Fish school quantity prediction method and device, nonvolatile storage medium and electronic equipment

Abstract

The invention discloses a fish school quantity prediction method and device, a nonvolatile storage medium and electronic equipment. The method comprises the steps that a first number detection value and a second number detection value of fish schools in a target area are acquired, and the number of the first fish schools in the target area is determined according to the first number detection value and the second number detection value; determining a fishing experiment result of the target area, and determining a fishing influence model according to the fishing experiment result; after the fishing application information is received, the fishing application information and the first fish school number are processed through a fishing influence model, the second fish school number is obtained, and the second fish school number is a predicted value of the fish school number after the fishing behavior corresponding to the fishing application information occurs. The technical problem that prediction is inaccurate due to the fact that a traditional fish school prediction technology lacks consideration on influence of human activities is solved.

Description

Technical Field

[0001] The present application relates to the field of image recognition, and more specifically, to a method, device, non-volatile storage medium and electronic device for predicting the number of fish. Background Art

[0002] Fishing bans in key waters are an important national policy of my country. Currently, some local waters have many hidden dangers of illegal fishing, insufficient law enforcement and supervision capabilities, and a lack of scientific statistical methods for the recovery of aquatic biological populations. For the prediction of fish populations, the main approach in the market is often to estimate the trend of the number based on long-term observations and periodic statistical results, but lacks analysis of the impact of human activities on the number of fish.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present application provide a method, device, non-volatile storage medium and electronic device for predicting the number of fish schools, so as to at least solve the technical problem of inaccurate prediction caused by the lack of consideration of the impact of human activities in traditional fish school prediction technology.

[0005] According to one aspect of an embodiment of the present application, a method for predicting the number of fish schools is provided, including: obtaining a first number detection value and a second number detection value of fish schools in a target area, and determining a first number of fish schools in the target area based on the first number detection value and the second number detection value, wherein the first number detection value is a number detection value determined by an optical camera, and the second number detection value is a number detection value determined by a sonar device; determining a fishing experiment result in the target area, and determining a fishing influence model based on the fishing experiment result, wherein the fishing experiment result includes fishing positions selected in the target area, fishing durations corresponding to each fishing position, and a difference between a number of fish schools corresponding to a first moment and a number of fish schools corresponding to a second moment, the first moment being a moment before the fishing experiment, and the second moment being a moment after the fishing experiment, and the fishing influence model being used to predict the impact of fishing behavior on the number of fish schools in the target area; after receiving fishing application information, processing the fishing application information and the first number of fish schools through the fishing influence model to obtain a second number of fish schools, wherein the second number of fish schools is a predicted value of the number of fish schools after the fishing behavior corresponding to the fishing application information occurs.

[0006] Optionally, obtaining a first quantity detection value and a second quantity detection value of a school of fish in a target area, and determining the first quantity of the school of fish in the target area based on the first quantity detection value and the second quantity detection value, includes: regularly collecting optical images through an optical camera set in each sub-area of ​​the target area, and determining the first quantity detection value of the corresponding sub-area based on the optical image, regularly collecting acoustic images through a sonar device set in each sub-area of ​​the target area, and determining the second quantity detection value of the corresponding sub-area based on the acoustic image, wherein each sub-area is provided with an optical camera and a sonar device, and the first quantity detection value and the second quantity detection value corresponding to each sub-area are weighted averaged. Calculation; determining the weight of the first quantity detection value of each sub-region in the weighted average calculation based on the quality evaluation index of the optical image of each sub-region captured by the optical camera; determining the weight of the second quantity detection value of the corresponding region based on the weight of the first quantity detection value of each sub-region, performing weighted average calculation on the first quantity detection value and the second quantity detection value based on the weight, and determining the first number of fish in each sub-region, wherein the weight of the first quantity detection value and the second quantity detection value of each sub-region is added to one, and the quality of the optical image is used to reflect the brightness, contrast and clarity of the optical image; determining the first number of fish in the target area based on the first number of fish in each sub-region.

[0007] Optionally, the first fish group quantity is determined by the following formula: Where i represents the sequence number of each sub-region, W i represents the weight of the first quantity detection value, O i Represents the first quantity detection value, V i Indicates the second quantity detection value.

[0008] Optionally, determining the weight of the first quantity detection value in the weighted average calculation includes: collecting optical image samples in the target area through an optical camera, obtaining scoring results of the optical image samples, constructing a training set and a test set based on the optical image samples and the scoring results corresponding to the optical samples, and inputting an image scoring model for training, wherein the scoring results include a brightness score, a contrast score, and a clarity score of the remaining optical images; inputting the optical image into a trained input image scoring model, obtaining a score output by the input image scoring model, and using the score as the weight of the first quantity detection value in the weighted average calculation.

