Adjustment method of binocular camera for deformation monitoring and method of deformation monitoring during tunnel excavation

Abstract

This invention discloses an adjustment method for a deformation monitoring binocular camera and a method for monitoring roadway deformation during excavation. The adjustment method for the deformation monitoring binocular camera in this invention allows adjustment of the lateral translation and pitch angles of the first and second cameras. The chips of the first and second cameras, or an external industrial control computer, can be used as processors to calculate and determine the lateral and longitudinal positions of feature points in the image in real time. Based on the differences between the lateral and longitudinal positions of the feature points in the image and the target set position, the translation position and pitch angle of the first and second cameras can be adjusted in real time. Therefore, the deformation of the roadway can be calculated more accurately based on the images of the feature points acquired by the binocular cameras. The adjustment method of the deformation monitoring binocular camera in this invention also enhances the applicability of the deformation monitoring binocular camera and broadens its application methods.

Description

Technical Field

[0001] This invention relates to the field of mining technology, and in particular to a method for adjusting a binocular camera for deformation monitoring and a method for monitoring deformation during tunnel excavation. Background Technology

[0002] Due to space constraints at the tunneling face, current mine pressure monitoring sensors are all located behind the tunneling face. Tunnel deformation mainly occurs within the first three hours after the surrounding rock is exposed; therefore, timely acquisition of tunnel deformation data during tunneling is crucial for evaluating the stability of the surrounding rock and optimizing tunnel support schemes. In existing tunneling processes, due to continuous unit movement and ongoing work by on-site personnel laying connecting nets and anchor bolts, traditional tunnel deformation measurement methods such as the cross-point method are difficult to implement. Furthermore, because underground coal mines have limited visual features, the commonly used techniques of laser scanning or lidar to acquire tunnel topography point clouds and calculate surface deformation in real time are difficult to implement. Summary of the Invention

[0003] This invention aims to at least partially solve one of the technical problems in related technologies. To this end, embodiments of this invention propose an adjustment method for a deformation monitoring binocular camera.

[0004] An embodiment of the present invention also proposes a method for monitoring roadway deformation during excavation.

[0005] The present invention discloses an adjustment method for a deformation monitoring binocular camera, wherein the binocular camera includes a first camera and a second camera, and the adjustment method for the binocular camera includes:

[0006] Start the first camera and the second camera;

[0007] The first camera and the second camera acquire images of feature points in the tunnel in real time from different angles, and the acquired images include at least one feature point set on the left side, right side and roof of the tunnel respectively.

[0008] Adjust the positions of the first camera and the second camera in the horizontal direction;

[0009] Calculate the lateral position of the feature point in the image;

[0010] Determine whether the horizontal position of the feature point in the image is within a first preset position range. If the horizontal position of the feature point in the image is not within the first preset position range, continue to adjust the positions of the first camera and the second camera in the horizontal direction until the horizontal position of the feature point in the image is within the first preset position range.

[0011] The lateral position of the feature point in the image is within a first preset position range, and the pitch angle of the first camera and the second camera is adjusted accordingly.

[0012] Calculate the vertical position of the feature point in the image;

[0013] Determine whether the vertical position of the feature point in the image is within a second preset position range. If the vertical position of the feature point in the image is not within the second preset position range, continue to adjust the pitch angle of the first camera and the second camera until the vertical position of the feature point in the image is within the second preset position range.

[0014] The deformation monitoring binocular camera adjustment method of this invention can adjust the lateral translation and pitch angles of the first and second cameras. The chips of the first and second cameras, or an external industrial control computer, can be used as processors to calculate and determine the lateral and longitudinal positions of feature points in the image in real time. Based on the difference between the lateral and longitudinal positions of feature points in the image and the target set position, the translation position and pitch angle of the first and second cameras can be adjusted in real time. Therefore, the deformation of the tunnel can be calculated more accurately based on the image of the feature points acquired by the binocular camera. The deformation monitoring binocular camera adjustment method of this invention can also make the deformation monitoring binocular camera more applicable and its application methods more extensive.

[0015] In some embodiments, the binocular camera includes a mounting bracket on which the first camera and the second camera are pivotally mounted to allow for adjustable pitch angles. The mounting bracket is provided with a linear guide rail extending along the horizontal direction, and one of the first camera and the second camera is mounted on and slidable along the linear guide rail.

[0016] In some embodiments, the linear guide rail includes a first linear guide rail and a second linear guide rail, both of which extend along the horizontal direction. The first camera is pivotally mounted on the first linear guide rail and can slide along it, and the second camera is pivotally mounted on the second linear guide rail and can slide along it.

