Fishing net detection method, device and equipment based on sonar information and medium

Abstract

The invention relates to a fishing net detection method and device based on sonar information, equipment and a storage medium. The method comprises the following steps: controlling an underwater robot to periodically emit sonar detection signals, and receiving sonar echo signals from a fishing net; processing the received sonar echo signal, and extracting acoustic characteristics reflecting the fishing net structure state; comparing the acoustic features with a preset acoustic feature model of a complete fishing net, and determining a comparison result; determining a fishing net structure state corresponding to the current detection position based on the comparison result; generating and storing a digital model of the fishing net; wherein each grid unit of the digital model corresponds to a fishing net hole at a detection position and is associated with a fishing net structure state at the detection position.

Description

Technical Field

[0001] This application relates to the field of fishing net detection technology, and in particular to a fishing net detection method, apparatus, equipment and storage medium based on sonar information. Background Technology

[0002] In the fields of aquaculture and marine fishing, fishing nets are a core production tool, and their structural integrity directly affects operational safety and economic benefits. Traditional fishing net inspection mainly relies on underwater visual inspection by divers. This method is inefficient, costly, and limited by water depth and visibility, posing high safety risks and making it difficult to achieve comprehensive and accurate inspection.

[0003] How to achieve automatic and accurate detection of underwater fishing nets is a problem that urgently needs to be solved. Summary of the Invention

[0004] In view of the above, this application provides a method, apparatus, device and storage medium for detecting fishing nets based on sonar information, the purpose of which is to solve the above-mentioned technical problems.

[0005] In a first aspect, this application provides a method for detecting fishing nets based on sonar information, the method comprising:

[0006] Control the underwater robot to periodically emit sonar detection signals and receive sonar echo signals from the fishing net;

[0007] The received sonar echo signal is processed to extract acoustic features that reflect the structural state of the fishing net;

[0008] The acoustic features are compared with a preset acoustic feature model of a complete fishing net to determine the comparison result;

[0009] Based on the comparison results, the fishing net structure status corresponding to the current detection location is determined; wherein, the fishing net structure status includes normal status and abnormal status;

[0010] A digital model of the fishing net is generated and stored; wherein each grid cell of the digital model corresponds to a mesh size of the fishing net at a detection location and is associated with the structural state of the fishing net at the detection location.

[0011] In some embodiments, processing the received sonar echo signal to extract acoustic features reflecting the structural state of the fishing net includes:

[0012] Time-frequency analysis was performed on the sonar echo signal to obtain a time-spectrum diagram;

[0013] Feature parameters are extracted from the time-spectrum graph; the feature parameters include one or more of the following: echo signal strength, echo width, spectral center frequency offset, and spectral entropy value.

[0014] The feature parameters are converted into acoustic features that characterize the state of the fishing net structure at the current detection location.

[0015] In some embodiments, comparing the acoustic features with a preset acoustic feature model of a complete fishing net and determining the comparison result includes:

[0016] Based on the current detection position, extract the local model at the corresponding position from the acoustic feature model;

[0017] Based on the local model, feature extraction is performed to obtain the template acoustic features;

[0018] The acoustic features are compared with the acoustic features of the template to obtain the comparison result.

[0019] In some embodiments, the feature extraction based on the local model to obtain template acoustic features includes:

[0020] Obtain the underwater environment at the current detection location;

[0021] Based on the underwater environment and the local model, a simulation environment is established;

[0022] Simulated sonar detection is performed on the local model within the simulation environment to obtain simulated sonar echo signals;

[0023] Feature extraction is performed on the simulated sonar echo signal to obtain the acoustic features of the template.

[0024] In some embodiments, comparing the acoustic features with the template acoustic features to obtain the comparison result includes:

[0025] Calculate the similarity between the acoustic features and the template acoustic features;

[0026] The comparison result is determined based on the similarity.

[0027] In some embodiments, comparing the acoustic features with the template acoustic features to obtain the comparison result includes:

[0028] The acoustic features and the template acoustic features are input into the comparison model;

[0029] The comparison result is determined based on the output of the comparison model; wherein the comparison model is a machine learning model.

