Method and device for measuring the meat yield rate of prawns

Abstract

The present invention discloses a method and device for measuring the meat yield of prawns, which solves technical problems existing in the prior art, such as a complex measurement process and low measurement accuracy. The method comprises: acquiring an image of the prawn to be measured, and obtaining the body length, total length of the abdominal segments, and dorsal width of the third abdominal segment of the prawn based on the image of the prawn to be measured; weighing the prawn to be measured to obtain the weight of the prawn to be measured; using the body length, total length of the abdominal segments, dorsal width of the third abdominal segment, and the weight of the prawn to be measured as input parameters of an established net meat weight model, and using the established net meat weight model to predict the net meat weight of the prawn to be measured; and determining the meat yield of the prawn to be measured based on the weight of the prawn to be measured and the net meat weight of the prawn to be measured: meat yield = net meat weight / body weight.

Description

Technical Field

[0001] The invention belongs to the technical field of aquaculture, and in particular relates to a method and a device for measuring the meat yield of prawns. Background Art

[0002] Prawns are a popular seafood due to their thin shells, rich protein, and delicious flavor. The head accounts for over 40% of the shrimp's total body weight, with only the abdominal and tail muscles considered edible as net meat. Shrimp meat yield, which measures the ratio of net meat weight to total body weight, is a key genetic improvement trait for prawns. The higher the meat yield, the greater the economic value.

[0003] Given that obtaining the net meat weight of prawns requires individual slaughter, determining meat yield is time-consuming and labor-intensive. Furthermore, during the genetic improvement process, slaughtered individuals cannot serve as candidate individuals. Therefore, individual selection is impossible, requiring only sibling selection, which reduces selection accuracy. To address this technical issue, existing techniques propose pre-establishing a meat yield model based on prawn morphological traits, then estimating the meat yield of prawns based on the meat yield model and measured prawn morphological traits. However, since these meat yield models rely solely on morphological traits as modeling data, accuracy often requires more than nine morphological traits, making the modeling process complex and the resulting meat yield model complex. Predicting meat yield based on the model also requires measuring up to nine or more morphological traits. Due to the numerous trait parameters and complex model, the parameter acquisition and modeling processes are cumbersome, inefficient, and prone to errors, resulting in low meat yield accuracy. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and device for measuring the meat yield of shrimp, so as to solve the technical problems existing in the prior art of using only the morphological traits of shrimp to establish a meat yield model, such as a complex measurement process and low measurement accuracy.

[0005] To achieve the above-mentioned object of the invention, the method for determining the meat yield of prawns provided by the present invention is implemented by the following technical solution:

[0006] A method for measuring the meat yield of shrimp, the method comprising:

[0007] Collecting an image of the shrimp to be tested, and obtaining the body length, total length of the abdominal segment, and dorsal width of the third abdominal segment of the shrimp to be tested based on the image of the shrimp to be tested;

[0008] Weighing the shrimp to be tested to obtain the weight of the shrimp to be tested;

[0009] The body length, the total length of the abdominal segment, the back width of the third abdominal segment and the body weight of the prawn to be tested are used as input parameters of the established net meat weight model, and the established net meat weight model is used to predict the net meat weight of the prawn to be tested;

[0010] Determine the meat yield of the shrimp according to the body weight and the net meat weight of the shrimp: meat yield = net meat weight / body weight;

[0011] The established net meat weight model is:

[0012] Y MW =k1+k2×BW+k3×AL+k4×A3W+k5×BL;

[0013] Among them, Y MW is the net meat weight, BW is the body weight, BL, AL, and A3W are body length, total length of abdominal segment, and back width of the third abdominal segment, respectively. k1 and k5 are known coefficients less than 0, respectively. k2, k3, and k4 are known coefficients greater than 0, respectively.

[0014] In some embodiments of the present application, the value range of the coefficient k1 is [-1.7121, -1.4371], the value range of the coefficient k2 is [0.4627, 0.4745], the value range of the coefficient k3 is [0.4484, 0.5432], the value range of the coefficient k4 is [0.5504, 0.7552], and the value range of the coefficient k5 is [-0.2037, -0.1419].