[0009] Optionally, determining the results of a fishing experiment in the target area, and determining a fishing impact model based on the fishing experiment results includes: randomly selecting multiple fishing locations in the target area, recording the fishing time corresponding to each fishing location and calculating the distance between each fishing location and each monitoring point, wherein the monitoring point is provided with an optical camera and a sonar device; obtaining the difference between the number of fish corresponding to a first moment and the number of fish corresponding to a second moment, wherein the number of fish corresponding to the first moment is obtained by weighted calculation based on a first quantity detection value at the first moment and a second quantity detection value at the first moment, and the number of fish corresponding to the second moment is obtained by weighted calculation based on the first quantity detection value at the second moment and the second quantity detection value at the second moment; constructing a linear regression fishing impact model based on the distance between the fishing location and each monitoring point, the fishing time, and the difference between the number of fish corresponding to the first moment and the second moment.

[0010] Optionally, the number of the second fish school is determined by the following formula: Y=X-wt / l, wherein Y is the number of the second fish school, X is the number of the first fish school, w is the influencing factor calculated by linear regression, t is the fishing time, and l is the distance between the fishing location and the monitoring point.

[0011] Optionally, the fishing application information includes the fishing location and the fishing duration. After receiving the fishing application information, the fishing application information and the first number of fish schools are processed by a fishing impact model to obtain the second number of fish schools, including: determining a distance set between the fishing location and each monitoring point; obtaining a second number of fish schools in each sub-area predicted by the fishing impact model based on the distance set, the first number of fish schools in each sub-area of ​​the target area, and the fishing time, wherein each sub-area is provided with a monitoring point, and each monitoring point is provided with an optical camera and a sonar device.

[0012] Optionally, after obtaining the second number of fish schools, the method also includes: comparing the second number of fish schools in each sub-area with a stored threshold value of the number of fish schools in the corresponding sub-area, and determining that the approval result of the fishing application is passed when the second number of fish schools in each sub-area is greater than the threshold value of the number of fish schools in the corresponding sub-area; and determining that the approval result of the fishing application is failed when the second number of fish schools in a sub-area is less than the threshold value of the number of fish schools in the corresponding sub-area.

[0013] According to another aspect of an embodiment of the present application, a fish population management device is also provided, including: a first determination module: obtaining a first quantity detection value and a second quantity detection value of fish in a target area, and determining the first fish population in the target area based on the first quantity detection value and the second quantity detection value, wherein the first quantity detection value is a quantity detection value determined by an optical camera, and the second quantity detection value is a quantity detection value determined by a sonar device; a second determination module: used to determine a fishing experiment result in the target area, and determine a fishing influence model based on the fishing experiment result, wherein the fishing experiment result includes a fishing position selected in the target area, a fishing time corresponding to each fishing position, and a difference between the number of fish corresponding to a first moment and the number of fish corresponding to a second moment, the first moment being a moment before the fishing experiment, and the second moment being a moment after the fishing experiment, and the fishing influence model being used to predict the impact of fishing behavior on the number of fish in the target area; a prediction module: used to, after receiving fishing application information, process the fishing application information and the first fish population through the fishing influence model to obtain the second fish population, wherein the second fish population is a predicted value of the fish population after the fishing behavior corresponding to the fishing application information occurs.

[0014] According to another aspect of an embodiment of the present application, a non-volatile storage medium is provided, in which a program is stored, wherein when the program is running, a device where the non-volatile storage medium is located is controlled to execute a method for predicting the number of fish.

[0015] According to another aspect of an embodiment of the present application, there is also provided an electronic device, including: a memory and a processor, the processor being configured to run a program stored in the memory, wherein the method for predicting the number of fish schools is executed when the program is run.

[0016] According to another aspect of an embodiment of the present application, a computer program product is also provided, including a computer program, which implements a method for predicting the number of fish schools when the computer program is executed by a processor.

