Large-scale structure displacement change tracking and monitoring method and system based on digital image

Abstract

The invention relates to the technical field of displacement change monitoring, in particular to a large-scale structure displacement change tracking monitoring method and system based on digital images, and the method comprises the following steps: manufacturing a target with a known shape and size; collecting a global digital image of the large-scale structure when no target is arranged, defining the global digital image as a first digital image, marking a fixed point and a displacement tracking point to be measured in the first digital image based on prior knowledge of the large-scale structure, and arranging targets at the fixed point and the displacement tracking point to be measured; acquiring a digital image of the large-scale structure after the target is arranged, and defining the digital image as a second digital image; based on the target in the second digital image, target structure displacement analysis is carried out, target theoretical center point position coordinates corresponding to the displacement tracking points to be measured are obtained, and displacement changes of the large-scale structure are analyzed. According to the invention, the image identification monitoring precision of the to-be-measured displacement tracking point and the accuracy and robustness of change tracking of the to-be-measured displacement tracking point can be obviously improved.

Description

Technical Field

[0001] The present invention relates to the technical field of displacement change monitoring, and in particular to a large-scale structure displacement change tracking monitoring method and system based on digital images. Background Art

[0002] During the construction and maintenance of large structures such as bridges, high-rise buildings, dams, tunnels, slopes, and large mechanical equipment, displacement change monitoring is often required to ensure their safety and stability.

[0003] Traditional displacement change monitoring methods are easily affected by various factors such as non-clear images composed of pixel blocks, external environment, equipment operation, etc., and do not have accurate mathematical lines and coordinate point descriptions, resulting in limited displacement change monitoring accuracy. With the development of displacement change monitoring technology, a displacement change monitoring technology based on displacement sensors has been proposed. The displacement of the measuring points is monitored by displacement sensors, which has high monitoring accuracy, but also has non-precise "fine" characteristics. In addition, existing photogrammetry can achieve non-contact "precise" morphological monitoring of small-scale objects, but for large structures, due to the low pixel per unit area of ​​the collected digital images, high-precision displacement change monitoring cannot be achieved; if the digital images (digital images with high pixel per unit area) are collected in segments and then spliced, the collection of digital images is more cumbersome and the splicing error is large.

[0004] In summary, the monitoring accuracy of existing large-scale structure displacement change monitoring technology is limited, and there is an urgent need for a technology that can improve the monitoring accuracy of large-scale structure displacement change. Summary of the invention

[0005] In order to solve the above problems, the present invention provides a large-scale structure displacement change tracking monitoring method and system based on digital images, which are used to improve the monitoring accuracy of large-scale structure displacement changes.

[0006] In order to achieve the above object, the technical solution of the present invention is as follows:

[0007] On the one hand, a method for tracking and monitoring displacement changes of a large structure based on digital images is provided, comprising the following steps:

[0008] Make targets of known shape and size;

[0009] A global digital image of the large structure without setting a target is acquired, which is defined as a first digital image. Fixed points and displacement tracking points to be measured are marked in the first digital image based on prior knowledge of the large structure, and targets are set at both the fixed points and the displacement tracking points to be measured.

[0010] Acquiring a digital image of the large structure after the target is set, which is defined as a second digital image;

[0011] Based on the target in the second digital image, the displacement analysis of the target structure is performed to obtain the theoretical center point position coordinates of the target corresponding to each displacement tracking point to be measured, and the displacement change of the large structure is analyzed.

[0012] Furthermore, the size of the target is proportional to the size of the large structure, and the color of the target is set according to the color of the large structure, ensuring that the color difference between the color of the target and the color of the large structure at the setting position is greater than a threshold.

[0013] Further, when the target is a plane target, the target is a rectangular target; when the rectangular target is set at the fixed point and the displacement tracking point to be measured, the side of the rectangular target is set at 45 degrees to the side of the image pixel block in the first digital image;

[0014] When the target is a rectangular target, the second digital image is acquired by directly acquiring a full-area digital image of the large structure, and all rectangular targets are simultaneously displayed in the second digital image.

[0015] Furthermore, the displacement analysis of the rectangular target structure is performed to obtain the coordinates of the theoretical center point of the rectangular target corresponding to each displacement tracking point to be measured, and the displacement change of the large structure is analyzed, including the following steps:

[0016] Performing denoising, enhancement, and binarization processing on the second digital image to improve the quality and recognition accuracy of the second digital image;

[0017] Performing regression analysis on the pixel coordinates of the outer contour of the rectangular target in the second digital image, and fitting to obtain mathematical equations of four edge lines of the rectangular target;

[0018] Obtain the intersection of the four edge straight lines, define it as the diagonal point of the rectangular target, and obtain the mathematical equations of the two diagonal lines of the rectangular target from the coordinates of the diagonal point of the rectangular target;

[0019] Based on the mathematical equations of the two diagonals, the intersection of the diagonals is solved and defined as the theoretical center point of the rectangular target;

[0020] The theoretical center points of the rectangular targets corresponding to the fixed points at time t and time t+1 are aligned, and the displacement changes of the theoretical center points of the rectangular targets corresponding to the displacement tracking points to be measured at time t and time t+1 are analyzed to obtain the displacement changes of the large structure.