[0030] In some embodiments, generating and storing the digital model of the fishing net includes:

[0031] Obtain historical detection results of the fishing net; wherein, the historical detection results include the historical structural state of the fishing net in the historical detection;

[0032] Based on the historical fishing net structure state and the fishing net structure state, a fishing net structure change trajectory is generated;

[0033] The trajectory of structural changes in the fishing net is dynamically demonstrated in the digital model of the fishing net.

[0034] Secondly, this application provides a sonar-based fishing net detection device, which includes:

[0035] The control module is used to control the underwater robot to periodically emit sonar detection signals and receive sonar echo signals from the fishing net;

[0036] The processing module is used to process the received sonar echo signal and extract acoustic features that reflect the structural state of the fishing net.

[0037] The comparison module is used to compare the acoustic features with a preset acoustic feature model of a complete fishing net and determine the comparison result;

[0038] The determination module is used to determine the fishing net structure state corresponding to the current detection location based on the comparison results; wherein, the fishing net structure state includes a normal state and an abnormal state;

[0039] A generation module is used to generate and store a digital model of the fishing net; wherein each grid cell of the digital model corresponds to a mesh size of the fishing net at a detection location and is associated with the structural state of the fishing net at the detection location.

[0040] Thirdly, this application provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0041] Memory, used to store computer programs;

[0042] When a processor executes a program stored in memory, it implements the steps of the sonar-information-based fishing net detection method described in any embodiment of the first aspect.

[0043] Fourthly, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the fishing net detection method based on sonar information as described in any embodiment of the first aspect.

[0044] The technical solutions provided in this application have the following advantages compared with the prior art:

[0045] Using an underwater robot to inspect fishing nets via sonar, the system processes the received sonar echo signals and extracts acoustic features reflecting the net's structural condition. These acoustic features are then compared to a pre-defined acoustic feature model of the complete fishing net, enabling precise identification of subtle anomalies such as mesh tears and rope wear. This significantly improves the accuracy and reliability of the inspection, eliminating the need for manual underwater intervention, saving labor costs and reducing personnel safety risks. Furthermore, by generating and storing a digital model of the fishing net associated with the detection location and its structural condition, the abstract acoustic data is transformed into an intuitive 3D visualization model, allowing users to directly observe the inspected net's condition. Attached Figure Description

[0046] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0047] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 This is a flowchart illustrating a preferred embodiment of the fishing net detection method based on sonar information according to this application;

[0049] Figure 2 This is a schematic diagram of a preferred embodiment of the fishing net detection device based on sonar information of this application;

[0050] Figure 3 This is a schematic diagram of a preferred embodiment of the electronic device of this application;

[0051] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments in this application without inventive effort are within the scope of protection of this application.

[0053] It should be noted that the use of terms such as "first" and "second" in this application is for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of those features. Furthermore, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, such a combination of technical solutions should be considered non-existent and not within the scope of protection claimed in this application.

[0054] Reference Figure 1 The diagram shown is a flowchart illustrating an embodiment of the sonar-based fishing net detection method of this application. The method is executed by an electronic device, which can be implemented by a software system and / or a hardware system. The sonar-based fishing net detection method includes:

[0055] Step 101: Control the underwater robot to periodically emit sonar detection signals and receive sonar echo signals from the fishing net.

[0056] An underwater robot is a machine or device that can operate autonomously or remotely in an underwater environment. Underwater robots can be equipped with sonar, thrusters, and control systems to perform underwater detection, inspection, or maintenance tasks.

[0057] Fishing nets can be made of mesh materials (such as nylon or polyethylene) and are commonly used for fishing or aquaculture. Examples include rectangular trawls or net cages used in marine aquaculture farms.

[0058] Sonar detection signals are sound wave signals emitted by sonar equipment for underwater detection. They obtain information about objects by the propagation and reflection of sound waves in the medium.

[0059] Sonar echo signals are sound wave signals reflected back after a sonar detection signal encounters an underwater object (such as a fishing net). They can carry information such as the object's distance, shape, and material.

[0060] Step 102: Process the received sonar echo signal to extract acoustic features that reflect the structural state of the fishing net.

