Fishery breeding water quality information detection method and device based on unmanned aerial vehicle

Abstract

The invention belongs to the technical field of water quality monitoring, and discloses a fishery breeding water quality information detection method and device based on an unmanned aerial vehicle. The method comprises the following steps: acquiring a multispectral remote sensing image of a target fishery breeding area acquired by an unmanned aerial vehicle; performing correction processing on the multispectral remote sensing image to obtain a target remote sensing image; extracting an image parameter value from the target remote sensing image; inputting the image parameter value into a water quality detection model; and performing correlation analysis on the image parameter values and water quality sample parameters through the water quality detection model to realize water quality information detection. According to the mode, the unmanned aerial vehicle is used for shooting the remote sensing image, the water quality detection model is used for monitoring the water quality according to the shot image, and the monitoring efficiency and the monitoring accuracy are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of water quality monitoring, and in particular to a method and device for detecting water quality information in fishery aquaculture based on an unmanned aerial vehicle. Background Art

[0002] Fishery farming refers to a series of processes such as artificial propagation, hatching, feeding, harvesting, and processing of aquatic resources to make them grow and reproduce and provide fishery products for humans. Fishery farming monitoring refers to monitoring the aquaculture waters to understand the water quality, fish conditions, disease conditions and other information of the aquaculture, so as to provide a basis for the production management and scientific development of fishery farming.

[0003] The traditional method of fishery monitoring is mainly manual monitoring, which requires professional technicians to conduct on-site sampling to monitor parameters such as water quality, water depth, and fish status. Manual monitoring has limitations, such as low monitoring frequency, small coverage area, and susceptibility to human factors.

[0004] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of the present invention is to provide a method and device for detecting water quality information in fishery aquaculture based on drones, aiming to solve the technical problems that manual monitoring methods have limitations, low monitoring frequency, small coverage area, and are easily affected by human factors.

[0006] To achieve the above object, the present invention provides a method for detecting water quality information of fishery aquaculture based on a drone, and the method for detecting water quality information of fishery aquaculture based on a drone comprises the following steps:

[0007] Acquire multispectral remote sensing images of the target fishery breeding area collected by UAV;

[0008] Performing correction processing on the multispectral remote sensing image to obtain a target remote sensing image;

[0009] Extracting image parameter values ​​from the target remote sensing image;

[0010] Inputting the image parameter value into a water quality detection model;

[0011] The water quality detection model is used to perform correlation analysis on the image parameter values ​​and water quality sample parameters to achieve water quality information detection.

[0012] In some embodiments, the step of obtaining a multispectral remote sensing image of a target fishery breeding area collected by a drone includes:

[0013] Determine the flight parameters of the drone, wherein the flight parameters include altitude, speed, and overlap rate, the altitude is determined by the resolution, focal length, and actual distance of the photographed target of the multispectral camera carried by the drone, and the speed is determined by the performance of the drone;

[0014] Determining shooting parameters of the multispectral camera, wherein the shooting parameters include exposure time, sensitivity, aperture size, and aperture band;

[0015] The UAV is controlled to fly according to the flight parameters according to a preset trajectory, and the multispectral camera carried by the UAV is controlled to collect multispectral remote sensing images of the target fishery breeding area according to the shooting parameters.

[0016] In some embodiments, the correction processing of the multispectral remote sensing image to obtain the target remote sensing image includes:

[0017] Selecting a number of control points from the multispectral remote sensing image;

[0018] Determine the image positions of a plurality of control points in the multispectral remote sensing image and the corresponding real positions in the target fishery breeding area;

[0019] constructing a polynomial variation model based on the image position and the true position;

[0020] Solving the polynomial change model to obtain transformation parameters;

[0021] Performing geometric correction on the multispectral remote sensing image using the transformation parameters to obtain a first reference remote sensing image;

[0022] A target remote sensing image is obtained based on the first reference remote sensing image.