[0021] Furthermore, the mathematical equations of the four edge lines of the rectangular target are:

[0022] y=a 1 x+b 1

[0023] y=a 2 x+b 2

[0024] y=a 3 x+b 3

[0025] y=a 4 x+b 4

[0026] In the formula, a 1 、a 2 、a 3 and a 4 are the slopes of the first edge line, the second edge line, the third edge line, and the fourth edge line, indicating that when x increases by one unit, y 1 ,y 2 ,y 3 and 4 The corresponding average increase is a 1 、a 2 、a 3 and a 4 Unit b 1 , b 2 , b 3 and b 4 are the intercepts of the first edge line, the second edge line, the third edge line, and the fourth edge line respectively; it means that when x=0, y 1 ,y 2 ,y 3 and 4 Value

[0027] Based on the mathematical equations of the four edge lines of the rectangular target, the coordinates of the intersection of the four edge lines are solved: (x 1 ,y 1 )(x 2 ,y 2 )(x 3 ,y 3 )(x 4 ,y 4 );

[0028] Based on the intersection of the four edge lines, the coordinates of the diagonal points of the rectangular target are obtained. Based on the coordinates of the diagonal points, the diagonal lines of the rectangular target are obtained. The coordinates of the intersection of the diagonal lines at time t (x t ,y t ) and the coordinates of the intersection of the diagonals at time t+1 (x t+1 ,y t+1 ), which are the theoretical center point position coordinates of the rectangular target at time t and time t+1 respectively;

[0029] After aligning the theoretical center points of the rectangular targets corresponding to the fixed points at time t and time t+1, the mathematical coordinate difference of the theoretical center point coordinates of the rectangular targets at time t and time t+1 corresponding to the same displacement tracking point to be measured is solved to obtain the displacement change of the rectangular target, and then the displacement change of the large structure is obtained.

[0030] Furthermore, when the target is a three-dimensional target, a number of numbers are set on the surface of the three-dimensional target to ensure that the number and center point position of the three-dimensional target can be identified by the same method in a digital image acquired at any angle;

[0031] When setting up stereo targets at fixed points and displacement tracking points to be measured, the stereo targets corresponding to the displacement tracking points to be measured are arranged at intervals of 10-30m, the number of stereo targets corresponding to the fixed points is greater than or equal to 4, and the stereo targets must be prevented from being blocked by surrounding objects.

[0032] Furthermore, when the target is a three-dimensional target, the second digital image is collected in the following manner:

[0033] The digital images of large structures with a certain degree of overlap are continuously collected by three image acquisition devices in rotation;

[0034] The image sequence of the stereo target acquired by the image acquisition device 1 is The image sequence of the stereo target acquired by the image acquisition device 2 is The image sequence of the stereo target acquired by the image acquisition device 3 is:

[0035] The stereoscopic target is simultaneously displayed in image sequences of at least two image acquisition devices; For monitoring stereo targets in I 1 Displacement in the (x, y) coordinate system, For monitoring stereo targets in I 2 Displacement in the (y, z) coordinate system, For monitoring stereo targets in I 3 Displacement in the (x, z) coordinate system.

[0036] Furthermore, the displacement analysis of the three-dimensional target structure is performed to obtain the coordinates of the theoretical center point of the three-dimensional target corresponding to each displacement tracking point to be measured, and the displacement change of the large structure is analyzed, including the following steps:

[0037] extract and The three-dimensional target in the image is extracted, the edge of the three-dimensional target is extracted, and the theoretical center point of the three-dimensional target is solved;

[0038] Based on the theoretical center point position coordinates of each stereo target in the second digital image: P 1 (x 1 ,y1 ), P 2 (x 2 ,y 2 ), P 3 (x 3 ,y 3 )…P n (x n ,y n ), and the known focal length f and depth information Z of the image acquisition device c , calculate the world coordinates P(x c ,y c , z c );

[0039] The world coordinate set of the theoretical center points of all three-dimensional targets is: S = {P 1 , P 2 , P 3 …P n};

[0040] S t = {P 1 , P 2 , P 3 …P n} to fit and obtain the large structure surface S at time t 1 , S t+1 = {P 1 , P 2 , P 3 …P n} to fit and obtain the large structure surface S at time t+1 2 ;

[0041] S 1 The expression is: S 1 {(x 1 ,y 1 , z 1 ), (x 2 ,y 2 , z 2 ), (x 3 ,y 3 , z 3 )…(x n ,y n , z n )};

[0042] S 2 The expression is: S 2 {(x 1 ,y 1 , z 1 ), (x 2 ,y 2 , z2 ), (x 3 ,y 3 , z 3 )…(x n ,y n , z n )};

[0043] The expression for the surface displacement change of a large structure is as follows:

[0044] Diff=S 2 -S 1

[0045] Thus, the surface displacement changes of large structures are analyzed and obtained.