[0017] In some embodiments, the binocular camera includes a first linear guide motor and a second linear guide motor. The first linear guide motor is used to drive the first camera to slide along the first linear guide, and the second linear guide motor is used to drive the second camera to slide along the second linear guide.

[0018] In some embodiments, the binocular camera includes a first rotary motor and a second rotary motor, the first rotary motor acting on the first camera to drive and adjust the pitch angle of the first camera, and the second rotary motor acting on the second camera to drive and adjust the pitch angle of the second camera.

[0019] In some embodiments, the feature point is a reflective auxiliary feature point. The first camera has a first fill light, and the second camera has a second fill light. After the first camera and the second camera are started, the first fill light and the second fill light are activated so that the reflective auxiliary feature point can reflect the light emitted by the first fill light and the second fill light when the image is acquired, so that the acquired image includes the reflected light of the feature point.

[0020] In some embodiments, the first camera is located near the left side of the tunnel, the second camera is located near the right side of the tunnel, and the horizontal direction is along the width direction of the tunnel.

[0021] In some embodiments, in the step of adjusting the positions of the first camera and the second camera in the horizontal direction, the closer the distance between the feature points, the smaller the horizontal distance between the first camera and the second camera is adjusted; the farther the distance between the feature points, the larger the horizontal distance between the first camera and the second camera is adjusted.

[0022] The present invention discloses an adjustment method for a deformation monitoring binocular camera, wherein the binocular camera includes a first camera and a second camera, and the adjustment method for the binocular camera includes:

[0023] Start the first camera and the second camera;

[0024] The first camera and the second camera acquire images of feature points in the tunnel in real time from different angles, and the acquired images include at least one feature point set on the left side, right side and roof of the tunnel respectively.

[0025] Adjust the pitch angles of the first camera and the second camera;

[0026] Calculate the vertical position of the feature point in the image;

[0027] Determine whether the vertical position of the feature point in the image is within the third preset position range. If the vertical position of the feature point in the image is not within the third preset position range, continue to adjust the pitch angle of the first camera and the second camera until the vertical position of the feature point in the image is within the third preset position range.

[0028] The vertical position of the feature point in the image is within a third preset position range, and the positions of the first camera and the second camera are adjusted in the horizontal direction;

[0029] Calculate the lateral position of the feature point in the image;

[0030] Determine whether the horizontal position of the feature point in the image is within the fourth preset position range. If the horizontal position of the feature point in the image is not within the fourth preset position range, continue to adjust the positions of the first camera and the second camera in the horizontal direction until the horizontal position of the feature point in the image is within the fourth preset position range.

[0031] The tunnel deformation monitoring method according to an embodiment of the present invention includes:

[0032] At least one feature point is set on the left side, right side and roof of the tunnel;

[0033] The horizontal position and pitch angle of the first camera and the second camera are adjusted according to the deformation monitoring binocular camera adjustment method described in any of the above embodiments.

[0034] The first camera and the second camera acquire images of the feature points from different angles;

[0035] Based on the disparity of feature points in the images captured by the first camera and the second camera, the three-dimensional spatial coordinates of the feature points in the camera coordinate system are calculated in real time.

[0036] The deformation of the tunnel surface is calculated in real time based on the change in the three-dimensional spatial coordinates of the feature points. Attached Figure Description

[0037] Figure 1 This is a perspective view of a deformation monitoring binocular camera according to an embodiment of the present invention.

[0038] Figure 2 This is another perspective view of the deformation monitoring binocular camera according to an embodiment of the present invention.

[0039] Figure 3 This is a flowchart of the deformation monitoring binocular camera adjustment method according to an embodiment of the present invention.

[0040] Figure 4 This is a schematic diagram illustrating the monitoring principle of the tunnel deformation monitoring method according to an embodiment of the present invention.

[0041] Figure label:

[0042] Binocular camera 100

[0043] First camera 110, first linear guide rail 111, first linear guide rail motor 112, first rotary motor 113

[0044] Second camera 120, second linear guide rail 121, second linear guide rail motor 122, second rotary motor 123

[0045] Mounting bracket 130

[0046] Feature point 200, first feature point 210, second feature point 220, third feature point 230.

[0047] First image 301, second image 302. Detailed Implementation

[0048] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0049] The following reference Figures 1-3 This invention describes an adjustment method for a deformation monitoring binocular camera 100 provided in an embodiment of the invention. For example... Figure 1 and Figure 2 As shown, the binocular camera 100 includes a first camera 110 and a second camera 120, and the adjustment method of the binocular camera 100 includes;

[0050] Step S101: Start the first camera 110 and the second camera 120;

[0051] Step S102: The first camera 110 and the second camera 120 acquire images of feature points 200 in the tunnel from different angles in real time, and the acquired images include at least one feature point 200 set on the left side, right side and roof of the tunnel respectively.

