Water ecological restoration evaluation method based on unmanned aerial vehicle image

Abstract

The application discloses an ecological restoration evaluation method based on unmanned aerial vehicle images and relates to the technical field of water ecological restoration evaluation, and comprises the following steps: obtaining a multispectral image of a target water ecological restoration area based on an unmanned aerial vehicle, and marking the image as a real-time monitoring image; constructing a real-time qualified evaluation value based on the real-time monitoring image; obtaining a historical clear water evaluation value based on the multispectral image of the qualified water ecological restoration area; obtaining a first distinguishing threshold value based on the historical clear water evaluation value; obtaining a historical algae pollution evaluation value based on the multispectral image of an unqualified water ecological restoration area; obtaining a second distinguishing threshold value and a third distinguishing threshold value based on the historical algae pollution evaluation value; and evaluating the water ecological restoration based on the real-time qualified evaluation value, the first distinguishing threshold value, the second distinguishing threshold value and the third distinguishing threshold value; the application is used to solve the problem that the existing ecological restoration evaluation technology cannot adapt to water ecological restoration evaluation, resulting in inaccurate water ecological restoration evaluation results.

Description

Technical Field

[0001] This invention relates to the field of ecological restoration assessment technology, specifically a method for assessing water ecological restoration based on UAV images. Background Technology

[0002] Aquatic ecosystem restoration is one of the core means to address the global water crisis and ecological degradation. Whether restoration projects have truly achieved their expected ecological goals and how to quantify their effectiveness have become core scientific issues that urgently need to be addressed in the field of water ecological management. Traditional ecological restoration assessment methods mainly rely on manual surveys and sampling. This method is subjective, complex, and time-consuming. Furthermore, existing ecological assessments primarily depend on extracting the G pass value from RGB, i.e., the green color of vegetation. However, this is not suitable for aquatic ecological restoration. For example, patent application CN118469351A discloses an ecological restoration assessment method that relies on extracting the G pass value from RGB, which is not suitable for aquatic ecological restoration. At the same time, the complexity of the aquatic environment means that existing ecological restoration assessment technologies cannot adapt to aquatic ecological restoration assessments, resulting in inaccurate assessment results. Summary of the Invention

[0003] This invention aims to at least partially address one of the technical problems in the prior art. It involves acquiring multispectral images of a target aquatic ecological restoration area using drones and marking them as real-time monitoring images; constructing real-time qualification assessment values ​​based on these images; obtaining historical clear water assessment values ​​from the multispectral images of qualified aquatic ecological restoration areas; obtaining a first differentiation threshold based on these historical clear water assessment values; obtaining historical algae pollution assessment values ​​from the multispectral images of unqualified aquatic ecological restoration areas; obtaining a second and third differentiation thresholds based on these historical algae pollution assessment values; and evaluating the aquatic ecological restoration based on the real-time qualification assessment values, the first differentiation threshold, the second differentiation threshold, and the third differentiation threshold. This addresses the problem that existing ecological restoration assessment technologies are inadequate for aquatic ecological restoration assessment, leading to inaccurate assessment results.

[0004] To achieve the above objectives, this application provides a method for assessing water ecological restoration based on UAV imagery, comprising the following steps: Multispectral images of the target aquatic ecological restoration area acquired by drones were labeled as real-time monitoring images. Construct real-time compliance assessment values ​​based on real-time monitoring images; Historical clear water assessment values ​​were obtained from multispectral images of qualified water ecological restoration areas; The first distinction threshold is obtained based on historical clear water assessment values; Historical algal pollution assessment values ​​were obtained from multispectral images of substandard aquatic ecological restoration areas. The second and third differentiation thresholds are obtained based on historical algae assessment values; The water ecological restoration is assessed based on real-time compliance assessment values, a first differentiation threshold, a second differentiation threshold, and a third differentiation threshold.

[0005] Furthermore, constructing real-time compliance assessment values ​​based on real-time monitoring images includes the following sub-steps: Acquire the near-infrared band of each pixel in the real-time monitoring image and mark it as the real-time near-infrared band; Obtain the red light band of each pixel in the real-time monitoring image and mark it as the real-time red light band; The real-time qualification assessment value of each pixel in the real-time monitoring image is obtained as follows: F1 = (H1 - H2) / (H1 + H2); where F1 is the real-time qualification assessment value, H1 is the real-time near-infrared band, and H2 is the real-time red band.

