A method and device for monitoring the settlement of reservoir dams

Abstract

This invention provides a method and apparatus for monitoring the settlement of a reservoir dam. It acquires an initial image and a image to be processed from an image acquisition device. The initial image is a dam image acquired by the image acquisition device at an initial moment, and the image to be processed is a dam image acquired by the image acquisition device at a target moment. The method determines the initial coordinates of a target point region in the initial image and the coordinates of the target point region in the image to be processed. The coordinates of the image to be processed are compared with the initial coordinates to determine the dam deformation. This method enables the determination of dam deformation based on images acquired by the image acquisition device, reducing the cost of dam deformation monitoring and improving the accuracy of dam deformation monitoring.

Description

Technical Field

[0001] This invention relates to the field of water conservancy engineering technology, and in particular to a method and device for monitoring the settlement of reservoir dams. Background Technology

[0002] Safety monitoring of reservoir dams involves monitoring and analyzing the dam's main structure, foundation, surrounding environment, and related facilities using various monitoring instruments and equipment. Among the many monitoring items, deformation monitoring can directly and effectively reflect the dam's operational status and determine whether the dam is in a safe condition. Therefore, dam deformation monitoring is the most important monitoring content in dam safety monitoring and is the first and only required monitoring item.

[0003] Currently, GNSS (Global Navigation Satellite System) is one method for monitoring dam deformation. This method establishes GNSS observation points to continuously monitor dam deformation, thus achieving deformation monitoring. However, the GNSS method has the following drawbacks: 1. GNSS observation points need to be located in relatively open areas where GNSS signals can be received. 2. The vertical accuracy of deformation monitored by the GNSS method is relatively poor. 3. The cost of setting up GNSS monitoring points is high, with each point costing tens of thousands of yuan. In short, the GNSS method has low accuracy and high cost, hindering its widespread adoption.

[0004] Therefore, reducing the cost and improving the accuracy of dam deformation monitoring are important issues that the industry urgently needs to address. Summary of the Invention

[0005] This invention provides a method and apparatus for monitoring the settlement of reservoir dams, which addresses the shortcomings of low accuracy and high cost in existing dam deformation monitoring technologies, thereby reducing the cost of dam deformation monitoring and improving its accuracy.

[0006] This invention provides a method for monitoring the settlement of a reservoir dam, wherein the dam is equipped with a target point area, and the method includes:

[0007] Acquire an initial image and an image to be processed from an image acquisition device, wherein the initial image is a dam image acquired by the image acquisition device at an initial moment, and the image to be processed is a dam image acquired by the image acquisition device at a target moment;

[0008] Determine the initial region coordinates of the target point region in the initial image, and determine the region coordinates of the target point region in the image to be processed.

[0009] The dam deformation is determined by comparing the coordinates of the area to be processed with the coordinates of the initial area.

[0010] Optionally, the initial region coordinates include the coordinates of multiple initial feature points, which are located in the target point region of the initial image; the region coordinates to be processed include the coordinates of multiple feature points to be processed, which are located in the target point region of the image to be processed.

[0011] The step of comparing the coordinates of the area to be processed with the initial coordinates of the area to determine the dam deformation includes:

[0012] Calculate the coordinates of the feature points to be processed and the difference between the coordinates of the initial feature points;

[0013] Calculate the average of the multiple differences to be processed, and determine the dam deformation based on the average.

[0014] Optionally, the step of sequentially calculating the difference between the coordinates of the feature points to be processed and the coordinates of the initial feature points includes:

[0015] Based on the pre-acquired micro-shift values, the coordinates of each of the feature points to be processed are adjusted to obtain the coordinates to be processed, wherein the micro-shift values ​​are obtained by feature matching of the image to be processed and the initial image;

[0016] The processing difference between the coordinates to be processed and the coordinates of the initial feature points is calculated sequentially.

[0017] Optionally, the image to be processed includes multiple images, each image to be processed corresponds to an average value, and each image to be processed corresponds to a different target time.

[0018] The step of determining dam deformation based on the average value includes:

[0019] Based on the relationship between the average value and the target time, a waveform diagram is constructed;

[0020] The waveform is subjected to signal separation to obtain multiple waveforms to be determined;

[0021] The waveform diagram to be determined that meets the preset waveform conditions will be used as the waveform diagram corresponding to the dam deformation.

[0022] The dam deformation is determined based on the waveform diagram corresponding to the dam deformation.

[0023] Optionally, the target time includes a first target time and a second target time, and the image to be processed includes a first image to be processed and a second image to be processed, wherein the first image to be processed corresponds to the first target time, the second image to be processed corresponds to the second target time, and the image acquisition devices corresponding to the first image to be processed and the second image to be processed are the same;

[0024] After the step of comparing the coordinates of the area to be processed with the initial coordinates of the area to determine the dam deformation, the method further includes:

[0025] For each target point region, verify whether the relationship between the dam deformation corresponding to the first image to be processed and the dam deformation corresponding to the second image to be processed meets the preset conditions.

[0026] If the relationship between the dam deformation corresponding to the first image to be processed and the dam deformation corresponding to the second image to be processed does not meet the preset conditions, the parameters of the image acquisition device are adjusted.

