Fish resource quantity determination method, device, equipment, medium and product

Abstract

The invention discloses a fish resource quantity determination method and device, equipment, a medium and a product, and relates to the field of fish resource evaluation.The method comprises the steps that a sonar image is obtained and subjected to bicubic interpolation processing, and the interpolated sonar image is obtained; performing morphological operation processing on the interpolated sonar image; acquiring a background image; carrying out binarization on the background image; gray level transformation and threshold segmentation are carried out on the background image after binarization, contour communication is carried out through closed operation, isolated points are deleted, and a pool contour is obtained; constructing a mask image; subtracting the background image from the sonar image after morphological operation processing, and then multiplying with the mask image to obtain a region of interest; performing gray scale transformation and threshold segmentation on the region of interest to obtain a threshold segmentation result; calculating the average target intensity of organisms in the pool; calculating a biological density based on the average target intensity; and calculating the total biomass in the pool based on the biological density. The method can improve the evaluation precision of the fish resource quantity.

Description

Technical Field

[0001] The present application relates to the field of fish resource assessment, and in particular to a method, device, equipment, medium and product for determining the amount of fish resources. Background Art

[0002] Factory farming uses high-density, intensive farming methods, which require accurate assessments of the amount of fish resources in the breeding ponds to optimize feed use, fish disease control and growth management, thereby improving the economic benefits of the fish farming industry.

[0003] Sonar equipment is widely used in the field of fish farming because it is harmless to fish, environmentally friendly, and unaffected by light and turbid water. Mechanical scanning sonar is an imaging sonar that emits only one beam and achieves 360° scanning or sector scanning back and forth through mechanical rotation. Compared with multi-beam forward-looking sonar, mechanical scanning sonar has the characteristics of low power consumption and low price; compared with split-beam sonar and ordinary single-beam sonar, the image of mechanical scanning sonar is recognizable and can achieve 360° all-round scanning. In summary, mechanical rotation sonar has a high cost-effectiveness and is suitable for the field of aquaculture.

[0004] Although mechanical scanning sonar can scan 360° horizontally, it has a limited vertical angle. Using image information obtained from the horizontal scanning area alone to count fish resources will reduce the accuracy of the system. In addition, according to the principle of sonar imaging, the sound waves reflect back and forth on the wall of the aquaculture pond, which will cause virtual images to appear on the sonar image. If not processed, the artifacts will be misjudged as organisms in the pond.

[0005] Therefore, how to improve the assessment accuracy of fish resources has become an urgent problem to be solved in this field. Summary of the invention

[0006] The purpose of this application is to provide a method, device, equipment, medium and product for determining fish resource quantity, which can improve the assessment accuracy of fish resource quantity.

[0007] To achieve the above objectives, this application provides the following solutions:

[0008] In a first aspect, the present application provides a method for determining fish stock quantity, comprising:

[0009] Acquire sonar images;

[0010] Performing bicubic interpolation processing on the sonar image to obtain an interpolated sonar image;

[0011] Performing morphological operation processing on the interpolated sonar image;

[0012] Get the background image;

[0013] Using a graphic thresholding method to binarize the background image;

[0014] The binarized background image is subjected to grayscale transformation and threshold segmentation, the contours are connected by closing operations, and isolated points are deleted to obtain the pool contour;

[0015] Construct a mask image based on the pool contour;

[0016] Subtracting the background image from the sonar image processed by the morphological operation, and then multiplying the resultant image by the mask image to obtain a sonar image of the interior of the pool, i.e., the region of interest;

[0017] Performing grayscale transformation and threshold segmentation on the region of interest to obtain a threshold segmentation result;

[0018] Calculate the average target intensity of organisms in the pool based on the threshold segmentation result;

[0019] calculating an organism density based on the average target intensity;

[0020] The total amount of organisms in the pool is calculated based on the organism density.

[0021] Optionally, the acquiring of the sonar image specifically comprises the following steps:

[0022] Obtain raw echo data through sonar scanning equipment;

[0023] In each scanning cycle, the raw echo data is analyzed to obtain the angle value θ corresponding to the current cycle and the raw echo data of 800 sampling points in the current cycle;

[0024] Convert the original echo data of the 800 sampling points into a Cartesian coordinate system;

[0025] Scaling the original echo data of 800 sampling points in the Cartesian coordinate system to obtain scaled original echo data;

[0026] Perform data filling on the scaled original echo data;

[0027] Repeat the above steps until the original echo data of all scanning cycles are filled to form a circular scanning image, that is, a sonar image.