[0015] In some embodiments of the present application, the value of the coefficient k1 is -1.5746, the value of the coefficient k2 is 0.4686, the value of the coefficient k3 is 0.4958, the value of the coefficient k4 is 0.6528, and the value of the coefficient k5 is -0.1728.

[0016] In some embodiments of the present application, collecting an image of a shrimp to be tested, and obtaining the body length, the total length of the abdominal segment, and the dorsal width of the third abdominal segment of the shrimp to be tested based on the image of the shrimp to be tested, specifically includes:

[0017] A back image of the shrimp to be tested in a stretched state is collected, and the body length, the total length of the abdominal segment, and the back width of the third abdominal segment of the shrimp to be tested are obtained based on the back image.

[0018] In some embodiments of the present application, the established net meat weight model is established using the following process:

[0019] Establish multiple full-sib families of shrimp and culture different families separately;

[0020] A set number of individual shrimps are selected from each family as sample shrimps, and the sample shrimps are marked according to the family, and all the marked sample shrimps are mixed and cultured;

[0021] After the mixed farming termination conditions are met, an image and weight of each sample shrimp in the mixed farming are obtained; and shape characteristics of the sample shrimp are obtained based on the image of the sample shrimp; the shape characteristics include at least the body length, the total length of the abdominal segment, and the dorsal width of the third abdominal segment of the sample shrimp;

[0022] Obtaining the net meat weight of the sample shrimp, and establishing multiple candidate net meat weight models using regression analysis based on the shape, body weight, and net meat weight of the sample shrimp;

[0023] The determination coefficient of each of the net meat weight models to be selected is obtained, and the net meat weight model to be selected corresponding to the maximum value of the determination coefficient is determined as the established net meat weight model.

[0024] In some embodiments of the present application, the method further comprises:

[0025] Obtaining the average meat yield of the family according to the meat yield of the tested shrimp;

[0026] Calculate the difference in average meat yield between different families based on the average meat yield of the family;

[0027] When the difference is greater than a preset difference threshold, the established net meat weight model is re-established.

[0028] To achieve the above-mentioned purpose, the device for measuring the meat yield of shrimp provided by the present invention is implemented by the following technical solution:

[0029] A device for measuring the meat yield of prawns, characterized in that the device comprises:

[0030] An image acquisition unit, used for acquiring images of the shrimp to be tested;

[0031] a shape and trait acquisition unit, configured to acquire the body length, the total length of the abdominal segments, and the dorsal width of the third abdominal segment of the shrimp to be tested based on the image of the shrimp to be tested;

[0032] A weight collection unit, used to weigh the shrimp to be tested and obtain the weight of the shrimp to be tested;

[0033] a net meat weight prediction unit, configured to use the body length, the total length of the abdominal segments, the back width of the third abdominal segment, and the body weight of the shrimp to be tested as input parameters of an established net meat weight model, and predict the net meat weight of the shrimp to be tested using the established net meat weight model;

[0034] a meat yield determination unit, configured to determine the meat yield of the shrimp to be tested according to the body weight of the shrimp to be tested and the net meat weight of the shrimp to be tested: meat yield = net meat weight / body weight;

[0035] The established net meat weight model is:

[0036] Y MW =k1+k2×BW+k3×AL+k4×A3W+k5×BL;

[0037] Among them, Y MW is the net meat weight, BW is the body weight, BL, AL, and A3W are body length, total length of abdominal segment, and back width of the third abdominal segment, respectively. k1 and k5 are known coefficients less than 0, respectively. k2, k3, and k4 are known coefficients greater than 0, respectively.

[0038] In some embodiments of the present application, the value range of the coefficient k1 is [-1.7121, -1.4371], the value range of the coefficient k2 is [0.4627, 0.4745], the value range of the coefficient k3 is [0.4484, 0.5432], the value range of the coefficient k4 is [0.5504, 0.7552], and the value range of the coefficient k5 is [-0.2037, -0.1419].