[0017] In an embodiment of the present application, a first quantity detection value and a second quantity detection value of fish schools in a target area are obtained, and the first quantity of fish schools in the target area are determined based on the first quantity detection value and the second quantity detection value, wherein the first quantity detection value is a quantity detection value determined by an optical camera, and the second quantity detection value is a quantity detection value determined by a sonar device; a fishing experiment result in the target area is determined, and a fishing influence model is determined based on the fishing experiment result, wherein the fishing experiment result includes fishing positions selected in the target area, fishing time corresponding to each fishing position, and the difference between the number of fish schools corresponding to a first moment and the number of fish schools corresponding to a second moment, wherein the first moment is a moment before the fishing experiment, and the second moment is a moment after the fishing experiment. The fishing impact model is used to predict the impact of fishing behavior on the number of fish in the target area; after receiving the fishing application information, the fishing application information and the first number of fish are processed by the fishing impact model to obtain the second number of fish, wherein the second number of fish is the predicted value of the number of fish after the fishing behavior corresponding to the fishing application information occurs. The first number detection value and the second number detection value are weighted calculated according to the quality of the optical image, and a fishing impact model is constructed to evaluate the impact of fishing on the number of fish, thereby achieving the purpose of improving detection accuracy, thereby achieving the technical effect of predicting the number of fish considering human activities, and then solving the technical problem of inaccurate prediction caused by the lack of consideration of the impact of human activities in traditional fish prediction technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0019] Figure 1 It is a structural schematic diagram of a computer terminal (mobile device) provided according to an embodiment of the present application;

[0020] Figure 2 It is a flowchart of a schematic diagram of the interaction between various modules of a method for predicting the number of fish schools according to an embodiment of the present application;

[0021] Figure 3 is a flow chart of a method for predicting the number of fish swarms according to an embodiment of the present application;

[0022] Figure 4 It is a structural schematic diagram of a fish population prediction device provided according to an embodiment of the present application; DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings 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 should fall within the scope of protection of the present application.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] In order to better understand the embodiments of the present application, the technical terms involved in the embodiments of the present application are explained as follows:

[0026] CNN (Convolutional Neural Network): A deep learning model specifically designed for processing image and video data. It simulates the working principle of the human visual system, extracts features from images through multi-layer convolution and pooling operations, and uses these features for classification and recognition tasks.

[0027] Linear Regression: A statistical method used to establish a linear relationship between variables. In linear regression, by modeling the linear relationship between the independent variable (input variable) and the dependent variable (output variable), the value of the dependent variable can be predicted or estimated. Linear regression is usually divided into two forms: simple linear regression (only one independent variable) and multiple linear regression (multiple independent variables). By fitting a linear regression model, applications such as prediction, association analysis, and analysis of the degree of influence between variables can be performed. The evaluation indicators of linear regression include the significance of the regression coefficient, the goodness of fit of the model (such as R-square value), residual analysis, etc. These indicators can be used to evaluate the accuracy and reliability of the model.

[0028] Random Forest: An ensemble learning method that performs classification and regression by building multiple decision trees and combining their results. Its features include randomly selecting features and data samples for training to reduce the correlation between features and the risk of overfitting, and to improve the diversity and generalization of the model. During the prediction process, random forests combine the results of multiple decision trees by voting or averaging. Random forests have the advantages of high accuracy, strong generalization ability, and robustness to high-dimensional data and noisy data. At the same time, they can evaluate feature importance and help feature selection and analysis.

[0029] VGG16 Net: A deep convolutional neural network model developed by the Visual Geometry Group at the University of Oxford. It improves the performance of the model by increasing the network depth, while keeping the network structure simple, and improving the accuracy and generalization ability of the model. VGG16 has achieved excellent image classification performance on the ImageNet dataset and is widely used in computer vision tasks such as image classification and object detection.

[0030] In the related art, the detection equipment of underwater target monitoring technology is single. At the same time, for the prediction of fish population, the main approach on the market is often based on long-term observation and forming periodic statistical results to estimate the trend of the number, lacking analysis of the impact of human activities on the number of fish. Therefore, there is a problem of inaccurate prediction due to the lack of consideration of the impact of human activities in traditional fish prediction technology. In order to solve this problem, a relevant solution is provided in the embodiment of the present application, which is described in detail below.

[0031] According to an embodiment of the present application, a method embodiment of a method for predicting the number of fish schools is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0032] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG. 1 shows a hardware structure block diagram of a computer terminal (or mobile device) for implementing a method for predicting the number of fish. Figure 1As shown, the computer terminal 10 (or mobile device 10) may include one or more (102a, 102b, ..., 102n are used to illustrate) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0033] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0034] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the fish population prediction method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, realizing the above-mentioned fish population prediction method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0035] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0036] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0037] The embodiment of the present application includes an Internet of Things monitoring module 21, a quantity storage module 22, a quantity expectation configuration module 23, an AI analysis module 24, a user interaction module 25, and a fishing activity storage module 26. Figure 2 A schematic diagram of the interaction between various modules is shown, such as Figure 2 As shown, the Internet of Things monitoring module 21 transmits the acquired fish school data to the quantity storage module 22, the AI ​​analysis module 24 regularly retrieves the fish school data stored in the quantity storage module 22, and trains the model through the fish school data. The AI ​​analysis module 24 also retrieves the fishing activity data stored in the fishing activity storage module 26 for training, and the user interacts with the system through the user interaction module 25, including obtaining the fish school data from the quantity storage module 22 for display, obtaining the fishing activity data stored in the fishing activity storage module 26 for display, and obtaining the configuration data from the quantity expectation configuration model module 23, and configuring the fish school quantity threshold (i.e., the expected configuration). The expected configuration is received by the quantity expectation configuration model module 23. When the fishing application is obtained, the quantity expectation configuration module 23 transmits the set fish school quantity threshold to the AI ​​analysis module 24, and the AI ​​analysis module 24 outputs the approval result and passes it to the user interaction module 25 for display.