[0027] Optionally, the step of verifying whether the relationship between the dam deformation corresponding to the target point region in the first image to be processed and the dam deformation corresponding to the second image to be processed meets a preset condition includes:

[0028] For each target point region, the coordinates of the target point region in the processing area corresponding to the first processing image are compared with the coordinates of the target point region in the processing area corresponding to the second processing image to determine the deformation to be processed.

[0029] The sum of the deformation to be processed and the dam deformation corresponding to the first image to be processed is taken as the sum to be processed.

[0030] Determine whether the difference between the value to be processed and the dam deformation corresponding to the second image to be processed is within a preset error range;

[0031] If the difference between the value to be processed and the dam deformation corresponding to the second image to be processed is within a preset error range, it is determined that the relationship between the dam deformation corresponding to the first image to be processed and the dam deformation corresponding to the second image to be processed satisfies a preset condition.

[0032] The present invention also provides a monitoring device for the settlement of a reservoir dam, wherein the dam is provided with a target point area, and the device includes:

[0033] The acquisition module is used to acquire an initial image and an image to be processed acquired by the image acquisition device, wherein the initial image is a dam image acquired by the image acquisition device at an initial moment, and the image to be processed is a dam image acquired by the image acquisition device at a target moment;

[0034] The determination module is used to determine the initial region coordinates of the target point region in the initial image and to determine the region coordinates of the target point region in the image to be processed.

[0035] The comparison module is used to compare the coordinates of the area to be processed with the coordinates of the initial area to determine the dam deformation.

[0036] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of a method for monitoring the settlement of a reservoir dam as described in any of the preceding claims.

[0037] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a method for monitoring the settlement of a reservoir dam as described in any of the preceding claims.

[0038] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of a method for monitoring the settlement of a reservoir dam as described in any of the preceding claims.

[0039] This invention provides a method and apparatus for monitoring the settlement of a reservoir dam. It acquires an initial image and a processing image from an image acquisition device. The initial image is a dam image acquired by the image acquisition device at an initial moment, and the processing image is a dam image acquired by the image acquisition device at a target moment. The method determines the initial coordinates of a target point region in the initial image and the coordinates of the target point region in the processing image. By comparing the processing coordinates with the initial coordinates, the dam deformation is determined. This method enables the determination of dam deformation based on images acquired by the image acquisition device, reducing the cost of dam deformation monitoring and improving the accuracy of dam deformation monitoring compared to the GNSS method. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0041] Figure 1 This is one of the flowcharts of a method for monitoring the settlement of a reservoir dam provided by the present invention;

[0042] Figure 2 This is a schematic diagram of the image acquisition device and the dam provided by the present invention;

[0043] Figure 3 This is a schematic diagram of a sequence of images acquired by the image acquisition device provided by the present invention;

[0044] Figure 4 This is a schematic diagram of the waveform provided by the present invention;

[0045] Figure 5 (a) One of the schematic diagrams of the waveform to be processed provided by the present invention;

[0046] Figure 5 (b) A second schematic diagram of the waveform to be processed provided by the present invention;

[0047] Figure 6 This is a schematic diagram of the structure of a monitoring device for the settlement of a reservoir dam provided by the present invention;

[0048] Figure 7 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0049] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0050] To reduce the cost and improve the accuracy of dam deformation monitoring, this invention discloses a method, device, electronic equipment, non-transitory computer-readable storage medium, and computer program product for monitoring the settlement of reservoir dams. The following is a detailed description... Figure 1 This invention describes a method for monitoring the settlement of a reservoir dam.

[0051] like Figure 1 As shown, a method for monitoring the settlement of a reservoir dam is provided, wherein the dam is equipped with a target area, and the method may include:

[0052] S101, acquire the initial image and the image to be processed acquired by the image acquisition device.

[0053] In order to obtain the dam deformation, the initial image and the image to be processed can be obtained from the image acquisition device. The initial image is the dam image acquired by the image acquisition device at the initial moment, and the image to be processed is the dam image acquired by the image acquisition device at the target moment.

[0054] In one implementation, the user can click the "Acquire Image" button at the initial moment and the target moment to obtain the initial image and the image to be processed captured by the image acquisition device.

[0055] In another implementation, an initial time and a target time can be preset, and the image acquisition device automatically sends the initial image and the image to be processed to the electronic device, thus acquiring both the initial image and the image to be processed. Both of these approaches are reasonable.

[0056] For example, the image acquisition device can automatically send the initial image and the image to be processed to the management system of the reservoir dam management office at the initial moment and the target moment, so that the management system of the reservoir dam management office can perform subsequent processing on the initial image and the image to be processed.

[0057] The initial time can be set according to the user's actual needs, and the target time is set by a preset time interval. This preset time can also be set according to the user's actual needs. For example, the preset time interval between the target time and the initial time can be 2 minutes, 5 minutes, or 10 minutes. There is no specific limitation here, and all of these are reasonable.

[0058] As one implementation method, the image acquisition device can be a high-precision camera, or it can be composed of a regular camera and an adjustable-focus telescope. For example, the image acquisition device can capture images where each pixel corresponds to a ground resolution of no more than 1 cm, thus ensuring that the pixel monitoring accuracy is better than 1 mm.

