Image-based riverbed sediment measurement method and device and storage medium

Abstract

This invention relates to the field of riverbed sediment measurement technology, and in particular to an image-based method, apparatus, equipment, and computer storage medium for riverbed sediment measurement. Under conditions where low-altitude drone flight is possible, this invention acquires images of the target riverbed sediment sampled by the drone at an altitude below the maximum flight altitude of a first drone, and then performs sediment particle size detection. Under conditions where low-altitude drone flight is not possible, it acquires images of the target riverbed sediment sampled by the drone at an altitude below the maximum flight altitude of a second drone, and inputs these images into a target sediment image super-resolution model to obtain a target super-resolution riverbed sediment image, which is then used for sediment particle size detection. This invention effectively improves the accuracy of riverbed sediment measurement.

Description

Technical Field

[0001] This invention relates to the field of riverbed sediment measurement technology, and in particular to an image-based method, apparatus, equipment, and computer storage medium for riverbed sediment measurement. Background Technology

[0002] Image-based riverbed sediment measurement techniques can quickly obtain geometric parameters such as particle size distribution and shape of sediment, but their accuracy is very poor when measuring fine-grained sediment. This is because fine-grained sediment typically occupies only a few pixels in an image, and its texture and edge features are difficult to clearly display, resulting in inaccurate measurement.

[0003] For the boundary particle size of gravel and sand, which is 2 mm (according to the "Specification for Analysis of River Sediment Particles" SL42-2010), accurate measurement of millimeter-sized sediment particles is very important for riverbed erosion and sedimentation management, aquatic habitat management, and flood control and disaster reduction.

[0004] However, the commonly used UAV mapping technology generally flies at an altitude of more than 20 meters (to ensure the efficiency and safety of the UAV and avoid collisions with trees, utility poles, etc.), which means that the smallest sediment particle size that can be identified from UAV images is usually tens or hundreds of millimeters, which cannot meet the measurement needs of millimeter-level fine sediment particles.

[0005] Currently, there is a lack of effective methods to overcome the impact of image resolution on the measurement accuracy of fine-grained sediment, so as to realize the measurement and identification of millimeter-level sediment particles by UAV sediment image measurement technology. Summary of the Invention

[0006] Therefore, the technical problem to be solved by the present invention is to overcome the problem of low measurement and identification accuracy of millimeter-level sediment particles based on UAV images in the prior art.

[0007] To address the aforementioned technical problems, this invention provides an image-based method for measuring riverbed sediment, comprising:

[0008] First riverbed sediment images were obtained from drones at different flight altitudes, and a scatter plot of drone flight altitude versus image resolution was created.

[0009] The scatter plot was fitted to obtain the fitting relationship between the UAV flight altitude and the image resolution;

[0010] Determine the resolution corresponding to the first smallest identifiable sediment particle size pixel value in the original resolution image, and obtain the first highest flight altitude of the UAV according to the fitting relationship;

[0011] Under conditions where the drone can fly at low altitudes, images of the first target riverbed sediment sampled by the drone at an altitude lower than the highest flight altitude of the first drone are obtained, and the particle size of the riverbed sediment is detected.

[0012] Preferably, the fitting relationship is:

[0013] R = 0.1·H 1.15

[0014] Where H is the drone's flight altitude and R is the image resolution.

[0015] Preferably, the pixel value of the first minimum sediment particle size is 4.

[0016] Preferably, the image-based riverbed sediment measurement method further includes:

[0017] Based on the fitted relationship, second riverbed sediment image samples with a resolution higher than a preset threshold are collected and upsampled n times to obtain third riverbed sediment samples, and a training set is constructed.

[0018] Using the third riverbed sediment sample as input and the second riverbed sediment image sample as output, a sediment image super-resolution model is constructed.

[0019] The super-resolution model of the sediment image is trained based on a deep learning algorithm to obtain a trained super-resolution model of the sediment image.

[0020] The trained super-resolution model of sediment image is tested and analyzed to determine the optimal upsampling factor and obtain the target super-resolution model of sediment image.

