A method for identifying the quality of snakehead fry

Abstract

This invention discloses a method for judging the quality of snakehead fry, belonging to the field of aquaculture. This method selects behavioral parameters of snakehead fry, such as average speed, acceleration, and uniformity of movement trajectory, as quality-related indicators to achieve accurate quality judgment. Through the intelligent means of this invention, a detection speed of 2 minutes per batch is achieved, while reducing fry damage by 85.6%. Furthermore, it enables earlier intervention for diseases based on the identification results, thereby improving the efficiency and accuracy of snakehead fry quality judgment and reducing errors and damage caused by manual operation. It has significant application value and promising prospects for widespread application.

Description

Technical Field

[0001] This invention relates to the field of aquaculture, specifically to a method for judging the quality of snakehead seedlings. Background Technology

[0002] As an important economic fish species, the quality of snakehead fry directly affects aquaculture profitability. Currently, the quality assessment of snakehead fry mainly relies on manual observation, judging by characteristics such as activity and body shape. This method is highly subjective, inefficient, and difficult to accurately quantify fry quality, failing to meet the needs of large-scale aquaculture for rapid and precise fry quality assessment. Furthermore, the measurement and capture processes can easily cause stress and mechanical damage to the fry, affecting their growth and survival rate.

[0003] Therefore, there is an urgent need for a scientific and efficient method for judging the quality of snakehead seedlings. Summary of the Invention

[0004] The purpose of this invention is to provide a method for judging the quality of snakehead fry, which can accurately count the fish, quickly detect the quality of the fry, and reduce the damage rate of the fry.

[0005] To achieve the above objectives, the technical solution provided by this invention is as follows:

[0006] A method for judging the quality of snakehead fry is proposed. This method selects behavioral parameters such as average velocity, acceleration, and uniformity of movement trajectory as quality-related indicators to achieve accurate judgment of snakehead fry quality. The specific steps are as follows:

[0007] (1) Collect fish fry movement data in real time through the data acquisition module, including video streams or sensor data;

[0008] (2) Calculate core indicators such as acceleration, average velocity, and uniformity of motion trajectory of an individual or group based on the collected data. The uniformity of motion trajectory includes parameters such as velocity variance and spatial distribution dispersion.

[0009] (3) The evaluation model was constructed using the Deepocsort algorithm and the backend software was developed using Python to achieve intelligent judgment of the quality of snakehead seedlings.

[0010] Furthermore, in step (1), the data acquisition module uses software such as DarkLabel to collect seedling labeling data.

[0011] Furthermore, for video stream data acquisition, a high-definition camera is installed above the breeding pond to capture real-time video of the seedlings' movement at a frame rate of 25 frames per second. The video is then input into DarkLabel software to automatically mark the seedlings and obtain the initial position coordinates of each seedling.

[0012] For sensor data acquisition, accelerometers and position sensors are deployed in the breeding pond. The accelerometers collect acceleration data of the seedlings' movement at a sampling frequency of 100Hz, and the position sensors collect position coordinate data of the seedlings at a sampling frequency of 50Hz.

[0013] Furthermore, in step (3), the evaluation model is constructed using the Deepocsort algorithm by using real-time collected dynamic behavior data of fish fry to construct the evaluation model;

[0014] The motion state adopts a Kalman filter model, and the state vector includes position. ,speed acceleration The state transition equation is:

[0015] ( )

[0016] In the formula: Let x be the current position coordinates of the target in the horizontal direction (x-axis direction). The position coordinates of the target in the horizontal direction (x-axis direction) at the previous moment; This represents the current position coordinates of the target in the vertical direction (y-axis direction). The position coordinates of the target in the vertical direction (y-axis direction) at the previous moment;

[0017] Let this be the target's velocity in the horizontal direction (x-axis direction) at the current moment. This represents the target's velocity in the horizontal direction (x-axis direction) at the previous moment; Let this be the target's velocity in the vertical direction (y-axis direction) at the current moment. This represents the target's velocity in the vertical direction (y-axis direction) at the previous moment;

[0018] Let x be the target's acceleration in the horizontal direction (x-axis direction) at the current moment. This represents the target's acceleration in the horizontal direction (x-axis direction) at the previous moment; Let this be the target's acceleration in the vertical direction (y-axis direction) at the current moment. This represents the target's acceleration in the vertical direction (y-axis direction) at the previous moment.

