the two lasers also serves as the image correction point for the shield tail gap. The horizontal laser line of the laser is always parallel to the lower edge of the segment, and the vertical laser line of the laser is always perpendicular to the lower edge of the segment. Figure 2 This diagram illustrates the illumination of the side end face of a tube segment by two cross-shaped lasers. The two lasers are fixed, meaning their physical distance remains constant. A zoom industrial camera is used to capture images of the shield tail gap calibrated by the two cross-shaped lasers. The zoom industrial camera ensures that the region of interest remains consistently sized across different shooting distances.

[0016] After obtaining the original shield tail gap image, this invention uses image processing to obtain the coordinates of the laser centers of the two lasers and the equation of the straight line of the lower edge of the tube side face from the original shield tail gap image, and calculates the angle between the camera plane and the shooting plane based on the shield tail gap value at the shooting point. Using the left endpoint of the lower edge of the tube side face as a reference point and keeping its position unchanged, the coordinates of the laser centers of the two lasers and the two endpoints of the lower edge of the tube side face are corrected (perspective transformation) based on the angle between the camera plane and the shooting plane, the physical distance between the two lasers, and the equation of the straight line of the lower edge of the tube side face obtained from the original shield tail gap image. The coordinates of the laser centers of the two lasers and the two endpoints of the lower edge of the tube are then compared before and after correction to obtain the image transformation matrix. The image transformation matrix is ​​then used to correct the original shield tail gap image.

[0017] Figure 3 A method for correcting shield tail gap images based on segment wedge shape is presented. The following section discusses... Figure 3 The method shown will be explained in detail.

[0018] Step 1: Initialize the laser and zoom industrial camera, and obtain the physical distance between the two lasers.

[0019] Step 2: Obtain the original shield tail gap image.

[0020] Step 3: Extract the laser center coordinates of the two lasers and the equation of the straight line at the lower edge of the side end face of the tube segment from the original shield tail gap image.

[0021] Step 4: Calculate the wedge shape of the tunnel segment based on the tunnel turning radius and other known conditions.

[0022] refer to Figure 4 Select a section of curved tunnel ABFE, with tunnel segment length L, wedge amount 2S, turning radius length R, angle of the curved tunnel X, and ring radius r.

[0023] Based on the definition of wedge quantity and the arc length formula, we can obtain:

[0024]

[0025] in The arc length of the centerline of the curved tunnel. For measuring the arc length inside a curved tunnel, The arc length is measured on the outside of the curved tunnel.

[0026] The relationship between the tunnel turning radius and the wedge shape is as follows:

[0027]

[0028] Step 5: Calculate the angle between the camera plane and the shooting plane, and the actual distance between the two lasers in the shot, using wedge measurements.

[0029] Step 5.1: Calculate the angle between the camera plane and the shooting plane based on the relative planar positions of the camera and the side end face of the tube segment, as shown in the following formula:

[0030]

[0031] Where β is the angle between the camera plane and the shooting plane; S is half of the wedge amount; r is the pipe ring radius; R is the tunnel turning radius; and L is the segment length.

[0032] Step 5.2: Since there is an angle between the camera plane and the shooting plane, the calibration information in the image cannot reflect the actual calibration situation. The present invention uses a wedge measurement to calculate the actual distance between the two lasers in the image, as shown in the following formula:

[0033]

[0034] Where q is the actual distance between the two lasers captured; w is the physical distance between the two lasers at the shield tail gap monitoring device end; S is half of the wedge amount; r is the tube ring radius; R is the tunnel turning radius; and L is the tube segment length.

[0035] The actual distance between the two lasers in the photograph is only needed when calculating the shield tail gap later. This invention does not involve the calculation of the shield tail gap.

[0036] Step 6: Based on the angle between the camera plane and the shooting plane, the physical distance between the two lasers, and the coordinates of the laser centers of the two lasers extracted from the original shield tail gap image, as well as the equation of the straight line of the lower edge of the tube segment side end face, coordinate correction (perspective transformation) is performed on four points: the coordinates of the laser centers of the two lasers and the two ends of the lower edge of the tube segment. The perspective transformation matrix is ​​shown in the following formula:

[0037]

[0038] Where (u,v) are the pixel coordinates in the perspective image captured by the camera; (x,y) are the pixel coordinates in the corrected image, and x = x' / w, y = y' / w'; T is the transformation matrix, a 11 a 12 ... a 33 These are the elements in the transformation matrix.

[0039] Step 7: Compare the coordinates of the four points before and after correction, and calculate the image transformation matrix. The image transformation matrix is ​​calculated as follows:

[0040]

[0041] Where (u,v) are the pixel coordinates in the perspective image captured by the camera; (x,y) are the pixel coordinates in the corrected image; and a, b, ..., m, l are the parameters of the perspective transformation matrix. The correction parameters are obtained by substituting the four sets of corresponding coordinates before and after correction into the above formula. Then, the original shield tail gap image is restored using the solved correction parameters. During the correction process, since the pixels in the restored image obtained from the perspective image are not continuous, bilinear interpolation is used to interpolate the missing pixels.

