Visual displacement monitoring method and system and storage medium

Abstract

The invention discloses a visual displacement monitoring method and system and a storage medium, and relates to the technical field of monitoring. The method comprises the following steps: acquiring first real-time image information acquired by an image acquisition device at the same moment and real-time attitude data of the image acquisition device acquired by an inertial sensor; based on the first real-time image information, target displacement data of the current position of the monitoring target relative to the corresponding standard monitoring target position are determined; based on the real-time attitude data, determining attitude change data of a current attitude of the image acquisition device relative to a corresponding standard attitude; obtaining a first attitude observation error between the image acquisition device and the monitoring target based on an imaging geometrical relationship between the monitoring target and the image acquisition device and the attitude change data; and based on the first attitude observation error, correcting the target displacement data to obtain effective target displacement data. The accuracy of displacement monitoring can be improved.

Description

Technical Field

[0001] The present application relates to the field of monitoring technologies, and in particular, to a visual displacement monitoring method, system, and storage medium. Background Art

[0002] The displacement or deflection of large structures such as bridges, tunnels, and dams is often closely related to their bearing capacity, which can intuitively reflect the structural performance of the facilities. Therefore, it is an important indicator in the current structural health monitoring. Among them, the visual displacement monitoring method is as follows: target marks are arranged on the surface of the area to be monitored of large structures such as bridges, and visual sensors such as cameras are arranged in stable fixed areas such as bridge piers. By means of the camera photographing the target marks, the displacement / deflection changes of large structures such as bridges are detected in real time.

[0003] However, in the related technologies, during the actual long-term use of visual sensors such as monitoring cameras, due to factors such as wind force and loosening of the fixed structure, there may be a phenomenon of attitude change caused by short-term vibration or a phenomenon of slow change in attitude over a long time, resulting in a problem of decreased monitoring accuracy. Summary of the Invention

[0004] The main purpose of the present application is to provide a visual displacement monitoring method, system, and storage medium, aiming to solve the technical problem that visual displacement monitoring is affected by attitude changes and is inaccurate.

[0005] To achieve the above purpose, the present application provides a visual displacement monitoring method, including:

[0006] Obtain the first real-time image information collected by an image acquisition device at the same moment, and the real-time attitude data of the image acquisition device collected by an inertial sensor; the image acquisition device is fixedly arranged in a fixed area on one side of the area to be monitored for deformation, and a monitoring target mark is fixedly arranged in the area to be monitored for deformation;

[0007] Based on the first real-time image information, determine the target displacement data of the current position of the monitoring target mark relative to the corresponding standard monitoring target mark position;

[0008] Based on the real-time attitude data, determine the attitude change data of the current attitude of the image acquisition device relative to the corresponding standard attitude;

[0009] Based on the imaging geometric relationship between the monitoring target mark and the image acquisition device and the attitude change data, obtain the first attitude observation error between the image acquisition device and the monitoring target mark;

[0010] Based on the first attitude observation error, correct the target displacement data to obtain effective target displacement data.

[0011] In a possible embodiment of the present application, based on the first attitude observation error, the target displacement data is corrected to obtain effective target displacement data, including:

[0012] Based on the first real-time image information, determine the reference displacement data of the reference target relative to the standard reference position; the reference target is fixedly arranged in the other fixed area on the other side of the deformation area to be monitored, and the monitoring target and the reference target are included in the picture of any frame of image collected by the image acquisition device;

[0013] Based on the imaging geometric relationship between the reference target and the image acquisition device and the attitude change data, obtain the second attitude observation error between the image acquisition device and the reference target;

[0014] Based on the difference between the reference displacement data and the second attitude observation error, determine the displacement observation error between the image acquisition device and the monitoring target;

[0015] Based on the displacement observation error and the first attitude observation error, correct the target displacement data to obtain effective target displacement data.

[0016] In a possible embodiment of the present application, based on the imaging geometric relationship between the monitoring target and the image acquisition device and the attitude change data, obtain the first attitude observation error between the image acquisition device and the monitoring target, including:

[0017] Based on the first ideal spatial distance information, attitude change data between the monitoring target and the image acquisition device, and Formula 1, obtain the first attitude observation error between the image acquisition device and the monitoring target;

[0018] Formula 1 is: ΔD ir = L i ·sinΔθ;

[0019] Wherein, L i is the first ideal spatial distance information, ΔD ir is the first attitude observation error, and Δθ is the attitude change data;

[0020] Or,

[0021] Based on the proportional relationship between the imaging areas of the monitoring target and the reference target in the first real-time image information, the second ideal spatial distance between the image acquisition device and the reference target, the attitude change data, and Formula 2, obtain the first attitude observation error between the image acquisition device and the monitoring target;

[0022] Formula 2 is:

[0023] Wherein, ΔD ir is the first attitude observation error, d iis the size of the monitoring target imaging area for the i-th monitoring target, d b is the size of the reference target imaging area, L b is the second ideal spatial distance, and Δθ is the attitude change data.

[0024] In a possible embodiment of the present application, the inertial sensor is fixedly arranged on the image acquisition device through a rigid body connection.

[0025] In a possible embodiment of the present application, the method further includes:

[0026] Obtain the second real-time image information collected by the image acquisition device;

[0027] Extract the actual imaging picture of the region of interest from the second real-time image information; wherein, the monitoring target has a region of interest;

[0028] Based on the imaging difference between the actual imaging picture and the ideal imaging picture of the region of interest, adjust the imaging parameters of the image acquisition device and / or the supplementary light parameters of the monitoring target, so that the imaging difference between the adjusted second real-time image information and the ideal imaging picture is less than the preset imaging difference.

[0029] In a possible embodiment of the present application, based on the imaging difference between the actual imaging picture and the ideal imaging picture, adjusting the imaging parameters of the image acquisition device and / or the supplementary light parameters of the monitoring target includes:

[0030] Perform image registration on the actual imaging picture and the ideal imaging picture to determine the matching pixel point pairs; wherein, the pixel point pairs include the source pixel points of the actual imaging picture and the matching pixel points of the ideal imaging picture;

[0031] Based on the imaging difference between the corresponding pixels of the actual imaging picture and the ideal imaging picture, adjust the imaging parameters of the image acquisition device and / or the supplementary light parameters of the monitoring target.