[0023] In some embodiments, obtaining a target remote sensing image based on the first reference remote sensing image includes:

[0024] Select a target site, place a calibration plate at the target site, and adjust the position of the calibration plate so that the calibration plate is located at the center of the picture of the multi-spectral camera;

[0025] Controlling the multi-spectral camera to collect images at a preset period of seconds, after collecting a number of images, determining the average radiation brightness of the images under the same light intensity, and constructing a radiation model based on the light intensity and the average radiation brightness;

[0026] Performing radiation correction on the first reference remote sensing image using the radiation model to obtain a second reference remote sensing image;

[0027] A target remote sensing image is obtained based on the second reference remote sensing image.

[0028] In some embodiments, obtaining a target remote sensing image based on the second reference remote sensing image includes:

[0029] Determining pixel values ​​of the second reference remote sensing image;

[0030] Determine the local intensity of each pixel in the second reference remote sensing image according to the pixel value;

[0031] The brightness and contrast of the second reference remote sensing image are adjusted according to the local intensity to obtain a target remote sensing image.

[0032] In some embodiments, the performing correlation analysis on the image parameter value and the water quality sample parameter by the water quality detection model to realize water quality information detection includes:

[0033] Determine the bands and band combinations that are related to chemical oxygen demand, temperature, and pH;

[0034] Acquire image parameter values ​​associated with the bands and the band combinations from the image parameter values;

[0035] Determining a correlation coefficient based on the image parameter value and the water quality sample parameter by the water quality detection model;

[0036] The water quality information of the target fishery breeding area is detected according to the correlation coefficient.

[0037] In some embodiments, the detecting of water quality information of the target fishery breeding area according to the correlation coefficient includes:

[0038] Determine the correlation between the image parameter value and the water quality sample parameter according to the magnitude of the correlation coefficient;

[0039] Determine the parameter values ​​corresponding to the chemical oxygen demand, the temperature and the pH based on the water quality sample parameters;

[0040] The actual chemical oxygen demand, actual temperature and actual pH corresponding to the target fishery breeding area are calculated according to the correlation and the parameter values ​​corresponding to the chemical oxygen demand, the temperature and the pH to realize water quality information detection.

[0041] In addition, to achieve the above-mentioned purpose, the present invention also proposes a fishery aquaculture water quality information detection device based on a drone, and the fishery aquaculture water quality information detection device based on a drone comprises:

[0042] An acquisition module, used to obtain multispectral remote sensing images of the target fishery breeding area collected by the UAV;

[0043] A processing module, used for performing correction processing on the multispectral remote sensing image to obtain a target remote sensing image;

[0044] An extraction module, used for extracting image parameter values ​​from the target remote sensing image;

[0045] An input module, used for inputting the image parameter value into a water quality detection model;

[0046] The detection module is used to perform correlation analysis on the image parameter value and the water quality sample parameter through the water quality detection model to realize water quality information detection.

[0047] In some embodiments, the acquisition module is used to determine the flight parameters of the drone, wherein the flight parameters include altitude, speed, and overlap rate, the altitude is determined by the resolution, focal length, and actual distance of the photographed target of the multi-spectral camera carried by the drone, and the speed is determined by the performance of the drone;

[0048] Determining shooting parameters of the multispectral camera, wherein the shooting parameters include exposure time, sensitivity, aperture size, and aperture band;

[0049] The UAV is controlled to fly according to the flight parameters according to a preset trajectory, and the multispectral camera carried by the UAV is controlled to collect multispectral remote sensing images of the target fishery breeding area according to the shooting parameters.

[0050] In some embodiments, the processing module is used to select a number of control points from the multispectral remote sensing image;

[0051] Determine the image positions of a plurality of control points in the multispectral remote sensing image and the corresponding real positions in the target fishery breeding area;

[0052] constructing a polynomial variation model based on the image position and the true position;

[0053] Solving the polynomial change model to obtain transformation parameters;

[0054] Performing geometric correction on the multispectral remote sensing image using the transformation parameters to obtain a first reference remote sensing image;

[0055] A target remote sensing image is obtained based on the first reference remote sensing image.

