NL2037440A - A method, system, and medium for intelligent recognition of fishing activities based on image processing - Google Patents
A method, system, and medium for intelligent recognition of fishing activities based on image processing Download PDFInfo
- Publication number
- NL2037440A NL2037440A NL2037440A NL2037440A NL2037440A NL 2037440 A NL2037440 A NL 2037440A NL 2037440 A NL2037440 A NL 2037440A NL 2037440 A NL2037440 A NL 2037440A NL 2037440 A NL2037440 A NL 2037440A
- Authority
- NL
- Netherlands
- Prior art keywords
- fishing
- relevant
- catch
- data information
- information
- Prior art date
Links
- 230000000694 effects Effects 0.000 title claims abstract description 65
- 238000012545 processing Methods 0.000 title claims abstract description 57
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000012544 monitoring process Methods 0.000 claims abstract description 13
- 238000005516 engineering process Methods 0.000 claims abstract description 10
- 230000006399 behavior Effects 0.000 claims description 77
- 238000012360 testing method Methods 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 18
- 238000013527 convolutional neural network Methods 0.000 claims description 12
- 241000251468 Actinopterygii Species 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 7
- 230000010365 information processing Effects 0.000 claims description 4
- 238000009499 grossing Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims 1
- 230000001105 regulatory effect Effects 0.000 abstract description 7
- 238000004458 analytical method Methods 0.000 abstract description 3
- 238000003706 image smoothing Methods 0.000 description 4
- 230000007613 environmental effect Effects 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 230000003542 behavioural effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 241000238557 Decapoda Species 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 235000015170 shellfish Nutrition 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000010792 warming Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This invention relates to a method, system, and medium for intelligent recognition of fishing activities based on image processing, belonging to the field of fisheries resource identification technology. The invention sets relevant threshold information and judges fishing behavior by analyzing data related to the catch, obtaining results of fishing behavior judgments. Based on the threshold information and fishing behavior judgment results, the invention generates fishing statistics reports and related alert information. This method can identify different types of catch and determine the method of capture. By combining image acquisition equipment and edge computing technology, the system can analyze catch images in real-time, providing timely and accurate information to fisheries regulatory authorities. Real-time monitoring and analysis of fishing methods help detect and prevent illegal fishing activities promptly, contributing to the protection of marine ecosystems and fisheries resources.
Description
A method, system, and medium for intelligent recognition of fishing activities based on image processing
This invention relates to the field of fisheries resource identification, particularly to a method, system, and medium for intelligent recognition of fishing activities based on image processing.
With the rapid development of the fishing industry, the diversification of fishing gear and methods has made it increasingly complex to identify the source and method of capture of fishery products. To ensure the sustainable development of fisheries and protect the marine ecosystem, it is necessary to accurately and efficiently identify and determine the source of fishery products.
The present invention overcomes the shortcomings of existing technologies and provides a method, system, and medium for intelligent recognition of fishing activities based on image processing.
To achieve the above objectives, the technical solution adopted by the present invention includes:
The first aspect of the present invention provides a method for intelligent recognition of fishing activities based on image processing, comprising the following steps:
Obtaining image data information of fishing activities in the target area and preprocessing the image data information of fishing activities to obtain processing results of image data information;
Identifying fishing-related catch data information through the processing results of image data information;
Setting relevant threshold information and judging fishing behavior by analyzing the fishing-related catch data information to obtain fishing behavior judgment results;
Generating fishing statistics reports based on the relevant threshold information and fishing behavior judgment results, and generating related alert information based on the fishing statistics reports.
Furthermore, in a preferred embodiment of the present invention, preprocessing of the image data information of fishing activities is performed to obtain processing results of image data information, specifically including:
Cropping the non-target area from the image data information of fishing activities to obtain the region of interest of the image data information of fishing activities;
Smoothing the region of interest of the image data information of fishing activities using a mean filter to obtain image smoothing processing results;
Extracting features from the image smoothing processing results using the Canny operator in relevant regions of interest to obtain processing results of image data information.
Furthermore, in a preferred embodiment of the present invention, the method includes identifying fishing-related catch data information through the processing results of image data information, specifically comprising:
Obtaining a large amount of image data information for various types of fishing resources and fishing tools through big data, and dividing this data into training and testing sets;
Building a fishing catch recognition model based on convolutional neural networks (CNN), and training the model using the training set until the relevant loss function converges and stabilizes, and saving the model parameters of the fishing catch recognition model;
Testing the fishing catch recognition model using the testing set until the model parameters of the fishing catch recognition model meet the preset requirements, and outputting the fishing catch recognition model;
Inputting the processing results of image data information into the fishing catch recognition model for identification, obtaining relevant types of fishing resources and fishing tools, and generating fishing-related catch data information based on the relevant types of fishing resources and fishing tools.