[0046] Further, any section C is selected on the large structure, and the boundary line L between the section C and the large structure is extracted; the boundary line L is obtained by sequentially connecting a number of three-dimensional targets;

[0047] The boundary line L at time t 1 The expression is: L 1 {(x 1 ,y 1 , z 1 ), (x 2 ,y 2 , z 2 ), (x 3 ,y 3 , z 3 )…(x n ,y n , z n )};

[0048] The boundary line L at time t+1 2 The expression is: L 2 {(x 1 ,y 1 , z 1 ), (x 2 ,y 2 , z 2 ), (x 3 ,y 3 , z 3 )…(x n ,y n , z n )};

[0049] The expression for the cross-sectional displacement change of large structures is as follows:

[0050] Diff=L 2 -L 1

[0051] Thus, the cross-sectional displacement changes of large structures are analyzed and obtained.

[0052] On the other hand, a large-scale structure displacement change tracking and monitoring system based on digital images is provided, comprising:

[0053] Target configuration module, used to make targets of known shape and size;

[0054] A target setting module is used to collect a global digital image of a large structure when no target is set, which is defined as a first digital image. Based on the prior knowledge of the large structure, fixed points and displacement tracking points to be measured are marked in the first digital image, and targets are set at both the fixed points and the displacement tracking points to be measured.

[0055] A real-time acquisition module, used to acquire a digital image of the large structure after the target is set, which is defined as a second digital image;

[0056] The displacement change monitoring module is used to perform target structure displacement analysis based on the target in the second digital image, obtain the target theoretical center point position coordinates corresponding to each displacement tracking point to be measured, and analyze the displacement change of the large structure.

[0057] The above scheme has the following beneficial effects:

[0058] 1. The present invention processes the non-clear image composed of pixel blocks into precise mathematical lines and coordinate point descriptions, and uses targets based on prior knowledge such as known size and shape of large structures (the relative accuracy of target image recognition is relatively high, and plane targets are suitable for large structures such as building structures, bridges, roads, pipelines, power facilities, and three-dimensional targets are suitable for large structures such as slopes). Through the above processing, the displacement changes of large structures are focused on a mathematical point, which can significantly improve the image recognition monitoring accuracy of the displacement tracking point to be measured; at the same time, the digital image processing method provided by the present invention can improve the accuracy and robustness of tracking the changes of the displacement tracking point to be measured.

[0059] 2. The present invention uses digital image processing technology to establish the relationship between the coordinates of dispersed target points and the unified measurement coordinate system, constructs a dense spatial point network of targets under the unified monitoring coordinate system, and forms a spatial monitoring surface and section. Through the overlay difference analysis of the surfaces and sections of large structures, the displacement change position and displacement change amount of the surfaces and sections of large structures are obtained, and the safety status of large structures is accurately and effectively evaluated and predicted.

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

[0061] Figure 1 This is a flow chart of a method for tracking and monitoring displacement changes of large structures based on digital images of the present invention;

[0062] Figure 2 It is a structural schematic diagram of a large-scale structure displacement change tracking and monitoring system based on digital images of the present invention;

[0063] Figure 3 It is a schematic diagram of rectangular target setting of a large-scale structure displacement change tracking and monitoring method and system embodiment based on digital image of the present invention;

[0064] Figure 4 A second digital image schematic diagram of a bridge according to an embodiment of a large-scale structure displacement change tracking and monitoring method and system based on digital images of the present invention;

[0065] Figure 5 A schematic diagram of a rectangular target outline of an embodiment of a large-scale structure displacement change tracking and monitoring method and system based on digital images of the present invention;

[0066] Figure 6 A schematic diagram of rectangular target pixel coordinates of an embodiment of a large-scale structure displacement change tracking and monitoring method and system based on digital images of the present invention;

[0067] Figure 7 It is a schematic diagram of edge straight lines after pixel coordinate fitting of a rectangular target in a large-scale structure displacement change tracking and monitoring method and system embodiment based on digital images of the present invention;

[0068] Figure 8 A schematic diagram of the theoretical center point position of a rectangular target in an embodiment of a large-scale structure displacement change tracking and monitoring method and system based on digital images of the present invention;

[0069] Fig. 9 A schematic diagram of displacement changes of a rectangular target in an embodiment of a large-scale structure displacement change tracking and monitoring method and system based on digital images of the present invention;

[0070] Fig.10 It is a schematic diagram of a spherical target structure of an embodiment of a large-scale structure displacement change tracking and monitoring method and system based on digital images of the present invention;