[0061] The structural condition of a fishing net refers to its physical state, including its integrity, deformation, damage, or blockage. For example, whether the net's mesh maintains a regular shape, whether the ropes are broken, or whether there are foreign objects attached to it.

[0062] Acoustic features are quantization parameters extracted from the processed sonar echo signal. These quantization parameters are related to the structural characteristics of the fishing net and can be used to infer the state of the fishing net.

[0063] In some embodiments, processing the received sonar echo signal to extract acoustic features reflecting the structural state of the fishing net may include the following operations:

[0064] S11, perform time-frequency analysis on the sonar echo signal to obtain a time-frequency spectrum.

[0065] Time-frequency analysis is a signal processing method used to analyze how the frequency components of a signal change over time, thereby revealing both the time and frequency domain characteristics of the signal. Examples include short-time Fourier transform, wavelet transform, or Wigner-Weil distribution.

[0066] A time-frequency spectrum is a visual representation of the results of time-frequency analysis. It can be a two-dimensional image, where the color or brightness of the pixels represents the intensity or energy of that frequency component at that moment.

[0067] S12, extract feature parameters from the time-spectrum graph.

[0068] Characteristic parameters are quantization metrics calculated from the time-frequency spectrogram. These parameters include one or more of the following: echo signal strength, echo width, spectral center frequency offset, and spectral entropy. Echo signal strength is a measure of the overall signal energy within the time range corresponding to the time-frequency spectrogram. Echo width is the time span of the echo signal energy distribution in the time domain. Spectral center frequency offset is the change in the energy center frequency of the signal spectrum relative to the center frequency of the transmitted signal. Spectral entropy is a measure of the uniformity or randomness of the energy distribution in the signal spectrum.

[0069] In some embodiments, the time-spectrum graph can be traversed and calculated according to a predefined formula or algorithm to obtain one or more of the aforementioned characteristic parameters. For example, the brightness values ​​of all pixels within a preset detection time window in the time-spectrum graph are summed to obtain the echo signal strength. On the time-spectrum graph, along the time axis, the start and end time points where the signal brightness exceeds the background noise threshold (e.g., 20% of the maximum brightness) are identified, and the difference between the two is the echo width. The time slot corresponding to the echo main lobe in the time-spectrum graph is selected, and the weighted average frequency of the spectrum of that time slot (with the energy of each frequency point as the weight) is calculated. The center frequency of the sonar device's transmitted pulse (e.g., 200 kHz) is subtracted from the average frequency to obtain the spectral center frequency offset. The time slot corresponding to the echo main lobe in the time-spectrum graph is selected, and the spectral energy distribution of that time slot is normalized to a probability distribution. The entropy value of the probability distribution is calculated according to the information entropy formula to obtain the spectral entropy value.

[0070] S13, convert the feature parameters into acoustic features that characterize the state of the fishing net structure at the current detection location.

[0071] The current detection location is the specific spatial position of the underwater robot during its sonar detection. For example, it is the three-dimensional coordinates obtained through the underwater robot's positioning system.

[0072] In some embodiments, the extracted feature parameters can be organized, combined, or further processed to obtain acoustic features. For example, four feature parameters—echo signal intensity A, echo width B, spectral center frequency offset C, and spectral entropy value D—can be extracted from the time-spectrum diagram. The values ​​of the four feature parameters can be arranged in order to form a four-dimensional vector [A, B, C, D]. This vector is the acoustic feature representing the state of the fishing net structure at the current detection location.

[0073] Step 103: Compare the acoustic features with the preset acoustic feature model of a complete fishing net to determine the comparison result.

[0074] The pre-defined acoustic feature model of a complete fishing net is a reference model pre-constructed based on the acoustic features of a complete, undamaged fishing net.

[0075] Alignment is the process of comparing two datasets or patterns to assess their similarity or difference.

[0076] The comparison result is the conclusion output by the comparison process, which can be expressed as a matching degree, difference value, or classification label.

[0077] In some embodiments, comparing the acoustic features with a preset acoustic feature model of a complete fishing net to determine the comparison result may include the following operations:

[0078] S21, Based on the current detection position, extract the local model at the corresponding position from the acoustic feature model.