Furthermore, in a preferred embodiment of the present invention, the method includes judging fishing behavior through the fishing-related catch data information, specifically comprising the following steps:
Obtaining relevant data on prohibited fishing resource types and related illegal fishing behavior data through big data, building a database, storing the relevant data on prohibited fishing resource types and related illegal fishing behavior in the database, and regularly updating the database;
Generating retrieval tags based on the fishing-related catch data information, inputting the retrieval tags into the relevant data on prohibited fishing resource types to perform data matching, and obtaining the relevant matching degree;
Determining whether there are prohibited fishing resource types with a matching degree greater than the preset matching degree. If there are prohibited fishing resource types with a matching degree greater than the preset matching degree, generating results indicating illegal fishing behavior.
If there are no prohibited fishing resource types with a matching degree greater than the preset matching degree, the system generates candidate illegal fishing behavior judgment results.
Furthermore, in a preferred embodiment of the present invention, the method includes generating a fishing statistics report based on the relevant threshold information and fishing behavior judgment results, specifically comprising the following steps:
If the fishing behavior judgment results indicate candidate illegal fishing behavior, compare these results with the relevant threshold information to calculate the deviation rate.
Determine if the deviation rate exceeds the preset deviation rate threshold. If the deviation rate is greater than the preset threshold, consider the candidate illegal fishing behavior judgment results as the final judgment results for illegal fishing behavior.
Obtain relevant fishing evaluation indicator data through big data and compare it with the judgment results for illegal fishing behavior.
Construct a table for sorting illegal fishing project information, input the data for illegal projects into the sorting table, generate a fishing statistics report based on the sorted illegal project information table, and visualize it according to preset criteria.
Furthermore, in a preferred embodiment of the present invention, the method includes generating relevant warning information based on the fishing statistics report, specifically comprising the following steps:
Obtain basic data information of the fishing personnel and the fishing vessel for relevant fishing boats, and store the relevant basic data information of the fishing personnel and the fishing vessel in a database.
Use remote sensing technology to acquire basic data information of fishing vessels involved in relevant illegal fishing activities. Input this information into the database and match it with the relevant data to determine the matching degree of the fishing vessel's basic data information.
Continuously monitor the geographic location information of fishing vessels involved in relevant illegal activities when the matching degree of the fishing vessel's basic data information does not meet the preset threshold. Generate warning information based on the geographic location information of these vessels and transmit it to the relevant monitoring terminal.
When the matching degree of the fishing vessel's basic data information meets the preset threshold, obtain the basic data information of the relevant fishing personnel and generate warning information based on the fishing statistics report. Transmit the warning information to the relevant fishing personnel according to preset protocols.
The second aspect of the present invention provides a fishing intelligent recognition system based on image processing. The system includes a memory and a processor,
where the memory contains a program for a fishing intelligent recognition method based on image processing. When the processor executes the program, it performs the following steps:
Obtain image data information of fishing activities in the target area and preprocess the 5 image data information to obtain processed image data information.
Recognize the processed image data information to obtain fishing-related catch data information.
Set relevant threshold information and judge fishing behavior based on the fishing- related catch data information to obtain fishing behavior judgment results.
Generate a fishing statistics report based on the relevant threshold information and fishing behavior judgment results, and generate related warning information based on the fishing statistics report.
In this embodiment, the step of recognizing the processed image data information to obtain fishing-related catch data information specifically includes:
Obtain a large amount of image data information on various types of fishing resources and fishing tools through big data and divide this data into training and testing sets.
Build a catch recognition model based on convolutional neural networks (CNNs) and train the model using the training set until the loss function converges steadily, saving the model parameters of the catch recognition model.
Test the catch recognition model using the testing set until the model parameters of the catch recognition model meet the preset requirements, and output the catch recognition model.
Processing the processed image data information through the catch recognition model to identify and classify relevant fishing resources and tools, and generating fishing catch data information related to fishing behavior based on the identified fishing resource and tool categories.
In accordance with this embodiment, the steps for behavior judgment related to fishing catch data information include:
Acquiring relevant data on prohibited fishing resource categories and related illegal fishing behavior data through big data, constructing a database, storing the relevant prohibited fishing resource category data and related illegal fishing behavior data in the database, and regularly updating the database.
