Target-free side slope deformation rapid comparison and identification method

Abstract

The invention relates to a target-free side slope deformation rapid comparison and identification method, and relates to the field of side slope deformation monitoring, and the method comprises the steps: carrying out the similarity recognition of a first side slope image and a second side slope image, obtaining the side slope similarity, and carrying out the significance analysis of the first side slope image and the second side slope image when the similarity is greater than a threshold value, and obtaining a first side slope significance map and a second side slope significance map; performing salient region coordinate screening to obtain first and second salient region coordinate distribution, and performing comparative analysis to obtain a basic deformation coefficient; and analyzing to obtain a movement error coefficient of the mobile monitoring equipment, performing error compensation on the basic deformation coefficient in combination with the slope similarity, and obtaining a compensation deformation coefficient interval as a deformation identification result. The technical problems that a traditional method depends on a target and a fixed monitoring instrument, the installation and maintenance cost is high, environment changes cannot be flexibly adapted, and deformation recognition accuracy and efficiency are low can be solved; and rapid, low-cost and high-precision slope deformation identification can be realized.

Description

Technical Field

[0001] The invention relates to the field of slope deformation monitoring, and in particular to a target-free slope deformation rapid comparison and identification method. Background Art

[0002] Slope deformation monitoring is an important part of geological disaster prevention and control, especially for early warning of geological disasters such as landslides and collapses.

[0003] At present, traditional slope deformation monitoring methods mainly rely on targets and fixed monitoring instruments, such as total stations, GPS, inclinometers and other equipment. These devices judge the potential risks of geological disasters by accurately measuring the displacement and angle changes of the target or directly monitoring the deformation of the slope surface.

[0004] However, traditional slope deformation monitoring methods have many technical difficulties and shortcomings, such as high cost and high maintenance requirements, poor environmental adaptability, low accuracy and efficiency, which restrict the accuracy, efficiency and application scope of slope deformation monitoring. Summary of the invention

[0005] The present invention aims to solve the technical problems that traditional slope deformation monitoring methods rely on targets and fixed monitoring instruments, have high installation and maintenance costs, cannot flexibly adapt to environmental changes, and have low deformation recognition accuracy and efficiency. A target-free slope deformation rapid comparison and identification method is provided to solve the problem.

[0006] The technical solution of the present invention to solve the above technical problems is as follows:

[0007] In a first aspect, the present invention provides a method for rapid comparison and identification of slope deformation without a target, comprising: using a mobile monitoring device, at a preset time within a first deformation monitoring period and a second deformation monitoring period, collecting a first slope image and a second slope image of a target slope at a preset orientation, wherein the mobile monitoring device comprises a drone or a mobile vehicle; performing similarity recognition on the first slope image and the second slope image to obtain slope similarity, and when the slope similarity is greater than a similarity threshold, performing significance analysis on the first slope image and the second slope image to obtain a first slope significance map and a second slope significance map; performing significant area coordinate screening on the first slope significance map and the second slope significance map, respectively, to obtain a first significant area coordinate distribution and a second significant area coordinate distribution, and performing comparative analysis to obtain a basic deformation coefficient of the target slope; based on the historical movement data of the mobile monitoring device, analyzing to obtain a movement error coefficient, combining the slope similarity, performing error compensation on the basic deformation coefficient, and obtaining a compensated deformation coefficient interval as a slope deformation identification result.

[0008] In a second aspect, the present invention provides a non-target slope deformation rapid comparison and identification system, comprising: a slope image acquisition module, used to collect a first slope image and a second slope image of a target slope at a preset orientation at a preset time within a first deformation monitoring period and a second deformation monitoring period through a mobile monitoring device, wherein the mobile monitoring device comprises an unmanned aerial vehicle or a mobile vehicle; an image saliency analysis module, used to perform similarity recognition on the first slope image and the second slope image to obtain slope similarity, and when the slope similarity is greater than a similarity threshold, perform similarity recognition on the first slope image and the second slope image; A significance analysis is performed to obtain a first slope significance map and a second slope significance map; a basic deformation coefficient analysis module is used to screen the coordinates of significant areas of the first slope significance map and the second slope significance map respectively, obtain the coordinate distribution of the first significant area and the coordinate distribution of the second significant area, and compare and analyze to obtain the basic deformation coefficient of the target slope; a basic deformation coefficient compensation module is used to analyze and obtain the movement error coefficient based on the historical movement data of the mobile monitoring device, and perform error compensation on the basic deformation coefficient in combination with the slope similarity to obtain the compensated deformation coefficient interval as the slope deformation identification result.