[0006] Furthermore, obtaining historical clear water assessment values ​​based on multispectral images of qualified aquatic ecological restoration areas includes the following sub-steps: Obtain images of clear water areas from multispectral images of qualified aquatic ecological restoration areas and label them as historical clear water images; Obtain the real-time qualification assessment value of each pixel in the historical clear water image and mark it as the historical clear water assessment value.

[0007] Furthermore, obtaining the first distinguishing threshold based on historical clean water assessment values ​​includes the following sub-steps: Obtain the first number of historical clean water assessment values; A Cartesian coordinate system is established with historical clean water assessment values ​​as the horizontal axis and the number of historical clean water assessment values ​​as the vertical axis. This system is labeled as the historical clean water coordinate system. Obtain the historical clean water assessment values ​​and corresponding quantities as coordinate points on the x and y axes, and mark them as historical clean water coordinate points; Plot all historical Qingshui coordinate points on the historical Qingshui coordinate system to obtain a scatter plot, and label it as the historical Qingshui scatter plot.

[0008] Furthermore, obtaining the first distinguishing threshold based on historical clean water assessment values ​​also includes the following sub-steps: Get the maximum value of the ordinate among all historical clear water coordinate points and mark it as the historical clear water height; Set a length value and mark it as the first rectangle setting value; Create a rectangle on the horizontal axis of the historical clear water coordinate system with a height equal to the historical clear water height and a width equal to the first rectangle's set value. This rectangle can be moved left and right and is marked as the first data rectangle. The total number of historical clean water assessment values ​​corresponding to the historical clean water coordinate points included within the first data rectangle is marked as the number of the first rectangle; The range of historical clear water assessment values ​​is marked as the historical clear water length; Assuming that the historical clear water assessment values ​​are uniformly distributed within the historical clear water length, obtain the number of rectangle judgments at this time and mark it as the average number of the first rectangle; Set a first ratio, obtain the product of the average number of first rectangles and the first ratio, and mark it as the first abnormal threshold; In the historical clear water scatter plot, the first data rectangle is shifted to the left starting from the rightmost historical clear water assessment value. When the number of the first rectangles is greater than or equal to the first anomaly threshold, the movement of the first data rectangle is stopped. The historical clear water assessment value corresponding to the largest x-coordinate of the first data rectangle at this time is obtained and marked as the first differentiation threshold.

[0009] Furthermore, obtaining historical algal pollution assessment values ​​based on multispectral images of substandard aquatic ecological restoration areas includes the following sub-steps: Obtain images of algae-contaminated areas from multispectral images of substandard aquatic ecological restoration areas and label them as historical algae-contaminated images; Obtain the real-time qualification assessment value of each pixel in the historical algae pollution image and mark it as the historical algae pollution assessment value.

[0010] Furthermore, obtaining the second and third differentiation thresholds based on historical algae assessment values ​​includes the following sub-steps: Obtain a second number of historical algae assessment values; A Cartesian coordinate system is established with historical algae assessment values ​​as the horizontal axis and the number of historical algae assessment values ​​as the vertical axis. This system is labeled as the historical algae coordinate system. Obtain historical algae assessment values ​​and corresponding quantities as coordinate points on the x and y axes, and mark them as historical algae coordinate points; Plot all historical algae pollution coordinates on the historical algae pollution coordinate system to obtain a scatter plot, and label it as the historical algae pollution scatter plot.

[0011] Furthermore, obtaining the second and third differentiation thresholds based on historical algae assessment values ​​also includes the following sub-steps: Get the maximum value of the ordinate among all historical algae coordinate points and mark it as the historical algae height; Set a length value and mark it as the second rectangle setting value; Create a rectangle on the horizontal axis of the historical algae coordinate system with a height equal to the historical algae height and a width equal to the second rectangle setting value, and mark it as the second data rectangle; The total number of historical algae assessment values ​​corresponding to the historical algae coordinate points included within the second data rectangle is marked as the number of the second rectangle; The range length of historical algae pollution assessment values ​​is marked as the historical algae pollution length; Assuming that the historical algae assessment values ​​are uniformly distributed within the length of the historical algae, the number of rectangle judgments at this time is obtained and marked as the average number of the second rectangle; Set a second ratio, obtain the product of the average number of the second rectangles and the second ratio, and mark it as the second abnormal threshold.