[0038] Specifically, the Internet of Things monitoring module 21 is mainly composed of underwater sonar equipment, underwater optical cameras, wireless data transmission devices, etc., which are used to collect data related to the number of underwater fish schools and send them to the data storage module for processing through the data transmission device; the number storage module 22 mainly involves data storage and management. The data is stored in the local database and the cloud server. The data such as the number of fish schools, fishing activities, and quantity configuration can be read, written, and managed. The expected number configuration module 23 is used to set and manage the parameters of the number of fish schools in the water area, the rules of fishing activities, and the expected number of fish schools. Users can configure and define the expected number of fish schools through this module, and adjust and optimize the system through this module. The AI ​​analysis module 24 refers to a module that processes, analyzes, and predicts data based on artificial intelligence technologies such as CNN. It is used to obtain information on the number of fish schools from the system storage data and perform tasks such as prediction and analysis. In this invention, the results of the optical camera and the acoustic camera can be evaluated, and the number weight of the optical camera can be increased under good optical conditions, thereby achieving an accurate estimate of the number of fish schools. The user interaction module 25 includes an operation interface for interaction, operation and feedback with the system, and provides corresponding users with functions such as fish population configuration, AI intelligent analysis, fishing activity application, fishing activity management, and historical data viewing through the management end and the user end. The fishing activity storage module 26 is mainly used to store data related to fishing activities, such as fishing locations, fishing times, fish caught and quantity, etc. These data can be used to record the impact of fishing activities on the number of fish, thereby providing data support for the supervision of fishing activities.

[0039] Under the above operating environment, the embodiment of the present application provides a method for predicting the number of fish swarms, such as Figure 3 As shown, the method comprises the following steps:

[0040] Step S302, obtaining a first number detection value and a second number detection value of the school of fish in the target area, and determining the number of the first school of fish in the target area according to the first number detection value and the second number detection value, wherein the first number detection value is a number detection value determined by an optical camera, and the second number detection value is a number detection value determined by a sonar device;

[0041] In some embodiments of the present application, an Internet of Things monitoring module is built underwater (target area), the number of the first fish school in the water area is counted through the AI ​​analysis module, and the fish school data (number, longitude and latitude of the water area, depth of the water area) is stored in a quantity storage module.

[0042] Specifically, since the optical camera is greatly affected by the lighting conditions, the first number detection value and the second number detection value are weighted averaged to count the number of the first school of fish. The number of the first school of fish in the water area is:

[0043]

[0044] The water area needs to be divided into multiple unit water areas (i.e., sub-areas) manually in advance, i represents the unit water area number, and in the present invention, one optical camera and one acoustic camera are placed in each unit water area. i Indicates the number of optical devices in the current water area, O i represents the total number of fish activities per day in the unit water area of ​​the current optical device (i.e., the first quantity detection value of the sub-area), V i represents the total number of fish activities per day in the unit water area of ​​the current acoustic device (i.e., the second quantity detection value of the sub-area). Further, W i It is mainly calculated by the brightness, contrast and clarity of the image. Here, the underwater image quality evaluation method based on deep regression forest is used as a reference. About 500 images are collected in the area. To ensure robustness, these images are taken by cameras in different waters at different times and scored manually by 20 scorers. The scores range from 0.1 to 1 and are divided into 10 levels with a step size of 0.1. The higher the score, the more consistent the image is with human visual perception and the better the visual quality. For each image, the highest and lowest scores are removed, and the average score given by the remaining 18 observers is recorded as the valid score; Next, the 4096-dimensional features of the image extracted by VGG16 Net and the corresponding quality scores that conform to human visual perception are sent to the random forest model for training. After the model training is completed, all images are sent to the VGG16 Net deep neural network to extract features, and the final score W is output through the random forest. i .