[0028] Optionally, the bicubic interpolation process is performed on the sonar image using the following formula:

[0029] T=A·B·C

[0030] Where A represents the weight vector in the x direction, B represents the 4*4 pixel matrix, that is, the pixel value in the 4*4 neighborhood, and C represents the weight vector in the y direction. A = [w(1+x')w(x')w(1-x')w(2-y')]; C = [w(1+y')w(y')w1-y')w(2-y')]; w represents the weight, x' represents the horizontal coordinate of the pixel point in the target image, y' represents the vertical coordinate of the pixel point in the target image, and p nm Represents pixel value, n=1, 2, 3, 4; m=1, 2, 3, 4.

[0031] Optionally, the biological density is calculated based on the average target intensity using the following formula:

[0032] ro=1.6393*pe-53.54

[0033] Where ro represents the biological density and pe represents the average target intensity.

[0034] Optionally, the total amount of organisms in the pool is calculated based on the biomass density using the following formula:

[0035] Val=ro*V

[0036] Among them, Val represents the total biomass in the pool, ro represents the biological density, and V represents the water volume in the pool.

[0037] Optionally, scaling the original echo data of 800 sampling points in the Cartesian coordinate system to obtain the scaled original echo data specifically adopts the following formula:

[0038] x'=mod(x*W / 1600), y'=mod(y*H / 1600)

[0039] Wherein, x' is the horizontal coordinate of the pixel point of the target image, y' is the vertical coordinate of the pixel point of the target image; W is the number of pixels in the horizontal direction of the target image, and H is the number of pixels in the vertical direction of the target image; mod() means rounding; x=rcos(θ), y=rsin(θ), x represents the horizontal coordinate of the original echo data point (the rth point), and after coordinate conversion, it is the horizontal coordinate in Cartesian coordinates; y represents the vertical coordinate of the original echo data point (the rth point), and after coordinate conversion, it is the vertical coordinate in Cartesian coordinates; r represents the number of the sampling point, and θ represents the currently reported angle value.

[0040] In a second aspect, the present application provides a device for determining the amount of fish resources, comprising:

[0041] Sonar, water quality sensor, water temperature sensor, 485-to-network switch and computer;

[0042] The sonar, water quality sensor and water temperature sensor are all connected to the computer via the 485-to-network port switch.

[0043] In a third aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any of the above-mentioned methods for determining fish resource quantities.

[0044] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above-mentioned methods for determining the amount of fish resources.

[0045] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of any of the above-mentioned methods for determining fish resource quantities.

[0046] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0047] The present application provides a method, device, equipment, medium and product for determining the amount of fish resources. First, the original echo data is constructed into a sonar image through coordinate transformation, bicubic interpolation, etc.; then the boundary of the breeding pond is extracted based on morphological operations and graphic thresholding methods, and the image of debris in the pond is removed based on the stationary object subtraction technology; then the pixel grayscale value in the area of ​​interest is converted into a db value, and the average target intensity in the area is calculated, and the biological density is inferred based on this; finally, blind spot correction is performed based on volume inversion, and finally the fish resource assessment result in the entire breeding pond is obtained. Compared with the traditional manual observation method, the present method automatically assesses fish resources through a program, and has the advantage of strong real-time performance and can save historical resource data for breeding analysis. Compared with the ordinary multi-beam sonar assessment method, the advantage of the present method is that the cost and power consumption are greatly reduced without reducing the assessment accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0049] Figure 1 A schematic diagram of a flow chart of a method for determining fish stock quantity provided in one embodiment of the present application;

[0050] Figure 2A schematic diagram of a sonar image after interpolation provided in an embodiment of the present application;

[0051] Figure 3 A schematic diagram of a background image provided in an embodiment of the present application;

[0052] Figure 4 A schematic diagram of a pool outline provided in an embodiment of the present application;

[0053] Figure 5 A schematic diagram of a mask image provided by an embodiment of the present application;

[0054] Figure 6 A schematic diagram of a region of interest provided in an embodiment of the present application;

[0055] Figure 7 A schematic diagram of a region of interest threshold segmentation result provided in an embodiment of the present application;

[0056] Figure 8 A schematic diagram of the structure of a device for determining the amount of fish resources provided in one embodiment of the present application;

[0057] Fig. 9 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0059] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0060] Figure 1 A flow chart of a method for determining fish stock quantity provided in an embodiment of the present application is shown in FIG. Figure 1 , the method in this application includes:

[0061] Step 101: Acquire sonar images.