[0012] Furthermore, obtaining the second and third differentiation thresholds based on historical algae assessment values ​​also includes the following sub-steps: In the historical algae scatter plot, the second data rectangle is shifted to the right starting from the leftmost historical algae assessment value. When the number of the second rectangles is greater than or equal to the second anomaly threshold, the movement of the second data rectangle is stopped. The historical algae assessment value corresponding to the smallest x-coordinate of the second data rectangle at this time is obtained and marked as the second discrimination threshold. In the historical algae scatter plot, the second data rectangle is shifted to the left starting from the rightmost historical algae assessment value. When the number of the second rectangles is greater than or equal to the second anomaly threshold, the movement of the second data rectangle is stopped. The historical algae assessment value corresponding to the largest x-coordinate of the second data rectangle at this time is obtained and marked as the third differentiation threshold.

[0013] Furthermore, the assessment of aquatic ecological restoration based on real-time compliance assessment values, a first distinguishing threshold, a second distinguishing threshold, and a third distinguishing threshold includes the following sub-steps: Areas with real-time qualification assessment values ​​less than the first distinction threshold are marked as areas of qualified clean water in real-time detection. The regions whose real-time qualification assessment values ​​are greater than the first distinction threshold and less than the second distinction threshold are marked as abnormally turbid regions detected in real time. Areas with real-time compliance assessment values ​​greater than the second distinction threshold and less than the third distinction threshold are marked as areas of abnormal algae detection in real time. Areas with real-time qualified assessment values ​​greater than the third distinction threshold are marked as qualified water-containing plant areas in real-time detection.

[0014] The beneficial effects of this invention are as follows: This invention acquires multispectral images of the target aquatic ecological restoration area using UAVs and marks them as real-time monitoring images; constructs real-time qualification assessment values ​​based on the real-time monitoring images; obtains historical clear water assessment values ​​based on the multispectral images of qualified aquatic ecological restoration areas; obtains a first differentiation threshold based on the historical clear water assessment values; obtains historical algae pollution assessment values ​​based on the multispectral images of unqualified aquatic ecological restoration areas; obtains a second and third differentiation thresholds based on the historical algae pollution assessment values; and evaluates aquatic ecological restoration based on the real-time qualification assessment values, the first differentiation threshold, the second differentiation threshold, and the third differentiation threshold. The advantage lies in its ability to adapt to aquatic ecological restoration assessment, thereby improving the accuracy of the aquatic ecological restoration assessment results. This invention constructs real-time qualification assessment values ​​based on real-time monitoring images. Its advantage lies in its ability to adapt to different water conditions and improve the accuracy of water ecological restoration assessment results. Attached Figure Description

[0015] Figure 1 This is a flowchart of the steps of the method of the present invention; Figure 2 This is a schematic diagram of the first distinguishing threshold. Figure 3 This is a schematic diagram of the second and third differentiation thresholds of the present invention. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] Example 1, please refer to Figure 1 As shown, this application provides a method for assessing water ecological restoration based on UAV imagery, including the following steps: Step S1: Based on the multispectral images of the target aquatic ecological restoration area acquired by the UAV, the images are marked as real-time monitoring images; that is, multispectral images of the target aquatic ecological restoration water surface area. The multispectral images are used for better assessment of aquatic ecological restoration.

