A small and micro water body monitoring, mapping and evaluation system and method

Abstract

The present invention discloses a small and micro water body monitoring, mapping and evaluation system and method, belonging to the technical field of water body monitoring, including: obtaining an initial image group of an area to be mapped, sequentially splicing all the initial images in the initial image group, and generating an area image of the area to be mapped; summarizing all point areas, generating water body points of the area to be mapped, and setting the water body points with actual areas within a preset area range as small and micro water body points; summarizing the list information of all small and micro water body points in the area to be mapped based on preset tags, inputting all supplementary images included in the supplementary image set into an image processing model for learning and training, and outputting the pollution level prediction of the small and micro water body points within the predicted time, and writing the pollution level prediction into the list information; generating a inspection route based on the water quality pollution degree and location coordinates, and sending the inspection route to the management personnel. Through the present invention, the integrity and accuracy of monitoring and evaluating small and micro water body points can be improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of water body monitoring, and particularly relates to a monitoring, mapping and evaluation system and method for small and micro water bodies. Background Art

[0002] With the acceleration of the urbanization process, the protection and treatment of small and micro water bodies have become an important part of water environment management. Small and micro water bodies include, but are not limited to, ditches, ponds, fish ponds, etc., and their health conditions are directly related to the regional ecological environment and the living quality of residents. The existing monitoring methods are inefficient and costly, and it is difficult to meet the current monitoring requirements. It is necessary to improve the monitoring efficiency and data accuracy to provide a scientific basis for the protection and treatment of small and micro water bodies.

[0003] Similar prior arts include a Chinese patent application with the publication number CN116597355A, which discloses a real-time monitoring method, system and device for the state of small and micro water bodies based on a vision system, and is applied to the technical field of water environment management; obtaining monitoring data of small and micro water bodies; comparing the current data with a preset threshold value to output the water body state; using the current data, historical data and water body state as a data set to train a water body state prediction model to obtain a calibrated water body state prediction model, and obtaining the water body state at a future moment according to the calibrated water body state prediction model, judging the early warning level through the water body state at the future moment, and feeding it back to the management personnel. This invention obtains the current water body state through images such as floating objects and the color, smell, water quality, etc. of the water body; at the same time, combines historical data with the current water body state to construct a water body state prediction model to predict the water body state at a future moment, obtains the water body state at the future moment, judges the early warning according to the water body state level at the future moment, and feeds it back to the management personnel for early warning. There is also a Chinese patent application with the publication number CN117078490A, which discloses a risk assessment method for urban small and micro water bodies based on synchronous analysis of multiple factors, including: collecting the direct water body data and indirect impact data of the target water body, respectively recorded as type A data and type B data, where type A data contains the time series data sequences of several direct indicators, and type B data contains the time series data sequences of several indirect indicators, obtaining the information richness of each time series data sequence, taking any time series data sequence of a direct indicator as the target direct data sequence, taking any time series data sequence of an indirect indicator as the target indirect data sequence, obtaining the correlation between the target direct data sequence and the target indirect data sequence, thereby obtaining the relevance between the target indirect data sequence and type A data, and thus obtaining the risk assessment value of the target water body. This invention adapts the dimension reduction parameters to improve the accuracy of the risk assessment value of urban small and micro water bodies.

[0004] However, in the above-mentioned prior art, the specific coordinates of small and micro water bodies are not investigated, which will lead to the problem of monitoring omission. Using multiple types of data to conduct risk assessment on small and micro water bodies makes the data collection method too complex and requires high equipment costs. Summary of the Invention

[0005] To solve the above problems, the present invention provides a monitoring, mapping and evaluation system and method for small and micro water bodies to solve the problems in the prior art.

[0006] To achieve the above invention purpose, the present invention proposes a monitoring, mapping and evaluation method for small and micro water bodies, including:

[0007] S1: Use a drone to obtain an initial image set of the area to be mapped based on a preset shooting trajectory and shooting method, splice all the initial images in the initial image set in sequence, and generate an area image of the area to be mapped;

[0008] S2: Construct an extraction model, extract the point area of the initial image based on the extraction model, calculate the measured area of the point area based on the shooting method, mark the position coordinates of all the point areas in the area image, summarize all the point areas, generate the water body points of the area to be mapped, and obtain the actual area of the water body points based on the measured area. Set the water body points whose actual area is within a preset area range as small and micro water body points;

[0009] S3: Summarize the list information of all the small and micro water body points in the area to be mapped based on a preset label. The drone obtains a supplementary image set corresponding to the small and micro water body points based on a preset time period, constructs an image processing model, inputs all the supplementary images included in the supplementary image set into the image processing model for learning and training, and outputs the pollution level prediction of the small and micro water body points within the prediction time, and write the pollution level prediction into the list information;

[0010] S4: Mark the water quality pollution degree of all the small and micro water body points based on the list information, generate a inspection route based on the water quality pollution degree and the position coordinates, and send the inspection route to the management personnel to complete the monitoring and evaluation of the small and micro water body points in the area to be mapped.