[0009] The beneficial effects of the present invention are as follows: a first slope image and a second slope image of a target slope are collected at a preset orientation at a preset time within a first deformation monitoring period and a second deformation monitoring period by a mobile monitoring device, wherein the mobile monitoring device includes a drone or a mobile vehicle; then similarity recognition is performed on the first slope image and the second slope image to obtain slope similarity, and when the slope similarity is greater than a similarity threshold, significance analysis is performed on the first slope image and the second slope image to obtain a first slope significance map and a second slope significance map; then significant area coordinates are screened for the first slope significance map and the second slope significance map, respectively, to obtain a first significant area coordinate distribution and a second significant area coordinate distribution, and the comparison is performed. The basic deformation coefficient of the target slope is obtained by analysis; the moving error coefficient is further obtained based on the historical movement data of the mobile monitoring device, and the basic deformation coefficient is error compensated in combination with the slope similarity to obtain the compensated deformation coefficient interval, and the compensated deformation coefficient interval is used as the slope deformation identification result; that is, by collecting images through flexible UAVs or mobile vehicles, combined with similarity analysis, significance analysis, error compensation and other technologies, target-free slope deformation monitoring can be achieved, avoiding high-cost target installation and maintenance requirements, and at the same time, it can flexibly respond to complex terrain and environmental changes, realize fast, low-cost and high-precision slope deformation identification, and achieve the technical effect of significantly improving the accuracy, reliability and efficiency of deformation identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1A schematic diagram of a flow chart of a method for rapid comparison and identification of slope deformation without a target provided by the present invention;

[0011] Figure 2 A schematic structural diagram of a target-free slope deformation rapid comparison and identification system provided by the present invention.

[0012] In the accompanying drawings, the components represented by the reference numerals are described as follows:

[0013] Slope image acquisition module 01, image saliency analysis module 02, basic deformation coefficient analysis module 03, basic deformation coefficient compensation module 04. DETAILED DESCRIPTION

[0014] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0015] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0016] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0017] Embodiment 1, as Figure 1 As shown, an embodiment of the present invention provides a method for rapid comparison and identification of slope deformation without a target, which specifically includes the following steps:

[0018] S100: Collecting a first slope image and a second slope image of a target slope at a preset position at preset times within a first deformation monitoring period and a second deformation monitoring period by a mobile monitoring device, wherein the mobile monitoring device includes a drone or a mobile vehicle.

[0019] Furthermore, step S100 of the present invention further includes:

[0020] S110: Control the movement of the mobile monitoring device to a preset position at preset moments in a first deformation monitoring cycle and a second deformation monitoring cycle, respectively, by means of the mobile monitoring device, wherein the first deformation monitoring cycle and the second deformation monitoring cycle are two adjacent deformation monitoring cycles; S120: Acquire a first slope image and a second slope image at the preset positions, respectively.

[0021] Specifically, first, a mobile monitoring device is selected, and the mobile monitoring device includes a drone or a mobile vehicle. By using the drone or the mobile vehicle as a mobile monitoring device, its flexibility allows the monitoring personnel to avoid relying on fixed monitoring points, and can dynamically monitor the slope at multiple angles and positions. At the same time, the device can adjust the flight or driving path according to the monitoring needs to ensure that the acquisition range and angle of the image data are accurate. Then, through the mobile monitoring device, at the preset time in the first deformation monitoring cycle and the second deformation monitoring cycle, respectively control to move to the preset position, wherein the first deformation monitoring cycle and the second deformation monitoring cycle are two adjacent deformation monitoring cycles before and after, and the deformation monitoring cycle can be set according to the actual monitoring needs. For example, the deformation monitoring cycle is set to 1 day, and the monitoring time is 2 pm every day, then the monitoring time of the first deformation monitoring cycle is 2 pm of the previous day, and the monitoring time of the second deformation monitoring cycle is 2 pm of the next day. The preset position includes the position (fixed acquisition position) and angle (fixed acquisition angle) of image acquisition, which can be set according to the actual monitoring scene to ensure that the acquired images are consistent in space and angle.

[0022] Then, at the preset position, the slope is imaged by a mobile monitoring device (drone or mobile vehicle) to obtain a first slope image of the first deformation monitoring period and a second slope image of the second deformation monitoring period. By obtaining the first slope image and the second slope image, basic data is provided for subsequent slope deformation analysis.

[0023] S200: Performing similarity recognition on the first slope image and the second slope image to obtain slope similarity, and when the slope similarity is greater than a similarity threshold, performing saliency analysis on the first slope image and the second slope image to obtain a first slope saliency map and a second slope saliency map.