[0032] In a possible embodiment of the present application, performing image registration on the actual imaging picture and the ideal imaging picture to determine the matching pixel point pairs includes:

[0033] Based on at least 4 first preset feature points in the ideal imaging picture and at least 4 second preset feature points respectively matching the first preset feature points in the actual imaging picture, determine the homography transformation matrix between the actual imaging picture and the ideal imaging picture;

[0034] Based on the homography transformation matrix, determine the matching pixel points respectively matching the source pixel points in the actual imaging picture from the ideal imaging picture, and obtain a plurality of pixel point pairs.

[0035] In a possible embodiment of the present application, a plurality of monitoring targets are fixedly arranged in the deformation area to be monitored, and each frame of image collected by the image acquisition device includes a plurality of monitoring targets;

[0036] Based on the imaging difference between the actual imaging pictures of all monitoring targets and the ideal imaging pictures of the region of interest, adjust the imaging parameters of the image acquisition device and / or the supplementary lighting parameters of the monitoring targets.

[0037] In a second aspect, the present application further provides a visual displacement monitoring system, including:

[0038] At least one monitoring target, which is fixedly arranged in the deformation area to be monitored;

[0039] An image sensor, which is fixedly arranged in a fixed area on one side of the deformation area to be monitored; and each frame of image collected by the image acquisition device includes a plurality of monitoring targets;

[0040] An inertial sensor, which is used to collect the real-time attitude data of the image acquisition device;

[0041] A displacement calculation device, which is connected to both the image sensor and the inertial sensor, and the displacement calculation device includes a processor, a memory and a computer program. When the computer program is executed by the processor, the steps of the visual displacement monitoring method are realized.

[0042] In a possible embodiment of the present application, a reference target is further included, which is fixedly arranged in a fixed area on the other side of the deformation area to be monitored, and each frame of image collected by the image acquisition device includes the monitoring target and the reference target.

[0043] In a third aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the visual displacement monitoring method are realized.

[0044] A visual displacement monitoring method proposed in an embodiment of the present application obtains the first real-time image information collected by an image acquisition device and the real-time attitude data of the image acquisition device collected by an inertial sensor. The image acquisition device is fixedly arranged in a fixed area on one side of the deformation area to be monitored, and a monitoring target is fixedly arranged in the deformation area to be monitored. Based on the first real-time image information, the target displacement data of the current position of the monitoring target relative to the corresponding standard monitoring target position is determined. Based on the real-time attitude data, the attitude change data of the current attitude of the image acquisition device relative to the corresponding standard attitude is determined. Based on the imaging geometric relationship between the monitoring target and the image acquisition device and the attitude change data, the first attitude observation error between the image acquisition device and the monitoring target is obtained. Based on the first attitude observation error, the target displacement data is corrected to obtain effective target displacement data.

[0045] It is not difficult to see that when the embodiment of the present application monitors the displacement of the area to be monitored of a large structure, in addition to obtaining the first real-time image information collected by the image acquisition device, it also collects the real-time attitude data of the image acquisition device through the inertial sensor, so as to measure the attitude change of the image acquisition device in real time, and then the target displacement data of the monitoring target can be corrected accordingly to improve the accuracy of displacement monitoring. Description of the Drawings

[0046] Figure 1 It is a schematic diagram of the system architecture of the visual displacement monitoring system of the present application;

[0047] Figure 2 It is a schematic diagram of the structure of the displacement calculation device of the present application;

[0048] Figure 3 It is a schematic flowchart of the first embodiment of the visual displacement monitoring method of the present application;

[0049] Figure 4 It is a schematic diagram of the attitude change of the image acquisition device in the visual displacement monitoring system of the present application;

[0050] Figure 5 It is a schematic flowchart of the second embodiment of the visual displacement monitoring method of the present application;

[0051] Figure 6 It is a schematic diagram of the position change of the image acquisition device in the visual displacement monitoring system of the present application;

[0052] Figure 7 It is a schematic flowchart of the third embodiment of the visual displacement monitoring method of the present application;

[0053] Figure 8 It is a schematic diagram of imaging effect adjustment in the visual displacement monitoring system of the present application;

[0054] Figure 9This is a registration schematic diagram of the actual imaging screen and the ideal imaging screen in the visual displacement monitoring system of the present application.

[0055] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. Specific embodiments

[0056] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0057] In the monitoring scheme for the displacement / deflection, etc. of large structures, the non-contact displacement monitoring scheme based on machine vision has the advantages of easy layout, high precision, and support for multi-point measurement. Specifically, the visual displacement monitoring method is as follows: target marks are arranged on the surface of the area to be monitored of large structures such as bridges, and visual sensors such as cameras are arranged in stable fixed areas such as bridge piers. By means of the camera photographing the target marks, the displacement / deflection changes of large structures such as bridges are detected in real time.

[0058] Among them, a related monitoring scheme is that the monitoring system includes three parts: a monitoring camera, a measurement target, and a reference target. During the displacement measurement, by calculating the relative displacement between the measurement target and the reference target, the influence of the camera's own movement on the displacement monitoring is compensated. However, the disadvantage of this monitoring scheme is that only the position change of the camera is considered. When the camera's attitude changes, there is still a problem of insufficient displacement monitoring accuracy.

[0059] Therefore, the embodiment of the present application provides a solution. This solution collects the real-time attitude data of the image acquisition device through an inertial sensor rigidly connected to the image acquisition device, thereby measuring the attitude change of the image acquisition device in real time, and then the target displacement data of the monitoring target can be corrected to improve the accuracy of displacement monitoring.

[0060] The inventive concept of the present application will be further elaborated below with some specific embodiments.

[0061] Refer to Figure 1 , Figure 1 This is a schematic diagram of the system architecture of the visual displacement monitoring system involved in the embodiment of the present application.

[0062] In this embodiment, the visual displacement monitoring system includes: at least one monitoring target 2, an image sensor, an inertial sensor, and a displacement calculation device.