[0011] Further, the step of using a drone to obtain an initial image set of the area to be mapped based on a preset shooting trajectory and shooting method includes the following steps:

[0012] Obtain the GIS coordinates of the area to be drawn, construct a region box containing the area to be drawn based on the GIS coordinates, set the shooting range, flight altitude, flight speed and shooting parameters of the drone, divide the region box into multiple grid points based on the shooting range, and the drone takes the grid points corresponding to the vertices of the region box as the starting point and flies and shoots at any grid point in an S-shaped route in turn to generate multiple initial images, and combine all the initial images to generate the initial image group. Among them, set the S-shaped route as the shooting trajectory, and set the combination of the flight altitude, the flight speed and the shooting parameters as the shooting method. There is an overlapping area between the initial images corresponding to any two adjacent grid points.

[0013] Further, generate the regional image of the area to be drawn based on the following steps:

[0014] Define the initial images corresponding to the two grid points adjacent to the starting point as comparison images, extract the feature points of the comparison images respectively based on the feature extraction algorithm, perform feature point matching on the feature points of the two comparison images to extract feature point pairs, set any feature point pair as a key point, and set the maximum pixel area included in all the key points as the overlapping area;

[0015] Calculate the transformation matrix between the key points in the two comparison images based on the least squares method, calculate the predicted positions of the remaining key points in the two comparison images based on the transformation matrix, calculate the residuals of all the key points based on the predicted positions and the actual positions of the remaining key points, adjust the parameters of the transformation matrix until the sum of all the residuals is the smallest, and set the adjusted transformation matrix as the image transformation matrix;

[0016] Stitch the two comparison images based on the image transformation matrix to generate a stitched image, and stitch the stitched image and the initial image corresponding to the next grid point based on this step to generate a new stitched image. Repeat this step until all the initial images corresponding to all the grid points are stitched, and set the last new stitched image as the regional image.

[0017] Further, the steps for extracting the point position area in the initial image based on the extraction model include the following:

[0018] The extraction model performs deblurring processing on the initial image based on the deblurring algorithm to generate a clear image, respectively obtains the reflectance ratio between any pixel in the clear image between the first preset band and the second preset band, and combines the reflectance ratios corresponding to all pixels to generate a reflectance ratio distribution image;

[0019] Construct a coordinate system, set the value corresponding to the reflectivity ratio in the reflectivity ratio distribution image as the abscissa, and set the number of pixels included in any reflectivity ratio as the ordinate. Based on the abscissa and the ordinate, fit and plot a first reflectivity distribution curve in the coordinate system;

[0020] In the first reflectivity distribution curve, extract two adjacent inflection points, calculate the difference between the ordinates corresponding to the two inflection points, set the two inflection points with the largest difference as the demarcation points, set the reflectivity ratio corresponding to the smallest number of pixels in the demarcation points as the first threshold, and set the pixels in the reflectivity ratio distribution image with a reflectivity ratio less than or equal to the first threshold as the sub-region;

[0021] Based on this step, generate a second threshold corresponding to the first preset band and the second preset band in the reflectivity ratio distribution image, and the second threshold is greater than the first threshold. Set the pixels in the sub-region with a new reflectivity ratio less than or equal to the second threshold as the point position region.

[0022] Further, the obtaining the actual area of the water body point position based on the measured area includes the following steps:

[0023] Based on the shooting method, calculate the number of pixels included in the point position region and the pixel area of any pixel, and set the product of the number of pixels corresponding to the point position region and the pixel area as the measured area;

[0024] In the regional image, if there are adjacent pixels between the point position regions included in any two initial images, merge the point position regions in the two initial images and set them as the water body point position. Otherwise, set the point position regions included in the two initial images as the water body point positions respectively;

[0025] Accumulate the measured areas of the point position regions corresponding to the water body point positions to generate the actual area.

[0026] Further, the summarizing the list information of all the small water body point positions in the area to be drawn based on the preset label includes the following steps:

[0027] The preset tag includes a location area, an area size, and a point ID. Obtain the grid position of the grid points corresponding to the initial image in the grid of the area box, and generate the point position of the small water body point in the area to be drawn based on the grid position and the position coordinates. Set the point position as the information of the location area, set the actual area corresponding to the small water body point as the information of the area size, mark and number the small water body points and set them as the information of the point ID, and summarize the information of all the small water body points based on the preset tag to generate the list information.

[0028] Further, based on the following steps, output the pollution level prediction of the small water body point within the predicted time:

[0029] The preset time period includes multiple time points. Combine all the supplementary images corresponding to the time points and set them as the supplementary image set;

[0030] The image processing model extracts the spectral data of all the supplementary images, clusters all the spectral data to generate a preset number of clustering clusters, extracts the best bands in each clustering cluster based on the feature selection algorithm, obtains the spectral data belonging to the best bands in the clustering cluster, and sets it as the training set. Input all the training sets into the image processing model for training and learning to generate a prediction model. The prediction model outputs the concentration prediction result within the predicted time based on the training set, and sets the concentration prediction result as the pollution level prediction.

[0031] Further, based on the following steps, generate the inspection route:

[0032] Set up a pollution concentration table. Calculate the water quality distribution mean based on the pollution level prediction and the actual area, obtain the pollution level corresponding to the water quality distribution mean in the pollution concentration table, and set the pollution level as the water quality pollution degree;

[0033] In the list information, arrange all the small water body points in descending order based on the water quality pollution degree to generate an inspection serial number, and connect the position coordinates of the small water body points in sequence based on the inspection serial number to generate the inspection route.