[0052] Step S103: Adjust the positions of the first camera 110 and the second camera 120 in the horizontal direction;

[0053] Step S104: Calculate the horizontal position of feature point 200 in the image;

[0054] Step S105: Determine whether the horizontal position of feature point 200 in the image is within the first preset position range. If the horizontal position of feature point 200 in the image is not within the first preset position range, continue to adjust the positions of the first camera 110 and the second camera 120 in the horizontal direction until the horizontal position of feature point 200 in the image is within the first preset position range.

[0055] Step S106: The lateral position of feature point 200 in the image is within the first preset position range; adjust the pitch angle of the first camera 110 and the second camera 120.

[0056] Step S107: Calculate the vertical position of feature point 200 in the image;

[0057] Step S108: Determine whether the vertical position of feature point 200 in the image is within the second preset position range. If the vertical position of feature point 200 in the image is not within the second preset position range, continue to adjust the pitch angle of the first camera 110 and the second camera 120 until the vertical position of feature point 200 in the image is within the second preset position range.

[0058] In step S102: the feature points 200 displayed in the image acquired by the first camera 110 include at least one feature point 200 on the left side of the tunnel, at least one feature point 200 on the right side of the tunnel, and at least one feature point 200 on the tunnel roof. The feature points 200 displayed in the image acquired by the second camera 120 include at least one feature point 200 on the left side of the tunnel, at least one feature point 200 on the right side of the tunnel, and at least one feature point 200 on the tunnel roof. It should be understood that the left side of the tunnel is the left wall of the tunnel, and the right side is the right wall of the tunnel.

[0059] Because the first camera 110 and the second camera 120 are positioned differently, their shooting angles are different. Therefore, there is parallax between the feature points 200 in the images captured by the first camera 110 and the second camera 120. Thus, the deformation of the tunnel can be calculated based on the coordinate changes of the feature points 200 using the principle of binocular vision measurement. It is understood that the feature points 200 in the image captured by the first camera 110 and the feature points 200 in the image captured by the second camera 120 are the same feature points.

[0060] The deformation monitoring binocular camera adjustment method of this invention can adjust the lateral translation and pitch angles of the first and second cameras. The chips of the first and second cameras, or an external industrial control computer, can be used as processors to calculate and determine the lateral and longitudinal positions of feature points in the image in real time. Based on the difference between the lateral and longitudinal positions of feature points in the image and the target set position, the translation position and pitch angle of the first and second cameras can be adjusted in real time. Therefore, the deformation of the tunnel can be calculated more accurately based on the image of the feature points acquired by the binocular camera. The deformation monitoring binocular camera adjustment method of this invention can also make the deformation monitoring binocular camera more applicable and its application methods more extensive.

[0061] In some embodiments, such as Figure 1 and Figure 2As shown, the binocular camera 100 includes a mounting bracket 130. A first camera 110 is pivotally mounted on the mounting bracket 130 to adjust its pitch angle, and a second camera 120 is pivotally mounted on the mounting bracket 130 to adjust its pitch angle. The mounting bracket 130 is provided with a linear guide rail extending in a horizontal direction. The first camera 110 and the second camera 120 are mounted on the linear guide rail and are slidable along the linear guide rail. It can be understood that the first camera 110 and the second camera 120 are located on the same horizontal plane, that is, the first camera 110 and the second camera 120 are at the same height.

[0062] To achieve step S103, the first camera 110 is slid along the linear guide rail to adjust its position in the horizontal direction, thereby adjusting the lateral position of the feature point 200 in the image captured by the first camera 110. Similarly, to achieve step S103, the second camera 120 is slid along the linear guide rail to adjust its position in the horizontal direction, thereby adjusting the lateral position of the feature point 200 in the image captured by the second camera 120.

[0063] exist Figure 1 and Figure 2 In the specific example shown, the mounting bracket 130 extends along the horizontal direction, and the linear guide rails include a first linear guide rail 111 and a second linear guide rail 121. Both the first linear guide rail 111 and the second linear guide rail 121 extend along the extension direction of the mounting bracket 130 and are both mounted on the upper surface of the mounting bracket 130. The first camera 110 is pivotally mounted on the first linear guide rail 111 and can slide along the first linear guide rail 111, and the second camera 120 is pivotally mounted on the second linear guide rail 121 and can slide along the second linear guide rail 121.

[0064] In other examples, the linear guide can be one that extends along the horizontal direction, and both the first camera 110 and the second camera 120 can be pivotally mounted on the linear guide and slidable along the extension direction of the linear guide.