[0024] Furthermore, step S200 of the present invention further includes:

[0025] S210: Obtain a pre-trained slope similarity recognition channel, wherein the slope similarity recognition channel is obtained by collecting multiple groups of sample slope images and marked sample slope similarity sets, and training based on a twin network until convergence; S220: Combine the first slope image and the second slope image and input them into the slope similarity recognition channel, and obtain the slope similarity through recognition output.

[0026] Specifically, first, a slope similarity recognition channel is constructed based on a twin network, wherein the twin network is a special neural network architecture, which consists of two identical sub-networks (usually sharing the same weights) and is used to process a pair of input data. Each sub-network independently extracts the features of the input data and maps these features into the same feature space, and then calculates the similarity between the two through a metric function (such as Euclidean distance or cosine similarity). In the slope similarity recognition task, the input of the twin network is two slope images (for example, the slope image of the first monitoring period and the slope image of the second monitoring period), and the two images will be processed by the two sub-networks of the network respectively, and the similarity measurement value will be output; the slope similarity recognition channel includes an input layer, a similarity comparison layer and an output layer, wherein the input data of the output layer is two slope images, and the output data of the output layer is the slope similarity of the two slope images.

[0027] Next, multiple groups of sample slope images are collected, and slope similarity is marked for each group of sample slope images, that is, a similarity label is marked for each group of images to indicate the similarity between the two images. Numerical labels (such as similarity values ​​from 0 to 1) can be used to indicate the similarity between image pairs to obtain a sample slope similarity set. Each group of sample slope images is further used as input, and the sample slope similarity is used as output. The multiple groups of sample slope images and the sample slope similarity sets are used as training data to perform supervised training on the slope similarity recognition channel. First, the input image pairs are processed by two sub-networks to generate feature vectors for each pair of images, and the similarity between them is calculated; then, the difference between the predicted value of the model and the true label is calculated by the loss function to obtain the loss value; then, the gradient of each weight parameter is calculated by the back propagation algorithm, the network parameters are updated, and the loss is reduced. Back propagation will adjust the weights of the convolutional layer and the fully connected layer in the sub-network so that the network can better extract features that are helpful for judging similarity; further, an optimization algorithm (such as Adam or SGD) is used to adjust the network parameters according to the gradient and minimize the loss function. Each round of training will update the model parameters through the gradient descent algorithm, so that the performance of the model on the training set is getting better and better; iterative training is performed until the loss function converges to obtain a trained slope similarity recognition channel. By constructing a slope similarity recognition channel based on the twin network, the similarity between the input slope images can be predicted, which significantly improves the scientificity, accuracy and efficiency of image similarity analysis.

[0028] The first slope image and the second slope image are then combined and input into the slope similarity recognition channel to perform image similarity recognition and output slope similarity, wherein the greater the slope similarity, the more similar the morphologies of the slope images collected twice, indicating that the slope deformation is small or there is no deformation; on the contrary, the smaller the slope similarity, the greater the slope deformation, and there may be risks of geological disasters such as landslides and collapses.

[0029] S230: Determine whether the slope similarity is greater than a slope similarity threshold; if so, perform saliency analysis on the first slope image and the second slope image to obtain a first slope saliency map and a second slope saliency map.

[0030] Further, step S230 of the present invention further includes:

[0031] S231: grayscale the first slope image and the second slope image to obtain a first grayscale slope image and a second grayscale slope image; S232: extract a first slope pixel point in the first grayscale slope image, and randomly extract a plurality of adjacent slope grayscale values ​​of a plurality of adjacent slope pixel points adjacent to the first slope pixel point; S233: randomly extract a plurality of random slope grayscale values ​​of a plurality of random slope pixel points in the first grayscale slope image, calculate the difference ratio between the mean of the plurality of adjacent slope grayscale values ​​and the mean of the plurality of random slope grayscale values, and obtain a first saliency; S234: continue to calculate to obtain the saliency of all slope pixel points in the first grayscale slope image, and obtain a first slope saliency map; S235: perform saliency analysis on the second slope image to obtain a second slope saliency map.

[0032] Specifically, it is determined whether the slope similarity is greater than a slope similarity threshold, wherein the slope similarity threshold is usually determined based on previous experience or experiments, and its setting depends on the conditions of image acquisition, the expected degree of slope deformation, and the characteristics of the similarity metric used. If the slope similarity is greater than the slope similarity threshold, indicating that the similarity difference between the two is small, then the first slope image and the second slope image are subjected to saliency analysis.

[0033] First, the first slope image and the second slope image are grayscaled. Grayscale processing is the process of converting a color image into a grayscale image. The purpose is to simplify the computational complexity in image processing while retaining important structure and texture information in the image. In slope deformation monitoring, the grayscale image can highlight the brightness changes in the deformation area, making the subsequent significance analysis and processing more efficient and accurate. Commonly used grayscale processing methods include weighted averaging, etc.; the first grayscale slope image and the second grayscale slope image are obtained.