[0034] The present invention also provides a small water body monitoring, drawing and evaluation system, which is used to implement the above-mentioned small water body monitoring, drawing and evaluation method. The system mainly includes:

[0035] A drawing module, which uses a drone to obtain an initial image group of the area to be drawn based on a preset shooting trajectory and shooting method, splices all the initial images in the initial image group in sequence, and generates the area image of the area to be drawn;

[0036] An extraction module constructs an extraction model, extracts the point position areas of the initial image based on the extraction model, calculates the measured areas of the point position areas based on the shooting method, marks the position coordinates of all the point position areas in the regional image, aggregates all the point position areas, generates the water body point positions of the area to be drawn, obtains the actual areas of the water body point positions based on the measured areas, and sets the water body point positions with the actual areas within a preset area range as small water body point positions;

[0037] An analysis module aggregates the list information of all the small water body point positions in the area to be drawn based on preset tags. The unmanned aerial vehicle obtains a supplementary image set corresponding to the small water body point positions based on a preset time period, constructs an image processing model, inputs all the supplementary images included in the supplementary image set into the image processing model for learning and training, and outputs the pollution level prediction of the small water body point positions within the predicted time, and writes the pollution level prediction into the list information;

[0038] A monitoring module marks the water quality pollution degrees of all the small water body point positions based on the list information, generates a inspection route based on the water quality pollution degrees and the position coordinates, sends the inspection route to the management personnel, and completes the monitoring and evaluation of the small water body point positions in the area to be drawn.

[0039] Compared with the prior art, the beneficial effects of the present invention are at least as follows:

[0040] The present invention first generates a regional image of the area to be drawn through an initial image group, which can improve the integrity of the area to be drawn. Then, the actual areas and position coordinates of the point position areas are accurately obtained through the extraction model, and the list information of the small water body point positions can be accurately obtained, improving the integrity of the list information. Finally, the water quality of the small water body point positions is predicted through the image processing model to output the pollution level prediction, improving the accuracy of monitoring the small water body point positions.

[0041] The present invention also constructs an inspection route for all the small water body point positions through the list information, which can avoid missing the monitoring and evaluation of the small water body point positions. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 is a step flow chart of a method for monitoring, drawing and evaluating small water bodies according to the present invention;

[0043] Figure 2 is a schematic diagram of the shooting trajectory of the unmanned aerial vehicle in the present invention;

[0044] Figure 3 is a structural diagram of a system for monitoring, drawing and evaluating small water bodies according to the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0045] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0046] It can be understood that the terms "first", "second", etc. used in the present application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish one element from another. For example, without departing from the scope of the present application, the first xx script may be referred to as the second xx script, and similarly, the second xx script may be referred to as the first xx script.

[0047] As Figure 1 shown, a monitoring, mapping and evaluation method for small and micro water bodies includes:

[0048] S1: Using a drone to obtain an initial image group of the area to be mapped based on a preset shooting trajectory and shooting method, splicing all the initial images in the initial image group in sequence, and generating an area image of the area to be mapped.

[0049] Specifically, the present invention uses a spectral imaging instrument carried by a drone to collect images of the area to be mapped, and realizes the monitoring, mapping and evaluation of small and micro water bodies through an image analysis process. In this embodiment, the shooting trajectory refers to the flight trajectory of the drone, and the shooting method refers to the shooting parameters of the spectral imaging instrument carried by the drone. Among them, the shooting method is related to both the flight altitude and the flight speed of the drone. The area to be mapped refers to the overall area where water body monitoring is required. The initial image group is composed of multiple initial images, and the initial image refers to the spectral image generated by the spectral imaging instrument. Among them, the initial image mainly includes the images generated during the process of shooting the area to be mapped. Since the area to be mapped is a relatively large area, the initial images can be spliced in sequence to generate an image containing the complete area to be mapped, which is the area image.

[0050] S2: Construct an extraction model, extract the point area of the initial image based on the extraction model, calculate the measured area of the point area based on the shooting method, mark the position coordinates of all point areas in the area image, summarize all point areas, generate the water body points of the area to be mapped, and obtain the actual area of the water body points based on the measured area. The water body points with the actual area within the preset area range are set as small and micro water body points.

[0051] Specifically, in this embodiment, the extraction model refers to a model used for image feature extraction. The position area can be identified through feature extraction. The position area refers to the area that may be water. The pixel area of any pixel in the initial image can be calculated from the flight altitude and shooting parameters included in the shooting method. The measured area of the position area can be calculated by the number of pixels corresponding to the position area. The position coordinates of the position area can be generated by marking the pixel coordinate points of the position area in the regional image. The water body position refers to all the position areas summarized in the area to be drawn. Since the same position area may be photographed and generated in different initial images, some suspected duplicate position areas need to be checked and set as the water body position. The actual area of the water body position can be calculated from the measured area. For example, the same position area B is photographed and generated in the initial images A1 and A2. Among them, the measured area of the position area B in the initial image A1 is C1, and the measured area of the position area B in the initial image A2 is C2. Then, the actual area C of the position area B needs to be calculated by comparing the number of pixels of the position area B in the regional image. The preset area range refers to the area range that defines small water bodies. For example, the preset area range is , and the water body positions with an actual area less than or equal to D are set as small water body positions.