[0063] Among them, the monitoring target 2 is fixedly arranged in the deformation area to be monitored; the image sensor is fixedly arranged in a fixed area on one side of the deformation area to be monitored; and the picture of any frame of image collected by the image acquisition device 1 includes a plurality of monitoring targets 2; the inertial sensor is used to collect the real-time attitude data of the image acquisition device 1; the displacement calculation device is connected to both the image sensor and the inertial sensor, and the displacement calculation device includes a processor, a memory and a computer program, and when the computer program is executed by the processor, the steps of the visual displacement monitoring method are realized.

[0064] Specifically, taking a large structure as a bridge as an example for specific illustration. At this time, the monitoring target 2 is an active target and is fixedly arranged on the lower surface of the bridge span structure. And the monitoring target 2 can include a plurality of them, which can be arranged at intervals along the length direction of the bridge span structure. The image acquisition device 1 is fixedly arranged at a relatively fixed position such as a pier on one side of the bridge span structure. The image sensor can be an all-pass camera, which can realize all-pass of visible light and infrared light. The inertial sensor includes a gyroscope and an accelerometer, which can measure the rotational angular velocity and displacement acceleration of the device itself. The inertial sensor can be rigidly connected to the all-pass camera, so that the real-time attitude of the all-pass camera can be measured. It is not difficult to see that the inertial sensor is rigidly connected to the all-pass camera, which is not only simple and convenient to install, but also convenient for subsequent maintenance. The reference target 3 can also be an active target and is fixed in another relatively fixed area visible to the camera, such as another pier.

[0065] Among them, the active target can be a visible light target or an infrared target. In a specific embodiment, since there is a certain light pollution phenomenon in the visible light target, the active target can be an infrared target to avoid the light pollution phenomenon.

[0066] The displacement calculation device is connected to the inertial sensor and the image sensor in a wired or wireless manner. As Figure 2 shown, the displacement calculation device can include a processor 1001, such as a CPU, a user interface 1003, a memory 1005, and a communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. Optionally, the user interface 1003 can also be a display screen (Display), an input unit such as a keyboard (Keyboard), etc. The memory 1005 can be a high-speed RAM memory, or a stable memory (non-volatile memory), such as a disk memory. Optionally, the memory 1005 can also be a storage device independent of the aforementioned processor 1001.

[0067] It can be understood that the displacement calculation device may further include a network interface 1004, and the network interface 1004 may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface). Optionally, the displacement calculation device may further include an RF (Radio Frequency) circuit, sensors, an audio circuit, a WiFi module, and so on.

[0068] Those skilled in the art can understand that Figure 2 the structure of the displacement calculation device shown in does not constitute a limitation on the displacement calculation device, and it may include more or fewer components than shown in the figure, or combine some components, or have different component arrangements.

[0069] It is worth mentioning that in some specific embodiments, the displacement calculation device may also be integrated with the image acquisition device 1.

[0070] Based on the above hardware system structure but not limited to the above hardware system structure, the first embodiment of the visual displacement monitoring method of the present application is proposed. Refer to Figure 3 , Figure 3 which is a schematic flowchart of the first embodiment of the visual displacement monitoring method of the present application.

[0071] It should be noted that although the logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than here.

[0072] In this embodiment, a visual displacement monitoring method includes:

[0073] Step S100, obtaining the first real-time image information collected by the image acquisition device and the real-time attitude data of the image acquisition device collected by the inertial sensor.

[0074] Among them, the image acquisition device is fixedly arranged in a fixed area on one side of the deformation area to be monitored, and a monitoring target is fixedly arranged in the deformation area to be monitored.

[0075] Specifically, the execution subject of this embodiment is the displacement calculation device in the visual displacement monitoring system. The displacement calculation device is connected to the image acquisition device and the inertial sensor through wired or wireless connections. The image acquisition device sends the first real-time image information collected in real time to the displacement calculation device, and during this process, the inertial sensor also sends the real-time attitude data collected in real time to the displacement calculation device. In an example, the inertial sensor is fixedly arranged on the image acquisition device through a rigid body connection.

[0076] The displacement calculation device can match the acquired first real-time image information and real-time attitude data according to their respective corresponding timestamps, so as to determine the first real-time image information reflecting the deformation situation of the deformation area to be monitored at the same moment, and the real-time attitude data reflecting the attitude change of the image acquisition device.

[0077] Step S200: Based on the first real-time image information, determine the target displacement data of the current position of the monitoring target relative to the corresponding standard monitoring target position.

[0078] Step S300: Based on the real-time attitude data, determine the attitude change data of the current attitude of the image acquisition device relative to the corresponding standard attitude.

[0079] The first real-time image information can reflect the current position of the monitoring target, so as to compare the current position with the standard monitoring target position to determine the target displacement data of the monitoring target relative to the corresponding standard monitoring target position.

[0080] Specifically, before the visual displacement monitoring system starts to run, the staff needs to perform initial calibration on the visual displacement monitoring system to adjust and calibrate the specific position, initial attitude, camera parameters, etc. of the image acquisition device, and adjust and calibrate the specific position, supplementary light parameters, etc. of each monitoring target, so that the visual displacement monitoring system meets the operating conditions to start running. After the initial calibration, a moment is used as the reference moment. At the reference moment, the reference image information after initial calibration is acquired through the image acquisition device, and at this reference moment, the reference attitude information after initial calibration is acquired through the inertial sensor. The position of the camera at this time, that is, the standard camera position, can also be recorded. The reference image information can reflect the standard monitoring target position of the monitoring target, and the reference attitude information can reflect the standard attitude of the image acquisition device. Then, the visual displacement monitoring system can start to run. And before the visual displacement monitoring system runs, the displacement calculation device can save the horizontal distance and actual size between the calibrated image acquisition device and each monitoring target. Such as the horizontal distance L i between the i-th monitoring target, and the actual size D i of the i-th monitoring target.

[0081] In this way, after the first real-time image information is acquired, the first real-time image information can be compared with the reference image information to determine the image displacement of the monitoring target as Δd i . And the imaging size of the i-th monitoring target in the first real-time image information can be identified as d i . According to the actual size D i of the i-th monitoring target and the imaging size d iBased on the proportional relationship between them, the target displacement data ΔD of the i-th monitoring target can be determined. i and the image displacement Δd i Based on the proportional relationship between them, the target displacement data ΔD is then calculated according to Formula 1. i . Among them, Formula 1 is:

[0082] The displacement calculation device can compare the real-time attitude data with the attitude data of the standard attitude, and the difference between the two is the attitude change data. It can be understood that since the vision displacement monitoring system is often used to observe the deflection / displacement changes of large structures such as bridges, therefore, the main factor affecting the observation of the deflection / displacement changes is the pitch angle change, that is, the attitude change data Δθ can be the pitch angle change data.