[0034] Next, randomly select any pixel point in the first grayscale slope image as the first slope pixel point, and randomly select multiple adjacent slope grayscale values ​​of multiple adjacent slope pixel points adjacent to the first slope pixel point, that is, randomly select multiple adjacent slope pixel points around the selected first slope pixel point with the point as the center. The coordinates of these adjacent pixel points should be located in the neighborhood of the first slope pixel point, and a neighborhood range (such as a window size of 3*3 or 5*5, setting a smaller neighborhood such as a 3*3 window can improve the accuracy of the significance analysis calculation) can be set to ensure that the selected adjacent pixel point is close enough to the central pixel point. Then, randomly select multiple random slope grayscale values ​​of multiple random slope pixel points in the first grayscale slope image, wherein the number of random slope pixel points is the same as the number of adjacent slope pixel points. Further, the grayscale values ​​of the plurality of adjacent slopes are averaged to obtain the grayscale mean of the adjacent slopes, and the grayscale values ​​of the plurality of random slopes are averaged to obtain the grayscale mean of the random slopes; then, the difference ratio between the grayscale mean of the adjacent slopes and the grayscale mean of the random slopes is calculated, wherein the difference ratio is the ratio of the difference between the grayscale mean of the adjacent slopes and the grayscale mean of the random slopes to the grayscale mean of the random slopes, for example, the grayscale mean of the adjacent slopes is 110, and the grayscale mean of the random slopes is 100, then the deviation ratio is (110-100) / 100=0.1; and the difference ratio is set as the first significance.

[0035] Then, the same method as that used to calculate the first saliency is used to continue calculating the saliency of all slope pixels in the first grayscale slope image, and the first slope saliency map is constructed in combination with the position coordinates of the pixels. The same method is further used to perform saliency analysis on the second slope image to generate a second slope saliency map.

[0036] S240: If not, re-collect the slope image, and when the slope similarities of the preset number of slope images collected continuously are not greater than the slope similarity threshold, output slope deformation prompt information for prompting.

[0037] Specifically, if the slope similarity is less than or equal to the slope similarity threshold, it indicates that the difference between the images is large, which may be caused by external environmental factors (such as weather changes, lighting problems, equipment errors, etc.). In this case, the similarity of the image group is not high enough, and the slope deformation comparison may not be accurate. Then, the continuous acquisition mechanism is started, and the new second slope image is re-acquired and its similarity with the first slope image is calculated; and when the slope similarity of the preset number of slope images acquired continuously (which can be set according to the actual scene, such as 5 consecutive acquisitions) is not greater than the slope similarity threshold, that is, when the similarity of the continuously acquired slope images is lower than the set threshold, it can be judged that this is not an error caused by the external environment (such as changes in weather, lighting, etc.), but a real slope deformation signal, and the slope deformation prompt information is output for prompting.

[0038] S300: Screening the coordinates of the significant regions of the first slope significance map and the second slope significance map respectively, obtaining the coordinate distribution of the first significant region and the coordinate distribution of the second significant region, and performing comparative analysis to obtain the basic deformation coefficient of the target slope.

[0039] Furthermore, step S300 of the present invention further includes:

[0040] S310: Filter the slope pixel points whose significance is greater than the significance threshold in the first slope significance map to obtain multiple first significant slope pixel points; S320: Cluster the adjacent first significant slope pixel points whose adjacent cluster number is greater than the cluster number threshold into a first significant area to obtain multiple first significant areas, and construct a first significant area coordinate distribution by combining the coordinates of the first significant slope pixel points in the multiple first significant areas; S330: Filter the coordinates of the significant areas of the second slope significance map to obtain a second significant area coordinate distribution.

[0041] Specifically, first, a suitable significance threshold is set according to actual conditions, which can be set after analyzing historical sample data; then, the significance of multiple pixel points in the first slope significance map is screened according to the significance threshold, and the slope pixel points greater than the significance threshold are set as first significant slope pixel points, thereby obtaining multiple first significant slope pixel points.

[0042] Next, a clustering number threshold is set (e.g., the number threshold is set to 50); and the adjacent first significant slope pixel points whose adjacent clustering number is greater than the clustering number threshold are clustered into the first significant region, that is, for each significant pixel point and its adjacent pixel points, if they also meet the significance threshold, they are considered to be adjacent and can be clustered into the same significant region, thereby obtaining multiple first significant regions. Then, the coordinates of the first significant slope pixel points in the multiple first significant regions are combined to construct the coordinate distribution of the first significant region. Then, based on the significance threshold and the clustering number threshold, the coordinates of the significant regions of the second slope significance map are screened, multiple second significant regions are obtained, and the coordinate distribution of the second significant region is constructed.