[0071] Fig.11 It is a schematic diagram of the arrangement position of spherical targets in an embodiment of a large-scale structure displacement change tracking and monitoring method and system based on digital images of the present invention;

[0072] Fig.12 A schematic diagram of image acquisition positions of an image acquisition device in an embodiment of a large-scale structure displacement change tracking and monitoring method and system based on digital images of the present invention;

[0073] Fig.13 A schematic diagram of the theoretical center point position of a spherical target in an embodiment of a large-scale structure displacement change tracking and monitoring method and system based on digital images of the present invention;

[0074] Fig.14 It is a schematic diagram of the comparison of the surface displacement change of the slope before and after the embodiment of the large-scale structure displacement change tracking and monitoring method and system based on digital images of the present invention;

[0075] Fig.15 It is a schematic diagram of the comparison of the cross-sectional displacement change of the slope before and after the embodiment of the large-scale structure displacement change tracking and monitoring method and system based on digital images of the present invention. DETAILED DESCRIPTION

[0076] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0077] The following is further described in detail through specific implementation methods:

[0078] Implementation example Figure 1 As shown: A large-scale structural displacement change tracking and monitoring method based on digital images includes the following steps:

[0079] S101: Make a target of known shape and size. The size of the target is proportional to the size of the large structure, and the color of the target is set according to the color of the large structure, ensuring that the color difference between the color of the target and the color of the large structure at the setting position is greater than a threshold, thereby ensuring that the digital image of the target can be clearly captured during subsequent digital image acquisition.

[0080] The target of this embodiment can be made into a plane target or a three-dimensional target according to actual needs. The plane target and the three-dimensional target are suitable for tracking and monitoring the displacement changes of different types of large structures. For the plane target, it is suitable for large structures such as building structures, bridges, roads, pipelines, power facilities, etc.; for the three-dimensional target, it is suitable for large structures such as slopes.

[0081] S102: Acquire a global digital image of the large structure when no targets are set, which is defined as a first digital image. Based on prior knowledge of the large structure, fixed points and displacement tracking points to be measured are marked in the first digital image, and targets are set at both the fixed points and the displacement tracking points to be measured.

[0082] S103: Acquire a digital image of the large structure after the target is set, which is defined as a second digital image.

[0083] S104: Based on the target in the second digital image, a displacement analysis of the target structure is performed to obtain the position coordinates of the target theoretical center point corresponding to each displacement tracking point to be measured, and the displacement change of the large structure is analyzed.

[0084] As attached Figure 2 As shown, accordingly, this embodiment proposes a large-scale structure displacement change tracking and monitoring system based on digital images, which is adapted to the above-mentioned large-scale structure displacement change tracking and monitoring method based on digital images, and is mainly composed of a target configuration module, a target setting module, a real-time acquisition module and a displacement change monitoring module.

[0085] The target configuration module is used to make targets of known shape and size; the target setting module is used to collect the global digital image of the large structure when no targets are set, which is defined as the first digital image. Based on the prior knowledge of the large structure, fixed points and displacement tracking points to be measured are marked in the first digital image, and targets are set at both the fixed points and the displacement tracking points to be measured; the real-time acquisition module is used to collect the digital image of the large structure after the targets are set, which is defined as the second digital image; the displacement change monitoring module is used to perform target structure displacement analysis based on the targets in the second digital image, obtain the theoretical center point position coordinates of the target corresponding to each displacement tracking point to be measured, and analyze the displacement change of the large structure.

[0086] In some embodiments, the target is fabricated as a planar target:

[0087] When the target is a plane target, it is preferred to make the plane target into a rectangular target, and the surface of the rectangular target can be treated with a nano-spraying process to ensure that the surface of the rectangular target is dust-free and resistant to aging in an outdoor environment; thereby ensuring that clear and effective digital images of the rectangular target can be collected during subsequent digital image acquisition.

[0088] The rectangular target of this embodiment is used to track and monitor the displacement change of the bridge. For a bridge structure of 100-500 meters in length, a rectangular target with a side length of 30x30-60x60cm is preferably used, and the frame width of the rectangular target is 10-30cm. When setting the rectangular target at the fixed point and the displacement tracking point to be measured, the side of the rectangular target is set at 45° to the side of the image pixel block in the first digital image (as shown in the attached figure). Figure 3 The purpose of the 45° tilt is to enhance edge recognition when extracting edge contours of rectangular targets, thereby making displacement change monitoring more accurate.

[0089] In this embodiment, the global digital image of the bridge is first acquired by an image acquisition device, and the image acquisition device of this embodiment is a digital camera with high resolution. Based on the first digital image and the prior knowledge of the bridge, two fixed points (G1, G2) are set at both ends of the bridge, two displacement tracking points to be measured (D1, D2) are set on the bridge, and rectangular targets with a size of 60x60cm are set at the two fixed points (G1, G2) and the two displacement tracking points to be measured (D1, D2). The frame edge is 10cm wide and black, which has obvious color difference with the large structure at the setting position, so as to facilitate the subsequent clear and effective acquisition of the digital image of the rectangular target.