[0019] Furthermore, the quality of fish fry is graded based on the constructed algorithm model. By setting different thresholds, the quality of fish fry is divided into different levels such as excellent, good, medium and poor.

[0020] Beneficial effects: Compared with the prior art, the advantages of the present invention are as follows:

[0021] By employing intelligent methods, a testing speed of 2 minutes per batch can be achieved, while reducing seedling damage by 85.6%. Furthermore, earlier intervention for diseases can be implemented based on the identification results, thereby improving the efficiency and accuracy of snakehead seedling quality assessment and reducing errors and damage caused by manual operation. This technology has significant application value and promising prospects for promotion. Attached Figure Description

[0022] Figure 1 This is a flowchart of the present invention. Detailed Implementation

[0023] The technical solution of the present invention will be described in detail below with reference to the accompanying drawings, but the scope of protection of the present invention is not limited to the embodiments described.

[0024] A method for judging the quality of snakehead fry is proposed. This method selects behavioral parameters such as average velocity, acceleration, and uniformity of movement trajectory as quality-related indicators to achieve accurate judgment of snakehead fry quality. The specific steps are as follows:

[0025] (1) Real-time data acquisition of fish fry movement data, including video stream or sensor data, is collected by using data acquisition modules such as DarkLabel. For video stream data acquisition, a high-definition camera with a resolution of 1920×1080 is installed above the breeding pond to capture the movement video of the fry in real time at a frame rate of 25 frames / second. The video is then input into DarkLabel software to automatically mark the fry and obtain the initial position coordinates of each fry. For sensor data acquisition, accelerometers and position sensors are arranged in the breeding pond. The accelerometers collect the acceleration data of the fry movement at a sampling frequency of 100Hz, and the position sensors collect the position coordinate data of the fry at a sampling frequency of 50Hz. The measurement range of the accelerometers is ±10g, and the positioning accuracy of the position sensors is ±1cm.

[0026] (2) Based on the collected data, calculate core indicators such as acceleration, average velocity, and uniformity of motion trajectory for individuals or groups. The uniformity of motion trajectory includes parameters such as velocity variance and spatial distribution dispersion. The calculation method is as follows:

[0027] The average velocity is calculated as follows: for an individual seedling, it is the ratio of its total displacement to its total time over a given period of time, i.e.:

[0028] ( )

[0029] Mode( )middle, This indicates the average speed of the seedlings over a period of time. , ) is the first The position coordinates at time t, where t is the time interval. ) is the first Position coordinates at that moment;

[0030] acceleration The calculation method is as follows: by performing differential processing on the velocity data, that is:

[0031] ( )

[0032] In the formula, For the first The speed of time, No. The velocity at any given moment, where Δt is the time interval;

[0033] velocity variance The calculation formula is

[0034] ( )

[0035] Spatial distribution dispersion This is measured by calculating the standard deviation of the seedling location coordinates, i.e.

[0036] ( )

[0037] In the formula, This represents the average value of the position coordinates.