[0043] S340: Comparatively analyzing the coordinate distribution of the first significant area and the coordinate distribution of the second significant area to obtain a basic deformation coefficient of the target slope.

[0044] Further, step S340 of the present invention further includes:

[0045] S341: traverse and calculate the repetition ratio of the coordinates of multiple first significant areas in the first significant area coordinate distribution and the coordinates of multiple second significant areas in the second significant area coordinate distribution, select the largest multiple repetition ratios, and obtain the repetition ratios of multiple significant area coordinates; S342: calculate the mean of the repetition ratios of the multiple significant area coordinates to obtain the average repetition ratio; S343: subtract the average repetition ratio from 1 to obtain the basic deformation coefficient.

[0046] Specifically, first, the repetition ratios of the coordinates of multiple first significant areas in the first significant area coordinate distribution and the coordinates of multiple second significant areas in the second significant area coordinate distribution are traversed and calculated, such as calculating the coincident pixels of the two areas by spatial distance or overlapping area, to evaluate the coordinate coincidence, wherein the repetition ratio represents the coincidence of the two significant areas in spatial coordinates, and the higher the repetition ratio, the smaller the change of the two areas, and vice versa, it indicates that there is deformation or difference, and multiple area repetition ratios are obtained; then, the largest multiple repetition ratios are selected from the multiple area repetition ratios (such as selecting the largest repetition ratios in the top 50%) and set them as the significant area coordinate repetition ratios, to obtain multiple significant area coordinate repetition ratios.

[0047] Then, the mean of the repetition ratios of the coordinates of the multiple significant regions is calculated to obtain the average repetition ratio; then, the average repetition ratio is subtracted from 1, and the difference between the two is used as the basic deformation coefficient, wherein the larger the average repetition ratio, the less obvious deformation has occurred, and the basic deformation coefficient is close to 0; the smaller the average repetition ratio, the larger the value of the basic deformation coefficient, indicating that a larger deformation has occurred. By calculating and analyzing the repetition ratios of the coordinates of the significant regions to obtain the basic deformation coefficient, the influence of environmental interference factors (such as light, weather, etc.) can be reduced, thereby obtaining more stable and accurate deformation analysis results under different environmental conditions, and improving the accuracy and reliability of slope deformation analysis.

[0048] S400: Based on the historical movement data of the mobile monitoring device, a movement error coefficient is obtained by analysis, and in combination with the slope similarity, error compensation is performed on the basic deformation coefficient to obtain a compensation deformation coefficient interval as a slope deformation identification result.

[0049] Furthermore, step S400 of the present invention further includes:

[0050] S410: Obtain the actual moving azimuth parameters of the mobile monitoring device under the same azimuth moving instruction in the historical time, and obtain a set of historical actual moving parameters; S420: Calculate the average azimuth deviation between the historical actual moving parameter set and the same azimuth moving instruction, and obtain a moving error coefficient; S430: Subtract the slope similarity from 1 to obtain an image error coefficient; S440: Use the moving error coefficient and the image error coefficient to perform error compensation on the basic deformation coefficient, and obtain a compensated deformation coefficient interval as a slope deformation identification result.

[0051] Specifically, when using mobile monitoring equipment (such as drones or mobile vehicles) to collect slope images, errors may occur, including equipment position errors (such as offset), shooting direction errors (such as inconsistent angles), and image acquisition errors (such as unstable image quality). These errors may lead to inaccurate slope deformation analysis results, so the influence of errors needs to be eliminated.

[0052] First, the actual moving azimuth parameters of the mobile monitoring device under the same azimuth moving instruction in the historical time are obtained at multiple monitoring time nodes. Since there may be errors in the movement of the device, the actual moving azimuth and the preset azimuth may deviate. The actual moving azimuth refers to the azimuth (including the shooting position and the shooting angle) that the device actually reaches when executing the moving instruction, and a set of historical actual moving parameters is obtained. Next, the average azimuth deviation between the historical actual moving parameter set and the same azimuth moving instruction is calculated, that is, for each moving instruction at a historical time point, the difference between the actual azimuth of the device and the preset azimuth is calculated, which can usually be expressed using the Euclidean distance (position deviation) and the angle difference (direction deviation), to obtain multiple azimuth deviations, and the average is calculated to obtain the moving error coefficient.