[0021] Determine the resolution corresponding to the second smallest identifiable sediment particle size pixel value in the super-resolution image processed by the target sediment image super-resolution model, and obtain the second highest flight altitude of the UAV according to the fitting relationship;

[0022] In the absence of conditions allowing for low-altitude drone flight, images of the second target riverbed sediment sampled by a drone at a height below the maximum flight altitude of the second drone were obtained.

[0023] The second target riverbed sediment image is input into the target sediment image super-resolution model to obtain the target super-resolution riverbed sediment image, and the riverbed sediment particle size is detected on the target super-resolution riverbed sediment image.

[0024] Preferably, the upsampling uses the nearest neighbor sampling algorithm.

[0025] Preferably, the optimal upsampling factor is 4.

[0026] Preferably, the pixel value of the second minimum sediment particle size is 1.

[0027] The present invention also provides an image-based riverbed sediment measurement device, comprising:

[0028] The scatter plot construction module is used to obtain the first riverbed sediment image samples taken by the UAV at different flight altitudes and to build a scatter plot of UAV flight altitude and image resolution;

[0029] The fitting relationship construction module is used to fit the scatter plot to obtain the fitting relationship between the UAV flight altitude and the image resolution;

[0030] The first UAV maximum flight altitude determination module is used to determine the resolution corresponding to the first smallest identifiable sediment particle size pixel value in the original resolution image, and to obtain the maximum flight altitude of the first UAV according to the fitting relationship.

[0031] The sediment measurement module is used to acquire images of the first target riverbed sediment sampled by the UAV at a height below the maximum flight altitude of the first UAV, under conditions where the UAV can fly at low altitudes, and to detect the particle size of the riverbed sediment.

[0032] The present invention also provides an image-based riverbed sediment measurement device, comprising:

[0033] Memory, used to store computer programs;

[0034] A processor is used to implement the steps of the above-described image-based riverbed sediment measurement method when executing the computer program.

[0035] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described image-based riverbed sediment measurement method.

[0036] The technical solution of the present invention has the following advantages compared with the prior art:

[0037] The image-based riverbed sediment measurement method of this invention, based on the fitting relationship between UAV flight altitude and image resolution, determines the resolution corresponding to the first smallest identifiable sediment particle size pixel value in the original resolution image. It obtains the highest flight altitude of the first UAV, and under conditions where low-altitude UAV flight is possible, acquires a first target riverbed sediment image sampled by the UAV at an altitude lower than the first UAV's highest flight altitude, and performs riverbed sediment particle size detection. Under conditions where low-altitude UAV flight is not possible, it determines the resolution corresponding to the second smallest identifiable sediment particle size pixel value in the super-resolution image processed by the target sediment image super-resolution model, and obtains the second UAV's highest flight altitude according to the fitting relationship. It then acquires a second target riverbed sediment image sampled by the UAV at an altitude lower than the second UAV's highest flight altitude, inputs the second target riverbed sediment image into the target sediment image super-resolution model to obtain a target super-resolution riverbed sediment image, and performs riverbed sediment particle size detection on the target super-resolution riverbed sediment image. This invention effectively improves the accuracy of riverbed sediment measurement. Attached Figure Description

[0038] To make the content of this invention easier to understand, the invention will be further described in detail below with reference to specific embodiments and accompanying drawings, wherein:

[0039] Figure 1 This is a flowchart illustrating the implementation of an image-based riverbed sediment measurement method provided by the present invention.

[0040] Figure 2 It is a scatter plot of the resolution of drone photos of riverbed sediment at different flight altitudes;

[0041] Figure 3 These are images of riverbed sediment at different resolutions;

[0042] Figure 4 A schematic diagram illustrating the training process of a super-resolution model for sediment images;

[0043] Figure 5 Output photos of newly sampled sediment and the corresponding 4x SRGAN super-resolution model. Detailed Implementation

[0044] The core of this invention is to provide an image-based method, apparatus, equipment, and computer storage medium for measuring riverbed sediment, which effectively improves the accuracy of riverbed sediment measurement.