[0059] For example, an image acquisition device can acquire images up to 2160x3840 pixels. By adjusting the focal length of a telescope with a focal length range of 6mm-120mm, it can acquire images with a pixel size of 0.0002mm after focusing.

[0060] S102, determine the initial region coordinates of the target point region in the initial image, and determine the region coordinates of the target point region in the image to be processed.

[0061] After obtaining the initial image and the image to be processed, the initial region coordinates of the target point region in the initial image can be determined, and the region coordinates of the target point region in the image to be processed can be determined.

[0062] In one implementation, the SURF (Speeded Up Robust Features) algorithm can be used to process the target point regions of both the initial image and the image to be processed. Using the target point region of the initial image as a reference, feature points are selected from both regions, and feature point matching is performed to eliminate gross errors. This allows the determination of the initial region coordinates of the target point region in the initial image and the region coordinates of the target point region to be processed in the image to be processed.

[0063] The number of feature points can be dozens or hundreds, which is reasonable.

[0064] The SURF algorithm processes the initial image and the image to be processed mainly through the following steps: Step 1: Constructing the Hessian matrix. Step 2: Constructing the scale space. Step 3: Feature point localization. Step 4: Feature point principal direction matching. Step 5: Generating feature point descriptors. Step 6: Feature point matching.

[0065] Constructing the Hessian matrix can obtain stable edge points (mutation points) in the image. Constructing the Hessian matrix can generate all interest points for subsequent feature point extraction. Specifically, a Hessian matrix can be calculated for each pixel in the initial image and the image to be processed.

[0066] When constructing the scale space, since the initial image and the image to be processed have the same image size, a box filter is used to process both the initial image and the image to be processed. The template size of the box filter used for the initial image and the image to be processed is different, and the blur coefficient of the box filter corresponding to the initial image is smaller than the blur coefficient of the box filter corresponding to the image to be processed.

[0067] After constructing the scale space, each pixel processed by the Hessian matrix is ​​compared with 26 neighboring points in the two-dimensional image space and the scale space to initially locate key points. Then, key points with weak energy and incorrectly located key points are filtered out to select the final stable feature points. This layer consists of 8 pixels, and each of the adjacent layers consists of 9 pixels.

[0068] After identifying stable feature points, feature point principal direction matching can be performed. Specifically, a trapezoidal histogram of stable feature points within their neighborhood can be generated. This can be achieved by calculating the Haar wavelet features within the circular neighborhood of each stable feature point. Within this circular neighborhood, the sum of all horizontal and vertical Haar wavelet features within a preset angle is calculated. After rotating the neighborhood by a preset interval, the sum of all horizontal and vertical Haar wavelet features within the circular neighborhood is calculated again. This process yields multiple sums of horizontal and vertical Haar wavelet features. The direction corresponding to the maximum sum of these sums is then taken as the principal direction of the feature point.

[0069] For example, the sum of all horizontal and vertical Harr wavelet features within a 60° sector can be calculated. After rotating at a preset interval, the sum of all horizontal and vertical Harr wavelet features within another 60° sector can be calculated again. The direction corresponding to the sector with the largest sum of horizontal and vertical Harr wavelet features is then selected as the principal direction of the feature point.

[0070] After selecting the principal direction of the feature point, a stable feature point descriptor can be generated. In the SURF algorithm, a 4x4 rectangular region block can be selected around the entire feature point, and the direction of the selected rectangular region block is along the principal direction of the feature point. Within each of these 4x4 = 16 regions, 5x5 = 25 pixels of horizontal and vertical Harr wavelet features are statistically analyzed. Here, horizontal and vertical refer to the principal direction. The Harr wavelet features include four directions: after the horizontal direction value, after the vertical direction value, after the absolute value of the horizontal direction, and the sum of the absolute values ​​of the vertical direction. These four values ​​are used as the feature vector of each sub-block region, resulting in a total of 4*4*4 = 64-dimensional vectors as the descriptor of the SURF features.

[0071] Furthermore, the Euclidean distance between two stable feature points can be calculated to determine the matching degree. The shorter the Euclidean distance, the better the matching degree between the two feature points. Alternatively, the trace can be determined based on the Hessian matrix. If the traces of two feature points have the same sign, it means that the two features have contrast changes in the same direction. If they are different, it means that the contrast changes of the two feature points are in opposite directions, and they are directly excluded even if the Euclidean distance is 0.

[0072] In this way, the matching points in the initial image and the image to be processed can be determined, and the matching points are located in the target point region. Then, the initial region coordinates of the target point region in the initial image and the region coordinates of the target point region in the image to be processed can be determined based on the matching points.

[0073] In another implementation, the APM (all-pixels participated matching) algorithm can be used to process the target point regions of the initial image and the target point regions of the image to be processed. Based on the target point regions of the initial image, feature matching is performed between the target point regions of the initial image and the target point regions of the image to be processed.

[0074] By using the least squares method to remove mismatched pixels, the initial coordinates of the target point region in the initial image and the coordinates of the target point region in the image to be processed can be determined.

[0075] As one implementation method, the SURF algorithm and the APM algorithm can be used simultaneously to process the initial image and the image to be processed. This allows the SURF algorithm and the APM algorithm to cross-check each other and select the algorithm with the optimal matching points for subsequent processing. This results in the calculation of more accurate initial region coordinates and the coordinates of the region to be processed.