[0090] When the target is a rectangular target, the second digital image is collected in the following manner: directly collect the global digital image of the large structure, and all rectangular targets are simultaneously displayed in the second digital image (such as the attached Figure 4 shown).

[0091] In some embodiments, each fixed point and the displacement tracking point to be measured are selected by a standard frame in the second digital image, and the center position coordinates of the standard frame relative to the frame of the second digital image are determined. The size of the standard frame is pre-set based on the prior knowledge of the large structure. When the actual displacement of the large structure is subsequently measured, since the size of the rectangular target is pre-set based on the prior knowledge of the large structure, that is, the length of each side of the rectangular target is known, the corresponding number of pixels is known, based on the side length and the number of pixels covered by the side length, the actual size corresponding to each pixel can be calculated, which facilitates the subsequent calculation of the actual displacement of the large structure.

[0092] The target of this embodiment is a rectangular target. The displacement analysis of the rectangular target structure is performed to obtain the coordinates of the theoretical center point of the rectangular target corresponding to each displacement tracking point to be measured, and the displacement change of the bridge is analyzed, including the following steps:

[0093] First, the second digital image is subjected to denoising, enhancement, and binarization processing to improve the quality and recognition accuracy of the second digital image; regression analysis is performed on the pixel coordinates of the outer contour of the rectangular target in the second digital image to obtain the mathematical equations of the four edge lines of the rectangular target by fitting, and the rectangular target contour is extracted (see attached). Figure 5 As shown in the figure, the regression analysis of the pixel coordinates of the image outer contour is shown in the attached Figure 6 shown.

[0094] Specifically, the mathematical equations of the four edge lines are:

[0095] y=a 1 x+b 1

[0096] y=a 2 x+b 2

[0097] y=a3 x+b 3

[0098] y=a 4 x+b 4

[0099] In the formula, a 1 、a 2 、a 3 and a 4 are the slopes of the first edge line, the second edge line, the third edge line, and the fourth edge line, indicating that when x increases by one unit, y 1 ,y 2 ,y 3 and 4 The corresponding average increase is a 1 、a 2 、a 3 and a 4 Unit b 1 , b 2 , b 3 and b 4 are the intercepts of the first edge line, the second edge line, the third edge line, and the fourth edge line respectively; it means that when x=0, y 1 ,y 2 ,y 3 and 4 The value of .

[0100] Then, the intersection of the four edge lines is obtained and defined as the diagonal points of the rectangular target. The mathematical equations of the two diagonals of the rectangular target are obtained from the coordinates of the diagonal points of the rectangular target. Based on the mathematical equations of the two diagonals, the intersection of the diagonals is solved and defined as the theoretical center point of the rectangular target.

[0101] Specifically, the coordinates of the intersection of the four edge lines are solved based on the mathematical equations of the four edge lines of the rectangular target: (x 1 ,y 1 )(x 2 ,y 2 )(x 3 ,y 3 )(x 4 ,y 4 ); Based on the intersection of the four edge lines, obtain the coordinates of the diagonal points of the rectangular target, obtain the diagonal lines of the rectangular target based on the coordinates of the diagonal points, and obtain the coordinates of the intersection of the diagonal lines at time t (x t ,y t ) and the coordinates of the intersection of the diagonals at time t+1 (x t+1 ,y t+1 ), as the theoretical center point position coordinates of the rectangular target at time t and time t+1 respectively. (As shown in the attached Figure 7 , 8 (shown)

[0102] After aligning the theoretical center points of the rectangular target corresponding to the fixed points at time t and time t+1, the coordinate difference of the theoretical center point of the rectangular target at time t and time t+1 corresponding to the displacement tracking point D1 to be measured is solved to obtain the displacement change of the rectangular target, and then the displacement change of the large structure is obtained. (As shown in the attached figure Fig. 9 (shown)

[0103] In addition, multiple second digital images can be obtained before and after the large structure is deformed, processed according to the above method, and the theoretical center point positions of the multiple second digital images are weighted averaged to reduce the errors caused by various external factors such as the digital image acquisition environment and operation. The above digital image processing processes are all performed through a computer image algorithm processing system, and mathematical coordinate difference solution, weighted average processing, etc. are all performed through a data analysis module constructed by a computer.

[0104] In some embodiments, the target is made into a three-dimensional target:

[0105] When the target is a three-dimensional target, it is necessary to set a number of numbers on its surface. It is preferred to make the three-dimensional target into a spherical target to ensure that the digital image acquired at any angle can use the same method to identify the number and center point position of the spherical target. For the spherical target of this embodiment, the mounting piece can be fixed at its bottom to ensure that it is effectively fixed while preventing the spherical target from being blocked by objects. And its surface is designed to be a regular hexagon with black and white. (As shown in the attached figure, the spherical target is a spherical target with a fixed mounting piece at its bottom to ensure that it is effectively fixed while preventing the spherical target from being blocked by objects.) Fig.10 As shown in the figure, the spherical target is also subjected to the nano-spraying process to ensure that the surface of the spherical target is free of dust and stains and is resistant to aging in the outdoor environment; thereby ensuring that clear and effective digital images of the spherical target can be collected during subsequent digital image acquisition.