[0052] S3: Based on the preset tags, summarize the list information of all small water body positions in the area to be drawn. The drone obtains the supplementary image set corresponding to the small water body positions based on the preset time period, constructs an image processing model, inputs all the supplementary images included in the supplementary image set into the image processing model for learning and training, and outputs the pollution level prediction of the small water body positions within the prediction time. Write the pollution level prediction into the list information.

[0053] Specifically, in this embodiment, the preset tags refer to various tag types. Summarize the database of all small water body positions through the preset tags, which is the list information. The supplementary image set is composed of multiple supplementary images. Among them, the preset time period refers to the set time period, and the drone realizes fixed-point shooting within the preset time period. The supplementary image is a spectral image generated by the spectral imaging instrument carried by the drone for shooting the small water body positions. Since the position coordinates of the small water body positions have been obtained, the supplementary image is a precise shooting of the small water body positions, so that the imaging of the supplementary image completely includes the small water body positions. The image processing model refers to a machine learning model, which can train and learn the supplementary image set, and predict the water quality change of the small water body positions within the prediction time through the change process, generate the pollution level prediction, and then summarize and write the pollution level prediction into the list information for convenient statistical analysis.

[0054] According to this solution, the accuracy of water quality monitoring of small water bodies can be improved.

[0055] S4: Mark the water quality pollution levels of all small and micro water body points based on the list information, generate an inspection route based on the water quality pollution levels and location coordinates, and send the inspection route to the management staff to complete the monitoring and evaluation of the small and micro water body points in the area to be mapped.

[0056] Specifically, in this embodiment, the water quality pollution level refers to the pollution index, and the water quality pollution level can be marked through pollution level prediction. The inspection route refers to the inspection planning route for manually monitoring small and micro water body points. By setting the inspection route, the monitoring efficiency of the management staff can be improved, and the monitoring and evaluation of small and micro water body points can be completed quickly.

[0057] As a preferred technical solution of the present invention, obtaining an initial image group of the area to be mapped by using a drone based on a preset shooting trajectory and shooting method includes the following steps:

[0058] Obtain the GIS coordinates of the area to be mapped, construct an area frame including the area to be mapped based on the GIS coordinates, set the shooting range, flight altitude, flight speed, and shooting parameters of the drone, divide the area frame into multiple grid points based on the shooting range, and the drone takes the grid point corresponding to the vertex of the area frame as the starting point and flies and shoots at any grid point in an S-shaped route in turn to generate multiple initial images, and combine all the initial images to generate an initial image group. Among them, the S-shaped route is set as the shooting trajectory, and the combination of the flight altitude, flight speed, and shooting parameters is set as the shooting method, and there is an overlapping area between the initial images corresponding to any two adjacent grid points.

[0059] Specifically, in this embodiment, the GIS coordinates, that is, the coordinates of the Geographic Information System, refer to the coordinates used to locate geographical elements such as points, lines, and surfaces in the geographical space, including but not limited to longitude and latitude coordinates, plane coordinates, elevation coordinates, etc. The area frame can be set as a rectangular frame including the area to be mapped according to the GIS coordinates. The shooting range refers to the size of the shooting area of the spectral imaging instrument carried by the drone. The flight altitude refers to the vertical height between the drone and the shooting ground, that is, the shooting height. The flight speed refers to the speed of the drone flying between grid points. The shooting time of the drone above the grid point can be set by the flight speed. The shooting parameters refer to the imaging parameters of the spectral imaging instrument, including but not limited to the resolution, etc. The shooting trajectory of the drone is as Figure 2 shown. The area frame M2 corresponding to the area to be mapped M1 is divided into multiple grid points. Among them, the drone flies and shoots from the grid point p1 as the starting point in the direction of the arrow → to adjacent grid points in turn, and the flight trajectory corresponding to the S-shaped route can be formed and set as the shooting trajectory. This shooting trajectory makes there be an overlapping area between the initial images corresponding to any two adjacent grid points, which is beneficial to the accuracy of drawing the area image of the area to be mapped.

[0060] As a preferred technical solution of the present invention, the regional image of the area to be drawn is generated based on the following steps:

[0061] Define the initial images corresponding to two grid points adjacent to the starting point as comparison images, respectively extract the feature points of the comparison images based on the feature extraction algorithm, perform feature point matching on the feature points of the two comparison images to extract feature point pairs, set any one of the feature point pairs as the key point, and set the maximum pixel area included in all key points as the superposition area.

[0062] Calculate the transformation matrix between the key points in the two comparison images based on the least squares method, calculate the predicted positions of the remaining key points in the two comparison images based on the transformation matrix, calculate the residuals of all key points based on the predicted positions and the actual positions of the remaining key points, adjust the parameters of the transformation matrix until the sum of all residuals is minimized, and set the adjusted transformation matrix as the image transformation matrix.

[0063] Stitch the two comparison images based on the image transformation matrix to generate a stitched image, and stitch the stitched image and the initial image corresponding to the next grid point based on this step to generate a new stitched image. Repeat this step until all the initial images corresponding to the grid points are stitched, and set the last new stitched image as the regional image.