[0062] The acquisition of sonar images specifically includes two parts: coordinate transformation and data scaling.

[0063] Coordinate transformation: For each scanning cycle, the reported data message, that is, the original echo data, is first parsed. After removing the header and control bytes, the data area is obtained as the angle value θ corresponding to this cycle, and the intensity value of 800 sampling points in this cycle (that is, the original echo data), with 1 byte for each sampling point (range 0 to 255). Since the sonar image is displayed in the Cartesian coordinate system, the data needs to be transformed from the polar coordinate system to the Cartesian coordinate system when displayed. The formula is as follows:

[0064] x=rcos(θ),y=rsin(θ)

[0065] Wherein, θ is the currently reported angle value, and r is the number of the sampling point (0 to 799).

[0066] Data scaling: The above x and y are floating point numbers, which need to be scaled according to the target image size and converted into the coordinate values ​​of each pixel (integer type). The formula is as follows:

[0067] x'=mod(x*W / 1600),y'=mod(y*H / 1600)

[0068] Among them, x', y' are the horizontal and vertical coordinates of the target pixel respectively; W is the number of pixels in the horizontal direction of the target image, and H is the number of pixels in the vertical direction of the target image; mod() means rounding.

[0069] Before scaling, the original data is equivalent to a circle with a radius of 800 pixels. x multiplied by W divided by 1600 is equivalent to scaling the Cartesian coordinate x in the range of 1 to 1600 to the range of 1 to W; the scaling in the y direction is the same.

[0070] Then, fill in the echo value of the sampling point numbered r at the (x', y') coordinate of the target image (the value range is 0 to 255, and the value size is just represented by the pixel grayscale). According to the above method, fill in the data of one scanning cycle each time until the whole circle is scanned, forming a circular scanning image (grayscale image).

[0071] Step 102: Perform bicubic interpolation processing on the sonar image to obtain an interpolated sonar image.

[0072] The data after coordinate transformation is interpolated using the bicubic interpolation algorithm to generate high-quality sonar images in the Cartesian coordinate system. Bicubic interpolation can smooth the image, reduce noise and improve image quality.

[0073] y'=y*N / H The interpolation value of the floating point coordinate point is the weighted sum of the pixel values ​​of the surrounding 4*4 integer coordinate points:

[0074]

[0075] The weight W(i,j) is calculated as follows, where a ranges from [-1,0] and is generally a fixed value of -0.5;

[0076] W(i,j)=w(d xi )*w(d yi )

[0077]

[0078] d xi =xi-x'

[0079] d yj =yj-y′

[0080] The interpolation kernel function and the x-direction weight x' form the x-direction weight vector A, and the interpolation kernel function and the y-direction weight y' form the y-direction weight vector C.

[0081] A=[w(1+x')w(')w(1-x')w(2-y')]

[0082] C=[w(1+y')w(y')w(1-y')w(2-y')]

[0083] Data matrix B constructed from the pixel values ​​of 16 neighborhood echo points:

[0084]

[0085] Finally, the pixel value T of the point to be interpolated is calculated by the weight vector matrices A and C in the X and Y directions and the data B. The formula is as follows:

[0086] T=A·B·C

[0087] The interpolated image is a grayscale image. After color mapping, the grayscale of 0 to 255 is mapped to different RGB colors, and finally the sonar image is obtained. For details, see Figure 2 .

[0088] Step 103: performing morphological operation processing on the interpolated sonar image.

[0089] The interpolated sonar images are preprocessed using morphological operations (erosion, dilation, opening, and closing) to remove noise and small interferences.

[0090] Step 104: Obtain a background image.

[0091] Background image means that during the installation of this system, there is no fish in the pond, and an image is collected as the background image. Figure 3 .

[0092] Step 105: binarize the background image using a graphic thresholding method.

[0093] Step 106: Perform grayscale transformation and threshold segmentation on the binary background image, connect the contours through closing operations, and delete isolated points to obtain the pool contour. For details, see Figure 4 .