[0106] The spherical targets of this embodiment are used to track and monitor the displacement changes of the slope. When setting spherical targets at fixed points and displacement tracking points to be measured, preferably, the spherical targets corresponding to the displacement tracking points to be measured are arranged at intervals of 10-30m. In this embodiment, the spherical targets corresponding to the displacement tracking points to be measured are arranged at intervals of 20m. The number of spherical targets corresponding to the fixed points is greater than or equal to 4, and all spherical targets must be prevented from being blocked by surrounding objects. (As shown in the attached figure, Fig.11 (shown)

[0107] The acquisition method of the second digital image of the spherical target in this embodiment is:

[0108] The three image acquisition devices are rotated to continuously acquire digital images of large structures with a certain degree of overlap. The image acquisition devices in this embodiment are also digital cameras with high resolution, and are set at positions as shown in the attached figure. Fig.11 As shown, attached Fig.11 1, 2, and 3 are the positions of the digital cameras. For monitoring the displacement change of the slope, it is preferred that after rain, earthquake, or other conditions that may cause the slope displacement occur, the digital camera is started to rotate and collect the second digital image of the monitored slope.

[0109] The image sequence of the spherical target acquired by the image acquisition device 1 is The image sequence of the spherical target collected by the image acquisition device 2 is: The image sequence of the spherical target acquired by the image acquisition device 3 is: The spherical target is simultaneously displayed in image sequences of at least two image acquisition devices; For monitoring spherical targets in I 1 Displacement in the (x, y) coordinate system, For monitoring spherical targets in I 2 Displacement in the (y, z) coordinate system, For monitoring spherical targets in I 3 (x, z) coordinate system. Fig.12 (shown)

[0110] When the target is a spherical target, a three-dimensional target structure displacement analysis is performed to obtain the coordinates of the theoretical center point of the three-dimensional target corresponding to each displacement tracking point to be measured, and analyze the displacement change of the slope, including the following steps:

[0111] (1) Slope surface deformation analysis

[0112] Due to the irregular slope surface, three cameras cannot guarantee that every spherical target can be monitored. In addition, the slope collapse is mainly downward. Therefore, first extract and The three-dimensional target in the image is extracted, and the edge of the three-dimensional target is solved to find the theoretical center point of the three-dimensional target. Because the target is a spherical structure, the target obtained by shooting at any angle is spherical. The edge of the spherical target is extracted to obtain the circular edge of the spherical target. The center point P of the circular ring is the theoretical center point of the three-dimensional target. (As shown in the attached figure, Fig.13 (shown)

[0113] Based on the theoretical center point position coordinates of each stereo target in the second digital image: P 1 (x 1 ,y 1 ), P 2 (x 2 ,y 2 ), P 3 (x 3 ,y 3 )…P n (x n ,yn ), and the known focal length f and depth information Z of the digital camera c , calculate the world coordinates P(x c ,y c , z c ), which is a relatively mature prior art and will not be described in detail here.

[0114] The above steps establish the mapping relationship between the three independent measurement planes and the world coordinate system where the slope is located. The n spherical targets arranged on site can form the world coordinate set of the theoretical center points of the n spherical targets: S = {P 1 , P 2 , P 3 …P n}. S is the spatial coordinate set of all spherical targets, which can form the surface (curved surface) of the slope.

[0115] Then, the world coordinate set S of the theoretical center points of the n spherical targets at time t is t = {P 1 , P 2 , P 3 …P n} to fit and obtain the slope surface (curved surface) S at time t 1 ; The world coordinate set S of the theoretical center points of the n spherical targets at time t+1 t+1 ={p′ 1 , p′ 2 , p′ 3 …p′ n} to fit and obtain the slope surface (curved surface) S at time t+1 2 ;

[0116] Among them, the slope surface (curved surface) S 1 The expression is: S 1 {(x 1 ,y 1 , z 1 ), (x 2 ,y 2 , z 2 ), (x 3 ,y 3 , z 3 )…(x n ,y n , z n )}; where the slope surface (curved surface) S 2 The expression is: S 2 {(x 1 ,y 1 , z 1 ), (x 2 ,y2 , z 2 ), (x 3 ,y 3 , z 3 )…(x n ,y n , z n )}.