[0064] Specifically, in this embodiment, the comparison image refers to the initial image corresponding to the grid point adjacent to the starting point. The feature extraction algorithm refers to the SIFT (Scale-Invariant Feature Transform) algorithm, which can detect and describe the local features in the image. These features are invariant to image transformations such as rotation, scale scaling, and brightness change, and then extract feature points and perform feature point matching. The feature point pair refers to the matching feature points in the two comparison images, that is, there is a corresponding transformation relationship between the feature point pairs. The maximum pixel area refers to the pixel range included by all the corresponding key points in the two comparison images, and this pixel range belongs to the same photographed area in the two comparison images.

[0065] The least squares method is a mathematical optimization technique that can find the homography matrix, that is, the transformation matrix, between two comparison images. Calculating the difference between the actual position of any key point and the predicted position rotated by the transformation matrix is the residual of any key point. For example, the actual position of the key point e1 in the comparison image E1 is (x1, y1), and the predicted position of the key point e1 in the comparison image E1 generated by the transformation matrix is (x2, y2). The residual H1 between (x1, y1) and (x2, y2) can be calculated by the first formula, where the first formula is: Accumulate the residuals corresponding to all key points to calculate the sum of the residuals. Adjust the parameters of the transformation matrix to minimize the sum of the residuals, and thus generate the image transformation matrix for the two comparison images.

[0066] The two comparison images can be stitched through rotation combination by the image transformation matrix to generate a stitched image. Then, perform the above stitching steps with the initial image corresponding to the next adjacent grid point to generate a new stitched image. Repeat this step to set the last new stitched image as the regional image of the area to be drawn.

[0067] As a preferred technical solution of the present invention, the steps for extracting the point area in the initial image based on the extraction model include:

[0068] The extraction model performs deblurring processing on the initial image based on the deblurring algorithm to generate a clear image, respectively obtains the reflectance ratio between any pixel in the clear image between the first preset band and the second preset band, and combines the reflectance ratios corresponding to all pixels to generate a reflectance ratio distribution image.

[0069] Construct a coordinate system, set the value corresponding to the reflectance ratio in the reflectance ratio distribution image as the abscissa, and set the number of pixels included in any reflectance ratio as the ordinate. Fit and draw in the coordinate system based on the abscissa and ordinate to generate the first reflectance distribution curve.

[0070] In the first reflectance distribution curve, extract two adjacent inflection points, calculate the difference in the ordinates corresponding to the two inflection points, set the two inflection points with the largest difference as the demarcation points, set the reflectance ratio corresponding to the smallest number of pixels in the demarcation points as the first threshold, and set the pixels in the reflectance ratio distribution image with a reflectance ratio less than or equal to the first threshold as the sub-region.

[0071] Based on this step, generate the second threshold corresponding to the first preset band and the second preset band in the reflectance ratio distribution image, and the second threshold is greater than the first threshold. Set the pixels in the sub-region with a new reflectance ratio less than or equal to the second threshold as the point area.

[0072] Specifically, in this embodiment, the deblurring algorithm is a method for correcting image sharpness, including but not limited to blur detection, machine learning methods, etc. It can perform radiometric correction, atmospheric correction, and geometric correction on the initial image to eliminate distortion and aberration, and define the initial image after deblurring processing as a clear image. Since the initial image is a spectral image, a spectral image is an image that records the radiation reflected or emitted by ground objects at different bands. These images can be multispectral images, containing several relatively wide bands, or hyperspectral images, containing hundreds of continuous and narrow bands. A band refers to the radiation within a specific wavelength range in a spectral image, and each band usually corresponds to a specific region of the electromagnetic spectrum, such as visible light, near-infrared, short-wave infrared, mid-wave infrared, or long-wave infrared bands. Reflectance refers to the ratio of the radiation reflected by the surface of a ground object to the incident radiation. Reflectance is band-specific, and different substances have different reflectances at different bands, which forms the unique spectral characteristics of each substance.

[0073] Among them, the first preset band refers to the red band, and the second preset band refers to the green band. In spectral imaging, the green band and the red band are very important bands because the green band contains information related to vegetation health status, biomass, and other surface features, and the red band contains various information related to surface features. The reflectance ratio refers to the ratio of the reflectances corresponding to the same pixel in the first preset band and the second preset band in the clear image. Based on the corresponding pixel coordinates, all reflectance ratios can generate a reflectance ratio distribution image.

[0074] To statistically analyze the change curve between the number of pixels and the reflectance in the reflectance ratio distribution image, the first reflectance distribution curve can be plotted through a coordinate system. Since there are significant differences in the reflectance of the ground and water in physical properties, the inflection points of the first reflectance distribution curve can be used for screening to obtain the demarcation points. Among them, the demarcation points include two inflection points, and the reflectance ratio of the inflection point with the smallest number of pixels is set as the first threshold. In the reflectance ratio distribution image, pixels less than or equal to the first threshold are likely to be water and shadow areas, and areas greater than the first threshold are surface areas. Therefore, further differentiation of sub-regions is required.