[0039] In some embodiments of the present application, the device further comprises:

[0040] The net meat weight model establishing unit is used to establish the established net meat weight model using the following process:

[0041] Establish multiple full-sib families of shrimp and culture different families separately;

[0042] A set number of individual shrimps are selected from each family as sample shrimps, and the sample shrimps are marked according to the family, and all the marked sample shrimps are mixed and cultured;

[0043] After the mixed farming termination conditions are met, an image and weight of each sample shrimp in the mixed farming are obtained; and shape characteristics of the sample shrimp are obtained based on the image of the sample shrimp; the shape characteristics include at least the body length, the total length of the abdominal segment, and the dorsal width of the third abdominal segment of the sample shrimp;

[0044] Obtaining the net meat weight of the sample shrimp, and establishing multiple candidate net meat weight models using regression analysis based on the shape, body weight, and net meat weight of the sample shrimp;

[0045] The determination coefficient of each of the net meat weight models to be selected is obtained, and the net meat weight model to be selected corresponding to the maximum value of the determination coefficient is determined as the established net meat weight model.

[0046] In some embodiments of the present application, the device further comprises:

[0047] a family average meat yield acquisition unit, configured to acquire the family average meat yield based on the meat yield of the shrimp to be tested;

[0048] an average meat yield difference obtaining unit, configured to calculate the difference in average meat yield between different families based on the average meat yield of the family;

[0049] a difference comparison unit, configured to compare the difference with the preset difference threshold and output a comparison result;

[0050] When the difference is greater than the preset difference threshold, the net meat weight model establishing unit re-establishes the established net meat weight model.

[0051] Compared with the prior art, the advantages and positive effects of the present invention are:

[0052] The present invention provides a method and device for determining the meat yield of prawns. The method and device utilize the weight, body length, total length of the abdominal segments, and dorsal width of the third abdominal segment of the prawns to establish a net meat weight model. The net meat weight of the prawns is predicted based on the net meat weight model. The meat yield of the prawns is then determined based on the net meat weight and body weight. By introducing the weight trait that has a greater impact on the net meat weight, only three shape traits need to be used to obtain the net meat weight with high prediction accuracy. The meat yield is then calculated based on the net meat weight and body weight, thereby obtaining the meat yield of the prawns with high accuracy and achieving accurate determination of the meat yield. The weight trait is easy to measure with low error, and the entire determination process requires fewer trait parameters. This simplifies the parameter acquisition process and the complexity of the model, improves the determination efficiency, is less prone to errors, and further improves the accuracy of the meat yield determination.

[0053] Other features and advantages of the present invention will become more apparent after reading the detailed description of the present invention in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0055] Figure 1 Shown is a flow chart of an embodiment of a method for measuring the meat yield of shrimp according to the present invention;

[0056] Figure 2 Shown is a schematic diagram of obtaining morphological traits based on images;

[0057] Figure 3Shown is a flow chart of another embodiment of the method for measuring the meat yield of shrimp according to the present invention;

[0058] Figure 4 FIG2 is a structural block diagram of an embodiment of a device for measuring the meat yield of prawns according to the present invention;

[0059] Figure 5 Shown is a structural block diagram of another embodiment of the device for measuring the meat yield of shrimps according to the present invention. DETAILED DESCRIPTION

[0060] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments.

[0061] To address the technical problems of the existing technology of estimating the meat yield of shrimp by relying solely on shrimp morphological trait parameters, such as the large number of required trait parameters, the complex measurement process, and the low measurement accuracy, the present invention creatively proposes to use body weight as one of the parameters for estimating the net meat weight of shrimp. By combining it with a small number of trait parameters, the net meat weight with high prediction accuracy can be obtained. The meat yield is calculated based on the net meat weight and body weight, and the meat yield of shrimp can be measured with high accuracy, thereby achieving the purpose of reducing the complexity of meat yield measurement and improving the measurement accuracy.

[0062] Figure 1 Shown is a flow chart of an embodiment of a method for determining the meat yield of shrimp according to the present invention.

[0063] like Figure 1 As shown, this embodiment uses the following process to determine the meat yield of shrimp.

[0064] S11: collecting images of the shrimp to be tested, and obtaining the body length, total length of the abdominal segments, and dorsal width of the third abdominal segment of the shrimp to be tested based on the images of the shrimp to be tested.