[0094] The background image is binarized by thresholding, the boundary of the breeding pool is extracted, and a mask image is constructed based on the boundary. The purpose of this step is to separate the internal area and the external area of ​​the breeding pool for subsequent processing. The boundary is the outline of the pool, the area inside the outline is the internal area of ​​the pool, which is a valid image; the area outside the pool is the external area, which is an invalid image and needs to be removed.

[0095] The process of extracting the pool contour is as follows: grayscale transformation and threshold segmentation are performed on the background image, the contours are connected through a closing operation (kernal_size is 6), and isolated points are deleted to finally obtain the pool contour.

[0096] Step 107: construct a mask image based on the pool contour.

[0097] Specifically, after obtaining the pool contour, use the findContours function of the opencv library to find the contour of the white curve. Use the drawContours function to fill the area within the contour, and then perform appropriate erosion operations on the area to trim a mask image. For details, see Figure 5 .

[0098] Step 108: subtract the background image from the sonar image processed by the morphological operation, and then multiply the resultant image by the mask image to obtain a sonar image of the interior of the pool, that is, the region of interest.

[0099] This step removes the stationary objects and converts the original image ( Figure 2 ), that is, the interpolated sonar image minus the background image ( Figure 3 ), and the mask image ( Figure 5 ) to extract the sonar image inside the pool ( Figure 6 ), that is, the region of interest (ROI), and the number of pixels in the ROI area is counted as n.

[0100] Step 109: Perform grayscale transformation and threshold segmentation on the region of interest to obtain a threshold segmentation result.

[0101] The threshold segmentation this time is to set the pixels with grayscale values ​​greater than 100 to 0, and keep other pixels unchanged, so as to further remove small noise points. The result is as follows Figure 7 shown.

[0102] Step 110: Calculate the average target intensity of organisms in the pool based on the threshold segmentation result.

[0103] The corresponding relationship between grayscale value and db value is: Among them, AB is contrast, TH is threshold, both are interface parameters.

[0104] Step 111: Calculate biological density based on the average target intensity.

[0105] According to the formula in step 110, Figure 7 The grayscale value corresponding to each pixel is converted to db value, summed, and divided by the ROI area n to obtain the average target intensity pe of the organisms in the pool area. The biological density ro is calculated according to the formula ro = 1.6393*pe-3.54.

[0106] Step 112: Calculate the total amount of organisms in the pool based on the organism density.

[0107] The water volume in the breeding pond is V=S*H, where S is the internal area and H is the water depth. The total biomass Val in the pond is calculated according to the formula Val=ro*V.

[0108] The above evaluation results Val are displayed in real time, and historical data are saved for breeding analysis and management.

[0109] In an exemplary embodiment, Figure 8 As shown, a device for determining the amount of fish resources is provided. The device is applied to factory farming scenarios, and can count the amount of fish resources in the farming pond in real time, save historical evaluation results, and save environmental information. The device includes:

[0110] Sonar, water quality sensor, water temperature sensor, 485-to-Ethernet switch and computer.

[0111] Among them, the sonar is a mechanical rotating sonar with a frequency of 650kHz~750kHz, a scanning range of 360°, a horizontal beam opening angle of 3°, a vertical opening angle of 30°, a scanning speed of 10s / circle, and a data interface of 485 interface.

[0112] The computer can run the following software:

[0113] Control software: used for mechanical rotating sonar, water quality sensor, water temperature sensor initialization, parameter configuration, data reading and raw sonar image construction.

[0114] Fish stock assessment algorithm: used to process sonar images and calculate the resource quantity Val.

[0115] Database: used to store historical data, including historical resource quantity, historical water quality, historical water temperature, etc.

[0116] Both the water quality sensor and the water temperature sensor use 485 interface.

[0117] The 485 to Ethernet switch is used to convert 3 channels of 485 data into 1 channel of UDP data and transmit it to the computer through the Ethernet port.

[0118] The working process of the device is as follows:

[0119] After the system is powered on, the control software initializes the mechanical rotating sonar and reads the initial values ​​of the water quality and water temperature sensors; when there are no fish in the breeding pond, the control software makes the sonar rotate one circle and converts the sonar data into original images as the background image; after starting normal operation, the control software makes the sonar rotate one circle every 10 seconds, continuously acquires sonar images, and calculates the resource quantity using the fish resource assessment algorithm; the resource quantity, water quality, and water temperature data are saved in the database.