[0018] Step S2, constructing a real-time compliance assessment value based on the real-time monitoring image; Step S2 includes the following sub-steps: Step S201: Obtain the near-infrared band of each pixel in the real-time monitoring image and mark it as the real-time near-infrared band; Step S202: Obtain the red light band of each pixel in the real-time monitoring image and mark it as the real-time red light band; Step S203: Obtain the real-time pass assessment value for each pixel in the real-time monitoring image: F1 = (H1 - H2) / (H1 + H2); where F1 is the real-time pass assessment value, H1 is the real-time near-infrared band, and H2 is the real-time red light band. If the F1 value is negative or close to 0 for clear water, it is because pure water molecules are strong absorbers. Whether it's red light or near-infrared light, once it hits the water surface, most of it is absorbed, and very little is reflected back to the sensor. If the F1 value is higher for turbid water than for clear water, it is because water... Suspended sediment and organic particles strongly scatter light. If abnormal algae have a moderately positive F1 value, it's because algae are prokaryotes. Although they have chlorophyll and can absorb red light, their cell structure is simple and lacks the complex porous sponge tissue found in higher plant leaves. Therefore, their near-infrared reflectivity is far inferior to that of higher plants. If normal, clear underwater vegetation has a high positive F1 value, it's because of the strong absorption peak of chlorophyll at red light and the strong reflection peak of the porous structure of leaves at near-infrared light. Therefore, F1 can be used to assess aquatic ecological restoration, and different ecological restoration situations can be identified.

[0019] Step S3 involves obtaining historical clear water assessment values ​​based on multispectral images of qualified aquatic ecological restoration areas. Step S3 includes the following sub-steps: Step S301: Obtain images of clear water areas from multispectral images of qualified aquatic ecological restoration areas and mark them as historical clear water images; Step S302: Obtain the real-time qualified assessment value of each pixel in the historical clear water image and mark it as the historical clear water assessment value.

[0020] Step S4: Obtain the first distinction threshold based on historical clean water assessment values; Step S4 includes the following sub-steps: Step S401: Obtain a first number of historical clean water assessment values; in order to obtain the range of historical clean water assessment values, the first number should not be set too small, for example, the first number is 1000; Step S402: Establish a Cartesian coordinate system with historical clean water assessment values ​​as the horizontal axis data and the number of historical clean water assessment values ​​as the vertical axis data, and mark it as the historical clean water coordinate system; Step S403: Obtain the historical clean water assessment values ​​and the corresponding quantities as coordinate points on the x-axis and y-axis, and mark them as historical clean water coordinate points; Step S404: Plot all historical clear water coordinate points on the historical clear water coordinate system to obtain a scatter plot, and mark it as a historical clear water scatter plot; For practical applications, please refer to Figure 2 As shown, the obtained historical scatter plot of clear water is presented.

[0021] Step S405: Obtain the maximum value of the ordinate among all historical clear water coordinate points and mark it as the historical clear water height; Step S406: Set a length value, marked as the first rectangle setting value; the first rectangle setting value is set to construct the first data rectangle, and the first data rectangle is used to observe the distribution of historical clear water evaluation values. Since the first rectangle setting value should not be too large, for example, the first rectangle setting value is 0.01. Step S407: Create a rectangle on the horizontal axis of the historical clear water coordinate system with a height equal to the historical clear water height and a width equal to the first rectangle setting value, and mark it as the first data rectangle; Step S408: Mark the total number of historical clean water assessment values ​​corresponding to the historical clean water coordinate points included in the first data rectangle as the number of the first rectangle; Step S409: Mark the range length of the historical clean water assessment value as the historical clean water length; Step S410: Assuming that the historical clear water assessment value is uniformly distributed within the historical clear water length, obtain the number of rectangle judgments at this time and mark it as the average number of the first rectangle. In practical applications, the average number of the first rectangle is: 1000 × (0.01 ÷ 0.36) = 27.8; the calculation result is rounded to one decimal place; where 1000 is the first quantity, 0.01 is the set value of the first rectangle, and 0.36 is the historical clear water length.

[0022] Step S411: Set a first ratio, obtain the product of the average number of the first rectangles and the first ratio, and mark it as the first anomaly threshold; in order to obtain the range area with a small distribution of historical clean water assessment values, the first anomaly threshold should not be set too large, that is, the first ratio should not be set too large, for example, the first ratio is 0.2. In practical applications, the first abnormal threshold is: 27.8 × 0.2 = 5.56.