[0079] The local model is a sub-model derived from the acoustic feature model based on the current detection location.

[0080] In some embodiments, a subset of acoustic feature data that is associated with the current detection location and represents the normal state near that location can be retrieved from the acoustic feature model through methods such as coordinate matching, spatial index query, or neighboring region calculation. This subset is the local model.

[0081] S22, Based on the local model, feature extraction is performed to obtain the template acoustic features.

[0082] Feature extraction is a data processing procedure that aims to calculate or summarize one or more more representative or concise numerical values ​​or vectors from one or more sets of data to encapsulate the core information of the original data.

[0083] Template acoustic features are standard acoustic features obtained by performing feature extraction operations on local models.

[0084] In some embodiments, the step of extracting features based on the local model to obtain template acoustic features may include the following operations:

[0085] S221, Obtain the underwater environment at the current detection location.

[0086] The underwater environment refers to the environmental conditions of the waters surrounding the current detection location. This includes factors such as visibility, depth, water pressure, and the concentration of suspended particulate matter in the water.

[0087] In some embodiments, the underwater environment at the current detection location can be obtained through various sensors mounted on the underwater robot.

[0088] S222, Based on the underwater environment and the local model, establish a simulation environment.

[0089] A simulation environment is a virtual underwater scene constructed using computer software to simulate the sonar detection process.

[0090] In some embodiments, the acquired underwater environmental parameters can be used as the medium physical properties input to the simulation software, and the three-dimensional structure of a normal fishing net represented by a local model can be imported into the simulation software to construct a simulation environment that simulates real detection conditions.

[0091] S223, Simulate sonar detection on the local model within the simulation environment to obtain simulated sonar echo signals.

[0092] Simulated sonar detection refers to the process in a simulation environment where, through numerical calculation methods, a real sonar system emits sound wave signals, the sound waves propagate in a virtual medium, interact with a virtual fishing net model (reflection and scattering), and are finally received by a virtual receiver.

[0093] Simulated sonar echo signals are acoustic signal data calculated and output by simulation software and received by a virtual receiver after the simulated sonar detection process has ended.

[0094] S224, Feature extraction is performed on the simulated sonar echo signal to obtain the acoustic features of the template.

[0095] Template acoustic features are obtained by extracting features from simulated sonar echo signals. They represent the standard acoustic features that a normal fishing net should have at the current detection location under specific underwater environmental conditions.

[0096] The feature extraction method can be the same as that described above, and will not be repeated here.

[0097] S23, compare the acoustic features with the acoustic features of the template to obtain the comparison result.

[0098] In some embodiments, comparing the acoustic features with the template acoustic features to obtain the comparison result includes: calculating the similarity between the acoustic features and the template acoustic features; and determining the comparison result based on the similarity.

[0099] In some embodiments, similarity can be calculated using various methods, such as calculating cosine distance, Euclidean distance, etc.

[0100] In some embodiments, the similarity score can be directly used as the comparison result.

[0101] In some embodiments, comparing the acoustic features with the template acoustic features to obtain the comparison result may further include: inputting the acoustic features and the template acoustic features into a comparison model; determining the comparison result based on the output of the comparison model; wherein the comparison model is a machine learning model.

[0102] The comparison model is a trained mathematical model built on machine learning algorithms. The comparison model can take two sets of feature data (i.e., acoustic features and template acoustic features) as input, and after complex nonlinear calculations, output similarity or difference (i.e., comparison result).

[0103] In some embodiments, the comparison model is a pre-trained neural network, which may include an input layer, a feature processing layer, and an output layer.

[0104] The input layer is the data entry point for the model.

[0105] The feature processing layer follows the input layer and includes one or more fully connected layers (also known as dense layers), each followed by a non-linear activation function layer (such as the ReLU function).

[0106] The output layer is the last layer of the model, used to output the final result. For binary classification tasks (match / non-match), the output layer is typically a fully connected layer followed by an activation function suitable for classification. If the output is a similarity probability, a single-neuron layer with a sigmoid activation function can be used, outputting a value between 0 and 1 representing the confidence level.