[0120] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Fig. 9 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data on a method for determining the amount of fish resources. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for determining the amount of fish resources is implemented.

[0121] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0122] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0123] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0124] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0125] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0126] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0127] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0128] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0129] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for determining fish stock quantity, characterized in that: The method for determining the amount of fish resources comprises: Acquire sonar images; Performing bicubic interpolation processing on the sonar image to obtain an interpolated sonar image; Performing morphological operation processing on the interpolated sonar image; Get the background image; Using a graphic thresholding method to binarize the background image; The binarized background image is subjected to grayscale transformation and threshold segmentation, the contours are connected by closing operations, and isolated points are deleted to obtain the pool contour; Construct a mask image based on the pool contour; Subtracting the background image from the sonar image processed by the morphological operation, and then multiplying the resultant image by the mask image to obtain a sonar image of the interior of the pool, i.e., the region of interest; Performing grayscale transformation and threshold segmentation on the region of interest to obtain a threshold segmentation result; Calculate the average target intensity of organisms in the pool based on the threshold segmentation result; calculating an organism density based on the average target intensity; The total amount of organisms in the pool is calculated based on the organism density.

2. The method for determining fish stock quantity according to claim 1, characterized in that: The step of obtaining the sonar image specifically comprises the following steps: Obtain raw echo data through sonar scanning equipment; In each scanning cycle, the raw echo data is analyzed to obtain the angle value θ corresponding to the current cycle and the raw echo data of 800 sampling points in the current cycle; Convert the original echo data of the 800 sampling points into a Cartesian coordinate system; Scaling the original echo data of 800 sampling points in the Cartesian coordinate system to obtain scaled original echo data; Perform data filling on the scaled original echo data; Repeat the above steps until the original echo data of all scanning cycles are filled to form a circular scanning image, that is, a sonar image.

3. The method for determining fish stock quantity according to claim 1, characterized in that: The bicubic interpolation process for the sonar image is specifically performed using the following formula: T=A·B·C Where A represents the weight vector in the x direction, B represents the 4*4 pixel matrix, that is, the pixel value in the 4*4 neighborhood, and C represents the weight vector in the y direction. A = [w(1+x')w(x')w(1-x')w(2-y')]; C = [w(1+y')w(y')w1-y')w(2-y')]; w represents the weight, x' represents the horizontal coordinate of the pixel point in the target image, y' represents the vertical coordinate of the pixel point in the target image, and p nm Represents pixel value, n=1, 2, 3, 4; m=1, 2, 3, 4.

4. The method for determining fish stock quantity according to claim 1, characterized in that: The biological density is calculated based on the average target intensity using the following formula: ro=1.6393*pe-53.54 Where ro represents the biological density and pe represents the average target intensity.

5. The method for determining fish stock quantity according to claim 1, characterized in that: The following formula is used to calculate the total amount of organisms in the pool based on the biodensity: Val=ro*V Among them, Val represents the total biomass in the pool, ro represents the biological density, and V represents the water volume in the pool.

6. The method for determining the amount of fish resources according to claim 1, characterized in that: The original echo data of 800 sampling points in the Cartesian coordinate system are scaled to obtain the scaled original echo data using the following formula: x'=mod(x*W / 1600), y'=mod(y*H / 1600) Wherein, x' is the horizontal coordinate of the pixel point of the target image, y' is the vertical coordinate of the pixel point of the target image; W is the number of pixels in the horizontal direction of the target image, and H is the number of pixels in the vertical direction of the target image; mod() means rounding; x=rcos(θ), y=rsin(θ), x represents the horizontal coordinate of the original echo data point in Cartesian coordinates after coordinate conversion, y represents the vertical coordinate of the original echo data point in Cartesian coordinates after coordinate conversion, r represents the number of the sampling point, and θ represents the currently reported angle value.

7. A device for determining the quantity of fish resources, characterized in that: The fish resource quantity determination device comprises: Sonar, water quality sensor, water temperature sensor, 485-to-network switch and computer; The sonar, water quality sensor and water temperature sensor are all connected to the computer via the 485-to-network switch.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method for determining the amount of fish resources described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for determining the amount of fish resources described in any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method for determining the amount of fish resources described in any one of claims 1 to 6 are implemented.

Images