[0065] The body length, the total length of the abdominal segments and the dorsal width of the third abdominal segment as the shape traits of the shrimp can be obtained by image analysis based on the shrimp image. The specific acquisition method can be achieved using existing technologies.

[0066] In some embodiments, the back image of the shrimp to be tested can be collected in a stretched state, and the body length, the total length of the abdominal segment and the back width of the third abdominal segment can be obtained based on the back image. Figure 2 The schematic diagram of obtaining morphological characteristics based on images is shown in FIG. 1 , and the specific implementation process is as follows:

[0067] Place the shrimp to be tested in low-temperature water below 10℃ to reduce its vitality, then place it on the image acquisition platform with its back facing up and abdomen facing down, and present it as shown in the figure. Figure 2The stretched state shown. An image acquisition device is placed above the image acquisition platform, and a ruler is placed next to the shrimp. The image acquisition device is used to capture the back image of the shrimp in the stretched state. Then, the morphological characteristics are measured using image processing software. First, the pixel value between the two specified points to be measured is measured, and then the pixel value per unit length (such as 1 cm) on the ruler is measured. The ratio of the pixel value between the two specified points to the pixel value per unit length is the actual distance between the two points to be measured. Figure 2 As shown, multiple shape traits of the shrimp can be obtained based on the back image, including body length BL, total length of abdominal segment AL, cephalothorax length CL, cephalothorax width CW, dorsal width of the first abdominal segment A1W, dorsal width of the second abdominal segment A2W, dorsal width of the third abdominal segment A3W, dorsal width of the fourth abdominal segment A4W, dorsal width of the fifth abdominal segment A5W, and dorsal width of the sixth abdominal segment A6W.

[0068] S12: Weigh the shrimp to be tested to obtain the weight of the shrimp to be tested.

[0069] S13: The body length, total length of the abdominal segments, dorsal width of the third abdominal segment and body weight of the shrimp to be tested are used as input parameters of the established net meat weight model, and the established net meat weight model is used to predict the net meat weight of the shrimp to be tested.

[0070] Among them, the established net meat weight model is:

[0071] Y MW =k1+k2×BW+k3×AL+k4×A3W+k5×BL;

[0072] In the formula, Y MW is the net meat weight, BW is the body weight, BL, AL, A3W are the body length, total length of the abdominal segment, and back width of the third abdominal segment respectively, k1 and k5 are known coefficients less than 0, and k2, k3, and k4 are known coefficients greater than 0. Moreover, Y in the above formula MW , BW, BL, AL, and A3W are dimensionless values. This means the net meat weight model formula only considers the magnitude, not the dimension. The actual units of the predicted net meat weight are consistent with the units of the measured body weight.

[0073] In some embodiments, the value ranges of the coefficients in the net meat weight model are as follows:

[0074] The value range of coefficient k1 is [-1.7121, -1.4371], the value range of coefficient k2 is [0.4627, 0.4745], the value range of coefficient k3 is [0.4484, 0.5432], the value range of coefficient k4 is [0.5504, 0.7552], and the value range of coefficient k5 is [-0.2037, -0.1419].

[0075] In some other embodiments, the specific values of the coefficients in the net meat weight model are:

[0076] The value of coefficient k1 is -1.5746, the value of coefficient k2 is 0.4686, the value of coefficient k3 is 0.4958, the value of coefficient k4 is 0.6528, and the value of coefficient k5 is -0.1728.

[0077] S14: Determine the meat yield of the shrimp to be tested based on the body weight and the net meat weight.

[0078] Among them, meat yield = net meat weight / body weight.

[0079] In this embodiment, by introducing the body weight trait that has a greater impact on net meat weight, only the three shape traits of body length, total length of abdominal segments, and dorsal width of the third abdominal segment need to be used to obtain a net meat weight with high prediction accuracy. The meat yield rate is then calculated based on the net meat weight and body weight, thereby obtaining a highly accurate meat yield rate of prawns and achieving accurate determination of the meat yield rate. Using the method of this embodiment, the body weight trait is easy to measure with low error. Fewer trait parameters are required for the entire measurement process, simplifying the parameter acquisition process and the complexity of the model, improving measurement efficiency, and being less prone to error, further improving the accuracy of meat yield determination.