Generating search tags based on the fishing catch data information related to fishing behavior, inputting the search tags into the relevant prohibited fishing resource category data for data matching, and obtaining the relevant matching degree.
Determining the presence of prohibited fishing resource category items with a matching degree greater than the preset matching degree. If such items exist, generating illegal fishing behavior judgment results.
If there are no prohibited fishing resource category items with a matching degree greater than the preset matching degree, generating candidate illegal fishing behavior judgment results.
The third aspect of the present invention provides a computer-readable storage medium comprising a program for intelligent recognition of fishing activities based on image processing. When executed by a processor, the program implements any of the steps of the intelligent recognition method for fishing activities based on image processing.
The invention addresses deficiencies in the background technology and offers the following beneficial effects: The invention involves obtaining image data information of fishing activities in the target area, preprocessing this information to obtain processed image data, recognizing the processed image data to obtain data on fishing activities, setting relevant threshold information, making behavioral judgments based on the fishing activity data, and generating fishing activity judgment results. Based on the relevant threshold information and fishing activity judgment results, the invention generates fishing statistics reports and relevant alerts. This method can identify different types of catch and assess how they were caught. Combined with image capture devices and edge computing technology, the system can analyze catch images in real-time, providing timely and accurate information to fisheries regulatory authorities. Real-time monitoring and analysis of fishing methods help in detecting and preventing illegal fishing activities promptly, contributing to the protection of marine ecosystems and fisheries resources.
In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are only These are some embodiments of the present invention. For those of ordinary skill in the art, drawings of other embodiments can be obtained based on these drawings without exerting creative efforts.
Figure | shows the overall method flow chart of an image processing-based fishery fishing intelligent identification method;
Figure 2 shows a first method flow chart of an image processing-based fishery fishing intelligent identification method,
Figure 3 shows a second method flow chart of an image processing-based fishery fishing intelligent identification method;
Figure 4 shows a system block diagram of a fishery fishing intelligent identification system based on image processing,
In order to more clearly understand the above objects, features and advantages of the present invention, the present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, as long as there is no conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.
Many specific details are set forth in the following description in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described here. Therefore, the protection scope of the present invention is not limited by the specific details disclosed below.
Limitations of Examples.
As shown in Figure 1, this invention provides a method, system, and medium for intelligent recognition of fishing activities based on image processing, including the following steps:
S102: Obtain image data information of fishing activities in the target area and preprocess this information to obtain processed image data. S104: Recognize the processed image data to obtain data on fishing activities. S106: Set relevant threshold information and make behavioral judgments based on the data on fishing activities to obtain fishing activity judgment results. S108: Generate fishing statistics reports based on the relevant threshold information and fishing activity judgment results, and generate relevant alerts based on the fishing statistics reports.
It is noted that this method can identify different types of catch and assess how they were caught. Combined with image capture devices and edge computing technology, the system can analyze catch images in real-time, providing timely and accurate information to fisheries regulatory authorities. Real-time monitoring and analysis of fishing methods help in detecting and preventing illegal fishing activities promptly, contributing to the protection of marine ecosystems and fisheries resources.
For example, ocean aerial drones, ship-mounted cameras, sonar, and other equipment can be used to obtain image data information of fishing activities in the target area.
Further, in a preferred embodiment of the present invention, the specific steps for preprocessing the image data information of fishing behavior include:
Cropping the image data information of fishing behavior to obtain the region of interest.
Smoothing the region of interest using the mean filter method to obtain the image smoothing processing result.
Extracting features from the image smoothing processing result using the Canny operator to obtain the image data information processing result.
As shown in Figure 2, further, in a preferred embodiment of the present invention, the specific steps for recognizing the image data information processing result and obtaining fishery-related catch data include: S202: Obtaining a large amount of image data information on fishery resource types and fishing tools through big data and dividing the data into training and testing sets. S204: Constructing a fishery catch recognition model based on convolutional neural networks (CNNs) and training the model using the training set until the relevant loss function converges steadily, saving the model parameters of the fishery catch recognition model. S206: Testing the fishery catch recognition model using the testing set until the model parameters of the fishery catch recognition model meet the preset requirements and outputting the model. S208:
Inputting the image data information processing result into the fishery catch recognition model for recognition, obtaining the relevant fishery resource types and fishing tool types, and generating fishery-related catch data based on the relevant fishery resource types and fishing tool types.
