CN117058630A - Coastal ship identification methods, systems, equipment and storage media - Google Patents
Coastal ship identification methods, systems, equipment and storage media Download PDFInfo
- Publication number
- CN117058630A CN117058630A CN202310848035.XA CN202310848035A CN117058630A CN 117058630 A CN117058630 A CN 117058630A CN 202310848035 A CN202310848035 A CN 202310848035A CN 117058630 A CN117058630 A CN 117058630A
- Authority
- CN
- China
- Prior art keywords
- image information
- coastal
- prevention
- identified
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
本申请公开了一种海岸船舶识别方法、系统、设备及存储介质，其中，海岸船舶识别方法，包括：获取训练数据集，所述数据集至少包括标签数据和/或目标值数据；将所述训练数据集输入至深度学习模型生成海岸防控识别模型；获取待识别图像信息，将所述获取待识别图像信息输入至所述海岸防控识别模型，输出目标位置和类别信息。该方法通过训练生成的海岸防控识别模型，利用待识别的图像信息，输出识别图像中船只目标位置和类别信息，提高了模型的识别效率、准确性和响应能力，帮助实现更安全、智能的监控和安全管理。
This application discloses a coastal ship identification method, system, equipment and storage medium. The coastal ship identification method includes: obtaining a training data set, the data set at least includes label data and/or target value data; The training data set is input into the deep learning model to generate a coastal prevention and control recognition model; the image information to be identified is obtained, the obtained image information to be identified is input into the coastal prevention and control identification model, and the target location and category information are output. This method generates a coastal prevention and control recognition model through training, uses the image information to be recognized, and outputs the target position and category information of the ship in the recognition image, which improves the recognition efficiency, accuracy and responsiveness of the model, and helps achieve safer and smarter Monitoring and security management.
Description
Technical Field
The application relates to the technical field of information, in particular to a coast ship identification method, a coast ship identification system, coast ship identification equipment and a coast ship identification storage medium.
Background
Due to the limitation of manual observation and analysis, the traditional video monitoring system is easy to have the problems of false alarm and missing report. The operator may have inaccurate decisions on abnormal events due to fatigue, line of sight misalignment, or neglecting fine details. And the traditional video monitoring system generally adopts a video recording mode to store data. For a large amount of monitoring data, management and retrieval becomes difficult. The operator needs to spend a lot of time and effort to find video data for a specific period of time. That is, the conventional video monitoring system has the disadvantages of human dependency, false alarm missing report, difficult data management, inefficient event processing, limited analysis capability, limited remote management, and the like.
Disclosure of Invention
In view of the foregoing drawbacks or shortcomings in the prior art, it is desirable to provide a coast vessel identification method, system, apparatus, and storage medium.
In one aspect, the present application provides a method for identifying a coastal vessel, comprising:
acquiring a training data set, wherein the data set at least comprises label data and/or target value data;
inputting the training data set into a deep learning model to generate a coast prevention and control recognition model; and acquiring the image information to be identified, inputting the image information to be identified into the coast prevention and control identification model, and outputting the target position and the category information.
In some embodiments, obtaining the image information to be identified, inputting the image information to be identified to the coast prevention and control identification model, and outputting the target position and the category information, and further comprising:
detecting the image information to be identified;
when the image information to be identified has a preset target, outputting target position and category information;
and when the image information to be identified does not have the preset target, continuing searching the image information to be identified.
In some embodiments, a training dataset is obtained, said dataset comprising at least tag data and/or target value data, further comprising, prior to:
preprocessing the training data set, wherein the preprocessing at least comprises one or more of the following: normalization, standardization and enhancement treatment to improve training effect of the model.
In some embodiments, the image information to be identified is acquired, the image information to be identified is input to the coast prevention and control identification model, and the target position and the category information are output, specifically:
the image information to be identified is video information and/or image information.
In some embodiments, the inputting the training data set into a deep learning model to generate a coast prevention and control recognition model further comprises:
acquiring a verification data set;
inputting the verification data set into a coast prevention and control identification model to generate an evaluation index, wherein the evaluation index at least comprises one or more of the following: accuracy, precision, recall;
and when the evaluation index is larger than a preset threshold value, generating a coast prevention and control identification model.