[0083] Of course, it can be understood that in the actual environment, the camera is affected by external factors such as wind, and the specific attitude change of the image acquisition device may be tilting up or down. Therefore, the positive and negative attitude change data can be used for distinction. Specifically, the following takes the vertical upward direction as the positive direction and the vertical downward direction as the negative direction for specific illustration. When the image acquisition device tilts down, the attitude change of the image acquisition device will cause the observed target displacement data to become larger, and this part of the observation error needs to be subtracted during correction. When the image acquisition device tilts up, the attitude change of the graphic acquisition device will cause the observed target displacement data to become smaller, and this part of the observation error needs to be compensated during correction. Thus, the downward tilt of the image acquisition device can be regarded as a negative angle change, and the upward tilt can be regarded as a positive angle change.

[0084] Step S400: Based on the imaging geometric relationship between the monitoring target and the image acquisition device and the attitude change data, obtain the first attitude observation error between the image acquisition device and the monitoring target.

[0085] Refer to Figure 4 , after determining the attitude change data, the camera attitude change geometric relationship can be constructed according to the imaging geometric relationship and the attitude change data (i.e., the pitch angle) between the monitoring target and the image acquisition device. Then, based on this camera attitude change geometric relationship, the first attitude observation error between the image acquisition device and the monitoring target is calculated using trigonometric functions.

[0086] Specifically, in a possible implementation manner, when the displacement calculation device executes step S400, it can obtain the first attitude observation error between the image acquisition device and the monitoring target based on the first ideal spatial distance information between the monitoring target and the image acquisition device and the attitude change data.

[0087] It can be expressed as Formula 1: ΔD ir = L i·sinΔθ;

[0088] wherein, L i is the first ideal spatial distance information between the monitoring target and the image acquisition device, that is, after initial calibration, the distance between the monitoring target and the image acquisition device measured at the reference time. ΔD ir is the first attitude observation error. It can be understood that in the visual displacement monitoring system, the attitude change of the image acquisition device is extremely small. For example, in one example, Δθ < 0.1. And when the angle is extremely small, the sine value of the angle is equal to the value of the angle itself. Therefore, ΔD ir = L i ·sinΔθ is approximately: ΔD ir = L i ·Δθ.

[0089] Step S500: Based on the first attitude observation error, correct the target displacement data to obtain effective target displacement data.

[0090] After calculating the first attitude observation error ΔD ir and the target displacement data ΔD i , the effective target displacement data ΔD im can be determined. Wherein, ΔD im = ΔD i + ΔD ir .

[0091] Of course, it can be understood that when the image acquisition device tilts downward, Δθ < 0, and at this time, ΔD ir < 0.

[0092] It can be seen that in this embodiment, when monitoring the displacement of the area to be monitored of the large structure, in addition to obtaining the first real-time image information collected by the image acquisition device, the real-time attitude data of the image acquisition device is also collected by the inertial sensor rigidly connected to the image acquisition device, so as to measure the attitude change of the image acquisition device in real time, and then the target displacement data of the monitoring target can be corrected to improve the accuracy of displacement monitoring. In addition, the inertial sensor is rigidly connected to the image acquisition device, so that the accuracy of the real-time attitude data collected by it is relatively high, further improving the accuracy of displacement monitoring.

[0093] Based on the above embodiment, a second embodiment of the visual displacement monitoring method of the present application is proposed. Refer to Figure 5 , Figure 5 which is the flow chart of the second embodiment of the visual displacement monitoring method in this embodiment.

[0094] In this embodiment, step S500 specifically includes:

[0095] Step S510: Based on the first real-time image information, determine the reference displacement data of the reference target relative to the standard reference position.

[0096] Step S520: Based on the imaging geometric relationship between the reference target and the image acquisition device and the attitude change data, obtain the second attitude observation error between the image acquisition device and the reference target.

[0097] Step S530: Based on the difference between the reference displacement data and the second attitude observation error, determine the displacement observation error between the image acquisition device and the monitoring target.

[0098] Step S540: Based on the displacement observation error and the first attitude observation error, correct the target displacement data to obtain the effective target displacement data.

[0099] Specifically, for the image acquisition device in the visual displacement monitoring system, although it is fixedly installed in a fixed area such as a bridge pier, during factors such as wind or vibration caused by vehicles passing during the normal operation of the bridge, it will inevitably cause short-term vibrations of the image acquisition device, or loosening of the fixing structure of the image acquisition device will also cause slow changes in the position of the image acquisition device. Therefore, it is necessary to compensate for the influence of the self-movement of the image acquisition device in the vertical direction on displacement monitoring during visual monitoring.

[0100] At this time, in the visual displacement monitoring system, a reference target is installed in a fixed area such as a bridge pier on the other side of the spanning structure of the bridge. The picture of any frame of the image collected by the image acquisition device includes the picture of the monitoring target, that is, the monitoring target imaging area and the picture of the reference target, that is, the reference target imaging area. And during initial calibration, the specific position of the reference target can be calibrated, and at the reference moment, the second ideal spatial distance L between the reference target and the image acquisition device is measured and saved. b Of course, in this embodiment, the reference image information can also reflect the standard reference position of the reference target.