[0056] The present invention obtains a multispectral remote sensing image of a target fishery breeding area collected by an unmanned aerial vehicle; performs correction processing on the multispectral remote sensing image to obtain a target remote sensing image; extracts image parameter values ​​from the target remote sensing image; inputs the image parameter values ​​into a water quality detection model; and performs correlation analysis between the image parameter values ​​and water quality sample parameters through the water quality detection model to achieve water quality information detection. In the above manner, a drone is used to shoot remote sensing images, and water quality monitoring is achieved based on the captured images using a water quality detection model, thereby improving monitoring efficiency and monitoring accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a flow chart of the first embodiment of the method for detecting water quality information of fishery aquaculture based on drone of the present invention;

[0058] Figure 2 It is a flow chart of a second embodiment of a method for detecting water quality information of fishery aquaculture based on drones according to the present invention;

[0059] Figure 3 This is a structural block diagram of the first embodiment of the fishery aquaculture water quality information detection device based on drone of the present invention.

[0060] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0061] 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.

[0062] The embodiment of the present invention provides a method for detecting water quality information of fishery aquaculture based on an unmanned aerial vehicle. Figure 1 , Figure 1 This is a flow chart of a first embodiment of a method for detecting water quality information in fishery aquaculture based on drones according to the present invention.

[0063] In this embodiment, the method for detecting fishery aquaculture water quality information based on drones includes the following steps:

[0064] Step S10: Acquire a multispectral remote sensing image of the target fishery breeding area collected by a drone.

[0065] In this embodiment, the executor of this embodiment is a UAV-based fishery aquaculture water quality information detection device, wherein the UAV-based fishery aquaculture water quality information detection device has functions such as data processing, data communication and program running. The UAV-based fishery aquaculture water quality information detection device can be a computer terminal device or other network device, and of course it can also be other devices with similar functions, and this embodiment does not limit this.

[0066] It should be noted that the traditional method of fishery monitoring is mainly manual monitoring, which requires professional technicians to conduct on-site sampling to monitor parameters such as water quality, water depth, and fish status. Manual monitoring has limitations, such as low monitoring frequency, small coverage area, and susceptibility to human factors.

[0067] This embodiment acquires a multispectral remote sensing image of a target fishery breeding area collected by a drone; performs correction processing on the multispectral remote sensing image to obtain a target remote sensing image; extracts image parameter values ​​from the target remote sensing image; inputs the image parameter values ​​into a water quality detection model; and performs correlation analysis between the image parameter values ​​and water quality sample parameters through the water quality detection model to detect water quality information. In the above manner, a drone is used to shoot remote sensing images, and water quality monitoring is achieved based on the captured images using a water quality detection model, thereby improving monitoring efficiency and accuracy.

[0068] In the specific implementation, in this embodiment, it is necessary to first obtain the multispectral remote sensing image of the target fishery breeding area collected by the drone. Specifically, in this embodiment, it is necessary to determine the flight parameters of the drone and the shooting parameters of the multispectral camera, and then control the drone to fly according to the preset trajectory according to the flight parameters, and control the multispectral camera carried by the drone to collect the multispectral remote sensing image of the target fishery breeding area according to the shooting parameters. Among them, the flight parameters include height, speed and overlap rate. The height is determined by the resolution, focal length and actual distance of the multispectral camera carried by the drone, and the speed is determined by the performance of the drone. The speed setting needs to ensure that the multispectral camera can capture clear images. The overlap rate is, for example, 70% to 90%. If the overlap rate is too low, it will result in image loss, and if the overlap rate is too high, it will increase the cost of shooting. The overlap rate in this embodiment is only for example, and it can be adjusted accordingly according to actual needs.

[0069] Further, the shooting parameters include exposure time, sensitivity, aperture size and aperture band. It should be noted that the exposure time and sensitivity depend on the brightness of the shooting target. If the shooting target is in a relatively dark environment, the exposure time is longer, and if the shooting target is in a relatively bright environment, the exposure time is relatively short. If the shooting target is in a relatively dark environment, the sensitivity can be lowered, and if the shooting target is in a relatively bright environment, the sensitivity can be increased. The aperture size is determined by the clarity of the captured image. The higher the required clarity, the larger the aperture needs to be set. The aperture band in this embodiment can select four main bands as needed, namely the visible light band, the near infrared band, the mid-infrared band and the thermal infrared band. Currently, more other bands can also be selected according to actual conditions. The preset trajectory can be a zigzag trajectory in the target fishery breeding area, and the specific trajectory can also be set by itself.