[0107] In some embodiments, a training dataset can be constructed using a large amount of historical data, including sample data and label data. The training dataset can be used for model training; for example, samples are input into the model to be trained to obtain the output results, and a loss function is constructed based on the output results and label data. The model parameters can be adjusted based on the loss function value until the loss function value converges, thus training a comparison model.

[0108] Step 104: Determine the fishing net structure status corresponding to the current detection location based on the comparison results.

[0109] The fishing net structure states include normal and abnormal states.

[0110] A normal state refers to a fishing net that is structurally intact and without defects, or whose function still meets the expected requirements. For example, the net has regular mesh shapes, no broken ropes, and no significant deformation.

[0111] An abnormal condition refers to a fishing net structure that is damaged, deformed, clogged, or otherwise defective. For example, torn mesh, worn ropes, or blockage caused by attached marine organisms.

[0112] In some embodiments, the comparison result value or label can be mapped to a state category. If the comparison result indicates a high match or conforms to the model range, the state is a normal state; otherwise, it is an abnormal state.

[0113] Step 105: Generate and store a digital model of the fishing net.

[0114] Each grid cell of the digital model corresponds to a fishing net mesh at a detection location and is associated with the fishing net structure state at the detection location.

[0115] A digital model of a fishing net is a virtual representation of the fishing net in a computer or digital system. It can be a three-dimensional geometric model, including the shape, structure, and state information of the fishing net.

[0116] Mesh cells are the basic geometric elements in a digital model, used to discretize the structure of a fishing net.

[0117] In some embodiments, a digital model can be constructed using computer graphics or modeling software based on the spatial coordinates of all detection locations and the corresponding fishing net structure state.

[0118] In some embodiments, generating and storing the digital model of the fishing net may include the following operations:

[0119] S31, Obtain the historical detection results of the fishing net; wherein, the historical detection results include the historical fishing net structure status of the fishing net in the historical detection.

[0120] Historical test results for fishing nets are a collection of data recorded from one or more tests conducted on the same fishing net prior to this test.

[0121] In some embodiments, all historical detection data records associated with the unique identifier (such as the fishing net ID) of the fishing net to be detected can be retrieved and loaded from the storage medium (such as a database or file system) through query statements or file read operations to obtain historical detection results.

[0122] S32, Based on the historical fishing net structure state and the fishing net structure state, generate the fishing net structure change trajectory.

[0123] The trajectory of changes in fishing net structure is a data sequence or graphical representation used to describe how the structural state of a specific location (or area) on a fishing net evolves over time.

[0124] S33, dynamically demonstrate the trajectory of the fishing net structure change in the digital model of the fishing net.

[0125] In some embodiments, a digital model of a fishing net can be loaded into a visualization engine or a graphical user interface. For each grid cell in the model, different visualization attributes (such as color, transparency, and texture) are assigned to the cell at different points in time based on the corresponding fishing net structure change trajectory data. By continuously or frame by frame updating the visualization attributes of all grid cells in the entire digital model, an animation showing the historical evolution of the fishing net's state can be formed.

[0126] Reference Figure 2 The diagram shown is a functional module schematic of the sonar-based fishing net detection device 100 of this application.

[0127] The sonar-based fishing net detection device 100 described in this application is installed in an electronic device. Depending on its function, the sonar-based fishing net detection device 100 includes a control module 110, a processing module 120, a comparison module 130, a determination module 140, and a generation module 150. These modules can also be referred to as units, which are a series of computer program segments that can be executed by the processor of an electronic device and perform a fixed function, and are stored in the memory of the electronic device.

[0128] In this embodiment, the functions of each module / unit are as follows:

[0129] The control module 110 is used to control the underwater robot to periodically emit sonar detection signals and receive sonar echo signals from the fishing net.

[0130] The processing module 120 is used to process the received sonar echo signal and extract acoustic features that reflect the structural state of the fishing net.

[0131] The comparison module 130 is used to compare the acoustic features with a preset acoustic feature model of a complete fishing net and determine the comparison result.