[0053] On the other hand, 1 is subtracted from the slope similarity, and the difference between the two is used as the image error coefficient; then the moving error coefficient and the image error coefficient are averaged to obtain the comprehensive error coefficient, and the basic deformation coefficient is error compensated according to the comprehensive error coefficient to obtain the compensation deformation coefficient interval. For example, assuming that the moving error coefficient and the image error coefficient are 0.01 and 0.03 respectively, and the basic deformation coefficient is 0.1, then the comprehensive error coefficient is 0.02, and the compensation deformation coefficient interval is 0.1±0.02. Finally, the compensation deformation coefficient interval is used as the slope deformation identification result. By combining the moving error coefficient and the image error coefficient and calculating the comprehensive error coefficient using the mean, the basic deformation coefficient of slope deformation monitoring can be error compensated to obtain a compensation deformation coefficient interval, which can provide a deformation amplitude range, reduce or avoid deviations caused by equipment or environmental errors, and further improve the accuracy and reliability of slope deformation monitoring.

[0054] The embodiment of the present invention provides a method for rapid comparison and identification of slope deformation without a target, which has at least the following technical effects:

[0055] By collecting images through flexible drones or mobile vehicles and combining technologies such as similarity analysis, saliency analysis and error compensation, target-free slope deformation monitoring can be achieved, avoiding the need for high-cost target installation and maintenance. At the same time, it can flexibly respond to complex terrain and environmental changes, achieve fast, low-cost and high-precision slope deformation identification, and achieve the technical effect of significantly improving the accuracy, reliability and efficiency of deformation identification.

[0056] Embodiment 2, as Figure 2 As shown, based on the same inventive concept of a non-target slope deformation rapid comparison and identification method provided in Embodiment 1, an embodiment of the present invention further provides a non-target slope deformation rapid comparison and identification system, comprising:

[0057] The slope image acquisition module 01 is used to collect the first slope image and the second slope image of the target slope at a preset time within the first deformation monitoring period and the second deformation monitoring period at a preset orientation through a mobile monitoring device, wherein the mobile monitoring device includes a drone or a mobile vehicle; the image saliency analysis module 02 is used to perform similarity recognition on the first slope image and the second slope image to obtain slope similarity, and when the slope similarity is greater than the similarity threshold, perform saliency analysis on the first slope image and the second slope image to obtain a first slope saliency map and a second slope saliency map; the basic deformation coefficient analysis module 03 is used to perform significant area coordinate screening on the first slope saliency map and the second slope saliency map respectively, obtain the first significant area coordinate distribution and the second significant area coordinate distribution, and compare and analyze to obtain the basic deformation coefficient of the target slope; the basic deformation coefficient compensation module 04 is used to analyze and obtain the movement error coefficient based on the historical movement data of the mobile monitoring device, and perform error compensation on the basic deformation coefficient in combination with the slope similarity to obtain the compensated deformation coefficient interval as the slope deformation identification result.

[0058] Furthermore, the target-free slope deformation rapid comparison and identification system also includes: through the mobile monitoring equipment, at preset times within the first deformation monitoring cycle and the second deformation monitoring cycle, respectively controlling the movement to preset positions, wherein the first deformation monitoring cycle and the second deformation monitoring cycle are two adjacent deformation monitoring cycles; and respectively acquiring the first slope image and the second slope image at the preset positions.

[0059] Furthermore, the target-free rapid comparison and identification system for slope deformation also includes: obtaining a pre-trained slope similarity identification channel, wherein the slope similarity identification channel is obtained by collecting multiple groups of sample slope images and marked sample slope similarity sets, and training based on a twin network until convergence; inputting the first slope image and the second slope image into the slope similarity identification channel, and identifying and outputting the slope similarity; judging whether the slope similarity is greater than a slope similarity threshold, and if so, performing a saliency analysis on the first slope image and the second slope image to obtain a first slope saliency map and a second slope saliency map; if not, re-collecting the slope image, and when the slope similarities of a preset number of slope images collected continuously are not greater than the slope similarity threshold, outputting slope deformation prompt information for prompting.

[0060] Furthermore, the target-free slope deformation rapid comparison and identification system also includes: grayscale processing the first slope image and the second slope image to obtain a first grayscale slope image and a second grayscale slope image; extracting a first slope pixel point in the first grayscale slope image, and randomly extracting a plurality of adjacent slope grayscale values ​​of a plurality of adjacent slope pixel points adjacent to the first slope pixel point; randomly extracting a plurality of random slope grayscale values ​​of a plurality of random slope pixel points in the first grayscale slope image, calculating the difference ratio between the mean of the plurality of adjacent slope grayscale values ​​and the mean of the plurality of random slope grayscale values, and obtaining a first saliency; continuing to calculate to obtain the saliency of all slope pixel points in the first grayscale slope image, and obtaining a first slope saliency map; performing saliency analysis on the second slope image, and obtaining a second slope saliency map.