[0045] To enable those skilled in the art to better understand the present invention, the invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are merely 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.

[0046] Please refer to Figure 1 , Figure 1 The flowchart illustrates the implementation of an image-based riverbed sediment measurement method provided by this invention; the specific operation steps are as follows:

[0047] S101: Obtain first riverbed sediment image samples taken by the UAV at different flight altitudes, and establish a scatter plot of UAV flight altitude versus image resolution;

[0048] S102: Fit the scatter plot to obtain the fitting relationship between the UAV flight altitude and the image resolution;

[0049] S103: Determine the resolution corresponding to the first smallest identifiable sediment particle size pixel value in the original resolution image, and obtain the first highest flight altitude of the UAV according to the fitting formula;

[0050] S104: Under conditions where the UAV can fly at low altitude, acquire images of the first target riverbed sediment sampled by the UAV at a height lower than the maximum flight altitude of the first UAV, and perform particle size detection on the riverbed sediment.

[0051] Based on the above embodiments, the present invention will provide a detailed description of step S101:

[0052] In one specific embodiment, a drone equipped with a 45-megapixel camera is used to sample riverbed sediment images at different altitudes for typical mountain river types with different riverbed morphologies and gradations, obtaining the first riverbed sediment image sample. A scatter plot of the drone's flight altitude (H, in meters) versus image resolution (R, in mm / pixel) is then obtained. Figure 2 , Figure 2 This study demonstrates the resolution differences in riverbed sediment photos taken by drones at different flight altitudes, intuitively illustrating the impact of flight altitude on image resolution and providing practical image data support for the creation and fitting of scatter plots.

[0053] Based on the above embodiments, the present invention will provide a detailed description of step S102:

[0054] In one specific embodiment, a power-law fit is performed on the scatter plot to obtain the fitting relationship between the UAV flight altitude and the image resolution:

[0055] R = 0.1·H 1.15

[0056] This fitted equation reveals the quantitative relationship between flight altitude and image resolution, providing a basis for determining the appropriate flight altitude.

[0057] Based on the above embodiments, the present invention will provide a detailed description of step S103:

[0058] According to the Nyquist sampling theorem, to distinguish a single sand particle, the sample length of that particle in the one-dimensional signal must be 2. Since RGB images are three-dimensional signals, the human eye requires a pixel length of 2 + 1 + 1 = 4 pixels to distinguish a sand particle. Based on extensive experience in manually identifying sand images, 4 pixels has also been determined as the smallest sand particle size pixel value that can be identified from an image. Figure 3 As shown. Therefore, 4 pixels are used as the first minimum silt particle size pixel value that can be identified from the image. In summary, if millimeter-sized silt particles need to be identified, the resolution must be at least 10 ÷ 4 = 2.5 mm / pixel. Furthermore, according to R = 0.1·H 1.15 The relationship requires a maximum flight altitude (i.e., the maximum flight altitude of the first UAV) of approximately 16 meters. Therefore, in open areas with conditions suitable for low-altitude UAV flight, sampling should be conducted at a flight altitude below 16 meters.

[0059] Based on the above embodiments, the image-based riverbed sediment measurement method of the present invention further includes:

[0060] S105: Based on the fitted relationship, collect second riverbed sediment image samples with a resolution higher than a preset threshold, and upsample them n times to obtain third riverbed sediment samples, and construct a training set;

[0061] S106: Using the third riverbed sediment sample as input and the second riverbed sediment image sample as output, construct a sediment image super-resolution model;

[0062] S107: Train the super-resolution model of the sediment image based on the deep learning algorithm to obtain the trained super-resolution model of the sediment image.

[0063] S108: Test and analyze the trained super-resolution model of sediment image to determine the optimal upsampling factor and obtain the target super-resolution model of sediment image.

[0064] S109: Determine the resolution corresponding to the second smallest sediment particle size pixel value that can be identified in the super-resolution image processed by the target sediment image super-resolution model, and obtain the second UAV's maximum flight altitude according to the fitting relationship.

