Water body submerging area early warning method based on image recognition

Abstract

The invention discloses a water body submerged area early warning method based on image recognition. The method comprises the following steps: performing three-dimensional reconstruction on a specified area; determining a corresponding relation list WL of different water levels and submerging areas; determining a monitoring position and a water level monitoring surface; performing field space calibration on the determined water level monitoring surface to obtain a homography matrix SM of the water level monitoring surface; the method comprises the following steps: acquiring an image containing a water level monitoring surface, identifying a water body in the acquired image by adopting a semantic segmentation model to obtain a water body segmentation map, and obtaining an original water line point set WS in a physical world corresponding to a pixel coordinate point set PS; performing abnormal data cleaning on the original water line point set WS to obtain a water line point set CWS; obtaining a regional water level according to the water line point set CWS; and obtaining the submerged area according to the regional water level and the corresponding relation list WL. According to the water body submerging area early warning method based on image recognition, the water body submerging area can be accurately calculated and early warned.

Description

Technical Field

[0001] The present invention belongs to the technical field of image processing, and in particular relates to a water body flooding area early warning method based on image recognition. Background Art

[0002] Water flooding is one of the most direct and widespread forms of disasters in extreme weather events. Its rapid and accurate early warning is of vital importance to reducing casualties, protecting property safety, and guiding emergency response and post-disaster reconstruction.

[0003] Traditional water flooding warning systems rely on weather forecasts, hydrological monitoring station data, and historical flood data analysis, but these methods have shortcomings such as limited prediction accuracy, delayed data updates, and difficulty covering all potential flooded areas. Especially in the face of rapidly changing extreme weather conditions, traditional warning methods often fail to quickly and accurately reflect actual flooding conditions, resulting in a significant reduction in warning effectiveness. Summary of the invention

[0004] The present invention provides a water body flooding area early warning method based on image recognition to solve the technical problem that the traditional early warning means mentioned above are not accurate enough, and specifically adopts the following technical solutions:

[0005] A water body flooding area early warning method based on image recognition, comprising:

[0006] S1: 3D reconstruction of the specified area;

[0007] S2: Determine a correspondence list WL between different water levels and flooded areas based on the three-dimensional reconstruction data;

[0008] S3: Determine a monitoring location and a water level monitoring surface photographed at the monitoring location;

[0009] S4: Perform on-site spatial calibration on the determined water level monitoring surface to obtain the homography matrix SM of the water level monitoring surface;

[0010] S5: collect images including water level monitoring surfaces, use semantic segmentation models to identify water bodies in the collected images of water level monitoring surfaces to obtain water body segmentation maps, use water body segmentation maps and images of water level monitoring surfaces to perform intersection calculations, obtain pixel coordinate point set PS of intersection lines obtained by the intersection calculations, transform pixel coordinate point set PS by homography matrix SM, and obtain original water level point set WS in the physical world corresponding to pixel coordinate point set PS;

[0011] S6: Clean the original water level point set WS for abnormal data to obtain the water level point set CWS;

[0012] S7: Obtain the regional water level according to the water level point set CWS;

[0013] S8: Obtain the flooded area according to the regional water level and the corresponding relationship list WL, and issue an early warning when the flooded area is greater than a preset value.

[0014] Furthermore, in step S1, the specific method of performing three-dimensional reconstruction on the designated area is:

[0015] Use drones equipped with laser radar to carry out aerial scanning operations in designated areas, collect three-dimensional point cloud data sets, and use the drone radar three-dimensional imaging algorithm to analyze and reconstruct the three-dimensional terrain model data of the designated area.

[0016] Furthermore, in step S2, when determining the correspondence list WL between different water levels and flooded areas, the water level step is set to 0.01 meters.