[0132] The determining module 140 is used to determine the fishing net structure state corresponding to the current detection location based on the comparison result; wherein, the fishing net structure state includes a normal state and an abnormal state;

[0133] The generation module 150 is used to generate and store a digital model of the fishing net; wherein each grid cell of the digital model corresponds to a fishing net mesh at a detection location and is associated with the fishing net structure state at the detection location.

[0134] The specific implementation of the fishing net detection device based on sonar information in this application is largely the same as the specific implementation of the fishing net detection method based on sonar information described above, and will not be repeated here.

[0135] Reference Figure 3 The diagram shown is a schematic representation of a preferred embodiment of the electronic device of this application.

[0136] The electronic device includes a processor 111, a communication interface 112, a memory 113, and a communication bus 114, wherein the processor 111, the communication interface 112, and the memory 113 communicate with each other through the communication bus 114.

[0137] The memory 113 is used to store computer programs, such as a fishing net detection program based on sonar information;

[0138] In some embodiments, the processor 111 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. The processor 111 can be used to control the overall operation of the electronic device, such as performing data interaction or communication-related control and processing. In this embodiment, the processor 111 is used to run program code stored in the memory 113 or process data.

[0139] The communication interface 112 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The communication interface 112 may also be used to establish a communication connection between the electronic device and other electronic devices.

[0140] The memory 113 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 113 may be an internal storage unit of the electronic device, such as the hard disk or memory of the electronic device. In other embodiments, the memory 113 may also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. of the electronic device. Of course, the memory 113 may include both internal storage units and external storage devices of the electronic device. In this embodiment, the memory 113 can be used to store the operating system and various computer programs installed on the electronic device, such as the program code of a fishing net detection program based on sonar information. In addition, the memory 113 can also be used to temporarily store various types of data that have been output or will be output.

[0141] Figure 3 Only an electronic device with components 111-114 is shown; however, it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0142] In one embodiment of this application, the processor 111, when executing a program stored in the memory 113, implements the sonar-information-based fishing net detection method provided in any of the foregoing method embodiments, including:

[0143] Control the underwater robot to periodically emit sonar detection signals and receive sonar echo signals from the fishing net;

[0144] The received sonar echo signal is processed to extract acoustic features that reflect the structural state of the fishing net;

[0145] The acoustic features are compared with a preset acoustic feature model of a complete fishing net to determine the comparison result;

[0146] Based on the comparison results, the fishing net structure status corresponding to the current detection location is determined; wherein, the fishing net structure status includes normal status and abnormal status;

[0147] A digital model of the fishing net is generated and stored; wherein each grid cell of the digital model corresponds to a mesh size of the fishing net at a detection location and is associated with the structural state of the fishing net at the detection location.

[0148] For a detailed explanation of the above steps, please refer to the above. Figure 1 A flowchart illustrating an embodiment of a fishing net detection method based on sonar information.

[0149] Furthermore, this application also proposes a computer-readable storage medium that is both non-volatile and volatile. This computer-readable storage medium is any one or any combination of several of the following: hard disk, multimedia card, SD card, flash memory card, SMC, read-only memory (ROM), erasable programmable read-only memory (EPROM), portable compact disc read-only memory (CD-ROM), USB memory, etc. The computer-readable storage medium includes a data storage area and a program storage area. The program storage area stores a fishing net detection program based on sonar information. When executed by a processor, the sonar-based fishing net detection program performs the following operations:

[0150] Control the underwater robot to periodically emit sonar detection signals and receive sonar echo signals from the fishing net;

[0151] The received sonar echo signal is processed to extract acoustic features that reflect the structural state of the fishing net;

[0152] The acoustic features are compared with a preset acoustic feature model of a complete fishing net to determine the comparison result;

[0153] Based on the comparison results, the fishing net structure status corresponding to the current detection location is determined; wherein, the fishing net structure status includes normal status and abnormal status;

[0154] A digital model of the fishing net is generated and stored; wherein each grid cell of the digital model corresponds to a mesh size of the fishing net at a detection location and is associated with the structural state of the fishing net at the detection location.

[0155] The specific implementation of the computer-readable storage medium in this application is largely the same as the specific implementation of the fishing net detection method based on sonar information described above, and will not be repeated here.