[0065] S110: Under conditions where low-altitude flight of the drone is not possible, acquire images of the second target riverbed sediment sampled by the drone at a height lower than the maximum flight altitude of the second drone.

[0066] S111: Input the second target riverbed sediment image into the target sediment image super-resolution model to obtain the target super-resolution riverbed sediment image, and perform riverbed sediment particle size detection on the target super-resolution riverbed sediment image.

[0067] Based on the above embodiments, this embodiment will provide a detailed description of step S105:

[0068] In one specific embodiment, such as Figure 3 As shown, in accordance with the fitting relationship in step S102, a large number of original high-resolution riverbed sediment image datasets (i.e., second riverbed sediment image samples) with a resolution of X are collected. The dataset needs to cover different river slopes, different riverbed morphology types, different river widths, different lithologies, and different sediment gradations. The drone flight altitude covers 10 meters to 200 meters to ensure the diversity and representativeness of the data.

[0069] In one specific embodiment, the nearest neighbor sampling algorithm is used to sample the original high-resolution photo at a resolution of X / n by a factor of n to obtain a resampled low-resolution photo dataset (i.e., the third riverbed sediment image sample).

[0070] Based on the above embodiments, this embodiment will provide a detailed description of step S107:

[0071] Training a deep learning super-resolution model for sediment images. Model algorithms can include SRCNN, SRGAN, etc., which can learn the mapping relationship from low-resolution images to high-resolution images, thereby improving the image resolution.

[0072] Based on the above embodiments, this embodiment will provide a detailed description of step S108:

[0073] In one specific embodiment, the optimal upsampling factor is 4x.

[0074] Based on the above embodiments, this embodiment will provide a detailed description of step S109:

[0075] In one specific embodiment, the human eye can recognize most of the 1-pixel mud and sand particles in the image processed by the super-resolution model, such as... Figure 4 As shown, this means that after super-resolution processing, the image resolution is significantly improved, enabling better identification of fine mud and sand particles. To identify millimeter-sized mud and sand, a resolution of at least 10 ÷ 1 = 10 mm / pixel is required. Furthermore, according to R = 0.1·H... 1.15The relationship requires that the highest possible flight altitude of the second drone is approximately 55 meters.

[0076] In summary, when low-altitude flight (below 16 meters) is not feasible, riverbed sediment should first be sampled at a flight altitude below 55 meters. The sampled material is then input into a sediment image super-resolution model. Finally, millimeter-sized sediment particles on the riverbed can be identified from the output image of the super-resolution model. This approach provides a solution for situations where low-altitude sampling is not feasible in practical applications, compensating for the insufficient resolution caused by flight altitude limitations through super-resolution technology.

[0077] Based on the above embodiments, the image-based riverbed sediment measurement of the present invention, based on the fitting relationship between the drone's flight altitude and image resolution, determines the resolution corresponding to the first smallest identifiable sediment particle size pixel value in the original resolution image, obtains the highest flight altitude of the first drone, and, under conditions where low-altitude drone flight is possible, acquires a first target riverbed sediment image sampled by the drone at an altitude lower than the first drone's highest flight altitude, and performs riverbed sediment particle size detection; under conditions where low-altitude drone flight is not possible, determines the resolution corresponding to the second smallest identifiable sediment particle size pixel value in the super-resolution image processed by the target sediment image super-resolution model, and, according to the fitting relationship, obtains the second drone's highest flight altitude, acquires a second target riverbed sediment image sampled by the drone at an altitude lower than the second drone's highest flight altitude, inputs the second target riverbed sediment image into the target sediment image super-resolution model to obtain a target super-resolution riverbed sediment image, and performs riverbed sediment particle size detection on the target super-resolution riverbed sediment image. The present invention effectively improves the accuracy of riverbed sediment measurement.

[0078] This invention also provides an image-based riverbed sediment measurement device; the specific device may include:

[0079] The scatter plot construction module is used to obtain the first riverbed sediment image samples taken by the UAV at different flight altitudes and to build a scatter plot of UAV flight altitude and image resolution;

[0080] The fitting relationship construction module is used to fit the scatter plot to obtain the fitting relationship between the UAV flight altitude and the image resolution;

[0081] The first UAV maximum flight altitude determination module is used to determine the resolution corresponding to the first smallest identifiable sediment particle size pixel value in the original resolution image, and to obtain the maximum flight altitude of the first UAV according to the fitting relationship.