[0101] Therefore, after receiving the first real-time image information, the displacement calculation device can compare the first real-time image information with the reference image information to determine the image displacement Δd of the reference target. b And the imaging size d of the reference target in the first real-time image information can be recognized. b According to the proportional relationship between the actual size D of the reference target and the imaging size d of the reference target. b The proportional relationship between the reference displacement data ΔD of the reference target and the image displacement Δd can be determined, and then the reference displacement data ΔD can be calculated accordingly. b And the image displacement Δd. b The proportional relationship between them, and then the reference displacement data ΔD is calculated based on this. b Among them,

[0102] It is understandable that since the reference target is fixedly set in a fixed area, ideally the reference target does not change in the view of the image acquisition device. At this time, it can be considered that the reference displacement data of the reference target includes at least two parts, namely the observed displacement caused by the attitude change of the image acquisition device and the observed displacement ΔD caused by the position change of the image acquisition device bt . Among them, when the reference target is regarded as fixed ideally, the observed displacement caused by the attitude change of the camera is the second attitude observation error ΔD between the image acquisition device and the reference target br . According to the imaging geometric relationship and attitude change data between the reference target and the image acquisition device, it is not difficult to obtain ΔD br = L b ·sinΔθ. Similarly, it is understandable that in the visual displacement monitoring system, the attitude change of the image acquisition device is extremely small. For example, in one example, Δθ < 0.1. And when the angle is extremely small, the sine value of the angle is equal to the value of the angle itself. Therefore, ΔD br = L b ·sinΔθ is approximately: ΔD br = L b ·Δθ.

[0103] Thus, the observed displacement ΔD caused by the position change of the image acquisition device can be calculated according to ΔD bt = ΔD b - ΔD br . Refer to bt . The observed displacement caused by the position change between the image acquisition device and any monitoring target is equal to ΔD Figure 6 . Thus, the displacement observation error ΔD bt can be determined. ΔD it , ΔD it = ΔD bt = ΔD b - ΔD br .

[0104] After determining the displacement observation error ΔD it , the effective target displacement data ΔD im can be determined. Among them, ΔD im = ΔD i + ΔD ir + ΔD it .

[0105] Of course, it can be understood that the displacement of the image acquisition device may be vibration, that is, it may be a vertical upward movement or a vertical downward movement relative to the position of the standard camera. Specifically, when the image acquisition device moves vertically downward, it will cause the observed target displacement data to become larger, and this part of the observation error needs to be subtracted during correction. When the image acquisition device moves vertically upward, the attitude change of the image acquisition device will cause the observed target displacement data to become smaller, and this part of the observation error needs to be compensated during correction. Thus, the ΔD generated by the vertical downward movement of the image acquisition device it can be regarded as negative data, while the ΔD generated by the vertical upward movement it is regarded as positive data.

[0106] That is, when the image acquisition device pitches downward and moves vertically downward relative to the position of the standard camera, Δθ < 0. At this time, ΔD ir < 0, ΔD it < 0.

[0107] It is not difficult to see that in this embodiment, based on the result of the camera attitude change and the displacement of the reference target under the camera view, the target displacement data of each measured target is jointly corrected, thereby improving the accuracy of displacement monitoring.

[0108] Among them, the observation error caused by the attitude change of the image acquisition device is proportional to the distance between the image acquisition device and the measured target, and is also proportional to the imaging size of the monitoring target in the image acquisition device. Therefore, in a possible implementation manner, when the displacement calculation device executes step S400, it can obtain the first attitude observation error between the image acquisition device and the monitoring target based on the proportional relationship between the imaging areas of the monitoring target and the reference target in the first real-time image information, the second ideal spatial distance between the image acquisition device and the reference target, and the attitude change data.

[0109] That is Thus, it can be converted to obtain: Of course, when Δθ is extremely small, formula two can be obtained: Among them, the size of the imaging area of the monitoring target, that is, the imaging size of the i-th monitoring target, and the size of the imaging area of the monitoring target is d i . The size of the imaging area of the reference target, that is, the imaging size of the reference target, and the size of the imaging area of the monitoring target is d b .

[0110] Based on the above embodiment, the third embodiment of the visual displacement monitoring method of the present application is proposed. Refer to Figure 7 , Figure 7 which is the flowchart of the third embodiment of the visual displacement monitoring method in this embodiment.

[0111] It should be noted that although the logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than here.

[0112] In this embodiment, the visual displacement monitoring method includes:

[0113] Step S10: Obtain the second real-time image information collected by the image acquisition device.

[0114] Step S20: Extract the actual imaging picture of the region of interest from the first real-time image information.

[0115] Among them, the monitoring target has a region of interest.

[0116] Step S30: Based on the imaging difference between the actual imaging picture and the ideal imaging picture of the region of interest, adjust the imaging parameters of the image acquisition device and / or the supplementary light parameters of the monitoring target, so that the imaging difference between the adjusted second real-time image information and the ideal imaging picture is less than the preset imaging error.

[0117] It can be understood that for the visual displacement monitoring system, its input is the image collected by the image acquisition device. Therefore, the imaging effect of the image is an important influencing factor for the accuracy of visual displacement monitoring. And the imaging effect of the image is related to lighting, the imaging parameters of the image acquisition device, and the supplementary light parameters of the monitoring target. For large structures such as bridges, lighting is greatly affected by natural ambient light, and natural ambient light changes continuously according to time. For example, in the evening, the visual displacement monitoring system is in a low-illumination environment. At this time, the clarity of the first real-time image information collected by the image acquisition device is low, resulting in blurred imaging, and further reducing the accuracy of subsequent calculation results (such as reference displacement data or target displacement data, etc.).

[0118] Therefore, in this embodiment, the imaging parameters of the image acquisition device and / or the supplementary light parameters of the monitoring target are adjusted through steps S0 - S30 to compensate for the influence of environmental illumination on the visual displacement monitoring effect.

[0119] Specifically, the displacement calculation device can execute step S100 in real time to obtain the real-time image information collected by the image acquisition device in real time, and synchronously execute the subsequent steps S20 - S30 and steps S200 - S500. At this time, the collected real-time image information is the first real-time image information and also the second real-time image information.

[0120] Of course, the displacement calculation device can also periodically execute steps S20 - S30 after each execution of step S100 according to a preset adjustment period. That is, at the adjustment moment corresponding to the preset adjustment period, the real-time image information collected by the image acquisition device is both the first real-time image information and the second real-time image information. And within the time period between adjacent adjustment moments, the real-time image information collected by the image acquisition device is the first real-time image information. In one example, the preset adjustment period can be 1 hour, that is, steps S20 - S30 are executed every 1 hour to cope with the influence of ambient light change on the imaging of the detection target.