[0017] Furthermore, in step S4, the specific method of performing on-site spatial calibration on the determined water level monitoring surface to obtain the homography matrix SM of the water level monitoring surface is:

[0018] A total station is used to calibrate the four top corner areas of the water level monitoring surface, namely, upper left A, lower left B, lower right C, and upper right D, to obtain the coordinates of the four calibration points in the physical world. At the same time, the pixel coordinates of the four calibration points in the collected image are associated to establish a correspondence between the pixel values ​​of the monitoring surface image and the actual values ​​in the physical world, thereby obtaining the homography matrix SM of the monitoring surface.

[0019] Furthermore, in step S6, the specific method of performing abnormal data cleaning on the original water level point set WS to obtain the water level point set CWS is:

[0020] S61: Determine a virtual water level straight line F;

[0021] S62: transforming the virtual water level line F using the homography matrix SM to obtain a physical virtual water level line PA in the physical world;

[0022] S63: Fitting the water level point set CWS to obtain a real-time water level straight line F1;

[0023] S64: Calculate the angle between the real-time water level line F1 and the physical virtual water level line PA;

[0024] S65: Calculate the difference between the water level mean of the original water level line point set WS and the regional water level before a preset time;

[0025] S66: If the angle is less than the preset angle threshold M, and the difference between the water level mean of the original water level line point set WS and the regional water level before the preset time is within the preset water level normal variation range N, then the data of the original water level line point set WS is normal, and there is no need to remove abnormal data, and the water level line point set CWS is directly obtained, otherwise execute S67;

[0026] S67: If the data of the original water level point set WS is abnormal, the DBSCAN algorithm is used to cluster the original water level point set WS to obtain multiple clusters, and steps S63 to S65 are executed in sequence for each cluster, and the cluster data with abnormal data are completely eliminated, and the normal cluster data are merged to obtain the water level point set CWS.

[0027] Furthermore, in step S65, the difference between the water level mean of the original water level line point set WS and the regional water level one minute ago is calculated.

[0028] Furthermore, in step S65, the specific method for calculating the water level mean of the original water level line point set WS is:

[0029] The water levels in the original water level line point set WS are sorted, the 10% of the highest water level and the 10% of the lowest water level data are eliminated, and the remaining water levels are averaged to obtain the water level mean.

[0030] Furthermore, when the DBSCAN algorithm is used to cluster the original water level point set WS, the domain radius eps is set to 0.03 meters in the DBSCAN algorithm, and the minimum number of points in the cluster MinPts is max(n / 5, 30), where n represents the number of points in the original water level point set WS.

[0031] Furthermore, in step S7, the specific method for calculating the regional water level according to the water level point set CWS is:

[0032] Identify and clean the data once per second to obtain 60 groups of water level point sets CWS within 1 minute. The one-minute regional water level point set AWS is obtained by calculating the spatial water level mean. The water level mean is calculated for the regional water level point set AWS to obtain the regional water level.

[0033] Furthermore, in step S7, the spatial water level mean value calculation method is:

[0034] The 60 water level point sets CWS within 1 minute are sorted according to the horizontal coordinate direction of the water level space, and the average of the 60 water level data at the same point position is calculated in turn to obtain the one-minute regional water level point set AWS.

[0035] The water body flooding area early warning method based on image recognition provided by the present invention can quickly and accurately calculate and warn of the water body flooding area.

[0036] The water body flooding area early warning method based on image recognition provided by the present invention integrates advanced technologies such as drone radar three-dimensional imaging technology, digital twin technology, image recognition and artificial intelligence prediction, to achieve real-time monitoring, accurate prediction and timely early warning of water body flooding areas under extreme weather conditions, and provide strong technical support for disaster prevention and mitigation work. Compared with traditional water level monitoring, which monitors a point and may not be accurate enough, the monitoring method of the present application monitors the water level of an area, which can not only improve the accuracy of early warning, but also effectively expand the monitoring coverage, making important contributions to reducing losses from extreme weather disasters and protecting people’s lives and property. It also solves the problem of abnormal identification caused by vehicles and personnel blocking the monitoring position. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0038] Figure 1 It is a schematic diagram of a water body flooding area early warning method based on image recognition of the present invention;

[0039] Figure 2 It is a schematic diagram of the spatial calibration of the water level monitoring surface of the present invention;

[0040] Figure 3 It is a schematic diagram of water level identification of the present invention;

[0041] Figure 4 It is a schematic diagram of water level straight line fitting of the present invention.