[0082] The sediment measurement module is used to acquire images of the first target riverbed sediment sampled by the UAV at a height below the maximum flight altitude of the first UAV, under conditions where the UAV can fly at low altitudes, and to detect the particle size of the riverbed sediment.

[0083] The image-based riverbed sediment measurement device of this embodiment is used to implement the aforementioned image-based riverbed sediment measurement method. Therefore, the specific implementation of the image-based riverbed sediment measurement device can be found in the embodiment section of the image-based riverbed sediment measurement method above. For example, the scatter plot construction module, the fitting relationship construction module, the first UAV maximum flight altitude determination module, and the sediment measurement module are used to implement steps S101, S102, S103, and S104 in the above-mentioned image-based riverbed sediment measurement method. Therefore, its specific implementation can be referred to the description of the corresponding embodiments, and will not be repeated here.

[0084] Based on the above embodiments, the image-based riverbed sediment measurement device of the present invention further includes:

[0085] The training set is based on the module used to collect second riverbed sediment image samples with a resolution higher than a preset threshold based on the fitting relationship, and upsample them n times to obtain third riverbed sediment samples, thus constructing the training set;

[0086] The model building module is used to construct a super-resolution model of sediment images by taking the third riverbed sediment sample as input and the second riverbed sediment image sample as output.

[0087] The model training module is used to train the super-resolution model of the sediment image based on the deep learning algorithm to obtain the trained super-resolution model of the sediment image.

[0088] The target model determination module is used to test and analyze the trained sediment image super-resolution model, determine the optimal upsampling factor, and obtain the target sediment image super-resolution model.

[0089] The second UAV maximum flight altitude determination module is used to determine the resolution corresponding to the second smallest identifiable sediment particle size pixel value in the super-resolution image processed by the target sediment image super-resolution model, and to obtain the maximum flight altitude of the second UAV according to the fitting relationship.

[0090] The sediment measurement module is also used for:

[0091] In the absence of low-altitude drone flight conditions, a second target riverbed sediment image is acquired by the drone at a height lower than the maximum flight altitude of the second drone. The second target riverbed sediment image is then input into a target sediment image super-resolution model to obtain a target super-resolution riverbed sediment image. Finally, the target super-resolution riverbed sediment image is subjected to riverbed sediment particle size detection.

[0092] A specific embodiment of the present invention also provides an image-based riverbed sediment measurement device, comprising: a memory for storing a computer program; and a processor for executing the computer program to implement the steps of the above-described image-based riverbed sediment measurement method.

[0093] A specific embodiment of the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described image-based riverbed sediment measurement method.

[0094] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0095] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0096] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0097] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0098] Obviously, the above embodiments are merely illustrative examples for clear explanation and are not intended to limit the implementation. Those skilled in the art will recognize that other variations or modifications can be made based on the above description. It is neither necessary nor possible to exhaustively list all possible implementations here. However, obvious variations or modifications derived therefrom are still within the scope of protection of this invention.