[0023] Step S412: In the historical clean water scatter plot, the first data rectangle is shifted to the left from the rightmost historical clean water assessment value. When the number of the first rectangles is greater than or equal to the first anomaly threshold, the movement of the first data rectangle is stopped. The historical clean water assessment value corresponding to the largest horizontal coordinate of the first data rectangle at this time is obtained and marked as the first differentiation threshold. In order to delete excessively large historical clean water assessment values, and thus obtain the maximum value of accurate historical clean water assessment values. In practical applications, in historical clear water scatter plots, the first data rectangle is shifted to the left from the rightmost historical clear water assessment value. The shift stops when the number of values ​​in the first rectangle is greater than or equal to 5.56. (See also...) Figure 2 As shown, the first data rectangle stops at a position where the first discrimination threshold is 0.03.

[0024] Step S5: Obtain historical algae pollution assessment values ​​based on multispectral images of the substandard aquatic ecosystem restoration area; Step S5 includes the following sub-steps: Step S501: Obtain images of algae-polluted areas from multispectral images of unqualified aquatic ecological restoration areas and mark them as historical algae-polluted images; algae-polluted areas refer to algae polluting the water surface. Step S502: Obtain the real-time qualification assessment value of each pixel in the historical algae image and mark it as the historical algae assessment value.

[0025] Step S6: Obtain the second and third differentiation thresholds based on historical algae assessment values; Step S6 includes the following sub-steps: Step S601: Obtain a second number of historical algae assessment values; in order to obtain the range of historical algae assessment values, the second number should not be set too small, for example, the second number is 500; Step S602: Establish a Cartesian coordinate system with historical algae assessment values ​​as the horizontal axis and the number of historical algae assessment values ​​as the vertical axis, and mark it as the historical algae coordinate system. Step S603: Obtain historical algae assessment values ​​and corresponding quantities as coordinate points on the x and y axes, and mark them as historical algae coordinate points. Step S604: Plot all historical algae coordinate points in the historical algae coordinate system to obtain a scatter plot, and mark it as a historical algae scatter plot. For practical applications, please refer to Figure 3 As shown, this is a scatter plot of historical algae pollution.

[0026] Step S605: Obtain the maximum value of the ordinate among all historical algae coordinate points and mark it as the historical algae height; Step S606: Set a length value, marked as the second rectangle setting value; the second rectangle setting value is set to construct the second data rectangle, which is used to observe the distribution of historical algae assessment values, because the first rectangle setting value should not be set too large, for example, the second rectangle setting value is 0.01; Step S607: Create a rectangle on the horizontal axis of the historical algae coordinate system with a height equal to the historical algae height and a width equal to the second rectangle setting value, and mark it as the second data rectangle; Step S608: Mark the total number of historical algae assessment values ​​corresponding to the historical algae coordinate points included in the second data rectangle as the number of the second rectangle; Step S609: Mark the range length of the historical algae assessment value as the historical algae length; Step S610: Assuming that the historical algae assessment value is uniformly distributed within the length of the historical algae, obtain the number of rectangle judgments at this time and mark it as the average number of the second rectangle. In practical applications, the average number of the second rectangle is: 500 × (0.01 ÷ 0.24) = 20.8; the calculation result is rounded to one decimal place; where 500 is the second quantity, 0.01 is the set value of the second rectangle, and 0.024 is the historical length of algae.

[0027] Step S611: Set a second ratio, obtain the product of the average number of the second rectangle and the second ratio, and mark it as the second anomaly threshold; in order to obtain the range area with a small distribution of historical algae assessment values, the second anomaly threshold should not be set too large, that is, the second ratio should not be set too large, for example, the second ratio is 0.2. In practical applications, the second abnormal threshold is: 20.8 × 0.2 = 4.16.

[0028] Step S612: In the historical algae scatter plot, the second data rectangle is shifted to the right starting from the leftmost historical algae assessment value. When the number of the second rectangles is greater than or equal to the second anomaly threshold, the movement of the second data rectangle is stopped. The historical algae assessment value corresponding to the minimum horizontal coordinate of the second data rectangle at this time is obtained and marked as the second discrimination threshold. In order to obtain a more accurate minimum historical algae assessment value. Step S613: In the historical algae scatter plot, the second data rectangle is shifted to the left from the rightmost historical algae assessment value. When the number of the second rectangles is greater than or equal to the second anomaly threshold, the movement of the second data rectangle is stopped. The historical algae assessment value corresponding to the largest horizontal coordinate of the second data rectangle at this time is obtained and marked as the third differentiation threshold. In order to obtain a more accurate maximum value of the historical algae assessment value. In practical applications, when the number of the second rectangles is greater than or equal to 4.16, the movement of the second data rectangle should be stopped. Please refer to [link / reference]. Figure 3 As shown, at the stopping position of the second data rectangle, the second differentiation threshold is 0.11, and the third differentiation threshold is 0.33.

