Net cage fish school number estimation method based on fish school density

Abstract

The invention discloses a net cage fish school number estimation method based on fish school density, and the method comprises the steps: obtaining a sonar image corresponding to the rotation scanning of a target net cage by a sonar through a step S1 and a step S2, and extracting the fish school number corresponding to each sonar image based on image recognition; a linear correlation curve # imgabs2 # of the effective area # imgabs0 # and the sampling depth # imgabs1 # of the netting in water and a nonlinear correlation curve # imgabs5 # of the fish school density # imgabs3 # and the sampling depth # imgabs4 # are obtained through the step S3, finally, integration is conducted on the two curves according to intervals through the step S4, the fish school number of each interval is calculated in a layered mode, and the estimated value # imgabs6 # of the net cage fish school number in the target net cage is obtained through accumulation. The method fully considers the non-uniformity of the fish school density and the net cage netting area along with the depth change, can improve the measurement accuracy of the net cage fish school number, and has the advantages of high accuracy and efficient, rapid and convenient implementation.

Description

Technical Field

[0001] The invention relates to fishery resource estimation and measurement, in particular to a method for estimating the number of fish stocks in net cages based on fish stock density. Background Art

[0002] In modern aquaculture, cage farming has become an important farming method due to its efficient space utilization and good water circulation. However, how to efficiently and accurately monitor the number of fish in the cage is still a key issue in aquaculture management. Traditional manual observation or monitoring methods, limited by water turbidity, light conditions and labor costs, often cannot provide accurate information on the number of fish, affecting the evaluation of aquaculture production and the optimization of feeding strategies. As an advanced underwater detection technology, sonar technology has been widely used in fishery monitoring because it can penetrate water and provide real-time information on fish distribution. However, existing sonar monitoring technologies mostly remain at the two-dimensional distribution recognition stage and cannot accurately estimate the overall number of fish in the cage, especially in complex environments where the fish density is unevenly distributed or the net is deformed, and the measurement error is large. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a method for estimating the number of fish in a cage based on fish density.

[0004] To solve the above technical problems, the technical solution adopted by the present invention is as follows:

[0005] A method for estimating the number of fish in a cage based on fish density, characterized by comprising:

[0006] Step S1, see Figure 2 , the target cage is scanned by sonar in the following manner: the sonar is arranged at the center of the target cage, and dives from the water surface to the bottom of the target cage or rises from the bottom of the target cage to the water surface at a fixed speed v in the vertical direction, and at the same time, the sonar performs rotational scanning in the horizontal direction at a constant angular velocity ω; thereby, the vertical movement of the sonar and the horizontal rotation scanning are performed synchronously, and the target cage is scanned as a whole to obtain complete sonar image data of the cage; wherein, the fixed speed v of the sonar for lifting and lowering needs to be moderate, that is, the overlapping part of each scan should not be too large, and a large area should not be left unscanned.

[0007] Step S2, see Figure 3 , from the complete sonar image data of the cage, based on each time the sonar completes a rotation scan, extract the sonar image corresponding to each rotation scan; wherein the complete sonar image data of the cage can be saved in a video format, and the sonar image can be extracted based on the time T required for the sonar to rotate and scan one circle, or based on other parameters;

[0008] Also, see Figure 4 and Figure 5 , each extracted sonar image is identified through the image recognition model to obtain the corresponding number of fish schools; The number of fish schools and sampling depth of the sonar image corresponding to the circle rotation scan are recorded as and , , is a positive integer, and , k is the total number of rotations of the sonar during the scanning process of step S1, is the single circle depth of the sonar moving in the vertical direction corresponding to one circle of rotation scanning completed in step S1;

[0009] Step S3: Obtaining a linear correlation curve and nonlinear correlation curve , the specific steps include:

[0010] Step S3-1, see Figure 6 According to the following formula, when the sonar performs each rotation scan, the effective area of ​​the net in the water corresponding to the part of the target cage net in the rotation scan period is calculated to approximately represent the deformation change of the target cage net in the water body:

[0011] ;

[0012] In the formula, Indicates the target cage mesh corresponds to The effective area in water scanned by a circle rotation, Indicates The total number of pixels in the target cage net inner area in the sonar image corresponding to the circular rotation scan, see Figure 6 The square area in ; Indicates The total number of pixels of the sonar image corresponding to the circular rotation scan; represents the rotation scanning area of ​​the sonar, which is determined by the scanning radius r of the sonar, according to calculate;