Claims

1. An image-based method for measuring riverbed sediment, characterized in that, include: First riverbed sediment images were obtained from drones at different flight altitudes, and a scatter plot of drone flight altitude versus image resolution was created. The scatter plot is fitted to obtain a fitting relationship between the UAV flight altitude and the image resolution, wherein the fitting relationship is: R = 0.1· H 1.15 Where H is the drone's flight altitude and R is the image unit pixel size; Determine the resolution corresponding to the first smallest identifiable sediment particle size pixel value in the original resolution image, and obtain the first highest flight altitude of the UAV according to the fitting relationship; Under conditions where the drone flies at low altitude, images of the first target riverbed sediment sampled by the drone at a height lower than the highest flight altitude of the first drone are obtained, and the particle size of the riverbed sediment is detected. The method further includes: Based on the fitted relationship, second riverbed sediment image samples with resolution higher than a preset threshold are collected, and the nearest neighbor sampling algorithm is used to sample the original high-definition photos at a resolution of X / n by reducing the resolution by n times to obtain a resampled low-resolution photo dataset, thus obtaining the third riverbed sediment sample and constructing a training set. Using the third riverbed sediment sample as input and the second riverbed sediment image sample as output, a sediment image super-resolution model is constructed. The super-resolution model of the sediment image is trained based on a deep learning algorithm to obtain a trained super-resolution model of the sediment image. The trained super-resolution model of sediment image is tested and analyzed to determine the optimal upsampling factor and obtain the target super-resolution model of sediment image. Determine the resolution corresponding to the second smallest identifiable sediment particle size pixel value in the super-resolution image processed by the target sediment image super-resolution model, and obtain the second UAV's maximum flight altitude according to the fitting relationship; In the absence of conditions allowing for low-altitude drone flight, images of the second target riverbed sediment sampled by a drone at a height below the maximum flight altitude of the second drone were obtained. The second target riverbed sediment image is input into the target sediment image super-resolution model to obtain the target super-resolution riverbed sediment image, and the riverbed sediment particle size is detected on the target super-resolution riverbed sediment image.

2. The image-based riverbed sediment measurement method according to claim 1, characterized in that, The first minimum sediment particle size pixel value is 4.

3. The image-based riverbed sediment measurement method according to claim 1, characterized in that, The optimal upsampling factor is 4.

4. The image-based riverbed sediment measurement method according to claim 1, characterized in that, The second minimum sediment particle size pixel value is 1.

5. An image-based riverbed sediment measurement device, characterized in that, include: The scatter plot construction module is used to obtain the first riverbed sediment image samples taken by the UAV at different flight altitudes and to build a scatter plot of UAV flight altitude and image resolution; The fitting relationship construction module is used to fit the scatter plot to obtain a fitting relationship between the UAV flight altitude and the image resolution, wherein the fitting relationship is: R = 0.1· H 1.15 Where H is the drone's flight altitude and R is the image unit pixel size; The first UAV maximum flight altitude determination module is used to determine the resolution corresponding to the first smallest identifiable sediment particle size pixel value in the original resolution image, and obtain the maximum flight altitude of the first UAV according to the fitting relationship. The sediment measurement module is used to acquire images of the first target riverbed sediment sampled by the UAV at a height below the maximum flight altitude of the first UAV, under conditions where the UAV is flying at low altitude, and to detect the particle size of the riverbed sediment. The sediment measurement module is also used for: Based on the fitted relationship, second riverbed sediment image samples with resolution higher than a preset threshold are collected, and the nearest neighbor sampling algorithm is used to sample the original high-definition photos at a resolution of X / n by reducing the resolution by n times to obtain a resampled low-resolution photo dataset, thus obtaining the third riverbed sediment sample and constructing a training set. Using the third riverbed sediment sample as input and the second riverbed sediment image sample as output, a sediment image super-resolution model is constructed. The super-resolution model of the sediment image is trained based on a deep learning algorithm to obtain a trained super-resolution model of the sediment image. The trained super-resolution model of sediment image is tested and analyzed to determine the optimal upsampling factor and obtain the target super-resolution model of sediment image. Determine the resolution corresponding to the second smallest identifiable sediment particle size pixel value in the super-resolution image processed by the target sediment image super-resolution model, and obtain the second UAV's maximum flight altitude according to the fitting relationship; In the absence of conditions allowing for low-altitude drone flight, images of the second target riverbed sediment sampled by a drone at a height below the maximum flight altitude of the second drone were obtained. The second target riverbed sediment image is input into the target sediment image super-resolution model to obtain the target super-resolution riverbed sediment image, and the riverbed sediment particle size is detected on the target super-resolution riverbed sediment image.

6. An image-based riverbed sediment measurement device, characterized in that, include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the steps of the image-based riverbed sediment measurement method as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the image-based riverbed sediment measurement method as described in any one of claims 1 to 4.

Images