[0117] Finally, the surface (curved surface) displacement change expression of the slope is obtained as follows:

[0118] Diff=S 2 -S 1

[0119] Thus, the surface displacement changes of large structures are analyzed and obtained, including the point number, location, and three-dimensional coordinate change description of the slope changes. (See Appendix Fig.14 (shown)

[0120] (2) Deformation analysis of arbitrary slope sections

[0121] Select any section C on the large structure and extract the boundary line L between section C and the large structure; the boundary line L is obtained by connecting several three-dimensional targets in sequence; if the slope near section C slips between time t and t+1, then the boundary line L between time t and t+1 1 and L 2 The line types will differ.

[0122] The boundary line L at time t 1 The expression is: L 1 {(x 1 ,y 1 , z 1 ), (x 2 ,y 2 , z 2 ), (x 3 ,y 3 , z 3 )…(x n ,y n , z n )}; The boundary line L at time t+1 2 The expression is: L 2 {(x 1 ,y 1 , z 1 ), (x 2 ,y 2 , z 2 ), (x 3 ,y 3 , z 3 )…(x n ,y n , z n )};

[0123] Finally, the slope section displacement change expression is obtained as follows:

[0124] Diff=L 2 -L 1

[0125] Thus, the cross-sectional displacement changes of large structures are analyzed and obtained. (See Appendix Fig.15 (shown)

[0126] Obviously, the above embodiments are merely examples for the purpose of clear explanation, and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived therefrom are still within the scope of protection of the present invention.

Claims

1. A large-scale structural displacement change tracking and monitoring method based on digital images, characterized in that: The steps include: Make targets of known shape and size; A global digital image of the large structure without setting a target is acquired, which is defined as a first digital image. Fixed points and displacement tracking points to be measured are marked in the first digital image based on prior knowledge of the large structure, and targets are set at both the fixed points and the displacement tracking points to be measured. Acquiring a digital image of the large structure after the target is set, which is defined as a second digital image; Based on the target in the second digital image, the displacement analysis of the target structure is performed to obtain the theoretical center point position coordinates of the target corresponding to each displacement tracking point to be measured, and the displacement change of the large structure is analyzed.

2. The large-scale structure displacement change tracking and monitoring method based on digital images according to claim 1 is characterized in that: The size of the target is proportional to the size of the large structure, and the color of the target is set according to the color of the large structure, ensuring that the color difference between the color of the target and the color of the large structure at the set position is greater than a threshold.

3. The large-scale structure displacement change tracking and monitoring method based on digital images according to claim 1 is characterized in that: When the target is a plane target, the target is a rectangular target; when the rectangular target is set at the fixed point and the displacement tracking point to be measured, the side of the rectangular target is set at 45 degrees to the side of the image pixel block in the first digital image; When the target is a rectangular target, the second digital image is acquired by directly acquiring a full-area digital image of the large structure, and all rectangular targets are simultaneously displayed in the second digital image.

4. The method for tracking and monitoring displacement changes of large structures based on digital images according to claim 3 is characterized in that: Perform displacement analysis on the rectangular target structure, obtain the coordinates of the theoretical center point of the rectangular target corresponding to each displacement tracking point to be measured, and analyze the displacement change of the large structure, including the following steps: Performing denoising, enhancement, and binarization processing on the second digital image to improve the quality and recognition accuracy of the second digital image; Performing regression analysis on the pixel coordinates of the outer contour of the rectangular target in the second digital image, and fitting to obtain mathematical equations of four edge lines of the rectangular target; Obtain the intersection of the four edge straight lines, define it as the diagonal point of the rectangular target, and obtain the mathematical equations of the two diagonal lines of the rectangular target from the coordinates of the diagonal point of the rectangular target; Based on the mathematical equations of the two diagonals, the intersection of the diagonals is solved and defined as the theoretical center point of the rectangular target; The theoretical center points of the rectangular targets corresponding to the fixed points at time t and time t+1 are aligned, and the displacement changes of the theoretical center points of the rectangular targets corresponding to the displacement tracking points to be measured at time t and time t+1 are analyzed to obtain the displacement changes of the large structure.

5. The method for tracking and monitoring large-scale structural displacement changes based on digital images according to claim 4 is characterized in that: The mathematical equations of the four edge lines of the rectangular target are: y=a1x+b1 y=a2x+b2 y=a3x+b3 y=a4x+b4 Wherein, a1, a2, a3 and a4 are the slopes of the first edge straight line, the second edge straight line, the third edge straight line and the fourth edge straight line respectively, b1, b2, b3 and b4 are the intercepts of the first edge straight line, the second edge straight line, the third edge straight line and the fourth edge straight line respectively; Based on the mathematical equations of the four edge lines of the rectangular target, the coordinates of the intersection of the four edge lines are solved: (x1, y1) (x2, y2) (x3, y3) (x4, y4); Based on the intersection of the four edge lines, the coordinates of the diagonal points of the rectangular target are obtained. Based on the coordinates of the diagonal points, the diagonal lines of the rectangular target are obtained. The coordinates of the intersection of the diagonal lines at time t (x t ,y t ) and the coordinates of the intersection of the diagonals at time t+1 (x t+1 ,y t+1 ), which are the theoretical center point position coordinates of the rectangular target at time t and time t+1 respectively; After aligning the theoretical center points of the rectangular targets corresponding to the fixed points at time t and time t+1, the mathematical coordinate difference of the theoretical center point coordinates of the rectangular targets at time t and time t+1 corresponding to the same displacement tracking point to be measured is solved to obtain the displacement change of the rectangular target, and then the displacement change of the large structure is obtained.