[0042] Figure numerals: 1. Water level monitoring surface; 2. Obstacle; 3. Water body. DETAILED DESCRIPTION

[0043] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0044] like Figure 1The present application shows a water flooding area early warning method based on image recognition, comprising: S1: three-dimensional reconstruction of a designated area. S2: determining a correspondence list WL between different water levels and flooded areas based on the three-dimensional reconstruction data. S3: determining the monitoring position and the water level monitoring surface. S4: performing on-site spatial calibration on the determined water level monitoring surface to obtain the homography matrix SM of the water level monitoring surface. S5: collecting an image including the water level monitoring surface, using a semantic segmentation model to identify the water body in the collected image including the water level monitoring surface to obtain a water body segmentation map, using the water body segmentation map and the image of the water level monitoring surface to perform intersection calculation, obtaining a pixel coordinate point set PS of the intersection line obtained by the intersection calculation, transforming the pixel coordinate point set PS through the homography matrix SM, and obtaining the original water level line point set WS in the physical world corresponding to the pixel coordinate point set PS. S6: performing abnormal data cleaning on the original water level line point set WS to obtain the water level line point set CWS. S7: obtaining the regional water level according to the water level line point set CWS. S8: Obtain the flooded area according to the regional water level and the corresponding relationship list WL, and issue an early warning when the flooded area is greater than the preset value. The water flooded area early warning method based on image recognition of the present application can detect the current water flooded area in a timely and accurate manner. The above steps are specifically introduced below.

[0045] For step S1: perform three-dimensional reconstruction on the designated area.

[0046] In an embodiment of the present application, three-dimensional reconstruction is performed by laser radar scanning.

[0047] The specific method for three-dimensional reconstruction of a designated area is to use a drone equipped with a laser radar to perform aerial scanning of the designated area, collect a three-dimensional point cloud data set, and use the drone radar three-dimensional imaging algorithm to analyze and reconstruct the three-dimensional terrain model data of the designated area.

[0048] For step S2: determine a correspondence list WL between different water levels and flooded areas based on the three-dimensional reconstruction data.

[0049] Specifically, using the three-dimensional terrain model data, the irregular triangulated network method can be used to calculate the submerged area of ​​the water body at different elevations, that is, to obtain the corresponding relationship of the submerged area under different water levels. As shown in Table 1, some relationship tables are listed. In the implementation of the present application, when determining the corresponding relationship list WL of different water levels and submerged areas, the water level step is set to 0.01 meters.

[0050] Table 1 Correspondence between different water levels and flooded areas

[0051] Serial number Water level (m) Flooded area (m2) 1 6.11 0.0148 2 6.12 0.0457 3 6.13 0.0937 4 6.14 0.1587 5 6.15 0.2408 6 6.16 0.3445 7 6.17 0.5295 8 6.18 0.9748

[0052] For step S3: determine the monitoring position and water level monitoring surface.

[0053] Combined with the 3D topographic model data, determine the monitoring position of the camera and the water level monitoring surface. Specifically, the monitoring position is to select the area with the lowest terrain in the 3D topographic model data. Install the camera near the monitoring position and adjust the camera angle to ensure that the camera can capture the water level monitoring surface.

[0054] The camera collects images in real time at a certain period. In this application, one image is set per second for image data collection. The camera uses a high-sensitivity black light ball camera and is equipped with an intelligent fill light to achieve all-weather high-quality image data collection.

[0055] The water level monitoring surface is to find a flat wall in the monitoring range corresponding to the monitoring position for water level monitoring reference. The wall needs to include the lowest terrain.

[0056] For step S4: perform on-site spatial calibration on the determined water level monitoring surface to obtain the homography matrix SM of the water level monitoring surface.