[0029] Step S7 involves assessing the aquatic ecosystem restoration based on real-time compliance assessment values, a first differentiation threshold, a second differentiation threshold, and a third differentiation threshold. Step S7 includes the following sub-steps: Step S701: Obtain areas where the real-time qualification assessment value is less than the first differentiation threshold and mark them as areas where the real-time detection is qualified clean water. Step S702: Obtain the region whose real-time qualification assessment value is greater than the first distinction threshold and less than the second distinction threshold, and mark it as the real-time detection abnormal turbidity region; Step S703: Obtain the area where the real-time qualified assessment value is greater than the second distinction threshold and less than the third distinction threshold, and mark it as the area of ​​abnormal algae detected in real time; Step S704: Obtain areas with real-time qualified assessment values ​​greater than the third distinction threshold and mark them as areas with qualified aquatic plants detected in real-time. Because the distribution of real-time qualified assessment values ​​is different in the four cases, and the real-time qualified assessment values ​​of areas with qualified clear water, areas with abnormal turbidity, areas with abnormal algae, and areas with qualified aquatic plants increase in that order, an intuitive water ecological restoration assessment can be performed based on the output results. In practical applications, for example, if a real-time qualified assessment value is -0.12, the area where -0.12 is less than the first distinguishing threshold of 0.3 is marked as a real-time qualified clean water area.

[0030] Example 2: This application also provides an electronic device, which may include: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus. The memory stores computer-readable instructions, and the processor can call the instructions in the memory. When the computer-readable instructions are executed by the processor, steps such as those in the water ecological restoration assessment method based on UAV images are performed to achieve the following functions: acquiring multispectral images of the target water ecological restoration area based on UAVs and marking them as real-time monitoring images; constructing real-time qualification assessment values ​​based on the real-time monitoring images; obtaining historical clear water assessment values ​​based on the multispectral images of qualified water ecological restoration areas; obtaining a first distinction threshold based on the historical clear water assessment values; obtaining historical algae pollution assessment values ​​based on the multispectral images of unqualified water ecological restoration areas; obtaining a second distinction threshold and a third distinction threshold based on the historical algae pollution assessment values; and assessing the water ecological restoration based on the real-time qualification assessment values, the first distinction threshold, the second distinction threshold, and the third distinction threshold.

[0031] Furthermore, when the logical instructions in the aforementioned memory can be implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0032] Example 3: This application also provides a computer program product, which includes a computer program stored on a computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the water ecological restoration assessment method based on UAV images provided by the above methods. The method includes: acquiring multispectral images of a target water ecological restoration area based on a UAV and marking them as real-time monitoring images; constructing a real-time qualified assessment value based on the real-time monitoring images; acquiring historical clear water assessment values ​​based on multispectral images of qualified water ecological restoration areas; acquiring a first distinction threshold based on historical clear water assessment values; acquiring historical algae pollution assessment values ​​based on multispectral images of unqualified water ecological restoration areas; acquiring a second distinction threshold and a third distinction threshold based on historical algae pollution assessment values; and assessing the water ecological restoration based on the real-time qualified assessment value, the first distinction threshold, the second distinction threshold, and the third distinction threshold.

[0033] Example 4: This application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it performs the steps of the above-described water ecological restoration assessment method based on UAV images to achieve the following functions: acquiring multispectral images of the target water ecological restoration area based on UAVs and marking them as real-time monitoring images; constructing real-time qualification assessment values ​​based on the real-time monitoring images; obtaining historical clear water assessment values ​​based on the multispectral images of qualified water ecological restoration areas; obtaining a first distinction threshold based on the historical clear water assessment values; obtaining historical algae pollution assessment values ​​based on the multispectral images of unqualified water ecological restoration areas; obtaining a second distinction threshold and a third distinction threshold based on the historical algae pollution assessment values; and assessing the water ecological restoration based on the real-time qualification assessment values, the first distinction threshold, the second distinction threshold, and the third distinction threshold.