[0156] It should be noted that the sequence numbers of the embodiments in this application are merely for descriptive purposes and do not represent the superiority or inferiority of the embodiments. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, apparatus, article, or method. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, apparatus, article, or method that includes that element.

[0157] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware simulation platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device to execute the methods described in the various embodiments of this application.

[0158] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for detecting fishing nets based on sonar information, characterized in that, The method includes: Control the underwater robot to periodically emit sonar detection signals and receive sonar echo signals from the fishing net; The received sonar echo signal is processed to extract acoustic features that reflect the structural state of the fishing net; The acoustic features are compared with a preset acoustic feature model of a complete fishing net to determine the comparison result; Based on the comparison results, the fishing net structure status corresponding to the current detection location is determined; wherein, the fishing net structure status includes normal status and abnormal status; A digital model of the fishing net is generated and stored; wherein each grid cell of the digital model corresponds to a mesh size of the fishing net at a detection location and is associated with the structural state of the fishing net at the detection location.

2. The fishing net detection method based on sonar information as described in claim 1, characterized in that, The process of processing the received sonar echo signal to extract acoustic features reflecting the structural state of the fishing net includes: Time-frequency analysis was performed on the sonar echo signal to obtain a time-spectrum diagram; Feature parameters are extracted from the time-spectrum graph; the feature parameters include one or more of the following: echo signal strength, echo width, spectral center frequency offset, and spectral entropy value. The feature parameters are converted into acoustic features that characterize the state of the fishing net structure at the current detection location.

3. The fishing net detection method based on sonar information as described in claim 1, characterized in that, The step of comparing the acoustic features with a preset acoustic feature model of a complete fishing net and determining the comparison result includes: Based on the current detection position, extract the local model at the corresponding position from the acoustic feature model; Based on the local model, feature extraction is performed to obtain the template acoustic features; The acoustic features are compared with the acoustic features of the template to obtain the comparison result.

4. The fishing net detection method based on sonar information as described in claim 3, characterized in that, The feature extraction based on the local model to obtain the template acoustic features includes: Obtain the underwater environment at the current detection location; Based on the underwater environment and the local model, a simulation environment is established; Simulated sonar detection is performed on the local model within the simulation environment to obtain simulated sonar echo signals; Feature extraction is performed on the simulated sonar echo signal to obtain the acoustic features of the template.

5. The fishing net detection method based on sonar information as described in claim 3, characterized in that, The step of comparing the acoustic features with the template acoustic features to obtain the comparison result includes: Calculate the similarity between the acoustic features and the template acoustic features; The comparison result is determined based on the similarity.

6. The fishing net detection method based on sonar information as described in claim 3, characterized in that, The step of comparing the acoustic features with the template acoustic features to obtain the comparison result includes: The acoustic features and the template acoustic features are input into the comparison model; The comparison result is determined based on the output of the comparison model; wherein the comparison model is a machine learning model.

7. The fishing net detection method based on sonar information as described in claim 1, characterized in that, The generation and storage of the digital model of the fishing net includes: Obtain historical detection results of the fishing net; wherein, the historical detection results include the historical structural state of the fishing net in the historical detection; Based on the historical fishing net structure state and the fishing net structure state, a fishing net structure change trajectory is generated; The trajectory of structural changes in the fishing net is dynamically demonstrated in the digital model of the fishing net.

8. A fishing net detection device based on sonar information, characterized in that, The device includes: The control module is used to control the underwater robot to periodically emit sonar detection signals and receive sonar echo signals from the fishing net; The processing module is used to process the received sonar echo signal and extract acoustic features that reflect the structural state of the fishing net. The comparison module is used to compare the acoustic features with a preset acoustic feature model of a complete fishing net and determine the comparison result; The determination module is used to determine the fishing net structure state corresponding to the current detection location based on the comparison results; wherein, the fishing net structure state includes a normal state and an abnormal state; A generation module is used to generate and store a digital model of the fishing net; wherein each grid cell of the digital model corresponds to a mesh size of the fishing net at a detection location and is associated with the structural state of the fishing net at the detection location.

9. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in a memory, implements the fishing net detection method based on sonar information as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the fishing net detection method based on sonar information as described in any one of claims 1 to 7.

Images