[0013] Step S3-2, see Figure 7 , based on the sampling depth corresponding to each rotation scan and the effective area of ​​the net in water , the effective area of ​​the net in water is obtained by linear fitting With sampling depth The linear correlation curve ;

[0014] Step S3-3: Convert the number of fish obtained in step S2 into fish density according to the following formula, so as to obtain a fish density data point based on each sonar image, and convert the first The fish density data point of the sonar image corresponding to the circle rotation scan is recorded as :

[0015] ;

[0016] In the formula, Indicates The fish density of the sonar image corresponding to the circle rotation scan;

[0017] And, for each sampling depth interval The corresponding two adjacent fish density data points and , interpolation is performed using the same interpolation method to obtain a batch of interpolated fish density data points corresponding to each sampling depth interval;

[0018] Therefore, based on all the fish density data points and the interpolated fish density data points, the fish density is fitted. With sampling depth The nonlinear correlation curve ;

[0019] Step S4: According to the following formula, the estimated value of the number of fish in the target cage is obtained by cumulative calculation: :

[0020] .

[0021] Therefore, the present invention first obtains the sonar image corresponding to each rotation scan of the target cage by the sonar through steps S1 and S2, and extracts the number of fish corresponding to each sonar image based on image recognition, and then obtains the effective area of ​​the net in the water through step S3. With sampling depth The linear correlation curve , and fish density With sampling depth The nonlinear correlation curve Finally, the two curves are integrated by interval in step S4, the number of fish in each interval is calculated layer by layer and accumulated to obtain the estimated value of the number of fish in the target cage. Therefore, the present invention fully considers the non-uniformity of fish density and cage net area with depth, so as to improve the measurement accuracy of the number of fish in the cage, and has the advantages of high accuracy, efficient, fast and convenient implementation.

[0022] Preferably, in step S1, the fixed speed v is calculated according to the following formula:

[0023] ;

[0024] Where H is the total depth of the target cage, T is the time required for the sonar to rotate and scan one circle at the angular velocity, and L is the scannable length of the target cage net by the sonar. Figure 2 The scannable length L is the length of the sonar scanning range projected onto the target cage net, which is calculated based on the sonar opening angle α.

[0025] Thus, it can be ensured that the water area scanned by the sonar when moving in the vertical direction is as non-repetitive as possible, while avoiding the situation where the sonar does not scan the water area.

[0026] Preferably, in step S1, the sonar is moved in the vertical direction by a mechanical lifting device driven by a motor or by human power; and the sonar is an omnidirectional sonar, so as to be able to perform 360° rotation scanning in the horizontal direction by driving the scanning beam.

[0027] Preferably, in step S2, the image recognition model adopts a YOLOv8s model, and its training method is as follows:

[0028] Step S2-1, randomly select 500 sonar images from the existing ones, divide them into training set and test set in a ratio of 7:3, and use YoloLabel software to mark the fish positions on the sonar images;

[0029] Step S2-2: Using the annotated sonar images, model training is performed based on ultralytics. The training parameters are: 300 training rounds, an initial learning rate of 0.001, and an image size of 800×600. Finally, the image recognition model is obtained, so that the image recognition model can be used to identify the position of fish schools in sonar images. See Figure 4 , count the fish positions and get the corresponding number of fish.

[0030] Therefore, in step S2, the present invention adopts the YOLOv8s model to efficiently and accurately count the number of fish schools, which greatly improves the data acquisition efficiency and accuracy compared to manual observation or traditional two-dimensional sonar analysis.

[0031] Preferably, in step S3-2, the linear fitting adopts univariate linear regression analysis, and the regression model is optimized by minimizing the mean square error.

[0032] The formula is:

[0033] ;

[0034] Where m is the number of samples, is the model's predicted value, is the true value.

[0035] Preferably: in step S3-3, the interpolation method uses cubic spline interpolation to avoid overfitting and underfitting, and obtain a nonlinear correlation curve The best fitting effect.

[0036] That is: for each sampling depth interval Construct a cubic polynomial , and use the cubic polynomial function of the partition interval To approximate the relationship between data points to obtain the final nonlinear correlation curve The cubic polynomial for each segment has the following form:

[0037] ;

[0038] in , , , is the coefficient to be determined.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] First, the present invention first obtains the sonar image corresponding to each rotation scan of the target cage by the sonar through steps S1 and S2, and extracts the number of fish corresponding to each sonar image based on image recognition, and then obtains the effective area of ​​the net in the water through step S3. With sampling depth The linear correlation curve , and fish density With sampling depth The nonlinear correlation curve Finally, the two curves are integrated by interval in step S4, the number of fish in each interval is calculated layer by layer and accumulated to obtain the estimated value of the number of fish in the target cage. Therefore, the present invention fully considers the non-uniformity of fish density and cage net area with depth, so as to improve the measurement accuracy of the number of fish in the cage, and has the advantages of high accuracy, efficient, fast and convenient implementation.