[0070] Step S20: performing correction processing on the multispectral remote sensing image to obtain a target remote sensing image.

[0071] It should be noted that the correction process in this embodiment includes geometric correction, radiation correction and vignetting correction. After the above correction processes are performed on the collected multispectral image in sequence, the target remote sensing image can be obtained.

[0072] Step S30: extracting image parameter values ​​from the target remote sensing image.

[0073] Step S40: inputting the image parameter values ​​into a water quality detection model.

[0074] After obtaining the processed target remote sensing image, in this embodiment, the image parameter value can be extracted from the target remote sensing image, and then the image parameter value can be input into the water quality detection model to realize the detection of water quality information. The image parameter value is the parameter value corresponding to each band or band combination in the multispectral image, such as chemical oxygen demand, temperature and pH.

[0075] It should be noted that the water quality detection model in this embodiment can be constructed by a genetic algorithm, and the specific process is 1) Design the objective function: the objective function should be able to compare the observed data with the simulated data to determine the feasibility of the model. By summarizing the experience of predecessors, the linear function model, the quadratic function model, the power function model and the exponential model are selected as the objective function model, and 20 groups are randomly selected from 28 groups of experimental data as training sets, and the remaining 8 groups are validation sets. 2) Determine the encoding method: use permutation coding to arrange the finite set DN value set. Permutation coding can simplify the problem and is often used to solve the traveling salesman problem. 3) Initialize the population: according to the encoding method, randomly generate a group of populations, and take the population size as 1.5 times the number of DN value groups. 4) Iterative operation: repeat the three operations of selection, crossover and mutation, and update the population until the termination condition is reached. 5) Selection operation: select individuals with high fitness as the parent generation, and use the tournament selection algorithm to select. 6) Crossover operation: perform a crossover operation on the individuals in the parent generation, and replace a part of it with the information of the corresponding part of another individual. 7) Mutation operation: perform mutation operation on the offspring after crossover, change some of its genes, and introduce new individual information. 8) Determine termination conditions: the condition for stopping iteration can be reaching the preset maximum number of iterations and the fitness value no longer changes significantly. 9) Output results: output the parameters of the individual with the highest fitness, which is the best model for this inversion, that is, the water quality detection model.

[0076] Step S50: performing correlation analysis on the image parameter values ​​and water quality sample parameters through the water quality detection model to achieve water quality information detection.

[0077] In the specific implementation, the detection process is to first determine the bands and band combinations related to chemical oxygen demand, temperature and pH, all bands include blue band, green band, red band, red edge 1 band, red edge 2 band and near infrared band. Then, the image parameter values ​​associated with the bands and band combinations are obtained from the image parameter values, and then the correlation coefficient is determined based on the image parameter values ​​and the water quality sample parameters through the water quality detection model. The calculation formula is:

[0078]

[0079] Among them, x and y are the image parameter values ​​and water quality sample parameters associated with the bands and band combinations, respectively, and x and y are their corresponding average values, respectively.

[0080] Finally, water quality information detection is carried out on the target fishery breeding area according to the correlation coefficient. The specific process is to determine the correlation between the image parameter value and the water quality sample parameter according to the size of the correlation coefficient, and convert the correlation coefficient into a percentage, which is the correlation. According to the above correlation and the parameter values ​​of chemical oxygen demand, temperature and pH included in the water quality sample parameters, the image parameter values ​​associated with the bands and band combinations can be calculated, that is, the actual chemical oxygen demand, actual temperature and actual pH corresponding to the target fishery breeding area, so as to realize water quality detection of the target fishery breeding area.

[0081] This embodiment acquires a multispectral remote sensing image of a target fishery breeding area collected by a drone; performs correction processing on the multispectral remote sensing image to obtain a target remote sensing image; extracts image parameter values ​​from the target remote sensing image; inputs the image parameter values ​​into a water quality detection model; and performs correlation analysis between the image parameter values ​​and water quality sample parameters through the water quality detection model to detect water quality information. In the above manner, a drone is used to shoot remote sensing images, and water quality monitoring is achieved based on the captured images using a water quality detection model, thereby improving monitoring efficiency and accuracy.