[0034] Based on the above description of the embodiments, the embodiments of the present invention can be provided as methods, systems, or computer program products. Based on this understanding, the above technical solutions, in essence or in terms of their contribution to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or certain parts of the embodiments.

[0035] In the embodiments provided in this application, it should be understood that the disclosed system or method can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of modules or units is only a logical functional division, and there may be other division methods in actual implementation. Furthermore, multiple modules or units may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interfaces. The indirect coupling or communication connection between systems, modules, and units may be electrical, mechanical, or other forms.

[0036] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for assessing water ecological restoration based on UAV imagery, characterized in that, Includes the following steps: Multispectral images of the target aquatic ecological restoration area acquired by drones were labeled as real-time monitoring images. Construct real-time compliance assessment values ​​based on real-time monitoring images; Historical clear water assessment values ​​were obtained from multispectral images of qualified water ecological restoration areas; The first distinction threshold is obtained based on historical clear water assessment values; Historical algal pollution assessment values ​​were obtained from multispectral images of substandard aquatic ecological restoration areas. The second and third differentiation thresholds are obtained based on historical algae assessment values; The water ecological restoration is assessed based on real-time compliance assessment values, a first differentiation threshold, a second differentiation threshold, and a third differentiation threshold.

2. The method for assessing water ecological restoration based on UAV imagery according to claim 1, characterized in that, Constructing a real-time compliance assessment value based on real-time monitoring images includes the following sub-steps: Acquire the near-infrared band of each pixel in the real-time monitoring image and mark it as the real-time near-infrared band; Obtain the red light band of each pixel in the real-time monitoring image and mark it as the real-time red light band; The real-time qualification assessment value of each pixel in the real-time monitoring image is obtained as follows: F1 = (H1 - H2) / (H1 + H2); where F1 is the real-time qualification assessment value, H1 is the real-time near-infrared band, and H2 is the real-time red band.

3. The method for assessing water ecological restoration based on UAV imagery according to claim 2, characterized in that, Obtaining historical clear water assessment values ​​based on multispectral images of qualified aquatic ecological restoration areas includes the following sub-steps: Obtain images of clear water areas from multispectral images of qualified aquatic ecological restoration areas and label them as historical clear water images; Obtain the real-time qualification assessment value of each pixel in the historical clear water image and mark it as the historical clear water assessment value.

4. The method for assessing water ecological restoration based on UAV imagery according to claim 3, characterized in that, Obtaining the first distinguishing threshold based on historical clean water assessment values ​​includes the following sub-steps: Obtain the first number of historical clean water assessment values; A Cartesian coordinate system is established with historical clean water assessment values ​​as the horizontal axis and the number of historical clean water assessment values ​​as the vertical axis. This system is labeled as the historical clean water coordinate system. Obtain the historical clean water assessment values ​​and corresponding quantities as coordinate points on the x and y axes, and mark them as historical clean water coordinate points; Plot all historical Qingshui coordinate points on the historical Qingshui coordinate system to obtain a scatter plot, and label it as the historical Qingshui scatter plot.

5. The method for assessing water ecological restoration based on UAV imagery according to claim 4, characterized in that, Obtaining the first distinguishing threshold based on historical clean water assessment values ​​also includes the following sub-steps: Get the maximum value of the ordinate among all historical clear water coordinate points and mark it as the historical clear water height; Set a length value and mark it as the first rectangle setting value; Create a rectangle on the horizontal axis of the historical clear water coordinate system with a height equal to the historical clear water height and a width equal to the first rectangle's set value. This rectangle can be moved left and right and is marked as the first data rectangle. The total number of historical clean water assessment values ​​corresponding to the historical clean water coordinate points included within the first data rectangle is marked as the number of the first rectangle; The range of historical clear water assessment values ​​is marked as the historical clear water length; Assuming that the historical clear water assessment values ​​are uniformly distributed within the historical clear water length, obtain the number of rectangle judgments at this time and mark it as the average number of the first rectangle; Set a first ratio, obtain the product of the average number of first rectangles and the first ratio, and mark it as the first abnormal threshold; In the historical clear water scatter plot, the first data rectangle is shifted to the left starting from the rightmost historical clear water assessment value. When the number of the first rectangles is greater than or equal to the first anomaly threshold, the movement of the first data rectangle is stopped. The historical clear water assessment value corresponding to the largest x-coordinate of the first data rectangle at this time is obtained and marked as the first differentiation threshold.