[0076] As another implementation method, both the SURF algorithm and the APM algorithm are used to process the initial image and the image to be processed. This allows for cross-checking using the SURF and APM algorithms, eliminating gross errors, before further processing. This approach enables the calculation of more accurate initial and image coordinates.

[0077] S103, compare the coordinates of the area to be processed with the coordinates of the initial area to determine the dam deformation.

[0078] After obtaining the coordinates of the area to be processed and the initial area coordinates, the coordinates of the area to be processed and the initial area coordinates can be compared to determine the change value (i.e., width) along the horizontal axis of the image coordinate system and the change value (i.e., height) along the vertical axis of the image coordinate system, thereby obtaining the dam deformation.

[0079] As can be seen, the method for monitoring the settlement of reservoir dams disclosed in this invention can determine the dam deformation based on images acquired by image acquisition equipment, thereby reducing the cost of dam deformation monitoring. Furthermore, it eliminates the need for manual observation, reducing labor costs. Compared with the GNSS method, it can improve the accuracy of dam deformation monitoring.

[0080] As one embodiment of the present invention, the above-mentioned initial region coordinates may include the coordinates of multiple initial feature points, which are located in the target point region of the initial image. The coordinates of the region to be processed include the coordinates of multiple feature points to be processed, which are located in the target point region of the image to be processed.

[0081] There is a correspondence between the initial feature points and the feature points to be processed; the feature points to be processed that correspond to the initial feature points are the feature points that match the initial feature points. The number of initial feature points and the number of feature points to be processed are the same.

[0082] For example, the initial region coordinates may include the coordinates of 5 initial feature points, and the region to be processed may include 5 feature points to be processed.

[0083] The step of comparing the coordinates of the area to be processed with the initial coordinates of the area to determine the dam deformation may include:

[0084] The coordinates of the feature points to be processed are calculated sequentially, and the difference between the coordinates of the initial feature points and the coordinates of the feature points to be processed is calculated.

[0085] After obtaining the coordinates of the feature points to be processed and the coordinates of the initial feature points, the processing difference between the coordinates of the feature points to be processed and the coordinates of their corresponding initial feature points can be calculated based on the correspondence between the initial feature points and the feature points to be processed. The processing difference includes the difference along the horizontal axis of the image coordinate system and the difference along the vertical axis of the image coordinate system. The processing difference can include multiple differences along the horizontal axis of the image coordinate system and differences along the vertical axis of the image coordinate system.

[0086] For example, the correspondence between the coordinates of the 5 initial feature points and the coordinates of the 5 feature points to be processed can be shown in Table 1:

[0087] Table 1

[0088] name coordinate name coordinate Initial feature point 1 (U1, V1) Feature point 1 to be processed (U6, V6) Initial feature point 2 (U2, V2) Feature point 2 to be processed (U7, V7) Initial feature point 3 (U3, V3) Feature points to be processed 3 (U8, V8) Initial feature point 4 (U4, V4) Feature points to be processed 4 (U9, V9) Initial feature point 5 (U5, V5) 5 feature points to be processed (U10, V10)

[0089] The coordinates of the feature point to be processed can be calculated, along with the differences between the coordinates of the initial feature points. Specifically, the differences between the initial feature point 1 and the feature point to be processed are calculated as U1-U6, V1-V6; the differences between the initial feature point 2 and the feature point to be processed are calculated as U2-U7, V2-V7; and so on. The differences between the initial feature point 5 and the feature point to be processed are calculated as U5-U10, V5-V10. This yields the difference to be processed.

[0090] Calculate the average of the multiple differences to be processed, and determine the dam deformation based on the average.

[0091] After obtaining the differences to be processed, the average of multiple differences can be calculated. The average can be the average along the horizontal axis of the image coordinate system and the average along the vertical axis of the image coordinate system, thus allowing the dam deformation to be determined based on the average. This method can further improve the accuracy of the determined dam deformation.

[0092] As one embodiment of the present invention, the step of sequentially calculating the difference between the coordinates of the feature points to be processed and the coordinates of the initial feature points may include:

[0093] Based on the pre-acquired micro-shift values, the coordinates of each of the feature points to be processed are adjusted to obtain the coordinates to be processed.

[0094] Since the initial image and the image to be processed were captured at different times, there may be a camera offset factor that causes the shooting angle of the captured image to change, resulting in a mismatch between the pixels included in the initial image and the image to be processed.

[0095] In order to obtain more accurate dam deformation data, image matching technology can be used to perform feature matching between the image to be processed and the initial image. This allows us to determine the micro-shift value of the image to be processed relative to the initial image. The micro-shift value is the deviation value of the pixels included in the initial image and the image to be processed.

[0096] After obtaining the micro-shift value, the coordinates of each feature point to be processed can be adjusted based on the obtained micro-shift value to obtain the coordinates to be processed. The coordinates to be processed can more accurately represent the coordinates of the target point region in the image to be processed.

[0097] The processing difference between the coordinates to be processed and the coordinates of the initial feature points is calculated sequentially.

[0098] After obtaining the coordinates to be processed, the difference between the coordinates to be processed and the coordinates of the initial feature points can be calculated sequentially, which can further improve the accuracy of dam deformation monitoring.