[0045] Step S304 determines the fishing experiment results in the target area, and determines the fishing impact model based on the fishing experiment results, wherein the fishing experiment results include the fishing positions selected in the target area, the fishing time corresponding to each fishing position, and the difference between the number of fish corresponding to the first moment and the number of fish corresponding to the second moment, the first moment is the moment before the fishing experiment, and the second moment is the moment after the fishing experiment, and the fishing impact model is used to predict the impact of fishing behavior on the number of fish in the target area;

[0046] In some embodiments of the present application, impact data is obtained by conducting fishing experiments, and the impact on the number of fish (the number of fish at each monitoring point, the longitude and latitude of the fishing point) is stored in a quantity storage module, and a fishing impact model is constructed through an AI analysis module, and the model is stored in the AI ​​analysis module.

[0047] Specifically, the spatial distance l for fishing, the fishing time t, and the number of fish before fishing Q are calculated through the fishing point and the monitoring points of all unit waters (i.e., the locations where the optical and acoustic equipment are placed). before And the number of fish after fishing Qafter Through multiple experiments, multiple sets of sampling data can be obtained to obtain the impact of fishing activities on the number of fish at different spatial distances. Linear regression is used to build a fishing activity prediction model, where Q before As training parameters X, Q after As the prediction parameter Y, due to the small data set, cross-validation was adopted to obtain the fish population prediction model Y = X-wt / l, where w represents the influencing factor of fishing activity quantity calculated by linear regression, t represents the fishing time, and l represents the spatial distance between the fishing location and the monitoring point of the unit water area;

[0048] Step S306, after receiving the fishing application information, the fishing application information and the first fish school number are processed by the fishing influence model to obtain the second fish school number, wherein the second fish school number is the predicted value of the fish school number after the fishing behavior corresponding to the fishing application information occurs.

[0049] In some embodiments of the present application, a fishing influence model and a quantity storage module are used to determine whether fishing can be conducted, and if so, the fishing activity is stored in the fishing activity storage module.

[0050] Specifically, the user applies for fishing through the interactive module and provides information (fishing location, duration), where the fishing location includes longitude and latitude information, and the manager sets the expected number Q for all the fish points under supervision. expect By calculating the longitude and latitude, we can get the distance set L = {l1,...,ln} of all points. Through the fish population prediction model, we can get the expected result set Q = {q1,...,qn} of the fish population. We can compare the fish population in set Q with Q in turn. expect , if both are greater than Q expect , then the fishing activity will be automatically approved; if it is less than , then the fishing activity will be automatically rejected.

[0051] In other embodiments of the present application, seasonal configuration can also be performed. The system calculates the appropriate expected number of fish as a reference based on the periodic changes in the seasonal number of fish, achieves scientific control of the total number of fish in the water area, and divides the seasonal time for fishing bans, such as increasing the expected number during the breeding season, to achieve more accurate population control.

[0052] Through the above steps, through the Internet of Things devices and AI technologies such as CNN, it is possible to realize the intelligent statistics of the number of fish in the waters and the prediction of the number of fish. The combination of image and acoustic detection methods improves the accuracy of statistics. Furthermore, it is possible to score by indicators such as image brightness, thereby changing the scoring of image and acoustic detection results, and perform weighted statistics according to the scoring results to obtain more accurate fish population statistics. At the same time, through fishing activities, a fishing impact model is constructed, which systematically evaluates the impact of fishing activities on fish in surrounding waters, provides a more accurate number counting method, and a more accurate prediction of the number of fish in waters. At the same time, it can carry out digital management of fishing for local water conservancy departments, support the ban on fishing in waters through scientific means, and reduce the cost of manual review.

[0053] Specifically, this application has the following advantages: it improves the accuracy of statistics under different water conditions, thereby providing scientific guidance for the management of fishing in the waters, and can also manage fishing activities in the waters online through population prediction:

[0054] (1) More accurate population statistics: Based on underwater cameras and underwater sonar IoT devices, the number of fish is sampled and analyzed. By evaluating the image quality and weighted statistics, a fish population model and a water area model are constructed, that is, the total number of daily fish activities in different areas of the water area and the total number of fish in the water area are obtained;

[0055] (2) More accurate prediction of fish population: By fishing in different areas, since the fishing spots are relatively fixed, a spatial impact model of fishing can be obtained, that is, the impact of anglers on the total number of daily fish activities in different water areas; the average number of fish per unit time in different areas is calculated to obtain the impact factor of fishing;

[0056] (3) Reduce the time cost of manual review of fishing activities: Calculate the permitted fishing areas and number of people based on the natural growth of fish in the waters and the minimum number of fish required, replacing the traditional manual review method;