6. The method for assessing water ecological restoration based on UAV imagery according to claim 5, characterized in that, Obtaining historical algal pollution assessment values ​​from multispectral images of substandard aquatic ecosystem restoration areas includes the following sub-steps: Obtain images of algae-contaminated areas from multispectral images of substandard aquatic ecological restoration areas and label them as historical algae-contaminated images; Obtain the real-time qualification assessment value of each pixel in the historical algae pollution image and mark it as the historical algae pollution assessment value.

7. The method for assessing water ecological restoration based on UAV imagery according to claim 6, characterized in that, Obtaining the second and third differentiation thresholds based on historical algae assessment values ​​includes the following sub-steps: Obtain a second number of historical algae assessment values; A Cartesian coordinate system is established with historical algae assessment values ​​as the horizontal axis and the number of historical algae assessment values ​​as the vertical axis. This system is labeled as the historical algae coordinate system. Obtain historical algae assessment values ​​and corresponding quantities as coordinate points on the x and y axes, and mark them as historical algae coordinate points; Plot all historical algae pollution coordinates on the historical algae pollution coordinate system to obtain a scatter plot, and label it as the historical algae pollution scatter plot.

8. The method for assessing water ecological restoration based on UAV imagery according to claim 7, characterized in that, Obtaining the second and third differentiation thresholds based on historical algae assessment values ​​also includes the following sub-steps: Get the maximum value of the ordinate among all historical algae coordinate points and mark it as the historical algae height; Set a length value and mark it as the second rectangle setting value; Create a rectangle on the horizontal axis of the historical algae coordinate system with a height equal to the historical algae height and a width equal to the second rectangle setting value, and mark it as the second data rectangle; The total number of historical algae assessment values ​​corresponding to the historical algae coordinate points included within the second data rectangle is marked as the number of the second rectangle; The range length of historical algae pollution assessment values ​​is marked as the historical algae pollution length; Assuming that the historical algae assessment values ​​are uniformly distributed within the length of the historical algae, the number of rectangle judgments at this time is obtained and marked as the average number of the second rectangle; Set a second ratio, obtain the product of the average number of the second rectangles and the second ratio, and mark it as the second abnormal threshold.

9. The method for assessing water ecological restoration based on UAV imagery according to claim 8, characterized in that, Obtaining the second and third differentiation thresholds based on historical algae assessment values ​​also includes the following sub-steps: In the historical algae scatter plot, the second data rectangle is shifted to the right starting from the leftmost historical algae assessment value. When the number of the second rectangles is greater than or equal to the second anomaly threshold, the movement of the second data rectangle is stopped. The historical algae assessment value corresponding to the smallest x-coordinate of the second data rectangle at this time is obtained and marked as the second discrimination threshold. In the historical algae scatter plot, the second data rectangle is shifted to the left starting from the rightmost historical algae assessment value. When the number of the second rectangles is greater than or equal to the second anomaly threshold, the movement of the second data rectangle is stopped. The historical algae assessment value corresponding to the largest x-coordinate of the second data rectangle at this time is obtained and marked as the third differentiation threshold.

10. The method for assessing water ecological restoration based on UAV imagery according to claim 9, characterized in that, The assessment of aquatic ecosystem restoration based on real-time compliance assessment values, a first distinguishing threshold, a second distinguishing threshold, and a third distinguishing threshold includes the following sub-steps: Areas with real-time qualification assessment values ​​less than the first distinction threshold are marked as areas of qualified clean water in real-time detection. The regions whose real-time qualification assessment values ​​are greater than the first distinction threshold and less than the second distinction threshold are marked as abnormally turbid regions detected in real time. Areas with real-time compliance assessment values ​​greater than the second distinction threshold and less than the third distinction threshold are marked as areas of abnormal algae detection in real time. Areas with real-time qualified assessment values ​​greater than the third distinction threshold are marked as qualified water-containing plant areas in real-time detection.

Images