In some embodiments, the validation data set is input into a coast protection and control recognition model, generating an evaluation index comprising at least one or more of: accuracy, precision, recall rate, still include:
and when the evaluation index is smaller than a preset threshold value, generating a coast prevention and control identification model again based on the training data set input.
In a second aspect, the present application provides a coastal vessel identification system comprising:
the acquisition module is used for acquiring a training data set, and the data set at least comprises label data and/or target value data;
the generation module is used for inputting the training data set into a deep learning model to generate a coast prevention and control recognition model;
the output module is used for acquiring the image information to be identified, inputting the acquired image information to be identified into the coast prevention and control identification model, and outputting the target position and the category information.
In some embodiments, the output module further comprises:
detecting the image information to be identified;
when the image information to be identified has a preset target, outputting target position and category information;
and when the image information to be identified does not have the preset target, continuing searching the image information to be identified.
In a third aspect, the present application also provides an electronic device, including a processor and a memory, where the memory stores at least one instruction, at least one program, a code set or an instruction set, where the instruction, the program, the code set or the instruction set is loaded and executed by the processor to implement the method for identifying a coastal vessel according to the above.
In a fourth aspect, the application also provides a non-transitory computer readable storage medium, characterized in that the instructions in the storage medium, when executed by a processor of a mobile terminal, enable the mobile terminal to perform a method for identifying a coastal vessel according to the above.
In summary, the coast ship identification method, the system, the equipment and the storage medium of the application output the ship target position and the category information in the identification image by training the generated coast prevention and control identification model and utilizing the image information to be identified, thereby improving the identification efficiency, the accuracy and the response capability of the model and helping to realize safer and more intelligent monitoring and safety management.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the detailed description of non-limiting embodiments, made with reference to the accompanying drawings in which:
FIG. 1 is a flow chart of a method for identifying a coastal vessel provided by an embodiment of the present application;
FIG. 2 is a convolutional neural network model diagram provided by an embodiment of the present application;
FIG. 3 is a real-time object detection algorithm provided by an embodiment of the present application;
FIG. 4 is a schematic diagram of output content of the coast prevention and control recognition model according to the embodiment of the application when a plurality of ships are involved;
FIG. 5 is a schematic diagram of a coast prevention and control model output ship class as a cargo ship according to an embodiment of the present application;
FIG. 6 is a schematic diagram of a coast prevention and control model output ship class as an engineering ship according to an embodiment of the present application;
FIG. 7 is a schematic diagram of a coast prevention and control recognition model output ship class as a passenger ship according to an embodiment of the present application;
FIG. 8 is a schematic diagram of a fishing boat according to the class of output vessels of the coast prevention and control recognition model according to the embodiment of the application;
FIG. 9 is a schematic diagram of a coast prevention and control recognition model output ship class as a law enforcement ship provided by an embodiment of the present application;
FIG. 10 is a schematic diagram of a shore protection and control identification model output ship board numbers according to an embodiment of the present application;
FIG. 11 is a block diagram of a coast vessel identification system provided by an embodiment of the present application;
fig. 12 is an internal structure diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The application is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the application and are not limiting of the application. It should be noted that, for convenience of description, only the portions related to the application are shown in the drawings.
It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.
The method can be applied to the field of information technology, and the embodiment of the application is illustrated by a coast ship identification method.
There are a number of categories in the art of ship identification, such as: false alarm and missing report: due to the limitation of manual observation and analysis, the traditional video monitoring system is easy to have the problems of false alarm and missing report. Operators may have inaccurate decisions on abnormal events due to fatigue, line of sight misalignment, or neglect of fine details, resulting in false positives or false negatives. Data management and retrieval difficulties: conventional video monitoring systems typically employ video recording to store data. For a large amount of monitoring data, management and retrieval becomes difficult. The operator needs to spend a lot of time and effort to find video data for a specific period of time, which causes inconvenience in post-investigation and evidence collection. Inefficient event handling: the handling of abnormal events by conventional video surveillance systems typically relies on active observation and judgment by the operator. Operators need to find abnormal events in time and take corresponding treatment measures. However, due to human resources limitations, the efficiency of processing events may be low, especially in large scale monitoring systems, where processing response time may be delayed. Limited analytical capabilities: conventional video surveillance systems lack advanced image processing and analysis functionality. They generally provide only basic video image display and video recording functions, and cannot realize intelligent analysis and identification of monitoring data. This limits the ability of the system to detect abnormal events, target recognition, behavioral analysis, and the like.