[0080] The established net meat weight model is a pre-established model that is directly used during the measurement process. To improve the accuracy of the model, in some embodiments, the established net meat weight model is obtained using the following process.

[0081] Establish multiple full-sib families of shrimp and culture different families separately.

[0082] A set number of shrimp individuals were selected from each family as sample shrimps, which were marked according to the family. All the marked sample shrimps were mixed and cultured.

[0083] After the mixed culture termination conditions are met, images and weights of each sample shrimp in the mixed culture are obtained. Based on the images of the sample shrimp, shape traits of the sample shrimp are obtained; the shape traits include at least the body length, total length of the abdominal segment, and dorsal width of the third abdominal segment of the sample shrimp.

[0084] The net meat weight of the sample shrimp was obtained, and based on the shape, body weight and net meat weight of the sample shrimp, multiple net meat weight models were established using regression analysis.

[0085] The coefficient of determination of each candidate net meat weight model is obtained, and the candidate net meat weight model corresponding to the maximum coefficient of determination is determined as the established net meat weight model.

[0086] The following is a specific example to further illustrate the process of establishing the net meat weight model.

[0087] Forty full-sib families were established through a nested mating design, and each family was cultured separately. When most individuals reached approximately 5 cm, 50 shrimp from each family were selected as sample shrimp. These shrimp were fluorescently labeled according to family lineage and then placed in a recirculating water raceway-type cement tank for mixed culture. After 60 days of culture, when the mixed culture conditions were met, 1,560 sample shrimp were harvested from the tanks and their meat yield was determined.

[0088] The collected shrimp were first placed in cold water (<10°C) to reduce their vitality. The shrimp were then placed on an image acquisition platform with their backs facing up and their abdomens facing down. A camera was placed above the platform, and a ruler was placed next to the shrimp. The shrimp were held in a stretched-out position while images of their backs were captured. The back images were used to determine the shrimp's body length, total abdominal segment length, and dorsal width of the third abdominal segment.

[0089] After taking photos, weigh the shrimp. Once the shrimp die, calculate the net meat weight (MW) of the dead shrimp. Divide the net meat weight by the shrimp's body weight to calculate the meat yield (MY).

[0090] Based on the net meat weight, meat yield, shape traits and body weight of the sample shrimp, a stepwise regression analysis method was used to establish multiple candidate net meat weight models and meat yield models, and the t-test t value, significance P value and determination coefficient R of each model were calculated. 2 The net meat weight models and meat yield models to be selected are shown in Table 1 and Table 2 below, respectively.

[0091] Table 1. Candidate net meat weight models

[0092]

[0093] Table 2 Meat yield model

[0094]

[0095] Among the meat yield models listed in Table 2, Model 4, which showed the highest prediction accuracy, had a coefficient of determination of only 0.2025. Further calculations revealed that the correlation coefficient between the predicted and observed values for this model was only 0.45. This suggests that using weight and a few other shape traits cannot directly and accurately predict meat yield.

[0096] Of the four net meat weight models listed in Table 1, Model 4 has a coefficient of determination of 0.9828, the highest among the four models. Further calculations show that the correlation coefficient between the predicted and observed values of Model 4 reaches 0.991, indicating that using body weight and a few shape traits can accurately predict net meat weight. Furthermore, considering that the coefficient of determination for meat yield in Table 2, corresponding to Model 4, is also the highest among the four meat yield models, Model 4 is therefore considered the established net meat weight model for determining shrimp meat yield.

[0097] For the established net meat weight model used to determine the meat yield of shrimp, if the coefficients in the model can be adjusted in time according to actual applications, the robustness and effectiveness of the model can be maintained and the accuracy of the predicted net meat weight can be improved.

[0098] Figure 3 The flowchart of another embodiment of the method for measuring the meat yield of prawns according to the present invention is shown. Specifically, the flowchart is about an embodiment of whether to update the net meat weight model.