[0082] refer to Figure 2 , Figure 2 This is a flow chart of a second embodiment of a method for detecting water quality information in fishery aquaculture based on drones according to the present invention.

[0083] Based on the above first embodiment, step S20 in the method for detecting water quality information of fishery aquaculture based on drone in this embodiment specifically includes:

[0084] Step S201: Selecting a number of control points from the multispectral remote sensing image.

[0085] It should be noted that the several control points selected in this embodiment are easily identifiable landmarks, such as road intersections and waterway intersections in the target fishery breeding area.

[0086] Step S202: determining the image positions of a number of control points in the multispectral remote sensing image and the corresponding real positions in the target fishery breeding area.

[0087] According to the control points determined above, the image position in the multispectral remote sensing image can be determined, and the actual position of the control points in the target fishery breeding area can be determined in combination with the target fishery breeding area.

[0088] Step S203: constructing a polynomial variation model based on the image position and the real position.

[0089] For example, Y = β0 + β1X + β2X 2 +β3X3 +…+β n X n , where β is the transformation parameter, X represents the image position, Y is the real position, and n is the order.

[0090] Step S204: Solve the polynomial change model to obtain transformation parameters.

[0091] Transformation parameters, also known as polynomial coefficients, refer to the coefficients of the polynomial function used to describe the transformation relationship. The calculation methods include the least squares method and the root mean square error minimization method. After the object is obtained as a change model, the transformation parameters can be obtained by solving it.

[0092] Step S205: performing geometric correction on the multispectral remote sensing image using the transformation parameters to obtain a first reference remote sensing image.

[0093] After obtaining the change parameters, each pixel in the image is resampled to match the correct geographical location. Through geometric correction, the pixel position in the multispectral remote sensing image can correspond to the geographical location in the real world.

[0094] Step S206: obtaining a target remote sensing image based on the first reference remote sensing image.

[0095] Further, the step S206 includes: selecting a target site, placing a calibration plate at the target site, and adjusting the position of the calibration plate so that the calibration plate is located at the center of the screen of the multispectral camera. The target site can be a target fishery breeding area, or a sample area with the same size and structure as the target fishery breeding area, controlling the multispectral camera to collect images at a preset cycle interval of seconds, and after collecting several images, determining the mean radiation brightness of several images under the same light intensity, and constructing a radiation model based on the light intensity and the mean radiation brightness. The construction of a radiation model based on the sample site can be realized through the above target site, for example, I=k*DN+b, where I represents light intensity, DN represents the mean radiation brightness, k is a proportional coefficient, which belongs to the factory parameter of the camera, and b is an intercept. The model can be used to determine the radiation brightness that the remote sensing image should have in combination with the light intensity of the target fishery breeding area, and the first reference remote sensing image can be radiation corrected according to the calculated radiation brightness, thereby obtaining a second reference remote sensing image.

[0096] Furthermore, after obtaining the second reference remote sensing image, the pixel value of the second reference remote sensing image is further determined in this embodiment, and then the local intensity of each pixel in the second reference remote sensing image is determined based on the pixel value. The local intensity is also the average pixel value of the neighborhood around each pixel (for example, a 3x3 or 5x5 area). Finally, the brightness and contrast of the second reference remote sensing image are adjusted based on the local intensity to obtain the target remote sensing image.