[0041] Second, the fixed speed v for driving the sonar to move up and down in the vertical direction in step S1 of the present invention is calculated according to a formula based on the total depth H, time T and scannable length L, which can ensure that the water body scanned by the sonar when moving in the vertical direction is as non-repetitive as possible, while avoiding the situation where the sonar is not scanned.

[0042] Third, in step S2, the present invention adopts the YOLOv8s model, which can efficiently and accurately count the number of fish schools, greatly improving the data acquisition efficiency and accuracy compared to manual observation or traditional two-dimensional sonar analysis.

[0043] Fourth, in step S3-3, the present invention uses cubic spline interpolation to avoid overfitting and underfitting and obtain a nonlinear correlation curve The best fitting effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments:

[0045] Figure 1 is a flow chart of the present invention;

[0046] Figure 2 It is a schematic diagram of sonar scanning in a water body in step S1 of the present invention;

[0047] Figure 3 The sonar image corresponding to the i-th rotation scan in step S2 of the present invention;

[0048] Figure 4 A schematic diagram of image data obtained by the image recognition model in step S2 of the present invention in recognizing the sonar image;

[0049] Figure 5 is the sampling depth of all sonar images obtained in step S2 of the present invention The number of fish The relationship curve diagram of

[0050] Figure 6 is the sum of the pixel points of the inner area of ​​the target cage net in step S3-1 of the present invention Schematic diagram of

[0051] Figure 7 is the sampling depth in step S3-3 of the present invention and the effective area of ​​the net in water And the linear correlation curve obtained by fitting Schematic diagram of . DETAILED DESCRIPTION

[0052] The present invention is described in detail below in conjunction with the embodiments and the accompanying drawings to help those skilled in the art better understand the inventive concept of the present invention. However, the protection scope of the claims of the present invention is not limited to the following embodiments. For those skilled in the art, all other embodiments obtained without creative work without departing from the inventive concept of the present invention belong to the protection scope of the present invention.

[0053] like Figure 1As shown, the present invention discloses a method for estimating the number of fish in a cage based on fish density, comprising:

[0054] Step S1, see Figure 2 , the target cage is scanned by sonar in the following manner: the sonar is arranged at the center of the target cage, and dives from the water surface to the bottom of the target cage or rises from the bottom of the target cage to the water surface at a fixed speed v in the vertical direction, and at the same time, the sonar performs rotational scanning in the horizontal direction at a constant angular velocity ω; thereby, the vertical movement of the sonar and the horizontal rotation scanning are performed synchronously, and the target cage is scanned as a whole to obtain complete sonar image data of the cage; wherein, the fixed speed v of the sonar for lifting and lowering needs to be moderate, that is, the overlapping part of each scan should not be too large, and a large area should not be left unscanned.

[0055] Preferably, in step S1, the fixed speed v is calculated according to the following formula:

[0056] ;

[0057] Where H is the total depth of the target cage, T is the time required for the sonar to rotate and scan one circle at the angular velocity, and L is the scannable length of the target cage net 1 by the sonar. Figure 2 The scannable length L is the length of the sonar scanning range projected onto the target cage net 1, which is calculated based on the sonar opening angle α.

[0058] Thus, it can be ensured that the water area scanned by the sonar when moving in the vertical direction is as non-repetitive as possible, while avoiding the situation where the sonar does not scan the water area.

[0059] Preferably, in step S1, the sonar is moved in the vertical direction by a mechanical lifting device driven by a motor or by human power; and the sonar is an omnidirectional sonar, so as to be able to perform 360° rotation scanning in the horizontal direction by driving the scanning beam.