[0099] In one embodiment of the present invention, the target point area set on the dam includes at least three points, namely the center of the dam and both ends of the dam. The target point areas can be densely deployed at locations prone to deformation, such as dam culverts and outlets. Target points can also be set at GNSS monitoring locations, thus combining GNSS monitoring with the monitoring of dam settlement, thereby improving the accuracy of dam deformation monitoring.

[0100] like Figure 2 The diagram shows the image acquisition equipment and the target area set up on the dam. Figure 2The dam shown as dam 205 is a dam with vehicles passing over its crest. To monitor the safe operation of the dam, an image acquisition device has been set up as an observation platform on its downstream right bank, and the image acquisition device is mounted on a concrete pier.

[0101] Dam 205 is equipped with target point areas 201, 202, 203 and 204. Image acquisition device 206 is used to capture images including target point area 201, image acquisition device 207 is used to capture images including target point area 202, image acquisition device 208 is used to capture images including target point area 203 and image acquisition device 209 is used to capture images including target point area 204.

[0102] In one embodiment of the present invention, the image acquisition device is installed on a concrete pier on a stable ground at a predetermined distance from the dam, and the instability of the concrete pier has an error of less than 0.1 pixels on the image acquired by the image acquisition device.

[0103] Image acquisition equipment can continuously monitor the target area set up on the dam. Based on the images acquired by the equipment, the deformation of the dam or the corresponding settlement curve can be obtained, thereby enabling the monitoring of the dam's settlement.

[0104] As one implementation method, when the texture of the dam image acquired by the image acquisition device does not meet the preset standard, paint can be sprayed on the target point area to make the target point area more obvious, thereby improving the accuracy of dam deformation monitoring.

[0105] In one embodiment of the present invention, each image acquisition device may acquire multiple images to be processed, that is, each image acquisition device may acquire a sequence of images, which includes multiple images to be processed, and the time interval between each image to be processed is consistent. Each image to be processed corresponds to an average value, and the target time corresponding to each image to be processed is different.

[0106] For example, such as Figure 3 As shown, the time interval between each image to be processed can be 2 minutes. That is, the time interval between image 301 and image 302 is 2 minutes, the time interval between image 302 and image 303 is 2 minutes, the time interval between image 301 and image 303 is 4 minutes, and the time interval between image 301 and image 30n is 2x(n-1) minutes.

[0107] The steps for determining dam deformation based on the average value described above may include:

[0108] Based on the relationship between the average value and the target time, a waveform diagram is constructed.

[0109] The average value can include the average value along the horizontal axis of the image coordinate system and the average value along the vertical axis of the image coordinate system. Therefore, a waveform can be constructed based on the average value along the horizontal axis of the image coordinate system, the average value along the vertical axis of the image coordinate system, and the target time.

[0110] For example, such as Figure 4 The image shown is a schematic diagram of a waveform. The horizontal axis of the waveform represents time, and the vertical axis represents the average value. The two waveforms with different gray levels represent the average values ​​along the horizontal and vertical axes of the image coordinate system, respectively.

[0111] The waveform diagrams are subjected to signal separation to obtain multiple waveform diagrams to be determined. The waveform diagrams to be determined that meet the preset waveform conditions are used as the waveform diagrams corresponding to the dam deformation.

[0112] The average values ​​of each image to be processed monitored by the image acquisition equipment include multiple signal contents such as observation error, environmental noise, overload vibration of the bridge above the dam and dam vibration and settlement, dam displacement, bridge overload vibration, structural stress and temperature deformation, and video observation error.

[0113] Therefore, to obtain more accurate dam deformation data, wavelet transform or Fourier transform methods can be used to analyze the waveform. Signal separation of the waveform yields multiple waveforms to be determined. Since the frequency characteristics corresponding to the aforementioned sources differ significantly in the waveforms, the waveform that meets the preset waveform conditions can be used as the waveform corresponding to the dam deformation.

[0114] For example, the multiple waveforms to be determined obtained can be as follows: Figure 5 (a) and Figure 5 As shown in (b), waveforms 501, 502, and 503 represent video observation errors (including instrument position and environmental interference errors). Waveforms 504, 505, and 506 can be considered as vibrations caused by passing vehicles on the bridge deck. Waveforms 507, 508, and 509 can be considered as elastic deformations of the dam bridge structure caused by environmental factors such as temperature. Waveform 509 and the results of subsequent longer-term filtering, namely waveforms 510 and 511, can be considered as information on dam foundation settlement, i.e., the waveforms corresponding to dam deformation. Waveform 511 is the waveform after filtering out waveforms 501-510. Waveform 512 is the original waveform.

[0115] The dam deformation is determined based on the waveform diagram corresponding to the dam deformation.

[0116] After obtaining the waveform diagram corresponding to the dam deformation, the dam deformation at any given time can be determined based on the waveform diagram. Therefore, this method can improve the accuracy of dam deformation monitoring.

[0117] As one embodiment of the present invention, the target time includes a first target time and a second target time, and the image to be processed includes a first image to be processed and a second image to be processed, wherein the first image to be processed corresponds to the first target time, the second image to be processed corresponds to the second target time, and the image acquisition devices corresponding to the first image to be processed and the second image to be processed are the same.