[0038] (3) The evaluation model is constructed using the Deepocsort algorithm by analyzing real-time collected dynamic behavior data of fish fry. Backend software development is then completed using Python to achieve intelligent quality assessment of snakehead fry. Details are as follows:

[0039] The motion state adopts a Kalman filter model, and the state vector includes position. ,speed acceleration The state transition equation is:

[0040] ( )

[0041] In the formula: Let x be the current position coordinates of the target in the horizontal direction (x-axis direction). The position coordinates of the target in the horizontal direction (x-axis direction) at the previous moment; This represents the current position coordinates of the target in the vertical direction (y-axis direction). The position coordinates of the target in the vertical direction (y-axis direction) at the previous moment;

[0042] Let this be the target's velocity in the horizontal direction (x-axis direction) at the current moment. This represents the target's velocity in the horizontal direction (x-axis direction) at the previous moment; Let this be the target's velocity in the vertical direction (y-axis direction) at the current moment. This represents the target's velocity in the vertical direction (y-axis direction) at the previous moment;

[0043] Let x be the target's acceleration in the horizontal direction (x-axis direction) at the current moment. This represents the target's acceleration in the horizontal direction (x-axis direction) at the previous moment; Let this be the target's acceleration in the vertical direction (y-axis direction) at the current moment. This represents the target's acceleration in the vertical direction (y-axis direction) at the previous moment.

[0044] (4) The quality of fish fry is graded based on the constructed algorithm model. By setting different thresholds, the quality of fish fry is divided into different grades such as excellent, good, medium and poor, as shown in the table below:

[0045]

[0046] As described above, although the invention has been shown and described with reference to specific preferred embodiments, it should not be construed as limiting the invention itself. Various changes in form and detail may be made without departing from the spirit and scope of the invention as defined in the appended claims.

Claims

1. A method for judging the quality of snakehead seedlings, characterized in that, By selecting the average velocity, acceleration, and trajectory uniformity parameters of snakehead seedlings as indicators of seedling quality, accurate judgment of snakehead seedling quality can be achieved. The specific steps are as follows: (1) Real-time data acquisition of fish fry movement data, including video streams or sensor data, is performed by the data acquisition module; DarkLabel software is used in the data acquisition module to collect fry tagging data. For video stream data acquisition, a high-definition camera is installed above the breeding pond to capture real-time video of the seedlings' movement at a frame rate of 25 frames per second. The video is then input into DarkLabel software, which automatically marks the seedlings and obtains the initial position coordinates of each seedling. For sensor data acquisition, accelerometers and position sensors are deployed in the breeding pond. The accelerometers collect acceleration data of the seedlings' movement at a sampling frequency of 100Hz, and the position sensors collect position coordinate data of the seedlings at a sampling frequency of 50Hz. (2) Calculate the core indicators of acceleration, average velocity, and uniformity of motion trajectory for individuals or groups based on the collected data. The uniformity of motion trajectory includes velocity variance and spatial distribution dispersion parameters. (3) The evaluation model was constructed using the Deepocsort algorithm and the backend software was developed using Python to achieve intelligent judgment of the quality of snakehead seedlings; The evaluation model is constructed using the Deepocsort algorithm by analyzing real-time collected dynamic behavior data of fish fry. The motion state adopts a Kalman filter model, and the state vector includes position. ,speed acceleration The state transition equation is: In the formula: Let x be the current position coordinates of the target in the horizontal direction (x-axis direction). The position coordinates of the target in the horizontal direction (x-axis direction) at the previous moment; This represents the current position coordinates of the target in the vertical direction (y-axis direction). The position coordinates of the target in the vertical direction (y-axis direction) at the previous moment; Let this be the target's velocity in the horizontal direction (x-axis direction) at the current moment. This represents the target's velocity in the horizontal direction (x-axis direction) at the previous moment; Let this be the target's velocity in the vertical direction (y-axis direction) at the current moment. This represents the target's velocity in the vertical direction (y-axis direction) at the previous moment; Let x be the target's acceleration in the horizontal direction (x-axis direction) at the current moment. This represents the target's acceleration in the horizontal direction (x-axis direction) at the previous moment; Let this be the target's acceleration in the vertical direction (y-axis direction) at the current moment. This represents the target's acceleration in the vertical direction (y-axis direction) at the previous moment.

2. The method for judging the quality of snakehead seedlings according to claim 1, characterized in that, The quality of fish fry is graded based on the constructed algorithm model. By setting different thresholds, the quality of fish fry is divided into different levels: excellent, good, medium and poor.

Images