[0060] Step S2, see Figure 3 , from the complete sonar image data of the cage, based on each time the sonar completes a rotation scan, extract the sonar image corresponding to each rotation scan; wherein the complete sonar image data of the cage can be saved in a video format, and the sonar image can be extracted based on the time T required for the sonar to rotate and scan one circle, or based on other parameters;

[0061] Also, see Figure 4 and Figure 5 , each extracted sonar image is identified through the image recognition model to obtain the corresponding number of fish schools; The number of fish schools and sampling depth of the sonar image corresponding to the circle rotation scan are recorded as and , , is a positive integer, and , k is the total number of rotations of the sonar during the scanning process of step S1, is the single circle depth of the sonar moving in the vertical direction corresponding to one circle of rotation scanning completed in step S1;

[0062] Preferably, in step S2, the image recognition model adopts a YOLOv8s model, and its training method is as follows:

[0063] Step S2-1, randomly select 500 sonar images from the existing ones, divide them into training set and test set in a ratio of 7:3, and use YoloLabel software to mark the fish positions on the sonar images;

[0064] Step S2-2: Using the annotated sonar images, model training is performed based on ultralytics. The training parameters are: 300 training rounds, an initial learning rate of 0.001, and an image size of 800×600. Finally, the image recognition model is obtained, so that the image recognition model can be used to identify the position of fish schools in sonar images. See Figure 4 , count the fish positions and get the corresponding number of fish.

[0065] Therefore, in step S2, the present invention adopts the YOLOv8s model to efficiently and accurately count the number of fish schools, which greatly improves the data acquisition efficiency and accuracy compared to manual observation or traditional two-dimensional sonar analysis.

[0066] Step S3: Obtaining a linear correlation curve And nonlinear correlation curve , the specific steps include:

[0067] Step S3-1, see Figure 6 According to the following formula, when the sonar performs each rotation scan, the effective area of ​​the net in the water corresponding to the part of the target cage net 1 in the rotation scan period is calculated to approximately represent the deformation change of the target cage net 1 in the water body:

[0068] ;

[0069] In the formula, It represents the effective area in water corresponding to the i-th rotation scan of the target cage net 1, Indicates The total number of pixels in the target cage net 1 internal area in the sonar image corresponding to the circle rotation scan, see Figure 6The square area in ; Indicates The total number of pixels of the sonar image corresponding to the circular rotation scan; represents the rotation scanning area of ​​the sonar, which is determined by the scanning radius r of the sonar, according to calculate;

[0070] Step S3-2, see Figure 7 , based on the sampling depth corresponding to each rotation scan and the effective area of ​​the net in water , the effective area of ​​the net in water is obtained by linear fitting With sampling depth The linear correlation curve ;

[0071] Preferably, in step S3-2, the linear fitting adopts univariate linear regression analysis, and the regression model is optimized by minimizing the mean square error.

[0072] The formula is:

[0073] ;

[0074] Where m is the number of samples, is the predicted value of the model, is the true value.

[0075] Step S3-3: Convert the number of fish obtained in step S2 into fish density according to the following formula, so as to obtain a fish density data point based on each sonar image, and record the fish density data point of the sonar image corresponding to the i-th rotation scan as :

[0076] ;

[0077] In the formula, It represents the fish density of the sonar image corresponding to the i-th rotation scan;

[0078] And, for each sampling depth interval The corresponding two adjacent fish density data points and , interpolation is performed using the same interpolation method to obtain a batch of interpolated fish density data points corresponding to each sampling depth interval;

[0079] Therefore, based on all the fish density data points and the interpolated fish density data points, the fish density is fitted. With sampling depth The nonlinear correlation curve ;

[0080] Preferably: in step S3-3, the interpolation method uses cubic spline interpolation to avoid overfitting and underfitting, and obtain a nonlinear correlation curve The best fitting effect.

[0081] That is: for each sampling depth interval Construct a cubic polynomial , and use the cubic polynomial function of the partition interval To approximate the relationship between data points to obtain the final nonlinear correlation curve The cubic polynomial for each segment has the following form:

[0082] ; in , , , is the coefficient to be determined.

[0083] Step S4: According to the following formula, the estimated value of the number of fish in the target cage is obtained by cumulative calculation: :

[0084] .

[0085] Therefore, the present invention first obtains the sonar image corresponding to each rotation scan of the target cage by the sonar through steps S1 and S2, and extracts the number of fish corresponding to each sonar image based on image recognition, and then obtains the effective area of ​​the net in the water through step S3. With sampling depth The linear correlation curve , and fish density With sampling depth The nonlinear correlation curve Finally, the two curves are integrated by interval in step S4, the number of fish in each interval is calculated layer by layer and accumulated to obtain the estimated value of the number of fish in the target cage. Therefore, the present invention fully considers the non-uniformity of fish density and cage net area with depth, so as to improve the measurement accuracy of the number of fish in the cage, and has the advantages of high accuracy, efficient, fast and convenient implementation.