[0118] After comparing the coordinates of the area to be processed with the initial coordinates of the area to determine the dam deformation, the method may further include:

[0119] For each target point region, verify whether the relationship between the dam deformation corresponding to the first image to be processed and the dam deformation corresponding to the second image to be processed meets the preset conditions.

[0120] To ensure monitoring quality, the monitoring accuracy of each image acquisition device can be verified. To verify the monitoring accuracy of the image acquisition devices, for each target point area, the relationship between the dam deformation corresponding to the first image to be processed and the dam deformation corresponding to the second image to be processed can be verified to see if it meets preset conditions.

[0121] If the relationship between the dam deformation corresponding to the first image to be processed and the dam deformation corresponding to the second image to be processed does not meet the preset conditions, it indicates that the parameters of the image acquisition device have changed significantly, affecting the acquired images to be processed. Therefore, the parameters of the image acquisition device can be adjusted. These parameters can be either built-in or external parameters of the image acquisition device.

[0122] If the relationship between the dam deformation corresponding to the first image to be processed and the dam deformation corresponding to the second image to be processed meets the preset conditions, it indicates that the parameters of the image acquisition device do not affect each image to be processed. Therefore, the parameters of the image acquisition device do not need to be adjusted.

[0123] It is evident that this method can be used to verify the monitoring accuracy of image acquisition equipment, thereby ensuring monitoring quality and improving the accuracy of dam deformation monitoring.

[0124] As one embodiment of the present invention, the step of verifying whether the relationship between the dam deformation corresponding to the target point region in the first image to be processed and the dam deformation corresponding to the second image to be processed satisfies a preset condition may include:

[0125] For each target point region, the coordinates of the target point region in the processing area corresponding to the first processing image are compared with the coordinates of the target point region in the processing area corresponding to the second processing image to determine the deformation to be processed.

[0126] For example, such as Figure 3 As shown, the coordinates of the region to be processed corresponding to the image to be processed 302 can be compared with the coordinates of the region to be processed corresponding to the image to be processed 303 to determine the deformation to be processed and obtain h23 and w23.

[0127] The sum of the deformation to be processed and the dam deformation corresponding to the first image to be processed is taken as the sum to be processed.

[0128] For example, suppose the dam deformation corresponding to the first image to be processed, i.e., the dam deformation corresponding to image 302 to be processed, can be h12 and w12, and the deformation to be processed is h23 and w23. The sum of the values ​​to be processed is h12+h23 and w12+w23.

[0129] Determine whether the difference between the value to be processed and the dam deformation corresponding to the second image to be processed is within a preset error range.

[0130] For example, the dam deformation corresponding to the second image to be processed, that is, the dam deformation corresponding to image 303 to be processed, can be h13 and w13. The difference between the sum of the values ​​to be processed and the dam deformation corresponding to image 303 to be processed is h12+h23-h12 and w12+w23-w13.

[0131] It can be determined whether the difference between the sum of values ​​to be processed and the dam deformation corresponding to the second image to be processed is within a preset error range. If the difference between the sum of values ​​to be processed and the dam deformation corresponding to the second image to be processed is within the preset error range, it indicates that the influence of the parameters of the image acquisition device on the acquired image can be ignored. Therefore, it can be determined that the relationship between the dam deformation corresponding to the first image to be processed and the dam deformation corresponding to the second image to be processed satisfies the preset conditions.

[0132] If the difference between the sum of the values ​​to be processed and the dam deformation corresponding to the second image to be processed is not within the preset error range, it indicates that the parameters of the image acquisition device have a significant impact on the acquired image. Therefore, it can be determined that the relationship between the dam deformation corresponding to the first image to be processed and the dam deformation corresponding to the second image to be processed does not meet the preset conditions.

[0133] In one implementation, the monitoring sensitivity and accuracy of the image acquisition device can also be determined by calculating the mean and standard deviation. Extensive experimental verification has shown that, when using artificial targets, the mean can reach 0.1 pixels, and for imaging targets with good natural textures, the detection standard deviation can reach 0.3 pixels.

[0134] As one embodiment of the present invention, the sequence of images acquired by the image acquisition device can be matched according to the size of the window, wherein the large window includes the image of the surrounding environment excluding the target point area, and the small window includes the image corresponding to the target point area.

[0135] By matching windows of different sizes in a sequence of images, and considering the different content monitored in each window, the displacement of the target within the smaller window, representing the bridge's displacement, can be detected. Further analysis, including data decomposition and reconstruction, can extract the bridge's deformation. Movement of the target point region corresponding to the smaller window indicates that the dam has deformed.

[0136] The following describes a monitoring device for the settlement of a reservoir dam provided by the present invention. The monitoring device for the settlement of a reservoir dam described below and the monitoring method for the settlement of a reservoir dam described above can be referred to in correspondence with each other.

[0137] like Figure 6 As shown, a monitoring device for the settlement of a reservoir dam is disclosed, wherein the dam is provided with a target area, and the device may include:

[0138] The acquisition module 610 is used to acquire the initial image and the image to be processed acquired by the image acquisition device.

[0139] The initial image is the dam image captured by the image acquisition device at an initial moment, and the image to be processed is the dam image captured by the image acquisition device at a target moment.