[0065] Furthermore, such as Figure 2 As shown, the binocular camera 100 includes a first linear guide motor 112 and a second linear guide motor 122. The first linear guide motor 112 is used to drive the first camera 110 to slide along the first linear guide 111, and the second linear guide motor 122 is used to drive the second camera 120 to slide along the second linear guide 121. The arrangement of the first linear guide motor 112 and the second linear guide motor 122 improves the automation level of the binocular camera 100. The horizontal positions of the first camera 110 and the second camera 120 can be accurately adjusted by manipulating the first linear guide motor 112 and the second linear guide motor 122.

[0066] In some embodiments, the adjustment of the pitch angle of the first camera 110 and the adjustment of the pitch angle of the second camera 120 are driven by a driving device to further improve the automation level of the binocular camera 100. Figure 2 The binocular camera 100 includes a first rotary motor 113 and a second rotary motor 123. The first rotary motor 113 acts on the first camera 110 to drive and adjust the pitch angle of the first camera 110, and the second rotary motor 123 acts on the second camera 120 to drive and adjust the pitch angle of the second camera 120. The pitch angle of the first camera 110 is accurately adjusted by controlling the first rotary motor 113, and the pitch angle of the second camera 120 is accurately adjusted by controlling the second rotary motor 123.

[0067] Specifically, the first camera 110 is pivotally connected to the first linear guide rail 111 via a first pivot axis (not shown in the figure). The first rotary motor 113 acts on the first pivot axis and drives it to rotate, thereby driving the first camera 110 to rotate around the central axis of the first pivot axis, and thus adjusting the pitch angle of the first camera 110. The interaction between the second camera 120 and the second rotary motor 123 is the same as that between the first camera 110, and will not be described in detail here.

[0068] In some embodiments, the first camera 110 is near the left side of the tunnel, and the second camera 120 is near the right side of the tunnel. The horizontal direction is along the width direction of the tunnel, that is, in step S103, the first camera 110 and the second camera 120 are translated along the width direction of the tunnel.

[0069] In some embodiments, step S103, adjusting the positions of the first camera 110 and the second camera 120 in the horizontal direction, specifically includes: the closer the feature points 200 are, the more the horizontal positions of the first camera 110 and the second camera 120 are adjusted to reduce the distance between them; the farther the feature points 200 are, the more the horizontal positions of the first camera 110 and the second camera 120 are adjusted to increase the distance between them.

[0070] Based on the position of feature point 200 in the depth, width and length directions of the tunnel, the distance between the first camera 110 and the second camera 120 is adjusted, thereby adjusting the parallax of feature point 200 in the images acquired by the first camera 110 and the second camera 120, so as to more accurately identify each feature point 200, accurately calculate the three-dimensional spatial coordinates of feature point 200 in the camera coordinate system, and thus obtain a more accurate tunnel deformation result.

[0071] Optionally, the mounting bracket 130 of the binocular camera 100 is mounted on the tunneling and anchoring machine or the bolt transfer machine, so that the binocular camera 100 moves with the tunneling and anchoring machine or the bolt transfer machine to perform on-site monitoring.

[0072] In some embodiments, the feature point 200 set on the alleyway is a reflective auxiliary feature point. The first camera 110 has a first supplementary light (not shown in the figure), and the second camera 120 has a second supplementary light (not shown in the figure). The reflective auxiliary feature point can reflect the light emitted by the first supplementary light and the second supplementary light. In step S101, after the first camera 110 and the second camera 120 are started, the first supplementary light and the second supplementary light are started so that when the image is acquired, the reflective auxiliary feature point can reflect the light emitted by the first supplementary light and the second supplementary light so that the acquired image includes the reflected light of the feature point 200.

[0073] Optionally, the reflective auxiliary feature points are made of highly reflective material, requiring no power supply and reducing the manufacturing cost of feature points 200.

[0074] In some optional embodiments, feature point 200 is a patch reflective auxiliary feature point, which is attached to the surface of the tunnel, making the installation simple and convenient.

[0075] In some alternative embodiments, feature point 200 is a spherical reflective auxiliary feature point, which can reflect light in different directions.

[0076] In other embodiments, feature point 200 is a light-emitting auxiliary feature point, which can emit light so that the emitted light from feature point 200 is included in the images captured by the first camera 110 and the second camera 120. In other words, feature point 200 actively emits light, making it easier for the first camera 110 and the second camera 120 to capture it.