[0099] like Figure 3 As shown, the method of this embodiment includes the following processes.

[0100] S21: Obtain the average meat yield of the family based on the meat yield of the shrimp to be tested.

[0101] The meat yield of the shrimp to be tested was Figure 1 The method of the embodiment is used for determination. If the family to which each shrimp to be tested belongs is known, the average meat yield of the family to which it belongs can be calculated based on the meat yield of each individual shrimp.

[0102] S22: Calculate the difference in average meat yield between different families based on the average meat yield of the families.

[0103] S23: Determine whether the difference is greater than a preset difference threshold. If so, execute step S24; otherwise, execute step S25.

[0104] The difference threshold is a preset value, which may be an empirical value, a test value, or a theoretically calculated value.

[0105] S24: Re-establish the established net meat weight model.

[0106] When using the net meat weight model provided by the present invention to measure shrimp meat yield, the meat yield of individuals within a family varies significantly, while the average meat yield of families varies less. If the difference in average meat yield between families exceeds a preset difference threshold, the accuracy of the original net meat weight model is considered to have declined, and the model needs to be updated. Specifically, the coefficients in the model need to be updated to achieve the purpose of re-establishing the net meat weight model. Thereafter, the newly established net meat weight model is used to measure shrimp meat yield.

[0107] The process of re-establishing the net meat weight model can be implemented using the process of the embodiment.

[0108] S25: Maintain the established net meat weight model.

[0109] If the difference in average meat yield between families is no greater than the preset difference threshold, the established net meat weight model will remain unchanged and continue to be used to determine the meat yield of shrimp.

[0110] Figure 4 The present invention shows a structural block diagram of an apparatus for measuring the meat yield of prawns according to an embodiment of the present invention.

[0111] like Figure 4 As shown, the structural units included in the device of this embodiment, the functions of the structural units and the relationships between them are as follows:

[0112] The device includes:

[0113] The image acquisition unit 31 is used to acquire images of the shrimp to be tested.

[0114] The shape and trait acquisition unit 32 is used to acquire shape and trait of the shrimp to be tested, such as body length, total length of abdominal segments, and back width of the third abdominal segment, based on the shrimp image to be tested acquired by the image acquisition unit 31 .

[0115] The weight collection unit 33 is used to weigh the shrimp to be tested and obtain the weight of the shrimp to be tested.

[0116] The net meat weight prediction unit 34 is used to use the body length, total length of the abdominal segment, and dorsal width of the third abdominal segment of the shrimp to be tested obtained by the shape trait acquisition unit 32 and the weight collected by the weight collection unit 33 as input parameters of the established net meat weight model, and use the established net meat weight model to predict the net meat weight of the shrimp to be tested.

[0117] The meat yield determination unit 35 is used to determine the meat yield of the shrimp to be tested based on the weight of the shrimp to be tested collected by the weight collection unit 33 and the net meat weight of the shrimp to be tested predicted by the net meat weight prediction unit, wherein the meat yield = net meat weight / body weight.

[0118] The device having the above structure, according to Figure 1 The method embodiment of measuring the meat yield of prawns and the process of other embodiments are used to measure the meat yield of prawns, so as to achieve the same Figure 1 The corresponding technical effects of the embodiment and other embodiments.

[0119] Figure 5 The figure shows a structural block diagram of another embodiment of the device for measuring the meat yield of shrimps according to the present invention.

[0120] like Figure 5As shown, the structural units included in the device of this embodiment, the functions of the structural units and the relationships between them are as follows:

[0121] The device includes:

[0122] The average meat yield rate of the family is obtained by the unit 41, which is used to obtain the average meat yield rate of the family according to the meat yield rate of the shrimp to be tested. Figure 4 The device of the embodiment is completed.

[0123] The average meat yield difference acquisition unit 42 is used to calculate the difference in average meat yield between different families based on the average meat yield of the family acquired by the family average meat yield acquisition unit 41.

[0124] The difference comparison unit 43 is used to compare the difference obtained by the average meat yield difference obtaining unit 42 with a preset difference threshold and output a comparison result.