[0057] like Figure 2 As shown, in the implementation manner of the present application, the specific method of performing on-site spatial calibration on the determined water level monitoring surface to obtain the homography matrix SM of the water level monitoring surface is:

[0058] A total station is used to calibrate the four top corner areas of the water level monitoring surface, namely, upper left A, lower left B, lower right C, and upper right D, to obtain the coordinates of the four calibration points in the physical world. At the same time, the pixel coordinates of the four calibration points in the collected image are associated to establish a correspondence between the pixel values ​​of the monitoring surface image and the actual values ​​in the physical world, thereby obtaining the homography matrix SM of the monitoring surface.

[0059] For step S5: collect images including water level monitoring surfaces, use semantic segmentation model to identify water bodies in the collected images to obtain water body segmentation map, use water body segmentation map and the image of water level monitoring surface to perform intersection calculation, obtain pixel coordinate point set PS of intersection lines obtained by intersection calculation, transform pixel coordinate point set PS through homography matrix SM, and obtain original water level line point set WS in the physical world corresponding to pixel coordinate point set PS.

[0060] like Figure 3 As shown in the figure, the captured image includes a water level monitoring surface 1, an obstacle 2, and a water body 3. The semantic segmentation model is used to identify the water body in the captured image to obtain a water body segmentation map. The water body semantic segmentation model is a model for identifying water bodies obtained by collecting, annotating, and training data containing water body images.

[0061] For step S6: the original water level point set WS is cleaned of abnormal data to obtain the water level point set CWS.

[0062] The original water level point set WS obtained has some abnormal data due to obstacles, water fluctuations and other factors. In the implementation of the present application, based on the historical regional water level data, a data cleaning algorithm is used to clean the original water level point set WS data, remove abnormal data, and obtain the water level point set CWS.

[0063] The specific method of cleaning the original water level point set WS for abnormal data to obtain the water level point set CWS is as follows:

[0064] S61: Determine a virtual water level line F. Specifically, the virtual water level line A is a pre-set virtual straight line, which is parallel to the ground line and serves as a horizontal reference.

[0065] S62: Use the homography matrix SM to transform the virtual water level line F to obtain the physical virtual water level line PA in the physical world.

[0066] S63: Fitting the water level point set CWS to obtain a real-time water level straight line F1.

[0067] Specifically, a water level straight line is found by fitting , so that the original water level point set WS ( , ) has the smallest sum of the squares of the vertical distances of all data points to this line, such as Figure 4 As shown, the calculation formula of m and b is as follows:

[0068] ;

[0069] ,

[0070] Where: n represents the number of WS points in the original water level point set; Represents the x physical coordinate of the original water level point set WS on the water level monitoring surface; represents the y physical coordinate of the original water level line point set WS point on the water level monitoring surface; m represents the slope of the fitted water level line, and b represents the intercept of the fitted water level line on the y axis.

[0071] S64: Calculate the angle between the real-time water level line F1 and the physical virtual water level line PA.

[0072] In this application, the angle between the real-time water level line F1 and the physical virtual water level line PA is calculated by the following formula: :

[0073]

[0074] Where: k represents the slope of the physical virtual water level straight line PA; m represents the slope of the fitted real-time water level straight line F1; Represents the angle between the real-time water level line F1 and the physical virtual water level line PA.

[0075] S65: Calculate the difference between the water level mean of the original water level line point set WS and the regional water level before a preset time.

[0076] In the implementation of the present application, the specific method for calculating the mean water level of the original water level line point set WS is: sort the water levels in the original water level line point set WS, remove 10% of the highest water level and 10% of the lowest water level, average the remaining water levels, and obtain the mean water level. Specifically, the difference between the mean water level of the original water level line point set WS and the regional water level one minute ago is calculated. The difference in the regional water level one minute ago is a known value obtained in the previous cycle.

[0077] S66: If the angle is less than the preset angle threshold M, and the difference between the water level mean of the original water level line point set WS and the regional water level before the preset time is within the preset normal water level change range N, then the data of the original water level line point set WS is normal, and there is no need to eliminate abnormal data. The water level line point set CWS is directly obtained, otherwise execute S67.