[0077] In other embodiments of the present invention, a method for adjusting a deformation monitoring binocular camera is provided. The binocular camera 100 includes a first camera 110 and a second camera 120. The method for adjusting the binocular camera 100 includes:

[0078] Step S201: Start the first camera 110 and the second camera 120;

[0079] Step S202: The first camera 110 and the second camera 120 acquire images of feature points 200 in the tunnel from different angles in real time, and the acquired images include at least one feature point 200 set on the left side, right side and roof of the tunnel respectively.

[0080] Step S203: Adjust the pitch angle of the first camera 110 and the second camera 120;

[0081] Step S204: Calculate the vertical position of feature point 200 in the image;

[0082] Step S205: Determine whether the vertical position of feature point 200 in the image is within the third preset position range. If the vertical position of feature point 200 in the image is not within the third preset position range, continue to adjust the pitch angle of the first camera 110 and the second camera 120 until the vertical position of feature point 200 in the image is within the third preset position range.

[0083] Step S206: The vertical position of feature point 200 in the image is within the range of the third preset position. Adjust the position of the first camera 110 and the second camera 120 in the horizontal direction.

[0084] Step S207: Calculate the horizontal position of feature point 200 in the image;

[0085] Step S208: Determine whether the horizontal position of feature point 200 in the image is within the fourth preset position range. If the horizontal position of feature point 200 in the image is not within the fourth preset position range, continue to adjust the positions of the first camera 110 and the second camera 120 in the horizontal direction until the horizontal position of feature point 200 in the image is within the fourth preset position range.

[0086] In step S202: the feature points 200 displayed in the image acquired by the first camera 110 include at least one feature point 200 on the left side of the tunnel, at least one feature point 200 on the right side of the tunnel, and at least one feature point 200 on the roof of the tunnel. The second camera 120 is similar.

[0087] The deformation monitoring binocular camera adjustment method of this invention can adjust the translation position and pitch angle of the first and second cameras in real time according to the difference between the horizontal and vertical positions of feature points in the image and the target set position. Therefore, the deformation of the roadway can be calculated more accurately based on the image of the feature points acquired by the binocular camera. The deformation monitoring binocular camera adjustment method of this invention can also make the deformation monitoring binocular camera more applicable and have a wider range of applications.

[0088] The following reference Figure 4 The present invention describes a method for monitoring roadway deformation during excavation, comprising:

[0089] Set feature points: Set at least one feature point on the left side, right side and roof of the roadway respectively;

[0090] Binocular camera adjustment: Adjust the horizontal position and pitch angle of the first camera 110 and the second camera 120 according to the adjustment method of the deformation monitoring binocular camera in any of the above embodiments, so that the lateral position of the feature point 200 in the image of the first camera 110 and the second camera 120 is within the corresponding preset position range, and the vertical position in the image is within the corresponding preset position range.

[0091] Image acquisition: The first camera 110 and the second camera 120 in the binocular camera 100 acquire images of the feature points 200 from different angles;

[0092] Coordinate Calculation: Based on the disparity of feature point 200 in the image acquired by the deformation monitoring binocular camera 100, the three-dimensional spatial coordinates of feature point 200 in the camera coordinate system are calculated in real time.

[0093] Deformation calculation: The deformation of the roadway surface is calculated in real time based on the change in the three-dimensional spatial coordinates of feature point 200.

[0094] The feature points 200 in the images acquired by the first camera 110 and the second camera 120 include at least one feature point 200 on the left side of the tunnel, at least one feature point 200 on the right side of the tunnel, and at least one feature point 200 on the roof of the tunnel. The feature points 200 in the images acquired from different angles are the same feature points 200. In the coordinate solving step, the coordinates of these feature points 200 are solved respectively.

[0095] The tunnel deformation monitoring method of this invention sets feature points on the tunnel surface, and a deformation monitoring binocular camera takes pictures of the feature points from different positions. The computer collects the camera images in real time and performs visual calculations. The method uses the binocular vision measurement principle to realize real-time monitoring of tunnel surface deformation. Moreover, the monitoring process is less affected by dust and can realize real-time continuous monitoring.

[0096] In some embodiments, such as Figure 4 As shown, feature 200 includes a first feature point 210, a second feature point 220 and a third feature point 230. The first feature point 210 is located on the top plate of the tunnel, the second feature point 220 is located on the left side of the tunnel, and the third feature point 230 is located on the right side of the tunnel opposite to the left side.

[0097] In the binocular camera adjustment and image acquisition steps, the images acquired by the first camera 110 and the second camera 120 both include a first feature point 210, a second feature point 220, and a third feature point 230. In the coordinate calculation step, using the principle of binocular vision measurement, the three-dimensional spatial coordinates of the first feature point 210, the second feature point 220, and the third feature point 230 in different images are calculated. In the deformation calculation step, the deformation of the roadway surface can be calculated in real time based on the changes in the three-dimensional spatial coordinates of the first feature point 210, the second feature point 220, and the third feature point 230. This requires a relatively small number of feature points 200, making it easier to arrange the feature points 200.