[0086] The present invention is not limited to the above-mentioned specific implementation modes. According to the above-mentioned contents, in accordance with the common technical knowledge and customary means in the field, without departing from the above-mentioned basic technical ideas of the present invention, the present invention can also make other various forms of equivalent modifications, replacements or changes, all of which fall within the protection scope of the present invention.

Claims

1. A method for estimating the number of fish in a cage based on fish density, characterized in that: include: Step S1, scanning the target cage with sonar in the following manner: the sonar is arranged at the center of the target cage, and dives from the water surface to the bottom of the target cage or rises from the bottom of the target cage to the water surface at a fixed speed v in the vertical direction, and at the same time, the sonar performs rotational scanning in the horizontal direction at a constant angular speed ω; thereby, obtaining complete sonar image data of the cage; Step S2, from the complete sonar image data of the cage, based on each time the sonar completes a rotation scan, extracting the sonar image corresponding to each rotation scan; Furthermore, each extracted sonar image is identified through the image recognition model to obtain the corresponding number of fish schools; The number of fish schools and sampling depth of the sonar image corresponding to the circle rotation scan are recorded as and , , is a positive integer, and , k is the total number of rotations of the sonar during the scanning process of step S1, is the single circle depth of the sonar moving in the vertical direction corresponding to one circle of rotation scanning completed in step S1; Step S3: Obtaining a linear correlation curve and nonlinear correlation curve , the specific steps include: Step S3-1, when the sonar performs each rotation scan, calculate the effective area of ​​the net (1) in the water corresponding to the rotation scan during the rotation scan period according to the following formula: ； In the formula, Indicates that the target cage net (1) corresponds to the The effective area in water scanned by a circle rotation, Indicates The sum of the pixel points of the inner area of ​​the target cage net (1) in the sonar image corresponding to the circular rotation scan; Indicates The total number of pixels of the sonar image corresponding to the circular rotation scan; represents the rotational scanning area of ​​the sonar; Step S3-2: Sampling depth corresponding to each rotation scan and the effective area of ​​the net in water , the effective area of ​​the net in water is obtained by linear fitting With sampling depth The linear correlation curve ; Step S3-3: Convert the number of fish obtained in step S2 into fish density according to the following formula, so as to obtain a fish density data point based on each sonar image, and convert the first The fish density data point of the sonar image corresponding to the circle rotation scan is recorded as : ； In the formula, Indicates The fish density of the sonar image corresponding to the circle rotation scan; And, for each sampling depth interval The corresponding two adjacent fish density data points and , interpolation is performed using the same interpolation method to obtain a batch of interpolated fish density data points corresponding to each sampling depth interval; Therefore, based on all the fish density data points and the interpolated fish density data points, the fish density is fitted. With sampling depth The nonlinear correlation curve ; Step S4: Calculate the estimated number of fish in the target cage according to the following formula: : 。 2. The method for estimating the number of fish in a cage based on fish density according to claim 1, characterized in that: In step S1, the fixed speed v is calculated according to the following formula: ； Wherein, H is the total depth of the target cage, T is the time required for the sonar to rotate and scan one circle at the angular velocity, and L is the scannable length of the target cage net (1) by the sonar.

3. The method for estimating the number of fish in a cage based on fish density according to claim 1, characterized in that: In step S1, the sonar is moved in the vertical direction by a mechanical lifting device driven by a motor or by human power; and the sonar is an omnidirectional sonar, so that it can perform 360° rotation scanning in the horizontal direction by driving the scanning beam.

4. The method for estimating the number of fish in a cage based on fish density according to any one of claims 1 to 3, characterized in that: In step S2, the image recognition model adopts the YOLOv8s model, and its training method is as follows: Step S2-1, randomly select 500 sonar images from the existing ones, divide them into training set and test set in a ratio of 7:3, and use YoloLabel software to mark the fish positions on the sonar images; Step S2-2, using the annotated sonar images, model training is performed based on ultralytics, and the training parameters are: 300 training rounds, an initial learning rate of 0.001, and an image size of 800×600. Finally, the image recognition model is obtained, so that the image recognition model can be used to identify the position of fish schools in the sonar image, and the fish school positions are counted to obtain the corresponding number of fish schools.

5. The method for estimating the number of fish in a cage based on fish density according to any one of claims 1 to 3, characterized in that: In step S3-2, the linear fitting adopts univariate linear regression analysis, and optimizes the regression model by minimizing the mean square error.

6. The method for estimating the number of fish in a cage based on fish density according to any one of claims 1 to 3, characterized in that: In the step S3-3, the interpolation method adopts cubic spline interpolation.

Images