[0097] The present embodiment selects a number of control points from the multispectral remote sensing image; determines the image positions of the control points in the multispectral remote sensing image and the corresponding real positions in the target fishery breeding area; constructs a polynomial change model based on the image positions and the real positions; solves the polynomial change model to obtain transformation parameters; uses the transformation parameters to perform geometric correction on the multispectral remote sensing image to obtain a first reference remote sensing image; selects a target site, places a calibration plate on the target site, and adjusts the position of the calibration plate so that the calibration plate is located at the center of the screen of the multispectral camera; controls the multispectral camera to collect images at a preset period of seconds, and after collecting a number of images, determines Determine the mean radiation brightness of several images under the same light intensity, and build a radiation model based on the light intensity and the mean radiation brightness; use the radiation model to perform radiation correction on the first reference remote sensing image to obtain a second reference remote sensing image; determine the pixel value of the second reference remote sensing image; determine the local intensity of each pixel in the second reference remote sensing image according to the pixel value; adjust the brightness and contrast of the second reference remote sensing image according to the local intensity to obtain a target remote sensing image. By performing geometric correction, radiation correction and vignetting correction on the multispectral remote sensing image in the above manner, a clear and effective multispectral remote sensing image can be obtained, which further improves the accuracy of subsequent water quality information detection.

[0098] Reference Figure 3 , Figure 3 This is a structural block diagram of the first embodiment of the fishery aquaculture water quality information detection device based on drone of the present invention.

[0099] like Figure 3 As shown, the fishery aquaculture water quality information detection device based on drone proposed in the embodiment of the present invention includes:

[0100] The acquisition module 10 is used to obtain multispectral remote sensing images of the target fishery breeding area collected by the drone.

[0101] The processing module 20 is used to perform correction processing on the multispectral remote sensing image to obtain a target remote sensing image.

[0102] The extraction module 30 is used to extract image parameter values ​​from the target remote sensing image.

[0103] The input module 40 is used to input the image parameter value into the water quality detection model.

[0104] The detection module 50 is used to perform correlation analysis on the image parameter value and the water quality sample parameter through the water quality detection model to realize water quality information detection.

[0105] This embodiment acquires a multispectral remote sensing image of a target fishery breeding area collected by a drone; performs correction processing on the multispectral remote sensing image to obtain a target remote sensing image; extracts image parameter values ​​from the target remote sensing image; inputs the image parameter values ​​into a water quality detection model; and performs correlation analysis between the image parameter values ​​and water quality sample parameters through the water quality detection model to detect water quality information. In the above manner, a drone is used to shoot remote sensing images, and water quality monitoring is achieved based on the captured images using a water quality detection model, thereby improving monitoring efficiency and accuracy.

[0106] In some embodiments, the acquisition module 10 is used to determine the flight parameters of the UAV, wherein the flight parameters include altitude, speed and overlap rate, the altitude is determined by the resolution, focal length and actual distance of the shooting target of the multispectral camera carried by the UAV, and the speed is determined by the performance of the UAV; determine the shooting parameters of the multispectral camera, wherein the shooting parameters include exposure time, sensitivity, aperture size and aperture band; control the UAV to fly according to the flight parameters according to a preset trajectory, and control the multispectral camera carried by the UAV to collect multispectral remote sensing images of the target fishery breeding area according to the shooting parameters.

[0107] In some embodiments, the processing module 20 is used to select a number of control points from the multispectral remote sensing image; determine the image positions of the control points in the multispectral remote sensing image and the corresponding real positions in the target fishery breeding area; construct a polynomial change model based on the image positions and the real positions; solve the polynomial change model to obtain transformation parameters; use the transformation parameters to perform geometric correction on the multispectral remote sensing image to obtain a first reference remote sensing image; and obtain a target remote sensing image based on the first reference remote sensing image.

[0108] In some embodiments, the processing module 20 is used to select a target site, place a calibration plate at the target site, and adjust the position of the calibration plate so that the calibration plate is located at the center of the screen of the multi-spectral camera; control the multi-spectral camera to collect images at a preset period of seconds, and after collecting several images, determine the average radiation brightness of several images under the same light intensity, and construct a radiation model based on the light intensity and the average radiation brightness; use the radiation model to perform radiation correction on the first reference remote sensing image to obtain a second reference remote sensing image; obtain the target remote sensing image based on the second reference remote sensing image.

[0109] In some embodiments, the processing module 20 is used to determine the pixel value of the second reference remote sensing image; determine the local intensity of each pixel in the second reference remote sensing image according to the pixel value; and adjust the brightness and contrast of the second reference remote sensing image according to the local intensity to obtain a target remote sensing image.