[0121] Specifically, referring to Figure 8 , the monitoring target is configured with ROI (region of interest) such as a target pattern, corner points, and prominent identifiers. Therefore, the imaging pictures of the region of interest are included in both the reference image information and the first real-time image information during the subsequent system operation. Among them, in some embodiments, image recognition is performed on the reference image information to identify the imaging picture of the ROI region, and this imaging picture can be used as the ideal imaging picture of the ROI region. Or, in some other embodiments, the design drawing or prior target image of the ROI region can be used as the ideal imaging picture.

[0122] When the displacement calculation device executes step S20, it can identify and extract the actual imaging picture of the ROI region from the first real-time image information based on an image recognition algorithm. Then, the actual imaging picture is compared with the ideal imaging picture to determine the imaging difference between the actual imaging picture and the ideal imaging picture of the ROI region. When the imaging difference is greater than the preset imaging error, it can be considered that the illuminance has seriously affected the imaging effect of the image acquisition device, thereby affecting the accuracy of the subsequent processing process. Thus, the imaging parameters of the image acquisition device and / or the supplementary light parameters of the monitoring target can be adjusted according to the imaging difference, so that the adjusted actual imaging picture of the monitoring target approaches the ideal imaging picture in terms of the imaging effect dimension, thereby improving the imaging effect under the current ambient illuminance.

[0123] Specifically, when the displacement calculation device executes step S30, it can adjust the imaging parameters of the image acquisition device and / or the supplementary light parameters of the monitoring target according to a preset step size, and then return to execute steps S10 - S30 until the imaging difference between the actual imaging picture of the ROI region in the collected second real-time image information and the ideal imaging picture is less than the preset imaging error, that is, the adjusted actual imaging picture of the monitoring target approaches the ideal imaging picture in terms of the imaging effect dimension, thereby reducing the influence of ambient light on displacement monitoring.

[0124] Of course, the displacement calculation device can also maintain a mapping relationship table between an imaging difference and adjustment parameters (imaging parameters of the image acquisition device and / or fill light parameters of the monitoring target). This mapping relationship table can be established before the system runs. For example, during the trial operation, an imaging difference and parameter adjustment test are carried out. That is, after obtaining real-time image information, the imaging parameters of the image acquisition device and / or the fill light parameters of the monitoring target are adjusted according to a preset step size, and the steps of obtaining real-time image information and adjusting the imaging parameters of the image acquisition device and / or the fill light parameters of the monitoring target according to the preset step size are executed in a loop until the imaging difference between the actual imaging picture and the ideal imaging picture of the region of interest in the acquired real-time image information is less than the preset imaging error. According to the total step size (i.e., adjustment parameter) adjusted during this loop process, the mapping relationship between the real-time image information initially obtained during this loop process and the adjustment parameter is obtained. In this way, when the system is officially running, the adjustment parameter corresponding to the current imaging difference can be directly obtained according to this mapping relationship, and the imaging parameters of the image acquisition device and / or the fill light parameters of the monitoring target are adjusted according to this adjustment parameter, so that when step S10 or step S100 is executed at the next moment, the imaging difference between the actual imaging picture and the ideal imaging picture of the region of interest in the second real-time image information is less than the preset imaging error.

[0125] It is worth mentioning that the displacement calculation device can adjust only the camera parameters of the image acquisition device, such as exposure parameters or gain parameters, according to the imaging difference. Of course, it can also adjust only the fill light parameters such as the fill light intensity of the monitoring target according to the imaging difference. Of course, it can also adjust the camera parameters of the image acquisition device, such as exposure parameters or gain parameters, and the fill light intensity and other fill light parameters of the monitoring target according to the imaging difference.

[0126] It is not difficult to see that in this embodiment, by adjusting the imaging parameters of the image acquisition device and / or the fill light parameters of the monitoring target, the system state is adjusted to make the actual target imaging effect consistent with the target imaging effect, thereby reducing the influence of ambient light on displacement monitoring.

[0127] Among them, in a specific embodiment, step S30 specifically includes:

[0128] Step S31: Perform image registration on the actual imaging picture and the ideal imaging picture to determine the matching pixel point pairs.

[0129] Among them, the pixel point pairs include the source pixel points of the actual imaging picture and the matching pixel points of the ideal imaging picture.

[0130] Step S32: Based on the imaging difference between the corresponding pixels of the actual imaging picture and the ideal imaging picture of the region of interest, adjust the imaging parameters of the image acquisition device and / or the fill light parameters of the monitoring target.

[0131] Please refer to Figure 9 , in this specific embodiment, feature points (such as Blob feature points) are extracted from the actual imaging screen and the ideal imaging screen of the ROI region respectively. The actual imaging screen and the ideal imaging screen are registered by means of feature point matching. The source pixel points of the actual imaging screen and the matching pixel points of the ideal imaging screen that match them are determined in the two screens, and pixel point pairs are obtained. At this time, the image parameter difference between the source pixel point and the matching pixel point in the pixel point pair can be used as the imaging difference between the corresponding pixels of the actual imaging screen and the ideal imaging screen.

[0132] Among them, when the displacement calculation device executes step S31, it can determine the homography transformation matrix between the actual imaging screen and the ideal imaging screen based on at least 4 first preset feature points in the ideal imaging screen and at least 4 second preset feature points in the actual imaging screen that respectively match the first preset feature points; based on the homography transformation matrix, the matching pixel points that respectively match the source pixel points in the actual imaging screen are determined from the ideal imaging screen, and multiple pixel point pairs are obtained.

[0133] Specifically, the first preset feature points and the second preset feature points can be Blob feature points of the ROI region such as a target pattern, corner points, prominent marks, etc. At least 4 first preset feature points need to be identified from the ideal imaging screen, and at least 4 second preset feature points that respectively match the at least 4 first preset feature points are identified from the actual imaging screen. Then, the homography transformation matrix for transforming the actual imaging screen into the ideal imaging screen is determined through the coordinates of each first preset feature point and the coordinates of the second feature point that matches it. After determining the homography transformation matrix, the corresponding relationship between all the pixels of the actual imaging screen and the ideal imaging screen can be obtained, thereby determining multiple pixel point pairs.

[0134] It can be understood that the imaging difference between the actual imaging screen and the ideal imaging screen can be taken as the imaging difference between the pixel pairs to which some of the image feature pixels belong, and the state of the system can be adjusted accordingly, that is, the imaging parameters of the image acquisition device and / or the fill light parameters of the monitoring target are adjusted.