It should be noted that fishery resource types can include marine organisms such as shrimp, fish, and shellfish, while fishing tool types in the image data information may include nets, fishing gear, electric fishing equipment, and so on. During the continuous training of the retrieval model using neural networks, the parameters and data distribution of the network model will be constantly updated. For example, the input of the second layer is obtained from the input data and the parameters of the first layer, and the parameters of the first layer change continuously during training, which will inevitably cause changes in the input data of the second layer. To ensure the smoothness of the loss function, it is necessary to adjust the data of each layer to a reasonable distribution range (until the model parameters of the fishery catch recognition model meet the preset requirements), so that the data can approximate an identity function or a residual function.
Furthermore, in a preferred embodiment of the present invention, the specific steps for behavior judgment based on the fishery-related catch data include:
Obtaining relevant data on prohibited fishing fishery resource types and related illegal fishing behavior data through big data, constructing a database, storing the relevant data on prohibited fishing fishery resource types and related illegal fishing behavior data in the database, and regularly updating the database.
Generating retrieval tags based on the fishery-related catch data and inputting the retrieval tags into the relevant data on prohibited fishing fishery resource types for data matching to obtain the relevant matching degree.
Determining if there are prohibited fishing fishery resource types with a matching degree greater than the preset threshold. If there are prohibited fishing fishery resource types with a matching degree greater than the preset threshold, then generating a judgment result for illegal fishing behavior.
If there are no prohibited fishing fishery resource types with a matching degree greater than the preset threshold, then generate candidate judgments for illegal fishing behavior.
For example, the relevant illegal fishing behavior data includes activities such as electric fishing and excessive fishing. This method allows for the initial screening of illegal fishing activities, thereby enhancing the rationality of fisheries regulatory supervision.
Regular updates to the database ensure timely implementation of regulations, such as if a certain fish species becomes a protected animal within a specific time period, facilitating timely regulatory actions and enhancing regulatory rationality.
Furthermore, in a preferred embodiment of the present invention, the steps for generating a fishing statistics report based on the threshold information and fishing behavior judgment results include:
If the fishing behavior judgment result is a candidate judgment for illegal fishing behavior, then compare the candidate judgment for illegal fishing behavior with the relevant threshold information to obtain a deviation rate.
Determine if the deviation rate is greater than the preset deviation rate threshold. If the deviation rate exceeds the preset threshold, then consider the candidate judgment for illegal fishing behavior as the judgment result for illegal fishing behavior.
Obtain relevant fishing evaluation index data through big data and compare it with the judgment result for illegal fishing behavior based on the relevant fishing evaluation index data to generate data on violations.
Create a table for sorting violation project information and input the violation project data into the sorting table. Generate a fishing statistics report based on the violation project information sorting table and visualize it according to preset methods.
It should be noted that the relevant threshold information refers to the threshold settings for fishing, typically indicating the set fishing quantity. The candidate judgment results for illegal fishing behavior include information about the fishing quantity. When the fishing quantity exceeds the preset quantity, it indicates excessive fishing behavior. This method effectively filters out excessive fishing behavior.
As shown in Figure 3, in a further preferred embodiment of the present invention, the steps for generating relevant warning information based on the fishing statistics report include:
S302: Obtain basic data information about the crew members and vessels of relevant fishing boats, store the relevant basic data information about the crew members and vessels in a database. 8304: Use remote sensing technology to obtain basic data information about fishing boats involved in illegal activities, match this information with the database to determine the matching degree of vessel basic data information.
S306: If the matching degree of vessel basic data information is not equal to the preset matching degree, continuously obtain the geographical location information of fishing boats involved in illegal activities, generate warning information based on this geographical information, and transmit it to relevant monitoring terminals.
S308: If the matching degree of vessel basic data information is equal to the preset matching degree, obtain basic data information about the crew members of the relevant fishing boats, generate warning information based on the fishing statistics report, and transmit the warning information to the crew members of the fishing boats according to preset methods.
It should be noted that the basic data information of fishing boats includes the type of the boat, fishing license information, etc., while the basic data information of the crew members of relevant fishing boats includes their name, gender, ID number, contact information, etc. When the matching degree of vessel basic data information is not equal to the preset matching degree, it indicates that the fishing boat is engaged in illegal fishing, such as boats without fishing permits. Monitoring their illegal operations continuously helps in rationalizing the supervision by regulatory authorities. When the matching degree of vessel basic data information is equal to the preset matching degree, it indicates the presence of illegal fishing activities, and timely warning information is transmitted to the crew members of the relevant fishing boats according to preset methods, improving the rationality of monitoring.