[0075] Analyze the first reflectance ratio image through the same steps, and set the corresponding second threshold, and the second threshold should be greater than the first threshold because the shadow part may be an algal area and also belongs to the point area. Combine the pixels with the new reflectance ratio less than or equal to the second threshold in the sub-region to generate the point area, where the new reflectance ratio refers to the reflectance ratio generated by reprocessing the first reflectance ratio image between the first preset band and the second preset band.

[0076] As a preferred technical solution of the present invention, obtaining the actual area of the water body point based on the measured area includes the following steps:

[0077] Calculate the number of pixels included in the point area and the pixel area of any pixel based on the shooting method, and set the product of the number of pixels corresponding to the point area and the pixel area as the measured area.

[0078] In the regional image, if there are adjacent pixels between the point areas included in any two initial images, merge the point areas in the two initial images and set them as the water body points; otherwise, set the point areas included in the two initial images as the water body points respectively.

[0079] Accumulate the measured areas of the point areas corresponding to the water body points to generate the actual area.

[0080] Specifically, in this embodiment, the pixel area refers to the actual area corresponding to each pixel, which can be converted and generated from the flight altitude of the drone and the resolution in the shooting parameters. Multiply the number of pixels included in the point area by the pixel area to calculate the measured area.

[0081] Adjacent pixels refer to pixels adjacent to each other. The existence of adjacent pixels indicates that the two point areas in the regional image that do not belong to the same initial image belong to the same water body. Therefore, merge the two point areas into one point area and define it as the water body point, and define other point areas as the water body points as well.

[0082] The actual area of the water body point is the measured area of the corresponding point area. If the water body point is generated by merging point areas, the actual area is the result of accumulating and calculating the measured areas of the point areas.

[0083] As a preferred technical solution of the present invention, summarizing the list information of all small and micro water body points in the area to be drawn based on preset tags includes the following steps:

[0084] The preset tags include location area, area size, and point ID. Obtain the grid position of the grid point corresponding to the initial image in the regional frame, and generate the point position of the small and micro water body point in the area to be drawn based on the grid position and the position coordinates. Set the point position as the information of the location area, set the actual area corresponding to the small and micro water body point as the information of the area size, mark the serial number of the small and micro water body point and set it as the information of the point ID, and summarize the information of all small and micro water body points based on the preset tags to generate the list information.

[0085] Specifically, in this embodiment, the position area refers to the coordinate position of the small water body point on the actual ground, the area size refers to the actual area of the small water body point, and the point ID is used to mark and distinguish each small water body point by setting an ID. The position of each small water body point in the area to be drawn can be determined through the grid position and the position coordinates, and the small water body points in the area to be drawn can be quickly located.

[0086] As a preferred technical solution of the present invention, the pollution level prediction of the small water body point within the predicted time is output based on the following steps:

[0087] The preset time period includes multiple time points, and the supplementary images corresponding to all time points are combined and set as a supplementary image set.

[0088] The image processing model extracts the spectral data of all supplementary images, clusters all the spectral data to generate a preset number of clustering clusters, extracts the best bands in each clustering cluster based on the feature selection algorithm, obtains the spectral data belonging to the best bands in the clustering cluster, and sets it as the training set. All the training sets are input into the image processing model for training and learning to generate a prediction model. The prediction model outputs the concentration prediction result within the predicted time based on the training set, and sets the concentration prediction result as the pollution level prediction.

[0089] Specifically, in this embodiment, the supplementary images corresponding to each time point form a supplementary image set, where the supplementary image set is a set of images generated by photographing the same small water body point.

[0090] The image processing model extracts the spectral data of all supplementary images through the algorithm corresponding to the machine learning model. Among them, the spectral data refers to the information of the spectral reflectance or radiance of each pixel point in the supplementary image changing with the wavelength. All the spectral data can be clustered by the Gaussian Mixture Model (GMM), and the preset number of clustering results are set as the clustering clusters. The best band refers to the band that is most effective in distinguishing and identifying specific features (such as the concentration of suspended green algae in the water body) selected from a large number of spectral bands included in the clustering cluster. The training set is constructed by the spectral data corresponding to the best band for learning and training the image processing model, and the trained image processing model is set as the prediction model. The concentration prediction result refers to the band distribution corresponding to the pollutant concentration in the small water body point. It can improve the accuracy of the prediction model and is beneficial to improving the accuracy of water quality assessment.

[0091] As a preferred technical solution of the present invention, the investigation route is generated based on the following steps:

[0092] Set up a pollution concentration table, predict the pollution level, calculate the mean value of water quality distribution based on the actual area, obtain the pollution level corresponding to the mean value of water quality distribution in the pollution concentration table, and set the pollution level as the degree of water quality pollution.

[0093] In the list information, arrange all the small and micro water body points in descending order based on the degree of water quality pollution, generate a survey serial number, and connect the position coordinates of the small and micro water body points in sequence based on the survey serial number to generate a survey route.

[0094] Specifically, in this embodiment, the pollution concentration table is a table used to measure the degree of water body pollution. Different pollution degree intervals correspond to different pollution levels. The mean value of water quality distribution refers to the ratio of the area showing pollution in the pollution level prediction to the actual area. Obtain the pollution degree interval corresponding to the mean value of water quality distribution in the pollution concentration table, and set the pollution level corresponding to the pollution degree interval as the pollution level of this small and micro water body point.