[0135] In addition, as an option in this embodiment, when calculating the homography transformation matrix, if there is no perspective transformation or affine transformation between the actual imaging screen transformation and the ideal imaging screen, at this time, the scaling ratio between the actual imaging screen and the ideal imaging screen can be obtained based on the proportional relationship between the first size and the second size. Based on the scaling ratio, the actual imaging screen is scaled to obtain the scaled actual imaging screen. The scaled actual imaging screen and the ideal imaging screen are registered to obtain multiple pixel point pairs.

[0136] Wherein, the first dimension is the dimension between any two source pixels among a plurality of pixel pairs, and the second dimension is the dimension between the corresponding two matching pixels.

[0137] Specifically, in this selection, the scaling is a homography transformation in a special scenario. The displacement calculation device performs image registration and determines feature point 1 of the actual imaging screen and feature point 3 of the ideal imaging screen. Feature point 2 in the actual imaging screen and feature point 4 in the ideal imaging screen form 2 groups of pixel pairs. In the actual imaging screen, the image distance between feature point 1 and feature point 2 is the first dimension, and the image distance between feature point 3 and feature point 4 is the second dimension. The proportional relationship between the first dimension and the second dimension is used as the scaling ratio between the actual imaging screen and the ideal imaging screen, so as to scale the actual imaging screen to obtain the scaled actual imaging screen. At this time, the scaled actual imaging screen and the ideal imaging screen have the same size, and the pixels with the same coordinates in the two are the corresponding pixels. For example, the pixel at the i-th row and j-th column in the ideal imaging screen and the pixel at the i-th row and j-th column in the scaled actual imaging screen correspond to each other. Then, a difference equation between the scaled actual imaging screen and the ideal imaging screen can be established accordingly. In one example, this difference equation is a pixel brightness difference equation.

[0138] For example: The difference equation is constructed as:

[0139]

[0140] Wherein, e = (I rij - I oij ), I oij represents the brightness value of the pixel at the i-th row and j-th column in the ideal imaging screen, and I rij represents the brightness value of the pixel at the i-th row and j-th column in the scaled actual imaging screen.

[0141] Of course, it can be understood that the actual imaging screen is related to the imaging parameter P c of the image acquisition device and / or the supplementary light parameter P m of the monitoring target, and can be expressed as I rij = f(P c , P m ). Of course, the difference equation between the scaled actual imaging screen and the ideal imaging screen can also be a difference equation in dimensions such as the statistical information of the pixel brightness in the region (such as the brightness histogram statistical information), or the difference equation can also be defined in other parametric / non-parametric forms that can measure the imaging difference between the two. This embodiment does not limit this.

[0142] Therefore, in this embodiment, by adjusting the system state based on the imaging differences between all pixel points of the actual imaged picture after scaling and the ideal imaged picture, the imaging difference representation on which the system state adjustment depends can be made more accurate, thereby improving the accuracy of system state adjustment.

[0143] In addition, in the visual displacement monitoring system, a plurality of monitoring targets are fixedly arranged in the deformation area to be monitored, and each frame of image captured by the image acquisition device includes a plurality of monitoring targets.

[0144] At this time, the displacement calculation device can adjust the imaging parameters of the image acquisition device and / or the supplementary light parameters of the monitoring target based on the imaging differences between the actual imaged pictures of some of the monitoring targets and the ideal imaged picture of the region of interest.

[0145] Alternatively, it can also be that the displacement calculation device adjusts the imaging parameters of the image acquisition device and / or the supplementary light parameters of the monitoring target based on the imaging differences between the actual imaged pictures of all the monitoring targets and the ideal imaged picture of the region of interest.

[0146] Specifically, the difference equation is constructed as:

[0147]

[0148] Where n represents the number of monitoring targets, that is, in this embodiment, the second real-time image information includes the actual imaged pictures of n monitoring targets. By adjusting the system state based on the imaging differences between all pixel points of the actual imaged pictures of all the monitoring targets after scaling and the ideal imaged picture, the imaging difference representation on which the system state adjustment depends can be made more accurate, thereby improving the accuracy of system state adjustment.

[0149] It can be seen that the visual displacement monitoring solution provided by this application has the following beneficial effects:

[0150] (1) The system adjusts the imaging parameters or the supplementary light parameters of the active target based on the difference between the actual imaging and the ideal imaging of the target ROI area, so that the imaging effect of the target is consistent with the target. While reducing the difficulty of system layout, the anti-interference ability of the visual displacement monitoring system to ambient light can be improved, and the stability of the long-term displacement monitoring system can be enhanced.

[0151] (2) The inertial sensor is fixedly connected to the image acquisition device, and the attitude change of the image acquisition device is measured in real time based on the inertial sensor. Moreover, the attitude change of the image acquisition device is combined with the displacement monitoring result of the reference target to correct the displacements of each monitoring target in real time, thereby eliminating the displacement monitoring error introduced by the position and attitude change of the image acquisition device and improving the system accuracy.

[0152] In addition, an embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the visual displacement monitoring method as described above are implemented. Therefore, details will not be elaborated here. In addition, the beneficial effects of adopting the same method will not be described in detail either. For the technical details not disclosed in the embodiment of the computer-readable storage medium involved in the present application, please refer to the description of the method embodiment of the present application. By way of example, the program instructions can be deployed to be executed on a computing device, or on multiple computing devices located at one location, or on multiple computing devices distributed at multiple locations and interconnected through a communication network.

[0153] Those of ordinary skill in the art can understand that all or part of the processes in the above method embodiments can be completed by instructing relevant hardware through a computer program. The above program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above method embodiments. Among them, the above storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), or the like.

[0154] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the accompanying drawings of the device embodiments provided in the present application, the connection relationships between the modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art can understand and implement this without creative effort.

[0155] Through the description of the above embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general hardware. Of course, it can also be implemented by dedicated hardware including application specific integrated circuits, dedicated CPUs, dedicated memories, dedicated components, etc. Generally, functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structures for implementing the same function can also be various, such as analog circuits, digital circuits or dedicated circuits, etc. However, for this application, software program implementation is a better embodiment in more cases. Based on such an understanding, the technical solution of this application, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium, such as a floppy disk, USB flash drive, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disc of a computer, etc., and includes several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of various embodiments of this application.