[0078] Specifically, in the present application, the angle threshold M is set to 3°, and the normal range of water level variation N is set to plus or minus 5 cm. It is understandable that the angle threshold M and the normal range of water level variation N can be specifically set as needed.

[0079] S67: If the data of the original water level point set WS is abnormal, the DBSCAN algorithm is used to cluster the original water level point set WS to obtain multiple clusters, and steps S63 to S65 are executed in sequence for each cluster, and the cluster data with abnormal data are completely eliminated, and the normal cluster data are merged to obtain the water level point set CWS.

[0080] In an embodiment of the present application, in step S65, in an embodiment of the present application, when the DBSCAN algorithm is used to cluster the original water level line point set WS, the domain radius eps is set to 0.03 meters in the DBSCAN algorithm, and the minimum number of points MinPts of the clustering cluster is max(n / 5, 30), where n represents the number of points in the original water level line point set WS.

[0081] For step S7: the regional water level is obtained according to the water level point set CWS.

[0082] In an implementation manner of the present application, the specific method for calculating the regional water level based on the water level line point set CWS is: identify and clean the data once per second to obtain 60 groups of water level line point sets CWS within 1 minute, obtain the one-minute regional water level line point set AWS by calculating the spatial water level mean, and calculate the water level mean of the regional water level line point set AWS to obtain the regional water level.

[0083] The spatial water level mean calculation method is as follows: sort the 60 groups of water level point sets CWS within 1 minute according to the spatial horizontal coordinate direction of the water level line, and calculate the average of the 60 groups of water level data at the same point position in turn to obtain the one-minute regional water level point set AWS.

[0084] For step S8: the flooded area is obtained according to the regional water level and the corresponding relationship list WL, and an early warning is issued when the flooded area is greater than a preset value.

[0085] In the implementation of the present application, a display device is provided to display the current regional water level and the flooded area on the display device. Optionally, when the flooded area exceeds a preset value, an early warning may be issued.

[0086] It is understandable that the water level warning elevation D can also be set based on the three-dimensional terrain model data combined with the elevation of the important locations flooded by the water body in the designated area. When the regional water level exceeds the set water level warning elevation D, an acoustic and optical on-site warning is carried out. The regional water level data can also be reported to the data twin platform every minute through the 4G network for three-dimensional drawing, and the changes in the current regional water level and flooded area can be displayed in real time.

[0087] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the above embodiments do not limit the present invention in any form, and any technical solution obtained by equivalent replacement or equivalent transformation falls within the protection scope of the present invention.

Claims

1. A water body flooding area early warning method based on image recognition, characterized in that: Include: S1: 3D reconstruction of the specified area; S2: Determine a correspondence list WL between different water levels and flooded areas based on the three-dimensional reconstruction data; S3: Determine a monitoring location and a water level monitoring surface photographed at the monitoring location; S4: Perform on-site spatial calibration on the determined water level monitoring surface to obtain the homography matrix SM of the water level monitoring surface; S5: collect images containing water level monitoring surfaces, use semantic segmentation models to identify water bodies in the collected images containing water level monitoring surfaces to obtain water body segmentation maps, use water body segmentation maps and images of water level monitoring surfaces to perform intersection calculations, obtain pixel coordinate point set PS of intersection lines obtained by the intersection calculations, transform the pixel coordinate point set PS through homography matrix SM, and obtain the original water level point set WS in the physical world corresponding to the pixel coordinate point set PS; S6: Clean the original water level point set WS for abnormal data to obtain the water level point set CWS; S7: Obtain the regional water level according to the water level point set CWS; S8: Obtain the flooded area according to the regional water level and the corresponding relationship list WL, and issue an early warning when the flooded area is greater than a preset value.