[0042] Step 8: Output the corrected shield tail gap image. The corrected image output by this invention is also used for accurate calculation of the shield tail gap; in other words, this invention provides the prerequisites for accurate calculation of the shield tail gap.

[0043] Save the shield tail gap image, perform digital image processing, calculate the shield tail gap value and output it, and the shield tail gap monitoring ends.

[0044] In some embodiments, a shield tail gap image correction system based on segment wedge amount is also provided, including: a first acquisition module, a second acquisition module, a feature extraction module, a first calculation module, a second calculation module, a perspective transformation module, a correction parameter calculation module, and an image restoration module.

[0045] The first acquisition module is configured to acquire the physical distance between the two lasers.

[0046] The second acquisition module is configured to acquire the original shield tail gap image.

[0047] The feature extraction module is configured to extract the laser center coordinates of the two lasers and the equation of the straight line at the lower edge of the side end face of the tube segment from the original shield tail gap image.

[0048] The first calculation module is configured to calculate the wedge shape of the tunnel boring machine segments.

[0049] The second calculation module is configured to calculate the angle between the camera plane and the shooting plane, as well as the actual distance between the two lasers being shot, using wedge measurements.

[0050] The perspective transformation module is configured to obtain the laser center coordinates of the two lasers and the straight line equation of the lower edge of the tube side end face from the angle between the camera plane and the shooting plane, the physical distance between the two lasers, and the original shield tail gap image, and then perform coordinate correction on four points: the laser center coordinates of the two lasers and the two ends of the lower edge of the tube side end face.

[0051] The correction parameter calculation module is configured to substitute the coordinates of four points before and after correction into the image transformation matrix to calculate the correction parameters;

[0052] The image restoration module is configured to restore the shield tail gap image using the image transformation matrix from which the correction parameters are solved.

[0053] For a more detailed implementation of each module of the shield tail gap image correction system based on segment wedge amount, please refer to the above-mentioned shield tail gap image correction method based on segment wedge amount.

[0054] In some embodiments, a shield tail gap image correction device based on segment wedge amount is also provided. The device includes a processor and a memory. The memory stores non-transitory instructions (e.g., one or more program modules). The processor executes the non-transitory instructions, which, when executed by the processor, can perform one or more steps in the shield tail gap image correction method based on segment wedge amount described above. The memory and processor can be interconnected via a bus system and / or other forms of connection mechanisms.

[0055] For example, a processor can be a central processing unit (CPU), a graphics processing unit (GPU), or other form of processing unit with data processing and / or program execution capabilities. For instance, a CPU can be based on x86 or ARM architectures. A processor can be a general-purpose processor or a special-purpose processor, capable of controlling other components in an electronic device to perform desired functions.

[0056] For example, the memory can be volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, erasable programmable read-only memory (EPROM), compact optical disc read-only memory (CD-ROM), USB memory, flash memory, etc. One or more program modules can be stored on the memory, and the processor can run one or more program modules to implement various functions of the electronic device.

[0057] In some embodiments, a storage medium is also provided for storing non-transitory instructions that, when executed by a computer, can implement one or more steps in the above-described shield tail gap image correction method based on segment wedge amount. That is, when the shield tail gap image correction method based on segment wedge amount provided in this application embodiment is implemented in software and sold or used as an independent product, it can be stored in a storage medium. For relevant descriptions of the storage medium, please refer to the corresponding description of the memory of the electronic device above; it will not be repeated here.

[0058] Based on information from a typical tunnel boring machine (TBM) site: the TBM ring radius is 3.2m, the segment length is 1.5m, and the distance between the two lasers in the image acquisition equipment is 120mm. Taking a TBM tail gap monitoring system based on machine vision and dual-laser calibration as an example, the system uses a zoom industrial camera to acquire images of the segment sidewalls and calibrates the TBM tail gap using lasers. In the monitoring of the TBM tail gap at the turning ring, the shooting angle causes image distortion, resulting in changes to the calibration information. To address the distorted images in the TBM tail gap monitoring process at the turning ring using the machine vision-based TBM tail gap monitoring system, the TBM segment wedge shape information is used to correct the TBM tail gap images.

[0059] The preset marking spacing, actual shooting spacing, and shooting plane angle results for different turning radii are shown in Table 1 below.

[0060] Table 1 Relationship between wedge amount and shooting angle

[0061]

[0062] As can be seen from the data in the table, taking a conventional shield tunneling site as an example, due to the presence of wedge-shaped data, there is a certain angle between the camera's shooting plane and the camera's imaging unit plane. This is not the case that the dual cross laser calibration laser is perpendicular to the tunnel segment under ideal system conditions. Although the angle is small, it will cause errors in the shield tail gap monitoring results during continuous turning.