Additionally, this method may include the following steps:
Obtain life habit data information of fish species involved in illegal fishing and environmental data information of the current operational area of relevant fishing boats through big data.
Calculate the degree of correlation between the life habit data information of fish species involved in illegal fishing and the environmental data information of the current operational area of relevant fishing boats using gray correlation analysis.
If the degree of correlation is greater than the preset level, identify the operational area where the degree of correlation exceeds the preset level as a key monitoring area.
Continuously monitor the key monitoring area by real-time tracking of fishing boat positions based on the updated location information of fishing boats in the key monitoring area.
It should be noted that when the correlation degree information exceeds the preset correlation degree information, it indicates that the environmental data information in the current operating area of the relevant fishing vessels is consistent with the living environment of illegally caught fish species. This method allows for the selection of key monitoring areas, making the monitoring of illegal fishing activities more reasonable.
As shown in Figure 4, the second aspect of the present invention provides a fishery fishing intelligent recognition system based on image processing. The system includes a memory 41 and a processor 62, where the memory 41 contains a fishery fishing intelligent recognition method program based on image processing. When the fishery fishing intelligent recognition method program based on image processing is executed by the processor 62, it performs the following steps:
Obtain image data information of fishing activities in the target area and preprocess the image data information of fishing activities to obtain processed image data information.
Identify the processed image data information to obtain fishery fishing behavior-related fishery resources data information.
Set relevant threshold information and judge fishery fishing behavior-related fishery resources data information to obtain fishery fishing behavior judgment results.
Generate fishing statistics reports based on the relevant threshold information and fishing behavior judgment results, and generate related warming information based on the fishing statistics reports.
In this embodiment, the fishing behavior-related fishery resources data information is obtained by identifying the processed image data information. Specifically:
Obtain a large amount of fishery resource types and fishery tool types image data information through big data, and divide this large amount of fishery resource types and fishery tool types image data information into training and testing sets.
Build a fishery resource recognition model based on convolutional neural networks (CNNs) and train this model using the training set until the relevant loss function converges and stabilizes, saving the model parameters of the fishery resource recognition model.
Test the fishery resource recognition model using the testing set until the model parameters of the fishery resource recognition model meet the preset requirements, and output the fishery resource recognition model.
Input the processed image data information into the fishery resource recognition model for identification, obtain the relevant fishery resource types and fishery tool types, and generate fishing behavior-related fishery resources data information based on the relevant fishery resource types and fishery tool types.
Based on this embodiment, behavior judgment on fishery catch data related to fishing activities is performed to obtain fishing behavior judgment results. The specific steps include:
Obtain relevant data on prohibited fishing fishery resource types and related data on illegal fishing behavior through big data. Construct a database and store the relevant data on prohibited fishing fishery resource types and related data on illegal fishing behavior in the database. Regularly update the database.
Generate search tags based on the fishery catch data related to fishing activities. Input these search tags into the relevant data on prohibited fishing fishery resource types for data matching to obtain relevant matching degrees.
Determine if there are any prohibited fishing fishery resource types with matching degrees greater than the preset matching degree. If such prohibited fishing fishery resource types exist, generate illegal fishing behavior judgment results.
If there are no prohibited fishing fishery resource types with matching degrees greater than the preset matching degree, generate candidate illegal fishing behavior judgment results.
The invention also provides a computer-readable storage medium containing a fishery catch intelligent recognition method based on image processing. When executed by a processor, this method realizes any of the steps of the fishery catch intelligent recognition method based on image processing.
It should be understood that the disclosed devices and methods can be implemented in other ways. The equipment embodiments described above are illustrative. For example, the division of units is a logical functional division, and in actual implementation, there may be different divisions, such as combining multiple units or components, integrating into another system, ignoring or not executing certain features. Additionally, the coupling or communication between the components shown or discussed can be indirect through interfaces, devices, or units, and can be electrical, mechanical, or other forms.
The units described as separate components can be physically separated or not. The components shown as unitary may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all units can be selected as needed to achieve the objectives of this embodiment.
Furthermore, in various embodiments of the present invention, all functional units can be integrated into one processing unit, or each unit can be separately implemented as an individual unit, or two or more units can be integrated into one unit. The integrated units can be implemented in hardware form or in the form of hardware combined with software functional units.
Those skilled in the art will understand that the steps of the above method embodiments can be completed using hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium, and when executed, it performs the steps of the method embodiments described above. The storage medium may include mobile storage devices, read-only memory (ROM), random access memory (RAM), hard disks, or optical disks, among various media capable of storing program code.