[0156] The above are only the preferred embodiments of this application, and do not limit the protection scope of this application accordingly. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of this application, or directly or indirectly applied in other related technical fields, shall be included in the protection scope of this application by the same token.

Claims

1. A visual displacement monitoring method, characterized in that, Including: Obtaining first real-time image information collected by an image acquisition device at the same moment, and real-time attitude data of the image acquisition device collected by an inertial sensor; The image acquisition device is fixedly arranged in a fixed area on one side of a deformation area to be monitored, and a monitoring target is fixedly arranged in the deformation area to be monitored; Based on the first real-time image information, determining target displacement data of the current position of the monitoring target relative to the corresponding standard monitoring target position; Based on the real-time attitude data, determining attitude change data of the current attitude of the image acquisition device relative to the corresponding standard attitude; Based on the imaging geometric relationship between the monitoring target and the image acquisition device and the attitude change data, obtaining a first attitude observation error between the image acquisition device and the monitoring target; Based on the first attitude observation error, correcting the target displacement data to obtain effective target displacement data.

2. The visual displacement monitoring method according to claim 1, wherein The step of correcting the target displacement data based on the first attitude observation error to obtain effective target displacement data includes: Based on the first real-time image information, determining reference displacement data of the reference target relative to the standard reference position; the reference target is fixedly arranged in another fixed area on the other side of the deformation area to be monitored, and the monitoring target and the reference target are included in the picture of any frame of image collected by the image acquisition device; Based on the imaging geometric relationship between the reference target and the image acquisition device and the attitude change data, obtaining a second attitude observation error between the image acquisition device and the reference target; Based on the difference between the reference displacement data and the second attitude observation error, determining a displacement observation error between the image acquisition device and the monitoring target; Based on the displacement observation error and the first attitude observation error, correcting the target displacement data to obtain the effective target displacement data.

3. The visual displacement monitoring method according to claim 2, wherein The step of obtaining the first attitude observation error between the image acquisition device and the monitoring target based on the imaging geometric relationship between the monitoring target and the image acquisition device and the attitude change data includes: Based on the first ideal spatial distance information between the monitoring target and the image acquisition device, the attitude change data, and Formula 1, obtaining the first attitude observation error between the image acquisition device and the monitoring target; Equation 1 is: ΔD ir = L i ·sinΔθ; where L i is the first ideal space distance information, ΔD ir is the first attitude observation error, and Δθ is the attitude change data; Or, Based on the proportional relationship between the imaging area of the monitoring target and the imaging area of the reference target in the first real-time image information, the second ideal spatial distance between the image acquisition device and the reference target, the attitude change data, and Formula 2, obtaining the first attitude observation error between the image acquisition device and the monitoring target; Formula 2 is as follows: where, ΔD ir is the first attitude observation error, d i is the size of the monitoring target imaging area of the i-th monitoring target, d b is the size of the reference target imaging area, L b is the second ideal spatial distance, and Δθ is the attitude change data.

4. The visual displacement monitoring method according to any one of claims 1 to 3, characterized in that The inertial sensor is fixedly arranged on the image acquisition device through a rigid body connection; And / or The method further includes: Obtaining second real-time image information collected by the image acquisition device; Extract the actual imaging picture of the region of interest from the second real-time image information; wherein, the monitoring target has the region of interest; Based on the imaging difference between the actual imaging picture and the ideal imaging picture of the region of interest, adjust the imaging parameters of the image acquisition device and / or the supplementary light parameters of the monitoring target, so that the imaging difference between the adjusted second real-time image information and the ideal imaging picture is less than a preset imaging difference.

5. The visual displacement monitoring method according to claim 4, wherein The adjusting the imaging parameters of the image acquisition device and / or the supplementary light parameters of the monitoring target based on the imaging difference between the actual imaging picture and the ideal imaging picture includes: Perform image registration on the actual imaging picture and the ideal imaging picture to determine matching pixel point pairs; wherein, the pixel point pairs include source pixel points of the actual imaging picture and matching pixel points of the ideal imaging picture; Based on the imaging difference between corresponding pixels of the actual imaging picture and the ideal imaging picture, adjust the imaging parameters of the image acquisition device and / or the supplementary light parameters of the monitoring target.

6. The visual displacement monitoring method according to claim 5, characterized in that, The performing image registration on the actual imaging picture and the ideal imaging picture to determine matching pixel point pairs includes: Based on at least 4 first preset feature points in the ideal imaging picture and at least 4 second preset feature points in the actual imaging picture that respectively match the first preset feature points, determine a homography transformation matrix between the actual imaging picture and the ideal imaging picture; Based on the homography transformation matrix, determine matching pixel points in the ideal imaging picture that respectively match each source pixel point in the actual imaging picture, and obtain a plurality of pixel point pairs.

7. The visual displacement monitoring method according to claim 5, characterized in that A plurality of the monitoring targets are fixedly arranged in the deformation region to be monitored, and the picture of any frame of image collected by the image acquisition device includes a plurality of the monitoring targets; Based on the imaging difference between the actual imaging pictures of all the monitoring targets and the ideal imaging picture of the region of interest, adjust the imaging parameters of the image acquisition device and / or the supplementary light parameters of the monitoring target.

8. A visual displacement monitoring system, characterized in that, Comprising: At least one monitoring target, which is fixedly arranged in the deformation region to be monitored; An image sensor, which is fixedly arranged in a fixed region on one side of the deformation region to be monitored; and the picture of any frame of image collected by the image acquisition device includes a plurality of the monitoring targets; An inertial sensor, which is used to collect the real-time attitude data of the image acquisition device; A displacement calculation device, which is connected to both the image sensor and the inertial sensor, and the displacement calculation device includes a processor, a memory and a computer program, and when the computer program is executed by the processor, it realizes the steps of the visual displacement monitoring method according to any one of claims 1 to 7.

9. The visual displacement monitoring system according to claim 8, wherein It further includes a reference target, which is fixedly arranged in a fixed region on the other side of the deformation region to be monitored, and the picture of any frame of image collected by the image acquisition device includes the monitoring target and the reference target.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the visual displacement monitoring method according to any one of claims 1 to 7 are implemented.

Images