[0061] Furthermore, the target-free slope deformation rapid comparison and identification system also includes: screening slope pixel points in the first slope significance map whose significance is greater than a significance threshold to obtain multiple first significant slope pixel points; clustering adjacent first significant slope pixel points whose adjacent clustering number is greater than a clustering number threshold into a first significant area to obtain multiple first significant areas, and combining the coordinates of the first significant slope pixel points in the multiple first significant areas to construct a first significant area coordinate distribution; screening the coordinates of the significant areas of the second slope significance map to obtain a second significant area coordinate distribution; and comparing and analyzing the first significant area coordinate distribution and the second significant area coordinate distribution to obtain the basic deformation coefficient of the target slope.

[0062] Furthermore, the target-free slope deformation rapid comparison and identification system also includes: traversing and calculating the repetition ratio of the coordinates of multiple first significant areas in the first significant area coordinate distribution and the coordinates of multiple second significant areas in the second significant area coordinate distribution, screening the largest multiple repetition ratios, and obtaining multiple significant area coordinate repetition ratios; calculating the mean of the multiple significant area coordinate repetition ratios to obtain an average repetition ratio; subtracting the average repetition ratio from 1 to obtain the basic deformation coefficient.

[0063] Furthermore, the target-free slope deformation rapid comparison and identification system also includes: obtaining actual moving azimuth parameters of the mobile monitoring device under the same azimuth moving instruction within the historical time to obtain a set of historical actual moving parameters; calculating the average azimuth deviation between the historical actual moving parameter set and the same azimuth moving instruction to obtain a moving error coefficient; subtracting the slope similarity from 1 to obtain an image error coefficient; using the moving error coefficient and the image error coefficient to perform error compensation on the basic deformation coefficient to obtain a compensated deformation coefficient interval as a slope deformation identification result.

[0064] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0065] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0066] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0067] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0068] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0069] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art understand the basic inventive concepts.

[0070] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and variations.

Claims

1. A method for rapid comparison and identification of slope deformation without a target, characterized in that: Methods include: By means of a mobile monitoring device, at a preset time in a first deformation monitoring period and a second deformation monitoring period, a first slope image and a second slope image of the target slope are collected at a preset orientation, wherein the mobile monitoring device includes a drone or a mobile vehicle; Performing similarity recognition on the first slope image and the second slope image to obtain slope similarity, and when the slope similarity is greater than a similarity threshold, performing saliency analysis on the first slope image and the second slope image to obtain a first slope saliency map and a second slope saliency map; Screening the coordinates of the significant regions of the first slope significance map and the second slope significance map respectively, obtaining the coordinate distribution of the first significant region and the coordinate distribution of the second significant region, and performing comparative analysis to obtain the basic deformation coefficient of the target slope; Based on the historical movement data of the mobile monitoring device, the movement error coefficient is analyzed and obtained, and combined with the slope similarity, the basic deformation coefficient is error compensated to obtain the compensated deformation coefficient interval as the slope deformation identification result.

2. The method for rapid comparison and identification of slope deformation without a target according to claim 1 is characterized in that: The method collects a first slope image and a second slope image of a target slope at a preset position at a preset time in a first deformation monitoring period and a second deformation monitoring period by a mobile monitoring device, including: By means of a mobile monitoring device, at preset moments in a first deformation monitoring cycle and a second deformation monitoring cycle, the device is respectively controlled to move to a preset position, wherein the first deformation monitoring cycle and the second deformation monitoring cycle are two adjacent deformation monitoring cycles; The first slope image and the second slope image are respectively acquired at the preset positions.

3. The method for rapid comparison and identification of slope deformation without a target according to claim 1 is characterized in that: Performing similarity recognition on the first slope image and the second slope image to obtain slope similarity, and when the slope similarity is greater than a similarity threshold, performing saliency analysis on the first slope image and the second slope image to obtain a first slope saliency map and a second slope saliency map, including: Acquire a pre-trained slope similarity recognition channel, wherein the slope similarity recognition channel is obtained by collecting multiple groups of sample slope images and marked sample slope similarity sets, and training the twin network until convergence; Combining the first slope image and the second slope image into the slope similarity recognition channel, and identifying and outputting the slope similarity; Determine whether the slope similarity is greater than a slope similarity threshold, and if so, perform saliency analysis on the first slope image and the second slope image to obtain a first slope saliency map and a second slope saliency map; If not, the slope image is collected again, and when the slope similarities of a preset number of slope images collected continuously are not greater than the slope similarity threshold, slope deformation prompt information is output for prompting.