Alternatively, if the integrated units of the present invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present invention, essentially or in terms of contributions to the existing technology, can be embodied in the form of software products. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (such as a personal computer, server, or network device) to execute all or part of the methods of various embodiments of the present invention. The aforementioned storage medium includes mobile storage devices,
ROM, RAM, hard disks, or optical disks, among various media capable of storing program code.
The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, and all of them should be covered. within the protection scope of the present invention.
Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.
Claims (10)
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310444658.0A CN116343018A (en) | 2023-04-24 | 2023-04-24 | Intelligent fishery fishing identification method, system and medium based on image processing |
Publications (1)
Publication Number | Publication Date |
---|---|
NL2037440A true NL2037440A (en) | 2024-05-23 |
Family
ID=86893102
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
NL2037440A NL2037440A (en) | 2023-04-24 | 2024-04-11 | A method, system, and medium for intelligent recognition of fishing activities based on image processing |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN116343018A (en) |
NL (1) | NL2037440A (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116821807B (en) * | 2023-08-30 | 2024-01-09 | 中国水产科学研究院南海水产研究所 | Machine vision-based fishery object identification and automatic recording method and system |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112418028A (en) * | 2020-11-11 | 2021-02-26 | 上海交通大学 | Satellite image ship identification and segmentation method based on deep learning |
CN114373165A (en) * | 2022-03-22 | 2022-04-19 | 江西省天轴通讯有限公司 | Law enforcement analysis method and device based on image recognition, storage medium and equipment |
CN115423225A (en) * | 2022-11-07 | 2022-12-02 | 中国水产科学研究院南海水产研究所 | Fishing port operation management method and system based on big data |
CN115953632A (en) * | 2023-01-16 | 2023-04-11 | 中国水产科学研究院渔业机械仪器研究所 | Fishing catch thing discernment and type device |
-
2023
- 2023-04-24 CN CN202310444658.0A patent/CN116343018A/en active Pending
-
2024
- 2024-04-11 NL NL2037440A patent/NL2037440A/en unknown
Also Published As
Publication number | Publication date |
---|---|
CN116343018A (en) | 2023-06-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Edelhoff et al. | Path segmentation for beginners: an overview of current methods for detecting changes in animal movement patterns | |
NL2037440A (en) | A method, system, and medium for intelligent recognition of fishing activities based on image processing | |
CN110097037A (en) | Intelligent monitoring method, device, storage medium and electronic equipment | |
CN114494837B (en) | Intelligent density identification method and system for fishery resources | |
CN110532888A (en) | A kind of monitoring method, apparatus and system | |
CN111177714A (en) | Abnormal behavior detection method and device, computer equipment and storage medium | |
CN111782484B (en) | Anomaly detection method and device | |
Vo et al. | An application of Convolutional Neural Network to lobster grading in the Southern Rock Lobster supply chain | |
CN112115996B (en) | Image data processing method, device, equipment and storage medium | |
CN115358155A (en) | Power big data abnormity early warning method, device, equipment and readable storage medium | |
CN115423225A (en) | Fishing port operation management method and system based on big data | |
CN117058630A (en) | Coast ship identification method, system, equipment and storage medium | |
CN117115637A (en) | Water quality monitoring and early warning method and system based on big data technology | |
CN116311036A (en) | Behavior recognition method, behavior recognition device, computer equipment and storage medium | |
CN115342937A (en) | Temperature anomaly detection method and device | |
CN115277472A (en) | Network security risk early warning system and method for multidimensional industrial control system | |
CN113723355A (en) | Target monitoring method and device, storage medium and electronic device | |
Guan et al. | Face recognition of a Lorisidae species based on computer vision | |
Coro et al. | Estimating hidden fishing activity hotspots from vessel transmitted data | |
Padmaja et al. | Catching Illegal Fishing Using Random Forest and Linear Regression Models | |
Prabu et al. | An Efficient Automated Water Quality Assessment System utilising Machine Learning and IoT | |
CN116992696B (en) | Fishing gear capturing and damage monitoring method and system based on digital twinning | |
Carpentieri et al. | Third Workshop on appropriate sampling schemes for Protected, Endangered and Threatened Species bycatch (WKPETSAMP3) | |
CN117671614A (en) | Evidence chain collection and display system and method based on multi-equipment linkage | |
CN118506356A (en) | Automatic detection method, device, medium and equipment for comprehensive treatment of food safety |