[0057] (4) Realize online fishing activity control: Through the fishing management system, anglers can apply for fishing and carry out fishing activities after approval, reducing the time cost of offline registration;

[0058] The present application embodiment provides a fish population management device, Figure 4 is a schematic diagram of the structure of the device, such as Figure 4As shown, the device includes: a first determination module 40: obtaining a first quantity detection value and a second quantity detection value of fish schools in a target area, and determining the first quantity of fish schools in the target area based on the first quantity detection value and the second quantity detection value, wherein the first quantity detection value is a quantity detection value determined by an optical camera, and the second quantity detection value is a quantity detection value determined by a sonar device; a second determination module 42: used to determine the fishing experiment results in the target area, and determine a fishing influence model based on the fishing experiment results, wherein the fishing experiment results include fishing positions selected in the target area, fishing durations corresponding to each fishing position, and a difference between the number of fish schools corresponding to a first moment and the number of fish schools corresponding to a second moment, wherein the first moment is a moment before the fishing experiment, and the second moment is a moment after the fishing experiment, and the fishing influence model is used to predict the impact of fishing behavior on the number of fish schools in the target area; a prediction module 44: used to process the fishing application information and the first number of fish schools through the fishing influence model after receiving the fishing application information, and obtain the second number of fish schools, wherein the second number of fish schools is a predicted value of the number of fish schools after the fishing behavior corresponding to the fishing application information occurs.

[0059] In some embodiments of the present application, the first determination module 40 obtains a first quantity detection value and a second quantity detection value of a school of fish in a target area, and determines the first quantity of the school of fish in the target area based on the first quantity detection value and the second quantity detection value, including: collecting optical images by an optical camera arranged in each sub-area of ​​the target area at regular intervals, and determining the first quantity detection value of the corresponding sub-area based on the optical image, collecting acoustic images by a sonar device arranged in each sub-area of ​​the target area at regular intervals, and determining the second quantity detection value of the corresponding sub-area based on the acoustic image, wherein each sub-area is provided with an optical camera and a sonar device, and the first quantity detection value and the second quantity detection value corresponding to each sub-area are respectively The measured values ​​are weighted averaged; based on the quality evaluation index of the optical image of each sub-area captured by the optical camera, the weight of the first quantity detection value of each sub-area in the weighted average calculation is determined; based on the weight of the first quantity detection value of each sub-area, the weight of the second quantity detection value of the corresponding area is determined, and the first quantity detection value and the second quantity detection value are weighted averaged according to the weight to determine the first number of fish in each sub-area, wherein the weight of the first quantity detection value and the second quantity detection value of each sub-area is added to one, and the quality of the optical image is used to reflect the brightness, contrast and clarity of the optical image; based on the first number of fish in each sub-area, the first number of fish in the target area is determined.

[0060] In some embodiments of the present application, the number of the first school of fish is determined by the following formula: Where i represents the sequence number of each sub-region, W irepresents the weight of the first quantity detection value, O i Represents the first quantity detection value, V i Indicates the second quantity detection value.

[0061] In some embodiments of the present application, the first determination module 40 determines the weight of the first quantity detection value in the weighted average calculation, including: collecting optical image samples in the target area through an optical camera, obtaining scoring results of the optical image samples, constructing a training set and a test set based on the optical image samples and the scoring results corresponding to the optical samples, and inputting an image scoring model for training, wherein the scoring results include a brightness score, a contrast score, and a clarity score of the remaining optical images; inputting the optical image into the trained input image scoring model, obtaining the score output by the input image scoring model, and using the score as the weight of the first quantity detection value in the weighted average calculation.

[0062] In some embodiments of the present application, the second determination module 42 determines the results of a fishing experiment in a target area, and determines a fishing impact model based on the fishing experiment results, including: randomly selecting multiple fishing locations in the target area, recording the fishing time corresponding to each fishing location and calculating the distance between each fishing location and each monitoring point, wherein the monitoring point is provided with an optical camera and a sonar device; obtaining the difference between the number of fish corresponding to a first moment and the number of fish corresponding to a second moment, wherein the number of fish corresponding to the first moment is obtained by weighted calculation based on a first quantity detection value at the first moment and a second quantity detection value at the first moment, and the number of fish corresponding to the second moment is obtained by weighted calculation based on the first quantity detection value at the second moment and the second quantity detection value at the second moment; constructing a linear regression fishing impact model based on the distance between the fishing location and each monitoring point, the fishing time, and the difference between the number of fish corresponding to the first moment and the number of fish corresponding to the second moment.