Limited remote management: the remote management capability of conventional video surveillance systems is relatively limited. Operators often need to observe and operate in real time at a monitoring center, and cannot flexibly and remotely manage and control the monitoring system. This limits the remote operation and emergency response capabilities of the system.
In summary, the conventional video monitoring system has the disadvantages of manpower dependence, false alarm missing report, difficult data management, inefficient event processing, limited analysis capability, limited remote management, and the like. These problems are particularly pronounced in large-scale monitoring systems.
Referring to fig. 1 in detail, the present application provides a method for identifying a coastal ship, comprising:
s101, acquiring a training data set, wherein the data set at least comprises label data and/or target value data.
Specifically, a training data set is first prepared, which should include collecting actual samples in situ, and labeling the sample set and corresponding labels or target values (e.g., classification labels, regression targets, etc.).
In some embodiments, a training dataset is obtained, said dataset comprising at least tag data and/or target value data, further comprising, prior to:
preprocessing the training data set, wherein the preprocessing at least comprises one or more of the following: normalization, standardization and enhancement treatment to improve training effect of the model.
Specifically, the data set is preprocessed, so that the effect of subsequent model training is improved, and the preprocessing process comprises operations such as data normalization, normalization or enhancement.
S102, inputting the training data set into a deep learning model to generate a coast prevention and control recognition model.
Specifically, the selection of an appropriate network architecture is important for training of deep learning models. Common network architectures include convolutional neural networks (Convolutional Neural Networks, CNN) for image processing, cyclic neural networks (Recurrent Neural Networks, RNN) for sequence data processing, and transducers (transducers) for natural language processing. The convolutional neural network is preferably selected for training, and the convolutional neural network model is shown in fig. 2. In other embodiments, the selection of the network may be adjusted based on the nature of the task and the characteristics of the data set.
First, a loss function is selected: the difference between the model predictive result and the real label is measured by selecting an appropriate loss function according to the task type. For example, classification problems typically use cross entropy loss functions, regression problems may use mean square error loss functions, where cross entropy loss functions are typically used.
Secondly, initializing parameters: parameters in the network are initialized. Random initialization and pre-training model initialization can be selected for initialization, and the initialization method is selected to help the model to converge faster and better fit data.
Further, forward propagation is adopted, through inputting the training data obtained in advance into a network architecture, forward propagation is carried out layer by layer from an input layer, and an output result of the network is calculated.
Then, the loss is calculated: the output of the network is compared with the real label and a loss value is calculated, where the loss value represents the magnitude of the model predicted error.
And then back-propagating, and calculating the gradient of the loss function to the network parameters through a back-propagation algorithm. The gradient represents the rate of change of the loss function with respect to a parameter from which the update direction can be adjusted.
Therefore, the parameter optimization is performed, for example, a gradient descent optimization algorithm is preferably adopted, and the parameters of the network are updated according to the gradient of the parameters so as to minimize the loss function, so that the prediction result of the model is more similar to the real label.
Finally, repeating forward propagation, loss calculation, backward propagation and parameter optimization operations until a preset iteration number or a preset loss function convergence is reached. Thereby generating a coast prevention and control recognition model.
In some embodiments, the inputting the training data set into a deep learning model to generate a coast prevention and control recognition model further comprises:
acquiring a verification data set;
inputting the verification data set into a coast prevention and control identification model to generate an evaluation index, wherein the evaluation index at least comprises one or more of the following: accuracy, precision, recall;
and when the evaluation index is larger than a preset threshold value, generating a coast prevention and control identification model.
Specifically, a validation dataset with data tags is obtained, the validation dataset comprising at least a live sample, and a labeled sample set and corresponding tags or targets (e.g., classification tags, regression targets, etc.). Adding the verification data set to the trained coast prevention and control recognition model to generate evaluation data, wherein the evaluation data at least comprises one or more of the following: accuracy, precision, recall. And outputting the coast prevention and control recognition model when all indexes of the evaluation data are within a preset range.