[0098] like Figure 4 As shown, in order to better characterize the roof subsidence and the approach of the two sides of the roadway, the second feature point 220 and the third feature point 230 are opposite each other in the width direction of the roadway, and the line connecting the second feature point 220 and the third feature point 230 is a horizontal line, which is orthogonal to the length direction of the roadway.

[0099] Furthermore, a perpendicular line is drawn from the first feature point 210 to the ground. This perpendicular line can connect with and be perpendicular to the line connecting the second feature point 220 and the third feature point 230, that is, the first feature point 210, the second feature point 220 and the third feature point 230 are on the same vertical plane.

[0100] In some embodiments, there are multiple sets of binocular cameras 100. The multiple sets of binocular cameras 100 are combined to take pictures from different angles, so that the accuracy of the three-dimensional spatial coordinates of the obtained feature points 200 in the camera coordinate system is higher, and thus the calculated deformation of the tunnel surface is more accurate.

[0101] In some embodiments, in the deformation calculation step: a line is drawn between the feature point 200 on the left side of the roadway and the feature point 200 on the right side of the roadway; the change in the vertical distance from the feature point 200 on the roadway roof to the line is taken as the roof subsidence; and the change in the length of the line is taken as the convergence of the two sides.

[0102] As an example, such as Figure 4 As shown, a line is drawn between the second feature point 220 and the third feature point 230. The change in the vertical distance between the first feature point 210 and the line is the amount of subsidence of the roadway roof. The change in the distance between the second feature point 220 and the third feature point 230 is the amount of convergence between the two sides of the roadway, that is, the change in the width of the roadway.

[0103] The following is based on Figure 4 The method for monitoring roadway deformation during excavation according to a specific embodiment of the present invention is described below. The method for monitoring roadway deformation during excavation includes the following steps:

[0104] Step 1: Set feature point 200, set a first feature point 210 on the top plate of the tunnel, set a second feature point 220 on the left side of the tunnel, and set a third feature point 230 on the right side of the tunnel.

[0105] Step 2: Start the program. Start the tunnel deformation monitoring program through the host computer software.

[0106] Step 3: Binocular camera adjustment and image acquisition. Adjust the horizontal position and pitch angle of the first camera 110 and the second camera 120 according to the adjustment method of the deformation monitoring binocular camera in any of the above embodiments, so that the horizontal and vertical positions of the first feature point 210, the second feature point 220 and the third feature point 230 in the acquired image are within the corresponding preset position range. Then, the first camera 110 and the second camera 120 acquire images of the first feature point 210, the second feature point 220 and the third feature point 230 from different angles. The first camera 110 obtains the first image 301 and the second camera 120 obtains the second image 302.

[0107] Step 4: Coordinate solution, including the following steps:

[0108] Step 401: Image correction. The binocular camera 100 transmits the acquired image to the computer. The computer obtains the image source file and performs format conversion, converting the image information into matrix data. The computer corrects the image into a distortion-free image according to the pre-calibrated distortion parameters.

[0109] Step 402: Feature point extraction. Extract feature points 200 from the corrected image. Calculate the two-dimensional centroid coordinates of the highlighted circular features in the image using a visual recognition algorithm.

[0110] Step 403: Feature point matching. Based on position and shape features, feature points 200 in the first image 301 and the second image 302 are matched to ensure that the matched feature points 200 correspond to the same feature point 200 in space.

[0111] Step 404: Solve the three-dimensional coordinates of the feature point. Based on the pre-calibrated extrinsic information of the binocular camera 100, and using the principle of triangulation, calculate the three-dimensional spatial coordinates of the feature point 200 in the camera coordinate system according to the difference in parallax of the same feature point 200 in the first camera 110 and the second camera 120 of the binocular camera 100.

[0112] Step 405: Top and side feature classification. Classify the feature points 200 with three-dimensional coordinates obtained from the actual solution and determine whether the feature points 200 are on the left side, right side, or roof of the roadway.

[0113] Step 5: Deformation calculation: The change in the vertical distance between the first feature point 210 and the line connecting the second feature point 220 and the third feature point 230 is taken as the top plate subsidence, and the change in the length of the line connecting the second feature point 220 and the third feature point 230 is taken as the two side slopes moving closer together.

[0114] Step 6: Data transmission: Transmit the calculated tunnel deformation data.