6. The large-scale structure displacement change tracking and monitoring method based on digital images according to claim 1 is characterized in that: When the target is a three-dimensional target, a number of numbers are set on the surface of the three-dimensional target to ensure that the number and center point position of the three-dimensional target can be identified by the same method in a digital image acquired at any angle; When setting up stereo targets at fixed points and displacement tracking points to be measured, the stereo targets corresponding to the displacement tracking points to be measured are arranged at intervals of 10-30m, the number of stereo targets corresponding to the fixed points is greater than or equal to 4, and the stereo targets must be prevented from being blocked by surrounding objects.

7. The method for tracking and monitoring displacement changes of large structures based on digital images according to claim 6 is characterized in that: When the target is a three-dimensional target, the second digital image is collected in the following manner: The digital images of large structures with a certain degree of overlap are continuously collected by three image acquisition devices in rotation; The image sequence of the stereo target acquired by the image acquisition device 1 is The image sequence of the stereo target acquired by the image acquisition device 2 is The image sequence of the stereo target acquired by the image acquisition device 3 is: The stereoscopic target is simultaneously displayed in image sequences of at least two image acquisition devices; For monitoring stereo targets in I 1 Displacement in the (x, y) coordinate system, For monitoring stereo targets in I 2 Displacement in the (y, z) coordinate system, For monitoring stereo targets in I 3 Displacement in the (x, z) coordinate system.

8. The large-scale structure displacement change tracking and monitoring method based on digital images according to claim 7 is characterized in that: Perform displacement analysis of the three-dimensional target structure, obtain the coordinates of the theoretical center point of the three-dimensional target corresponding to each displacement tracking point to be measured, and analyze the displacement changes of large structures, including the following steps: extract and The three-dimensional target in the image is extracted, the edge of the three-dimensional target is extracted, and the theoretical center point of the three-dimensional target is solved; Based on the theoretical center point position coordinates of each stereo target in the second digital image: P1 (x1, y1), P2 (x2, y2), P3 (x3, y3) ... P n (x n ,y n ), and the known focal length f and depth information Z of the image acquisition device c , calculate the world coordinates P(x c ,y c , z c ); The world coordinate set of the theoretical center points of all three-dimensional targets is: S = {P1, P2, P3...P n }; S t = {P1, P2, P3 ... P n } to obtain the large structure surface S1 at time t, and S t+1 = {P1, P2, P3 ... P n } Perform fitting to obtain the large structure surface S2 at time t+1; The expression of S1 is: S1{(x1, y1, z1), (x2, y2, z2), (x3, y3, z3)…(x n ,y n , z n )}; The expression of S2 is: S2{(x1, y1, z1), (x2, y2, z2), (x3, y3, z3)…(x n ,y n , z n )}; The expression for the surface displacement change of a large structure is as follows: Diff=S2-S1 Thus, the surface displacement changes of large structures are analyzed and obtained.

9. The method for tracking and monitoring displacement changes of large structures based on digital images according to claim 9 is characterized in that: Select any section C on the large structure and extract the boundary line L between the section C and the large structure; the boundary line L is obtained by connecting several three-dimensional targets in sequence; The expression of the boundary line L1 at time t is: L1{(x1, y1, z1), (x2, y2, z2), (x3, y3, z3)…(x n ,y n , z n )}; The expression of the boundary line L2 at time t+1 is: L2{(x1, y1, z1), (x2, y2, z2), (x3, y3, z3)…(x n ,y n , z n )}; The expression for the cross-sectional displacement change of large structures is as follows: Diff=L2-L1 Thus, the cross-sectional displacement changes of large structures are analyzed and obtained.

10. A large-scale structural displacement change tracking and monitoring system based on digital images, characterized in that: include: Target configuration module, used to make targets of known shape and size; A target setting module is used to collect a global digital image of a large structure when no target is set, which is defined as a first digital image. Based on the prior knowledge of the large structure, fixed points and displacement tracking points to be measured are marked in the first digital image, and targets are set at both the fixed points and the displacement tracking points to be measured. A real-time acquisition module, used to acquire a digital image of the large structure after the target is set, which is defined as a second digital image; The displacement change monitoring module is used to perform target structure displacement analysis based on the target in the second digital image, obtain the target theoretical center point position coordinates corresponding to each displacement tracking point to be measured, and analyze the displacement change of the large structure.

Images