In some embodiments, the validation data set is input into a coast protection and control recognition model, generating an evaluation index comprising at least one or more of: accuracy, precision, recall rate, still include:
and when the evaluation index is smaller than a preset threshold value, generating a coast prevention and control identification model again based on the training data set input.
Specifically, the verification data set is added into a trained coast prevention and control recognition model to generate evaluation data, and the evaluation data at least comprises one or more of the following: accuracy, precision, recall. And when one of the indexes of the evaluation data is not in the preset range, training the coast prevention and control identification model again.
S103, obtaining image information to be identified, inputting the obtained image information to be identified into the coast prevention and control identification model, and outputting target position and category information.
Specifically, the image information to be identified is acquired, so that the image information is input into a pre-trained coast prevention and control identification model, and the target position and category information are output. The coast prevention and control recognition model uses a deep learning model, and improves the model performance through training data with larger scale and diversity, thereby improving the recognition accuracy of complex scenes, illumination changes, shielding and other conditions. The category information is different ship categories such as cargo ships, engineering ships, passenger ships, fishing ships, law enforcement ships, etc., as shown in fig. 5, 6, 7, 8, and 9, respectively.
For example, an image to be identified is input, which is 416×416×3, three prediction results with different scales are obtained through a dark network, each scale corresponds to N channels, and includes predicted information, and a real-time object detection algorithm is shown in fig. 3. YOLOv3 has a total of 13 x 3+26 x 26 x 3+52 x 52 x 3 predictions. Each prediction corresponds to 6 dimensions, 4 (coordinate values), 1 (confidence score), 1 (category number), respectively.
In a specific embodiment, when there are a plurality of ships in the image information to be recognized, the output content is as shown in fig. 4.
In other embodiments, the acquiring the image information to be identified is input to the coast prevention and control identification model, and the outputting information further includes: and (5) a ship board number. For example, the ship board identification is shown in fig. 10.
In some embodiments, obtaining the image information to be identified, inputting the image information to be identified to the coast prevention and control identification model, and outputting the target position and the category information, and further comprising:
detecting the image information to be identified;
when the image information to be identified has a preset target, outputting target position and category information;
and when the image information to be identified does not have the preset target, continuing searching the image information to be identified.
Specifically, the pre-trained coast prevention and control recognition model is utilized to input the image information to be recognized, and when the preset target does not exist in the current image information, the target position and the category information are not output, and the image information is continuously searched. And outputting the target position and the category information after the current image continues to have the preset target.
In some embodiments, the image information to be identified is acquired, the image information to be identified is input to the coast prevention and control identification model, and the target position and the category information are output, specifically:
the image information to be identified is video information and/or image information.
Specifically, the image information to be identified may be obtained as video information or image information.
In some embodiments, the coast vessel identification method further comprises: and when the target position and the category information are abnormal, sending out alarm information.
Specifically, when the ship target position approaches the coast or the target positions of two ships approach each other or the ship class information is the high-level ship, alarm information is sent out so as to remind. By way of example, images or video streams in the surveillance video may be analyzed by the model to automatically detect and identify abnormal behavior, events or objects. The method can identify abnormal moving modes, abnormal objects, dangerous behaviors and the like, so that real-time abnormal detection and early warning are realized, and a user is helped to quickly find potential security threats.
In summary, the coast ship identification method provided by the application utilizes the image information to be identified to output the ship target position and the category information in the identification image through the coast prevention and control identification model generated by training, improves the identification efficiency, accuracy and response capability of the model, and helps to realize safer and more intelligent monitoring and safety management.
With further reference to fig. 11, there is shown a coast vessel identification system 200 according to the present disclosure comprising: an acquisition module 210, a generation module 220, and an output module 230.
An acquisition module 210 for acquiring a training dataset, the dataset comprising at least tag data and/or target value data;
a generating module 220, configured to input the training data set to a deep learning model to generate a coast prevention and control recognition model;
the output module 230 is configured to obtain image information to be identified, input the obtained image information to the coast prevention and control identification model, and output target position and category information.