[0110] In some embodiments, the detection module 50 is used to determine the bands and band combinations related to chemical oxygen demand, temperature and pH; obtain image parameter values ​​associated with the bands and band combinations from the image parameter values; determine the correlation coefficient based on the image parameter values ​​and water quality sample parameters through the water quality detection model; and perform water quality information detection on the target fishery breeding area according to the correlation coefficient.

[0111] In some embodiments, the detection module 50 is used to determine the correlation between the image parameter value and the water quality sample parameter according to the size of the correlation coefficient; determine the parameter values ​​corresponding to the chemical oxygen demand, the temperature and the pH based on the water quality sample parameters; calculate the actual chemical oxygen demand, actual temperature and actual pH corresponding to the target fishery breeding area according to the correlation and the parameter values ​​corresponding to the chemical oxygen demand, the temperature and the pH, so as to realize water quality information detection.

[0112] An embodiment of the present application also provides a drone-based fishery aquaculture water quality information detection device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus, and the memory is used to store a drone-based fishery aquaculture water quality information detection program; the processor is used to implement the above-mentioned drone-based fishery aquaculture water quality information detection method when executing the program stored in the memory.

[0113] The communication bus mentioned in the above-mentioned drone-based fishery aquaculture water quality information detection equipment can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc.

[0114] The communication interface is used for communication between the above-mentioned drone-based fishery aquaculture water quality information detection equipment and other equipment.

[0115] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0116] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, and discrete hardware components.

[0117] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive Solid State Disk (SSD)), etc.

[0118] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0119] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0120] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

[0121] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present invention. In specific applications, technicians in this field can make settings as needed, and the present invention does not limit this.

[0122] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0123] In addition, for technical details not described in detail in this embodiment, please refer to the drone-based fishery aquaculture water quality information detection method provided in any embodiment of the present invention, which will not be repeated here.

[0124] In addition, it should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0125] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0126] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0127] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

[0128] It is understandable that the system provided by the embodiment of the present invention corresponds to the method provided by the embodiment of the present invention, and the explanation, examples and beneficial effects of the relevant contents can refer to the corresponding parts in the above method.

Claims

1. A method for detecting water quality information in fishery aquaculture based on drones, characterized in that: The method for detecting water quality information of fishery aquaculture based on drone includes: Acquire multispectral remote sensing images of the target fishery breeding area collected by UAV; Performing correction processing on the multispectral remote sensing image to obtain a target remote sensing image; Extracting image parameter values ​​from the target remote sensing image; Inputting the image parameter value into a water quality detection model; The water quality detection model is used to perform correlation analysis on the image parameter values ​​and water quality sample parameters to achieve water quality information detection.

2. The method for detecting water quality information of fishery aquaculture based on drone according to claim 1, characterized in that: The method of obtaining a multispectral remote sensing image of a target fishery breeding area collected by a drone includes: Determine the flight parameters of the drone, wherein the flight parameters include altitude, speed, and overlap rate, the altitude is determined by the resolution, focal length, and actual distance of the photographed target of the multispectral camera carried by the drone, and the speed is determined by the performance of the drone; Determining shooting parameters of the multispectral camera, wherein the shooting parameters include exposure time, sensitivity, aperture size, and aperture band; The UAV is controlled to fly according to the flight parameters according to a preset trajectory, and the multispectral camera carried by the UAV is controlled to collect multispectral remote sensing images of the target fishery breeding area according to the shooting parameters.

3. The method for detecting water quality information of fishery aquaculture based on drone according to claim 1, characterized in that: The step of correcting the multispectral remote sensing image to obtain a target remote sensing image includes: Selecting a number of control points from the multispectral remote sensing image; Determine the image positions of a plurality of control points in the multispectral remote sensing image and the corresponding real positions in the target fishery breeding area; constructing a polynomial variation model based on the image position and the true position; Solving the polynomial change model to obtain transformation parameters; Performing geometric correction on the multispectral remote sensing image using the transformation parameters to obtain a first reference remote sensing image; A target remote sensing image is obtained based on the first reference remote sensing image.