[0063] In some embodiments of the present application, the number of the second fish school is determined by the following formula: Y=4-wt / l, wherein Y is the number of the second fish school, 4 is the number of the first fish school, w is the influencing factor obtained by linear regression calculation, t is the fishing time, and l is the distance between the fishing location and the monitoring point.

[0064] In some embodiments of the present application, the fishing application information includes the fishing location and the fishing duration. After receiving the fishing application information, the prediction module 44 processes the fishing application information and the first number of fish schools through a fishing impact model to obtain the second number of fish schools, including: determining a distance set between the fishing location and each monitoring point; obtaining a second number of fish schools in each sub-area predicted by the fishing impact model based on the distance set, the first number of fish schools in each sub-area of ​​the target area, and the fishing time, wherein each sub-area is provided with a monitoring point, and each monitoring point is provided with an optical camera and a sonar device.

[0065] In some embodiments of the present application, after obtaining the second number of fish schools, the method further includes: comparing the second number of fish schools in each sub-area with a stored threshold value of the number of fish schools in the corresponding sub-area, and determining that the approval result of the fishing application is passed when the second number of fish schools in each sub-area is greater than the threshold value of the number of fish schools in the corresponding sub-area; and determining that the approval result of the fishing application is failed when the second number of fish schools in a sub-area is less than the threshold value of the number of fish schools in the corresponding sub-area.

[0066] It should be noted that the various modules in the above-mentioned fish population management device can be program modules (for example, a set of program instructions that implement a certain specific function) or hardware modules. For the latter, it can be expressed in the following forms, but is not limited to this: the expression form of each of the above-mentioned modules is a processor, or the functions of each of the above-mentioned modules are implemented by a processor.

[0067] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0068] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0069] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0070] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0071] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0072] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the relevant technology or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc. Various media that can store program codes.

[0073] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for predicting the number of fish, characterized in that: include: Acquire a first quantity detection value and a second quantity detection value of a school of fish in a target area, and determine the first quantity of the school of fish in the target area according to the first quantity detection value and the second quantity detection value, wherein the first quantity detection value is a quantity detection value determined by an optical camera, and the second quantity detection value is a quantity detection value determined by a sonar device; Determine the fishing experiment results in the target area, and determine the fishing impact model based on the fishing experiment results, wherein the fishing experiment results include the fishing locations selected in the target area, the fishing time corresponding to each fishing location, and the difference between the number of fish corresponding to a first moment and the number of fish corresponding to a second moment, the first moment being the moment before the fishing experiment, and the second moment being the moment after the fishing experiment, and the fishing impact model is used to predict the impact of fishing behavior on the number of fish in the target area; After receiving the fishing application information, the fishing application information and the first number of fish schools are processed by the fishing impact model to obtain a second number of fish schools, wherein the second number of fish schools is a predicted value of the number of fish schools after the fishing behavior corresponding to the fishing application information occurs.

2. The method for predicting the number of fish swarms according to claim 1, characterized in that: Acquiring a first quantity detection value and a second quantity detection value of a school of fish in a target area, and determining a first quantity of the school of fish in the target area according to the first quantity detection value and the second quantity detection value, comprising: The optical images are collected periodically by an optical camera arranged in each sub-area of ​​the target area, and the first quantity detection value of the corresponding sub-area is determined according to the optical image; the acoustic images are collected periodically by a sonar device arranged in each sub-area of ​​the target area, and the second quantity detection value of the corresponding sub-area is determined according to the acoustic image, wherein each sub-area is provided with one optical camera and one sonar device, and the first quantity detection value and the second quantity detection value corresponding to each sub-area are weighted averaged; Determining the weight of the first quantity detection value of each of the sub-areas in the weighted average calculation according to the quality evaluation index of the optical image of each of the sub-areas captured by the optical camera; According to the weight of the first quantity detection value of each of the sub-areas, the weight of the second quantity detection value of the corresponding area is determined, and the first quantity detection value and the second quantity detection value are weighted averaged according to the weight to determine the first number of fish in each of the sub-areas, wherein the weight of the first quantity detection value and the second quantity detection value of each sub-area is added to one, and the quality of the optical image is used to reflect the brightness, contrast and clarity of the optical image; The first number of fish schools in the target area is determined according to the first number of fish schools in each of the sub-areas.

3. The method for predicting the number of fish swarms according to claim 2, characterized in that: The first fish group quantity is determined by the following formula: Where i represents the sequence number of each sub-region, W i represents the weight of the first quantity detection value, O i Represents the first quantity detection value, V i Indicates the second quantity detection value.