[0095] Arrange the pollution levels corresponding to all small and micro water body points in descending order in sequence by the survey serial number, which is convenient for connecting the position coordinates in sequence according to the survey serial number to generate a survey route. Based on the survey route, the management personnel can quickly realize the monitoring and evaluation of the small and micro water body points.

[0096] As Figure 3 shown, the present invention also provides a small and micro water body monitoring, mapping and evaluation system, which is used to implement the above-mentioned small and micro water body monitoring, mapping and evaluation method. The system mainly includes:

[0097] A mapping module, which uses a drone to obtain an initial image set of the area to be mapped based on a preset shooting trajectory and shooting method, splices all the initial images in the initial image set in sequence, and generates an area image of the area to be mapped.

[0098] An extraction module, which constructs an extraction model, extracts the point area of the initial image based on the extraction model, calculates the measured area of the point area based on the shooting method, marks the position coordinates of all point areas in the area image, summarizes all point areas, generates the water body points of the area to be mapped, and obtains the actual area of the water body points based on the measured area. Set the water body points with the actual area within the preset area interval as small and micro water body points.

[0099] An analysis module, which summarizes the list information of all small and micro water body points in the area to be mapped based on a preset label. The drone obtains a supplementary image set corresponding to the small and micro water body points based on a preset time period, constructs an image processing model, inputs all the supplementary images included in the supplementary image set into the image processing model for learning and training, and outputs the pollution level prediction of the small and micro water body points within the prediction time, and writes the pollution level prediction into the list information.

[0100] The monitoring module marks the water quality pollution degree of all small and micro water body points based on the list information, generates a survey route based on the water quality pollution degree and location coordinates, sends the survey route to the management personnel, and completes the monitoring and evaluation of the small and micro water body points in the area to be mapped.

[0101] It should be understood that although the steps in the flowcharts of the embodiments of the present invention are shown in sequence according to the indication of the arrows, these steps do not necessarily have to be executed in the order indicated by the arrows. Unless clearly stated in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment may include multiple sub-steps or multiple stages. These sub-steps or stages do not necessarily have to be executed at the same moment, but can be executed at different moments. The execution order of these sub-steps or stages does not necessarily have to be sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0102] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The above program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0103] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope described in this specification.

[0104] The above embodiments only represent several implementation manners of the present invention. Their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the patent for the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all fall within the protection scope of the present invention. Therefore, the protection scope of the patent for the present invention shall be subject to the appended claims.

[0105] The above is only the preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A monitoring, mapping and evaluation method for small water bodies, characterized in that, The method includes the following steps: S1: Use a drone to obtain an initial image set of the area to be mapped based on a preset shooting trajectory and shooting method, sequentially splice all the initial images in the initial image set, and generate an area image of the area to be mapped; S2: Construct an extraction model, extract the point regions of the initial images based on the extraction model, calculate the measured area of the point regions based on the shooting method, mark the position coordinates of all the point regions in the area image, summarize all the point regions to generate the water body points of the area to be mapped, obtain the actual area of the water body points based on the measured area, and set the water body points with the actual area within a preset area range as small and micro water body points; The extraction of the point regions of the initial images based on the extraction model includes the following steps: S21: The extraction model performs deblurring processing on the initial image based on a deblurring algorithm to generate a clear image, respectively obtains the reflectance ratio between any pixel in the clear image between a first preset band and a second preset band, and combines the reflectance ratios corresponding to all pixels to generate a reflectance ratio distribution image; S22: Construct a coordinate system, set the value corresponding to the reflectance ratio in the reflectance ratio distribution image as the abscissa, set the number of pixels included in any reflectance ratio as the ordinate, and fit and draw a first reflectance distribution curve in the coordinate system based on the abscissa and the ordinate; S23: In the first reflectance distribution curve, extract two adjacent inflection points, calculate the difference between the ordinates corresponding to the two inflection points, set the two inflection points with the largest difference as demarcation points, set the reflectance ratio corresponding to the smallest number of pixels in the demarcation points as the first threshold, and set the pixels with the reflectance ratio less than or equal to the first threshold in the reflectance ratio distribution image as sub-regions; S24: Generate a second threshold corresponding to the sub-region in the first preset band and the second preset band based on the same steps as S21 - S23, and the second threshold is greater than the first threshold, and set the pixels with the new reflectance ratio less than or equal to the second threshold in the sub-region as the point regions; S3: Summarize the list information of all the small and micro water body points in the area to be mapped based on a preset label, the drone obtains a supplementary image set corresponding to the small and micro water body points based on a preset time period, constructs an image processing model, inputs all the supplementary images included in the supplementary image set into the image processing model for learning and training, and outputs a pollution level prediction of the small and micro water body points within the predicted time, and writes the pollution level prediction into the list information; S4: Mark the water quality pollution degree of all the small and micro water body points based on the list information, generate a inspection route based on the water quality pollution degree and the position coordinates, and send the inspection route to the management personnel to complete the monitoring and evaluation of the small and micro water body points in the area to be mapped.