4. The method for detecting water quality information of fishery aquaculture based on drone as claimed in claim 3, characterized in that: The step of obtaining a target remote sensing image based on the first reference remote sensing image includes: Select a target site, place a calibration plate at the target site, and adjust the position of the calibration plate so that the calibration plate is located at the center of the picture of the multi-spectral camera; Controlling the multi-spectral camera to collect images at a preset period of seconds, after collecting a number of images, determining the average radiation brightness of the images under the same light intensity, and constructing a radiation model based on the light intensity and the average radiation brightness; Performing radiation correction on the first reference remote sensing image using the radiation model to obtain a second reference remote sensing image; A target remote sensing image is obtained based on the second reference remote sensing image.

5. The method for detecting water quality information of fishery aquaculture based on drone according to claim 4, characterized in that: The step of obtaining a target remote sensing image based on the second reference remote sensing image comprises: Determining pixel values ​​of the second reference remote sensing image; Determine the local intensity of each pixel in the second reference remote sensing image according to the pixel value; The brightness and contrast of the second reference remote sensing image are adjusted according to the local intensity to obtain a target remote sensing image.

6. The method for detecting water quality information of fishery aquaculture based on drone according to claim 1, characterized in that: The performing correlation analysis on the image parameter value and the water quality sample parameter by the water quality detection model to realize water quality information detection includes: Determine the bands and band combinations that are related to chemical oxygen demand, temperature, and pH; Acquire image parameter values ​​associated with the bands and the band combinations from the image parameter values; Determining a correlation coefficient based on the image parameter value and the water quality sample parameter by the water quality detection model; The water quality information of the target fishery breeding area is detected according to the correlation coefficient.

7. The method for detecting water quality information of fishery aquaculture based on drone according to claim 6, characterized in that: The detecting of water quality information of the target fishery breeding area according to the correlation coefficient comprises: Determine the correlation between the image parameter value and the water quality sample parameter according to the magnitude of the correlation coefficient; Determine the parameter values ​​corresponding to the chemical oxygen demand, the temperature and the pH based on the water quality sample parameters; The actual chemical oxygen demand, actual temperature and actual pH corresponding to the target fishery breeding area are calculated according to the correlation and the parameter values ​​corresponding to the chemical oxygen demand, the temperature and the pH to realize water quality information detection.

8. A fishery aquaculture water quality information detection device based on drone, characterized in that: The fishery aquaculture water quality information detection device based on drone includes: An acquisition module, used to obtain multispectral remote sensing images of the target fishery breeding area collected by the UAV; A processing module, used for performing correction processing on the multispectral remote sensing image to obtain a target remote sensing image; An extraction module, used for extracting image parameter values ​​from the target remote sensing image; An input module, used for inputting the image parameter value into a water quality detection model; The detection module is used to perform correlation analysis on the image parameter value and the water quality sample parameter through the water quality detection model to realize water quality information detection.

9. The fishery aquaculture water quality information detection device based on drone as claimed in claim 8, characterized in that: The acquisition module is used to determine the flight parameters of the UAV, wherein the flight parameters include altitude, speed and overlap rate, the altitude is determined by the resolution, focal length and actual distance of the shooting target of the multi-spectral camera carried by the UAV, and the speed is determined by the performance of the UAV; Determining shooting parameters of the multispectral camera, wherein the shooting parameters include exposure time, sensitivity, aperture size, and aperture band; The UAV is controlled to fly according to the flight parameters according to a preset trajectory, and the multispectral camera carried by the UAV is controlled to collect multispectral remote sensing images of the target fishery breeding area according to the shooting parameters.

10. The fishery aquaculture water quality information detection device based on drone as claimed in claim 8, characterized in that: The processing module is used to select a number of control points from the multispectral remote sensing image; Determine the image positions of a plurality of control points in the multispectral remote sensing image and the corresponding real positions in the target fishery breeding area; constructing a polynomial variation model based on the image position and the true position; Solving the polynomial change model to obtain transformation parameters; Performing geometric correction on the multispectral remote sensing image using the transformation parameters to obtain a first reference remote sensing image; A target remote sensing image is obtained based on the first reference remote sensing image.

Images