4. The method for rapid comparison and identification of slope deformation without a target according to claim 3 is characterized in that: Performing saliency analysis on the first slope image and the second slope image to obtain a first slope saliency map and a second slope saliency map includes: grayscale the first slope image and the second slope image to obtain a first grayscale slope image and a second grayscale slope image; Extracting a first slope pixel point in the first grayscale slope image, and randomly extracting a plurality of adjacent slope grayscale values ​​of a plurality of adjacent slope pixel points adjacent to the first slope pixel point; Randomly extracting a plurality of random slope grayscale values ​​of a plurality of random slope pixel points in the first grayscale slope image, calculating a difference ratio between an average of the plurality of adjacent slope grayscale values ​​and an average of the plurality of random slope grayscale values, and obtaining a first saliency; Continue to calculate and obtain the saliency of all slope pixels in the first grayscale slope image to obtain a first slope saliency map; A saliency analysis is performed on the second side slope image to obtain a second side slope saliency map.

5. The method for rapid comparison and identification of slope deformation without a target according to claim 1 is characterized in that: The first slope significance map and the second slope significance map are respectively screened for significant area coordinates to obtain the first significant area coordinate distribution and the second significant area coordinate distribution, and the basic deformation coefficient of the target slope is obtained by comparative analysis, including: Screening the slope pixel points whose significance is greater than the significance threshold in the first slope significance map to obtain a plurality of first significant slope pixel points; Clustering adjacent first significant slope pixel points whose adjacent clustering number is greater than a clustering number threshold into a first significant region, obtaining multiple first significant regions, and combining the coordinates of the first significant slope pixel points in the multiple first significant regions to construct a coordinate distribution of the first significant region; Screening the coordinates of significant regions on the second slope significance map to obtain a second significant region coordinate distribution; The coordinate distribution of the first significant area and the coordinate distribution of the second significant area are compared and analyzed to obtain the basic deformation coefficient of the target slope.

6. The method for rapid comparison and identification of slope deformation without a target according to claim 5 is characterized in that: Comparative analysis is performed on the coordinate distribution of the first significant area and the coordinate distribution of the second significant area to obtain the basic deformation coefficient of the target slope, including: traversing and calculating the repetition ratios of the coordinates of a plurality of first significant regions in the first significant region coordinate distribution and the coordinates of a plurality of second significant regions in the second significant region coordinate distribution, selecting the largest multiple repetition ratios, and obtaining multiple significant region coordinate repetition ratios; Calculating the mean of the repetition ratios of the plurality of significant region coordinates to obtain an average repetition ratio; The basic deformation coefficient is obtained by subtracting the average repetition ratio from 1.

7. The method for rapid comparison and identification of slope deformation without a target according to claim 1 is characterized in that: Based on the historical movement data of the mobile monitoring device, the movement error coefficient is obtained by analysis, and combined with the slope similarity, the basic deformation coefficient is error compensated to obtain the compensation deformation coefficient interval as the slope deformation identification result, including: Acquire actual movement azimuth parameters of the mobile monitoring device under the same movement azimuth instruction in historical time, and obtain a historical actual movement parameter set; Calculate the average azimuth deviation between the historical actual movement parameter set and the same azimuth movement instruction to obtain a movement error coefficient; Subtracting the slope similarity from 1 to obtain an image error coefficient; The movement error coefficient and the image error coefficient are used to perform error compensation on the basic deformation coefficient to obtain a compensated deformation coefficient interval as a slope deformation identification result.

8. A non-target slope deformation rapid comparison and identification system, characterized in that: The steps for implementing the method for rapid comparison and identification of slope deformation without a target as described in any one of claims 1 to 7 include: A slope image acquisition module is used to acquire a first slope image and a second slope image of a target slope at a preset position at a preset time within a first deformation monitoring period and a second deformation monitoring period by a mobile monitoring device, wherein the mobile monitoring device includes a drone or a mobile vehicle; An image saliency analysis module is used to perform similarity recognition on the first slope image and the second slope image to obtain slope similarity, and when the slope similarity is greater than a similarity threshold, perform saliency analysis on the first slope image and the second slope image to obtain a first slope saliency map and a second slope saliency map; A basic deformation coefficient analysis module is used to screen the coordinates of the significant regions of the first slope significance map and the second slope significance map respectively, obtain the coordinate distribution of the first significant region and the coordinate distribution of the second significant region, and compare and analyze to obtain the basic deformation coefficient of the target slope; The basic deformation coefficient compensation module is used to analyze and obtain the movement error coefficient based on the historical movement data of the mobile monitoring device, and to perform error compensation on the basic deformation coefficient in combination with the slope similarity to obtain the compensated deformation coefficient interval as the slope deformation identification result.

Images