2. The method according to claim 1, characterized in that, The step of obtaining the initial image group of the area to be drawn by using a drone based on a preset shooting trajectory and shooting method includes the following steps: Obtain the GIS coordinates of the area to be drawn, construct an area frame including the area to be drawn based on the GIS coordinates, set the shooting range, flight altitude, flight speed and shooting parameters of the drone, divide the area frame into multiple grid points based on the shooting range, and the drone takes off from the grid point corresponding to the vertex of the area frame and flies and shoots at any grid point in an S-shaped route in turn to generate multiple initial images, and combine all the initial images to generate the initial image group. Among them, set the S-shaped route as the shooting trajectory, and set the combination of the flight altitude, the flight speed and the shooting parameters as the shooting method, and there is an overlapping area between the initial images corresponding to any two adjacent grid points.

3. The method according to claim 2, wherein Generate the area image of the area to be drawn based on the following steps: Define the initial images corresponding to the two grid points adjacent to the starting point as comparison images, extract the feature points of the comparison images respectively based on the feature extraction algorithm, perform feature point matching on the feature points of the two comparison images to extract feature point pairs, set any one feature point pair as the key point, and set the largest pixel area included in all the key points as the overlapping area; Calculate the transformation matrix of the key points between the two comparison images based on the least squares method, calculate the predicted positions of the remaining key points in the two comparison images based on the transformation matrix, calculate the residuals of all the key points based on the predicted positions and the actual positions of the remaining key points, adjust the parameters of the transformation matrix until the sum of all the residuals is the smallest, and set the adjusted transformation matrix as the image transformation matrix; Stitch the two comparison images based on the image transformation matrix to generate a stitched image, and stitch the stitched image and the initial image corresponding to the next grid point based on this step to generate a new stitched image. Repeat this step until all the initial images corresponding to all the grid points are stitched, and set the last new stitched image as the area image.

4. The method according to claim 1, wherein The step of obtaining the actual area of the water body point based on the measured area includes the following steps: Calculate the number of pixels included in the point area and the pixel area of any pixel based on the shooting method, and set the product of the number of pixels corresponding to the point area and the pixel area as the measured area; In the area image, if there are adjacent pixels between the point areas included in any two initial images, merge the point areas in the two initial images and set them as the water body points, otherwise, set the point areas included in the two initial images as the water body points respectively; Accumulate the measured areas of the point areas corresponding to the water body points to generate the actual area.

5. The method according to claim 2, wherein The step of summarizing the list information of all the small water body points in the area to be drawn based on the preset label includes the following steps: The preset tag includes a position area, an area size, and a point ID. Obtain the grid position of the grid point corresponding to the initial image in the grid of the area frame, and generate the point position of the small water body point in the area to be drawn based on the grid position and the position coordinates. Set the point position as the information of the position area, set the actual area corresponding to the small water body point as the information of the area size, mark the serial number of the small water body point and set it as the information of the point ID, and summarize the information of all the small water body points based on the preset tag to generate the directory information.

6. The method according to claim 1, wherein Output the pollution level prediction of the small water body point within the predicted time based on the following steps: The preset time period includes multiple time points. Combine all the supplementary images corresponding to the time points and set them as the supplementary image set; The image processing model extracts the spectral data of all the supplementary images, clusters all the spectral data to generate a preset number of clustering clusters, extracts the best bands in each clustering cluster based on the feature selection algorithm, obtains the spectral data belonging to the best bands in the clustering cluster, and sets it as the training set. Input all the training sets into the image processing model for training and learning to generate a prediction model. The prediction model outputs the concentration prediction result within the predicted time based on the training set, and sets the concentration prediction result as the pollution level prediction.

7. The method according to claim 6, wherein Generate the inspection route based on the following steps: Set up a pollution concentration table, calculate the mean value of water quality distribution based on the pollution level prediction and the actual area, obtain the pollution level corresponding to the mean value of water quality distribution in the pollution concentration table, and set the pollution level as the water quality pollution degree; In the directory information, arrange all the small water body points in descending order based on the water quality pollution degree to generate an inspection serial number, and connect the position coordinates of the small water body points in sequence based on the inspection serial number to generate the inspection route.

8. A small and micro water body monitoring, mapping and evaluation system for implementing the method according to any one of claims 1-7, characterized in that, The system includes the following modules: A drawing module that uses a drone to obtain an initial image group of the area to be drawn based on a preset shooting trajectory and shooting method, splices all the initial images in the initial image group in sequence, and generates the area image of the area to be drawn; An extraction module that constructs an extraction model, extracts the point area of the initial image based on the extraction model, calculates the measured area of the point area based on the shooting method, marks the position coordinates of all the point areas in the area image, summarizes all the point areas to generate the water body points of the area to be drawn, and obtains the actual area of the water body points based on the measured area. Set the water body points with the actual area within the preset area range as small water body points; The analysis module summarizes the list information of all the small water body points in the area to be drawn based on preset tags. The drone obtains a supplementary image set corresponding to the small water body points based on a preset time period, constructs an image processing model, inputs all the supplementary images included in the supplementary image set into the image processing model for learning and training, and outputs the pollution level prediction of the small water body points within the predicted time, and writes the pollution level prediction into the list information; The monitoring module marks the water quality pollution degree of all the small water body points based on the list information, generates an inspection route based on the water quality pollution degree and the position coordinates, sends the inspection route to the management personnel, and completes the monitoring and evaluation of the small water body points in the area to be drawn.

Images