2. The water body flooding area early warning method based on image recognition according to claim 1 is characterized in that: In step S1, the specific method for performing three-dimensional reconstruction on the designated area is: A drone equipped with a laser radar is used to perform aerial scanning operations on a designated area, collect a three-dimensional point cloud data set, and analyze and reconstruct the three-dimensional terrain model data of the designated area through the drone radar three-dimensional imaging algorithm.

3. The water body flooding area early warning method based on image recognition according to claim 1 is characterized in that: In step S2, when determining the correspondence list WL between different water levels and flooded areas, the water level step is set to 0.01 meters.

4. The water body flooding area early warning method based on image recognition according to claim 1 is characterized in that: In step S4, the specific method of performing on-site spatial calibration on the determined water level monitoring surface to obtain the homography matrix SM of the water level monitoring surface is: A total station is used to calibrate the four position points of upper left A, lower left B, lower right C, and upper right D in the four vertex areas of the water level monitoring surface to obtain the coordinates of the four calibration points in the physical world. At the same time, the pixel coordinates of the four calibration points in the collected image are associated to establish a correspondence between the pixel values ​​of the monitoring surface image and the actual values ​​in the physical world, thereby obtaining the homography matrix SM of the monitoring surface.

5. The water body flooding area early warning method based on image recognition according to claim 1 is characterized in that: In step S6, the specific method of cleaning the original water level point set WS for abnormal data to obtain the water level point set CWS is: S61: Determine a virtual water level straight line F; S62: transforming the virtual water level line F using the homography matrix SM to obtain a physical virtual water level line PA in the physical world; S63: Fitting the water level point set CWS to obtain a real-time water level straight line F1; S64: Calculate the angle between the real-time water level line F1 and the physical virtual water level line PA; S65: Calculate the difference between the water level mean of the original water level line point set WS and the regional water level before a preset time; S66: If the angle is less than the preset angle threshold M, and the difference between the water level mean of the original water level line point set WS and the regional water level before the preset time is within the preset water level normal variation range N, then the data of the original water level line point set WS is normal, and there is no need to remove abnormal data, and the water level line point set CWS is directly obtained, otherwise execute S67; S67: If the data of the original water level point set WS is abnormal, the DBSCAN algorithm is used to cluster the original water level point set WS to obtain multiple clusters, and steps S63 to S65 are executed in sequence for each cluster, and the cluster data with abnormal data are completely eliminated, and the normal cluster data are merged to obtain the water level point set CWS.

6. The water body flooding area early warning method based on image recognition according to claim 5 is characterized in that: In step S65, the difference between the water level mean of the original water level line point set WS and the regional water level one minute ago is calculated.

7. The water body flooding area early warning method based on image recognition according to claim 5 is characterized in that: In step S65, the specific method for calculating the water level mean of the original water level line point set WS is: The water levels in the original water level line point set WS are sorted, the 10% of the highest water level and the 10% of the lowest water level data are eliminated, and the remaining water levels are averaged to obtain the water level mean.

8. The water body flooding area early warning method based on image recognition according to claim 5 is characterized in that: When the DBSCAN algorithm is used to cluster the original water level point set WS, the domain radius eps is set to 0.03 meters in the DBSCAN algorithm, and the minimum number of points in the cluster MinPts is max(n / 5, 30), where n represents the number of points in the original water level point set WS.

9. The water body flooding area early warning method based on image recognition according to claim 1 is characterized in that: In step S7, the specific method for calculating the regional water level according to the water level point set CWS is: Identify and clean the data once per second to obtain 60 groups of water level point sets CWS within 1 minute. The one-minute regional water level point set AWS is obtained by calculating the spatial water level mean. The water level mean is calculated for the regional water level point set AWS to obtain the regional water level.

10. The water body flooding area early warning method based on image recognition according to claim 9 is characterized in that: In step S7, the spatial water level mean value is calculated by: The 60 water level point sets CWS within 1 minute are sorted according to the horizontal coordinate direction of the water level space, and the average of the 60 water level data at the same point position is calculated in turn to obtain the one-minute regional water level point set AWS.

Images