[0125] The net meat weight model establishing unit 44 is used to re-establish an established net meat weight model when the difference value output by the difference comparison unit 43 is greater than a preset difference value threshold value.

[0126] If the difference value output by the difference comparison unit 43 is not greater than the preset difference threshold value, the previously established net meat weight model is maintained unchanged, and there is no need to re-establish the net meat weight model.

[0127] The net meat weight model establishing unit 44 establishes the net meat weight model using the following process:

[0128] Establish multiple full-sib families of shrimp and culture different families separately.

[0129] A set number of shrimp individuals were selected from each family as sample shrimps, which were marked according to the family. All the marked sample shrimps were mixed and cultured.

[0130] After the conditions for ending the mixed farming are met, the image and weight of each sample shrimp in the mixed farming are obtained; the shape traits of the sample shrimp are obtained based on the image of the sample shrimp; the shape traits at least include the body length, the total length of the abdominal segment and the dorsal width of the third abdominal segment of the sample shrimp.

[0131] The net meat weight of the sample shrimp was obtained, and based on the shape, body weight and net meat weight of the sample shrimp, multiple net meat weight models for selection were established using regression analysis.

[0132] The coefficient of determination of each candidate net meat weight model is obtained, and the candidate net meat weight model corresponding to the maximum coefficient of determination is determined as the established net meat weight model.

[0133] The device having the above structure, according to Figure 3The method embodiment of measuring the meat yield of prawns and the process of other embodiments are used to measure the meat yield of prawns, so as to achieve the same Figure 3 The corresponding technical effects of the embodiment and other embodiments.

[0134] 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, it is still possible for a person skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to replace some of the technical features therein with 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 claimed to be protected by the present invention.

Claims

1. A method for determining the meat yield of shrimp, characterized in that: The method comprises: Collecting an image of the shrimp to be tested, and obtaining the body length, total length of the abdominal segment, and dorsal width of the third abdominal segment of the shrimp to be tested based on the image of the shrimp to be tested; Weighing the shrimp to be tested to obtain the weight of the shrimp to be tested; The body length, the total length of the abdominal segment, the back width of the third abdominal segment and the body weight of the prawn to be tested are used as input parameters of the established net meat weight model, and the established net meat weight model is used to predict the net meat weight of the prawn to be tested; Determine the meat yield of the shrimp according to the body weight and the net meat weight of the shrimp: meat yield = net meat weight / body weight; The established net meat weight model is: AND MW =k1+k2×BW+k3×AL+k4×A3W+k5×BL; Among them, Y MW is the net meat weight, BW is the body weight, BL, AL, and A3W are the body length, total length of the abdominal segment, and dorsal width of the third abdominal segment, respectively; k1 and k5 are known coefficients less than 0, respectively; k2, k3, and k4 are known coefficients greater than 0, respectively; The established net meat weight model was established using the following process: Establish multiple full-sib families of shrimp and culture different families separately; A set number of individual shrimps are selected from each family as sample shrimps, and the sample shrimps are marked according to the family, and all the marked sample shrimps are mixed and cultured; After the mixed farming termination conditions are met, an image and weight of each sample shrimp in the mixed farming are obtained; and shape characteristics of the sample shrimp are obtained based on the image of the sample shrimp; the shape characteristics include at least the body length, the total length of the abdominal segment, and the dorsal width of the third abdominal segment of the sample shrimp; Obtaining the net meat weight of the sample shrimp, and establishing multiple candidate net meat weight models using regression analysis based on the shape, body weight, and net meat weight of the sample shrimp; Obtaining a coefficient of determination for each of the to-be-selected net meat weight models, and determining the to-be-selected net meat weight model corresponding to the maximum value of the coefficient of determination as the established net meat weight model; The method further comprises: Obtaining the average meat yield of the family according to the meat yield of the tested shrimp; Calculate the difference in average meat yield between different families based on the average meat yield of the family; When the difference is greater than a preset difference threshold, the established net meat weight model is re-established.