[0063] Unlike the original monitoring method, the addition of shield tail gap image correction based on segment wedge measurement transforms the original image from a distorted image into a normal image, avoiding the influence of distorted images on calibration information and calibration coordinate position, and providing an important guarantee for improving the quality and accuracy of shield tail gap images.

Claims

1. A method for correcting a shield tail gap image based on a segment wedge amount, the shield tail gap being measured by a shield tail gap monitoring device, the shield tail gap monitoring device including two lasers that provide distance calibration for shield tail gap measurement, and a camera that photographs a shield tail gap image under calibration of the two lasers, characterized in that, The method includes: Obtain the physical distance between the two lasers; Obtain the original shield tail gap image; Extract the coordinates of the laser centers of the two lasers and the equation of the straight line at the lower edge of the side end face of the tube segment from the original shield tail gap image; The wedge shape of the tunnel lining segments is calculated, where the relationship between the tunnel turning radius and the wedge shape is: The angle between the camera plane and the shooting plane, as well as the actual distance between the two lasers in the shot, are calculated using the wedge measurement. The formula for calculating the angle between the camera plane and the shooting plane is as follows: wherein β is the angle between the camera plane and the shooting plane, S is half of the wedge amount, r is the tube ring radius, R is the tunnel turning radius, L is the segment length; The formula for the distance between two lasers is as follows: wherein q is the actual distance between the two lasers; w is the physical distance between the two lasers at the end of the shield tail gap monitoring device; S is half the wedge amount; r is the pipe ring radius; R is the tunnel turning radius, L is the segment length; Based on the angle between the camera plane and the shooting plane, the physical distance between the two lasers, the laser center coordinates of the two lasers extracted from the original shield tail gap image, and the straight line equation of the lower edge of the tube side end face, coordinate correction is performed on four points: the laser center coordinates of the two lasers and the two ends of the lower edge of the tube side end face. Substitute the coordinates of the four points before and after correction into the image transformation matrix to calculate the correction parameters. The original shield tail gap image is restored using the image transformation matrix from which the correction parameters are solved.

2. The method of claim 1, wherein the method is based on the amount of wedge of the segment. Bilinear interpolation was used to interpolate the missing pixels that appeared during the reconstruction of the shield tail gap image.

3. A shield tail gap image correction system based on segment wedge amount, the shield tail gap is measured by a shield tail gap monitoring device, the shield tail gap monitoring device includes a double laser for distance calibration of shield tail gap measurement, and a camera for shooting shield tail gap image under double laser calibration, characterized in that, The system includes: The first acquisition module is configured to acquire the physical distance between the two lasers; The second acquisition module is configured to acquire the original shield tail gap image; The feature extraction module is configured to extract the laser center coordinates of the two lasers and the equation of the straight line at the lower edge of the side end face of the tube segment from the original shield tail gap image. The first calculation module is configured to calculate the wedge shape of the tunnel boring machine segments, wherein the relationship between the tunnel turning radius and the wedge shape is: The second calculation module is configured to calculate the angle between the camera plane and the shooting plane using a wedge measurement. The perspective transformation module is configured to perform coordinate correction on four points—the laser center coordinates of the two lasers and the two ends of the lower edge of the tube segment's side face—based on the angle between the camera plane and the shooting plane, the physical distance between the two lasers, and the original shield tail gap image. The formula for calculating the angle between the camera plane and the shooting plane is as follows: wherein β is the angle between the camera plane and the shooting plane, S is half of the wedge amount, r is the tube ring radius, R is the tunnel turning radius, L is the segment length; The formula for the distance between two lasers is as follows: wherein q is the actual distance between the two lasers; w is the physical distance between the two lasers at the end of the shield tail gap monitoring device; S is half the wedge amount; r is the tube ring radius; R is the tunnel turning radius, L is the segment length; The correction parameter calculation module is configured to substitute the coordinates of four points before and after correction into the image transformation matrix to calculate the correction parameters; and An image restoration module is configured to restore the shield tail gap image using the image transformation matrix from which the correction parameters are solved.

4. The system for correcting the tail gap image based on the segment wedge amount according to claim 3, wherein Bilinear interpolation was used to interpolate the missing pixels that appeared during the reconstruction of the shield tail gap image.

5. A shield tail gap image correction device based on the amount of wedge of a segment, characterized by, include: processor; Memory, including one or more program modules; The one or more program modules are stored in the memory and configured to be executed by the processor, and the one or more program modules include instructions for implementing the shield tail gap image correction method based on segment wedge amount as described in any one of claims 1-2.

6. A storage medium for storing non-transitory instructions, characterized in that, When the non-temporary instructions are executed by the processor, the shield tail gap image correction method based on segment wedge amount as described in any one of claims 1-2 can be implemented.

Images