[0115] Specifically, in step 4, based on the principle of binocular vision measurement, the first camera 110 and the second camera 120 of the binocular camera 100 simultaneously observe the first feature point 210 located on the top plate. Figure 4 P in m When the first camera 110 obtains a first image 301 containing image point P1, the second camera 120 obtains a second image 302 containing image point P2, and the first feature point 210 ( Figure 4 P in m The first feature point 210 is the intersection of the line connecting the optical center of the first camera 110 and image point P1, and the line connecting the optical center of the second camera 120 and image point P2. Solve for the first feature point 210. Figure 4 P in m The process of determining the three-dimensional coordinates of a given object can be represented as:

[0116]

[0117] In the formula, s1 is the projection scale factor of the first camera 110, s2 is the projection scale factor of the second camera 120, P1' is the homogeneous coordinate of the image point of the first camera 110, P2' is the homogeneous coordinate of the image point of the second camera 120, K1 is the intrinsic parameter matrix of the first camera 110, K2 is the intrinsic parameter matrix of the second camera 120, [R1|t1] is the extrinsic parameter matrix of the first camera 110, [R2|t2] is the extrinsic parameter matrix of the second camera 120, P m ' represents the homogeneous coordinates of the first feature point 210 in the global coordinate system.

[0118] Setting the coordinate system of the first camera 110 as the global coordinate system and considering distortion, the distortion formula and 3D coordinate formula in the coordinate system of the first camera 110 are as follows:

[0119]

[0120] Where P1” represents the homogeneous coordinates of the image points after distortion correction by the first camera 110, P2” represents the homogeneous coordinates of the image points after distortion correction by the second camera 120, d1 represents the distortion function of the first camera 110, d2 represents the distortion function of the second camera 120, I represents the identity matrix, [R S |t SLet ] be the extrinsic parameter matrix between the first camera 110 and the second camera 120, which has the following formula:

[0121]

[0122] The intrinsic and extrinsic parameter matrices and distortion parameters of the stereo camera 100 are solved using nonlinear optimization, as shown in the following formula:

[0123] min∑||P1-P1(K, R, t, d; P m )|| 2

[0124] Where P1 is the estimated value of point P1 in the reprojected image coordinate system. R is obtained through nonlinear optimization. S and t S Then, given the image coordinates P1, the first feature point 210 in the global coordinate system can be obtained. Figure 4 P in m The three-dimensional coordinates of )

[0125] P m =RP1+T

[0126] Based on the above steps, the second feature point 220 in the global coordinate system is calculated respectively. Figure 4 P in l The three-dimensional coordinates P l and the third feature point 230 ( Figure 4 P in r The three-dimensional coordinates P r .

[0127] Deformation monitoring during excavation assumes that the relative distance between feature points remains constant in the moving coordinate system. The distance between the line connecting the second feature point 220 and the third feature point 230 in the same cross section is approximated as the distance between the two sides of the roadway. The formula for calculating the convergence of the two sides is as follows:

[0128] α=Δ||P l -P r ||

[0129] The change in distance between the lines connecting the first feature point 210 to the second feature point 220 and the third feature point 230 under the same cross-section is approximated as the roof subsidence, and the solution formula is as follows:

[0130]

[0131] The tunnel deformation monitoring method provided in this embodiment of the invention can be used to monitor tunnel deformation. By simply installing three reflective auxiliary feature points on the surface of the tunnel, the surface deformation monitoring of the tunnel during the tunneling process can be realized. The monitoring process is less affected by dust and can achieve real-time continuous monitoring.

[0132] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this invention and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0133] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0134] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection, an electrical connection, or a connection that allows communication between them; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise explicitly limited. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0135] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature is in indirect contact with the second feature through an intermediate medium. Furthermore, "above," "over," and "on top" of the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.

[0136] In this invention, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to a specific feature, structure, material, or characteristic described in connection with that embodiment or example, which is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0137] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for adjusting a deformation monitoring binocular camera, characterized in that, The binocular camera comprises a first camera and a second camera, and the adjustment method of the binocular camera comprises the following steps: starting the first camera and the second camera; the first camera and the second camera collect images of feature points in the tunnel in real time from different angles, and the collected images include at least one feature point arranged on the left and right sides and the roof of the tunnel respectively; adjusting the positions of the first camera and the second camera in the horizontal direction; calculating the lateral positions of the feature points in the images; judging whether the lateral positions of the feature points in the images are within a first preset position range, if the lateral positions of the feature points in the images are not within the first preset position range, then continuously adjusting the positions of the first camera and the second camera in the horizontal direction until the lateral positions of the feature points in the images are within the first preset position range; adjusting the pitch angles of the first camera and the second camera when the lateral positions of the feature points in the images are within the first preset position range; calculating the longitudinal positions of the feature points in the images; judging whether the longitudinal positions of the feature points in the images are within a second preset position range, if the longitudinal positions of the feature points in the images are not within the second preset position range, then continuously adjusting the pitch angles of the first camera and the second camera until the longitudinal positions of the feature points in the images are within the second preset position range; in the step of adjusting the positions of the first camera and the second camera in the horizontal direction, the closer the distance between the feature points, the smaller the horizontal distance between the first camera and the second camera, and the farther the distance between the feature points, the larger the horizontal distance between the first camera and the second camera.