4. The method for predicting the number of fish swarms according to claim 2, characterized in that: Determining the weight of the first number of detection values ​​in the weighted average calculation includes: Collecting optical image samples in the target area by the optical camera, obtaining scoring results of the optical image samples, constructing a training set and a test set according to the optical image samples and the scoring results corresponding to the optical samples, and inputting the image scoring model for training, wherein the scoring results include brightness scores, contrast scores, and clarity scores of the remaining optical images; The optical image is input into a trained input image scoring model, a score output by the input image scoring model is obtained, and the score is used as a weight in a weighted average calculation of the first quantity detection value.

5. The method for predicting the number of fish swarms according to claim 1, characterized in that: Determining the fishing experiment results of the target area, and determining the fishing impact model according to the fishing experiment results includes: Randomly selecting a plurality of fishing locations in the target area, recording the fishing time corresponding to each of the fishing locations and calculating the distance between each of the fishing locations and each monitoring point, wherein the optical camera and the sonar device are placed at the monitoring point; Obtaining a difference between the number of fish schools corresponding to the first moment and the number of fish schools corresponding to the second moment, wherein the number of fish schools corresponding to the first moment is obtained by weighted calculation based on a first number detection value at the first moment and a second number detection value at the first moment, and the number of fish schools corresponding to the second moment is obtained by weighted calculation based on the first number detection value at the second moment and the second number detection value at the second moment; A linear regression fishing impact model is constructed based on the distance between the fishing location and each of the monitoring points, the duration of the fishing, and the difference between the number of fish corresponding to the first moment and the number of fish corresponding to the second moment.

6. The method for predicting the number of fish swarms according to claim 5, characterized in that: The second fish group quantity is determined by the following formula: Y=X-wt / l Among them, Y is the number of the second fish school, X is the number of the first fish school, w is the influencing factor obtained by linear regression calculation, t is the fishing time, and l is the distance between the fishing position and the monitoring point.

7. The method for predicting the number of fish swarms according to claim 1, characterized in that: The fishing application information includes a fishing location and a fishing duration. After receiving the fishing application information, the fishing application information and the first number of fish schools are processed by the fishing influence model to obtain the second number of fish schools, including: Determine a distance set between the fishing location and each monitoring point; The fishing impact model is obtained based on the distance set, the first fish number set of each sub-area of ​​the target area and the second fish number set of each sub-area predicted by the fishing time, wherein each sub-area is provided with a monitoring point, and each monitoring point is provided with an optical camera and a sonar device.

8. The method for predicting the number of fish swarms according to claim 7, characterized in that: After obtaining the second number of fish schools, the method further includes: The second number of fish schools in each sub-area is compared with the stored fish school number threshold of the corresponding sub-area. When the second number of fish schools in each sub-area is greater than the fish school number threshold of the corresponding sub-area, the approval result of the fishing application is determined to be passed; when the second number of fish schools in a sub-area is less than the fish school number threshold of the corresponding sub-area, the approval result of the fishing application is determined to be failed.

9. A fish population management device, characterized in that: include: A first determination module: obtaining a first quantity detection value and a second quantity detection value of a school of fish in a target area, and determining the first quantity of the school of fish in the target area according to the first quantity detection value and the second quantity detection value, wherein the first quantity detection value is a quantity detection value determined by an optical camera, and the second quantity detection value is a quantity detection value determined by a sonar device; The second determination module is used to determine the fishing experiment results in the target area, and determine the fishing impact model based on the fishing experiment results, wherein the fishing experiment results include the fishing locations selected in the target area, the fishing time corresponding to each fishing location, and the difference between the number of fish corresponding to a first moment and the number of fish corresponding to a second moment, the first moment being the moment before the fishing experiment, and the second moment being the moment after the fishing experiment, and the fishing impact model is used to predict the impact of fishing behavior on the number of fish in the target area; Prediction module: used for, after receiving the fishing application information, processing the fishing application information and the first number of fish schools through the fishing influence model to obtain the second number of fish schools, wherein the second number of fish schools is the predicted value of the number of fish schools after the fishing behavior corresponding to the fishing application information occurs.

10. A non-volatile storage medium, characterized in that: The non-volatile storage medium stores a program, wherein when the program is executed, the device where the non-volatile storage medium is located is controlled to execute the fish population prediction method according to any one of claims 1 to 8.

11. An electronic device, characterized in that: include: A memory and a processor, wherein the processor is used to run a program stored in the memory, wherein the program, when running, executes the fish population prediction method described in any one of claims 1 to 8.

12. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for predicting the number of fish swarms described in any one of claims 1 to 8 is implemented.

Images