[0140] The determination module 620 is used to determine the initial region coordinates of the target point region in the initial image and to determine the region coordinates of the target point region in the image to be processed.

[0141] The comparison module 630 is used to compare the coordinates of the area to be processed with the coordinates of the initial area to determine the dam deformation.

[0142] In one embodiment of the present invention, the initial region coordinates include the coordinates of multiple initial feature points, which are located in the target point region of the initial image; the region coordinates to be processed include the coordinates of multiple feature points to be processed, which are located in the target point region of the image to be processed.

[0143] The comparison module 630 mentioned above may include:

[0144] The first calculation unit is used to sequentially calculate the coordinates of the feature points to be processed and the difference between the coordinates of the initial feature points and the coordinates of the feature points to be processed.

[0145] The second calculation unit is used to calculate the average of multiple differences to be processed, and to determine the dam deformation based on the average value.

[0146] As one embodiment of the present invention, the first computing unit described above may include:

[0147] The adjustment subunit is used to adjust the coordinates of each of the feature points to be processed based on the pre-acquired micro-shift values, so as to obtain the coordinates to be processed.

[0148] The micro-shift value is obtained by feature matching between the image to be processed and the initial image.

[0149] The calculation subunit is used to sequentially calculate the difference between the coordinates to be processed and the coordinates of the initial feature point.

[0150] In one embodiment of the present invention, the image to be processed includes multiple images, each image to be processed corresponds to an average value, and each image to be processed corresponds to a different target time.

[0151] The second calculation unit mentioned above may include:

[0152] Construct sub-units to build waveform diagrams based on the relationship between the average value and the target time.

[0153] The separation subunit is used to perform signal separation on the waveform diagram to obtain multiple waveform diagrams to be determined.

[0154] The first determining subunit is used to take the waveform diagram to be determined that meets the preset waveform conditions as the waveform diagram corresponding to the dam deformation.

[0155] The second determining subunit is used to determine the dam deformation based on the waveform diagram corresponding to the dam deformation.

[0156] In one embodiment of the present invention, the target time includes a first target time and a second target time, and the image to be processed includes a first image to be processed and a second image to be processed, wherein the first image to be processed corresponds to the first target time, the second image to be processed corresponds to the second target time, and the image acquisition devices corresponding to the first image to be processed and the second image to be processed are the same.

[0157] The above-mentioned device may also include

[0158] The verification module is used to verify, after comparing the coordinates of the area to be processed and the coordinates of the initial area to determine the dam deformation, whether the relationship between the dam deformation of the target point area in the first image to be processed and the dam deformation of the target point area in the second image to be processed meets a preset condition for each target point area.

[0159] The adjustment module is used to adjust the parameters of the image acquisition device when the relationship between the dam deformation corresponding to the first image to be processed and the dam deformation corresponding to the second image to be processed does not meet the preset conditions.

[0160] As one embodiment of the present invention, the verification module may include:

[0161] The first determining unit is used to compare the coordinates of the target point region in the processing area corresponding to the first processing image with the coordinates of the target point region in the processing area corresponding to the second processing image for each target point region, and determine the deformation to be processed.

[0162] The second determining unit is used to take the sum of the deformation to be processed and the dam deformation corresponding to the first image to be processed as the sum to be processed.

[0163] The third determining unit is used to determine whether the difference between the value to be processed and the dam deformation corresponding to the second image to be processed is within a preset error range.

[0164] The fourth determining unit is used to determine, when the difference between the dam deformation corresponding to the first image to be processed and the dam deformation corresponding to the second image to be processed is within a preset error range, that the relationship between the dam deformation corresponding to the first image to be processed and the dam deformation corresponding to the second image to be processed satisfies a preset condition.

[0165] Figure 7 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 7 As shown, the electronic device may include a processor 710, a communications interface 720, a memory 730, and a communication bus 740, wherein the processor 710, the communications interface 720, and the memory 730 communicate with each other via the communication bus 740. The processor 710 can call logical instructions in the memory 730 to execute a method for monitoring the settlement of a reservoir dam provided by the above methods.

[0166] Furthermore, the logical instructions in the aforementioned memory 730 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0167] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute a method for monitoring the settlement of a reservoir dam provided by the above methods.

[0168] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform a method for monitoring the settlement of a reservoir dam provided by the methods described above.

[0169] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0170] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, 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 can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0171] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for monitoring the settlement of a reservoir dam, characterized in that, The dam is provided with a target point area, and the method comprises: acquiring an initial image collected by an image collection device and a to-be-processed image, wherein the initial image is a dam image collected by the image collection device at an initial time, and the to-be-processed image is a dam image collected by the image collection device at a target time; determining initial region coordinates of the target point area in the initial image and to-be-processed region coordinates of the target point area in the to-be-processed image; comparing the to-be-processed region coordinates and the initial region coordinates to determine dam deformation; the initial region coordinates comprise coordinates of a plurality of initial feature points located in the target point area of the initial image, and the to-be-processed region coordinates comprise coordinates of a plurality of to-be-processed feature points located in the target point area of the to-be-processed image; the step of comparing the to-be-processed region coordinates and the initial region coordinates to determine dam deformation comprises: sequentially calculating to-be-processed difference values of the coordinates of the to-be-processed feature points and the coordinates of the initial feature points; calculating an average value of a plurality of the to-be-processed difference values, and determining dam deformation based on the average value; the target time comprises a first target time and a second target time, the to-be-processed image comprises a first to-be-processed image and a second to-be-processed image, wherein the first to-be-processed image corresponds to the first target time, the second to-be-processed image corresponds to the second target time, and the image collection devices corresponding to the first to-be-processed image and the second to-be-processed image are consistent; after the step of comparing the to-be-processed region coordinates and the initial region coordinates to determine dam deformation, the method further comprises: for each target point area, verifying whether a relationship between dam deformation corresponding to the first to-be-processed image of the target point area and dam deformation corresponding to the second to-be-processed image of the target point area satisfies a preset condition; in a case where the relationship between the dam deformation corresponding to the first to-be-processed image and the dam deformation corresponding to the second to-be-processed image does not satisfy the preset condition, adjusting parameters of the image collection device.