2. The adjustment method of the deformation monitoring binocular camera according to claim 1, characterized in that, The binocular camera comprises a mounting frame, the first camera and the second camera are pivotally arranged on the mounting frame so that the pitch angles are adjustable, a straight guide rail extending in the horizontal direction is arranged on the mounting frame, and the first camera and the second camera are arranged on the straight guide rail and can slide along the straight guide rail.

3. The adjustment method of the deformation monitoring binocular camera according to claim 2, characterized in that, The straight guide rail comprises a first straight guide rail and a second straight guide rail, both of which extend in the horizontal direction, the first camera is pivotally arranged on the first straight guide rail and can slide along the first straight guide rail, and the second camera is pivotally arranged on the second straight guide rail and can slide along the second straight guide rail.

4. The adjustment method of the deformation monitoring binocular camera according to claim 3, characterized in that, The binocular camera comprises a first straight guide rail motor and a second straight guide rail motor, the first straight guide rail motor is used to drive the first camera to slide along the first straight guide rail, and the second straight guide rail motor is used to drive the second camera to slide along the second straight guide rail.

5. The adjustment method of the deformation monitoring binocular camera according to any one of claims 1-4, characterized in that, The binocular camera comprises a first rotating motor and a second rotating motor, the first rotating motor acts on the first camera to drive the adjustment of the pitch angle of the first camera, and the second rotating motor acts on the second camera to drive the adjustment of the pitch angle of the second camera.

6. The adjustment method of the deformation monitoring binocular camera according to claim 1, characterized in that, The feature point is a reflective auxiliary feature point, the first camera has a first light supplement lamp, the second camera has a second light supplement lamp, and the first light supplement lamp and the second light supplement lamp are started after the first camera and the second camera are started, so that the reflective auxiliary feature point can reflect the light emitted by the first light supplement lamp and the second light supplement lamp when the image is collected, so that the collected image includes the reflection of the feature point.

7. The adjustment method of the deformation monitoring binocular camera according to claim 1, characterized in that, The first camera is adjacent to the left side of the roadway, and the second camera is adjacent to the right side of the roadway.

8. An adjustment method of a deformation monitoring binocular camera, characterized in that, The adjustment method of the binocular camera includes: starting the first camera and the second camera; The first camera and the second camera collect images of feature points in the roadway from different angles, and the collected images include at least one feature point arranged on the left side, the right side and the roof of the roadway respectively; adjust the pitch angle of the first camera and the second camera; calculate the longitudinal position of the feature point in the image; determine whether the longitudinal position of the feature point in the image is within a third preset position range, if the longitudinal position of the feature point in the image is not within the third preset position range, continue to adjust the pitch angle of the first camera and the second camera until the longitudinal position of the feature point in the image is within the third preset position range; The longitudinal position of the feature point in the image is within the third preset position range, and the position of the first camera and the second camera is adjusted in the horizontal direction; calculate the transverse position of the feature point in the image; determine whether the transverse position of the feature point in the image is within a fourth preset position range, if the transverse position of the feature point in the image is not within the fourth preset position range, continue to adjust the position of the first camera and the second camera in the horizontal direction until the transverse position of the feature point in the image is within the fourth preset position range; In the step of adjusting the position of the first camera and the second camera in the horizontal direction, the closer the distance between the feature points, the smaller the horizontal distance between the first camera and the second camera, and the farther the distance between the feature points, the larger the horizontal distance between the first camera and the second camera.

9. A method of monitoring deformation of a tunnel as it is excavated, characterised in that, comprise: arranging at least one feature point on the left side, the right side and the roof of the roadway respectively; adjusting the horizontal position and the pitch angle of the first camera and the second camera according to the adjustment method of the deformation monitoring binocular camera according to any one of claims 1-8; The first camera and the second camera collect images of the feature points from different angles; According to the parallax of the feature points in the images collected by the first camera and the second camera, the three-dimensional space coordinates of the feature points in the camera coordinate system are calculated in real time; According to the change amount of the three-dimensional space coordinates of the feature points, the deformation of the surface of the roadway is calculated in real time.

Images