2. The method for determining the meat yield of prawns according to claim 1, wherein: The value range of the coefficient k1 is [-1.7121, -1.4371], the value range of the coefficient k2 is [0.4627, 0.4745], the value range of the coefficient k3 is [0.4484, 0.5432], the value range of the coefficient k4 is [0.5504, 0.7552], and the value range of the coefficient k5 is [-0.2037, -0.1419].

3. The method for determining the meat yield of prawns according to claim 2, wherein: The value of the coefficient k1 is -1.5746, the value of the coefficient k2 is 0.4686, the value of the coefficient k3 is 0.4958, the value of the coefficient k4 is 0.6528, and the value of the coefficient k5 is -0.1728.

4. The method for determining the meat yield of prawns according to claim 1, wherein: Collecting an image of the shrimp to be tested, and obtaining the body length, the total length of the abdominal segment, and the dorsal width of the third abdominal segment of the shrimp to be tested based on the image of the shrimp to be tested, specifically comprising: A back image of the shrimp to be tested in a stretched state is collected, and the body length, the total length of the abdominal segment, and the back width of the third abdominal segment of the shrimp to be tested are obtained based on the back image.

5. A device for measuring the meat yield of shrimp, characterized in that: The device comprises: An image acquisition unit, used for acquiring images of the shrimp to be tested; a shape and trait acquisition unit, configured to acquire the body length, the total length of the abdominal segments, and the dorsal width of the third abdominal segment of the shrimp to be tested based on the image of the shrimp to be tested; A weight collection unit, used to weigh the shrimp to be tested and obtain the weight of the shrimp to be tested; a net meat weight prediction unit, configured to use the body length, the total length of the abdominal segments, the back width of the third abdominal segment, and the body weight of the shrimp to be tested as input parameters of an established net meat weight model, and predict the net meat weight of the shrimp to be tested using the established net meat weight model; a meat yield determination unit, configured to determine the meat yield of the shrimp to be tested according to the body weight of the shrimp to be tested and the net meat weight of the shrimp to be tested: meat yield = net meat weight / body weight; The established net meat weight model is: AND MW =k1+k2×BW+k3×AL+k4×A3W+k5×BL; Among them, Y MW is the net meat weight, BW is the body weight, BL, AL, and A3W are the body length, total length of the abdominal segment, and dorsal width of the third abdominal segment, respectively; k1 and k5 are known coefficients less than 0, respectively; k2, k3, and k4 are known coefficients greater than 0, respectively; The device further comprises: The net meat weight model establishing unit is used to establish the established net meat weight model using the following process: Establish multiple full-sib families of shrimp and culture different families separately; A set number of individual shrimps are selected from each family as sample shrimps, and the sample shrimps are marked according to the family, and all the marked sample shrimps are mixed and cultured; After the mixed farming termination conditions are met, an image and weight of each sample shrimp in the mixed farming are obtained; and shape characteristics of the sample shrimp are obtained based on the image of the sample shrimp; the shape characteristics include at least the body length, the total length of the abdominal segment, and the dorsal width of the third abdominal segment of the sample shrimp; Obtaining the net meat weight of the sample shrimp, and establishing multiple candidate net meat weight models using regression analysis based on the shape, body weight, and net meat weight of the sample shrimp; Obtaining a coefficient of determination for each of the to-be-selected net meat weight models, and determining the to-be-selected net meat weight model corresponding to the maximum value of the coefficient of determination as the established net meat weight model; a family average meat yield acquisition unit, configured to acquire the family average meat yield based on the meat yield of the shrimp to be tested; an average meat yield difference obtaining unit, configured to calculate the difference in average meat yield between different families based on the average meat yield of the family; a difference comparison unit, configured to compare the difference with a preset difference threshold and output a comparison result; When the difference is greater than the preset difference threshold, the net meat weight model establishing unit re-establishes the established net meat weight model.

6. The device for measuring the meat yield of prawns according to claim 5, characterized in that: The value range of the coefficient k1 is [-1.7121, -1.4371], the value range of the coefficient k2 is [0.4627, 0.4745], the value range of the coefficient k3 is [0.4484, 0.5432], the value range of the coefficient k4 is [0.5504, 0.7552], and the value range of the coefficient k5 is [-0.2037, -0.1419].

Images