2. The method of claim 1, wherein, the step of sequentially calculating to-be-processed difference values of the coordinates of the to-be-processed feature points and the coordinates of the initial feature points comprises: adjusting the coordinates of each to-be-processed feature point based on a pre-acquired micro-shift value to obtain to-be-processed coordinates, wherein the micro-shift value is obtained by performing feature matching on the to-be-processed image and the initial image; sequentially calculating to-be-processed difference values of the to-be-processed coordinates and the coordinates of the initial feature points.

3. The method of claim 1, wherein, the to-be-processed image comprises a plurality of to-be-processed images, each to-be-processed image corresponds to an average value, and target times corresponding to the to-be-processed images are different; the step of determining dam deformation based on the average value comprises: constructing a waveform graph based on the relationship between the average value and the target time; performing signal separation on the waveform graph to obtain a plurality of to-be-determined waveform graphs; taking a to-be-determined waveform graph that satisfies a preset waveform condition as a waveform graph corresponding to the dam deformation. Determine the dam deformation based on the waveform diagram corresponding to the dam deformation.

4. The method of claim 1, wherein, The step of verifying whether the relationship between the dam deformation corresponding to the first to-be-processed image and the dam deformation corresponding to the second to-be-processed image satisfies a preset condition comprises: For each target point region, compare the to-be-processed region coordinates of the target point region corresponding to the first to-be-processed image with the to-be-processed region coordinates of the target point region corresponding to the second to-be-processed image to determine a to-be-processed deformation; Take the sum of the to-be-processed deformation and the dam deformation corresponding to the first to-be-processed image as a to-be-processed sum; Determine whether the difference between the to-be-processed sum and the dam deformation corresponding to the second to-be-processed image is within a preset error range; In a case where the difference between the to-be-processed sum and the dam deformation corresponding to the second to-be-processed image is within the preset error range, determine that the relationship between the dam deformation corresponding to the first to-be-processed image and the dam deformation corresponding to the second to-be-processed image satisfies the preset condition.

5. A device for monitoring the settlement of a reservoir dam, characterized in that, The dam is provided with a target point region, and the device comprises: An acquisition module configured to acquire an initial image and a to-be-processed image collected by an image collection device, wherein the initial image is a dam image collected by the image collection device at an initial time, and the to-be-processed image is a dam image collected by the image collection device at a target time; A determination module configured to determine initial region coordinates of a target point region in the initial image and to-be-processed region coordinates of the target point region in the to-be-processed image; A comparison module configured to compare the to-be-processed region coordinates and the initial region coordinates to determine a dam deformation; The initial region coordinates comprise coordinates of a plurality of initial feature points located in the target point region of the initial image, and the to-be-processed region coordinates comprise coordinates of a plurality of to-be-processed feature points located in the target point region of the to-be-processed image; The comparison module comprises: A first calculation unit configured to sequentially calculate to-be-processed differences between the coordinates of the to-be-processed feature points and the coordinates of the initial feature points; A second calculation unit configured to calculate an average value of a plurality of to-be-processed differences and to determine a dam deformation based on the average value; The target time comprises a first target time and a second target time, and the to-be-processed image comprises a first to-be-processed image and a second to-be-processed image, wherein the first to-be-processed image corresponds to the first target time, the second to-be-processed image corresponds to the second target time, and the image collection devices corresponding to the first to-be-processed image and the second to-be-processed image are consistent; The device further comprises: A verification module configured to, after the comparison module compares the to-be-processed region coordinates and the initial region coordinates to determine a dam deformation, verify, for each target point region, whether the relationship between the dam deformation corresponding to the first to-be-processed image and the dam deformation corresponding to the second to-be-processed image satisfies a preset condition. An adjusting module is configured to adjust parameters of the image acquisition device when a relationship between a dam deformation corresponding to the first to-be-processed image and a dam deformation corresponding to the second to-be-processed image does not satisfy the preset condition.

6. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the steps of the method for monitoring the reservoir dam settlement amount according to any one of claims 1 to 4.

7. A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method for monitoring the reservoir dam settlement amount according to any one of claims 1 to 4.

8. A computer program product, comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method for monitoring the reservoir dam settlement amount according to any one of claims 1 to 4. The computer program is executed by the processor to implement the steps of the method for monitoring the reservoir dam settlement amount according to any one of claims 1 to 4.

Images