In some embodiments, the output module 230 further comprises:
detecting the image information to be identified;
when the image information to be identified has a preset target, outputting target position and category information;
and when the image information to be identified does not have the preset target, continuing searching the image information to be identified.
According to the coast ship identification system provided by the application, the coast prevention and control identification model generated through training is utilized, the image information to be identified is utilized to output the ship target position and the category information in the identification image, the identification efficiency, accuracy and response capability of the model are improved, and safer and more intelligent monitoring and safety management are facilitated.
The division of the modules or units mentioned in the above detailed description is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit in accordance with embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation instructions of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, blocks shown in two separate connections may in fact be performed substantially in parallel, or they may sometimes be performed in the reverse order, depending on the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. The above description is only illustrative of the preferred embodiments of the present application and of the principles of the technology employed. It will be appreciated by persons skilled in the art that the scope of the disclosure referred to in the present application is not limited to the specific combinations of technical features described above, but also covers other technical features which may be formed by any combination of the technical features described above or their equivalents without departing from the spirit of the disclosure. Such as the above-mentioned features and the technical features disclosed in the present application (but not limited to) having similar functions are replaced with each other.
In one embodiment, an electronic device is provided, which may be a terminal, and an internal structure diagram thereof may be as shown in fig. 12. The electronic device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the electronic device is configured to provide computing and control capabilities. The memory of the electronic device includes a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, an operator network, near Field Communication (NFC) or other technologies. The computer program when executed by a processor implements a security situation aware asset vulnerability prediction method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in FIG. 12 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, the coast vessel identification system provided by the present application may be implemented in the form of a computer program that is executable on an electronic device as shown in fig. 3. The memory of the electronic device may store various program modules that make up the coast ship identification system.
The memory in the electronic device stores at least one instruction, at least one program, a code set, or an instruction set, where the instruction, the program, the code set, or the instruction set is loaded and executed by the processor to implement the method for identifying a coastal vessel according to any one of the embodiments, for example, implement a method for identifying a coastal vessel, including: acquiring a training data set, wherein the data set at least comprises label data and/or target value data; inputting the training data set into a deep learning model to generate a coast prevention and control recognition model; and acquiring the image information to be identified, inputting the image information to be identified into the coast prevention and control identification model, and outputting the target position and the category information.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of: acquiring a training data set, wherein the data set at least comprises label data and/or target value data; inputting the training data set into a deep learning model to generate a coast prevention and control recognition model; and acquiring the image information to be identified, inputting the image information to be identified into the coast prevention and control identification model, and outputting the target position and the category information.
In one embodiment, a computer program product is provided, which when executed by a processor of a mobile terminal, causes the mobile terminal to perform the steps of: acquiring a training data set, wherein the data set at least comprises label data and/or target value data; inputting the training data set into a deep learning model to generate a coast prevention and control recognition model; and acquiring the image information to be identified, inputting the image information to be identified into the coast prevention and control identification model, and outputting the target position and the category information.
Those skilled in the art will appreciate that implementing all or part of the above-described methods may be accomplished by way of a computer program, which may be stored on a non-transitory computer readable storage medium, that when executed may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, or the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static random access memory (Static Random Access Memory, SRAM), dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features of each of the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
Unless defined otherwise, technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. The terminology used herein is for the purpose of describing particular implementations only and is not intended to be limiting of the application. Terms such as "disposed" or the like as used herein may refer to either one element being directly attached to another element or one element being attached to another element through an intermediate member. Features described herein in one embodiment may be applied to another embodiment alone or in combination with other features unless the features are not applicable or otherwise indicated in the other embodiment.
The present application has been described in terms of the above embodiments, but it should be understood that the above embodiments are for purposes of illustration and description only and are not intended to limit the application to the embodiments described. Those skilled in the art will appreciate that many variations and modifications are possible in light of the teachings of the application, which variations and modifications are within the scope of the application as claimed.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310848035.XA CN117058630A (en) | 2023-07-11 | 2023-07-11 | Coastal ship identification methods, systems, equipment and storage media |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310848035.XA CN117058630A (en) | 2023-07-11 | 2023-07-11 | Coastal ship identification methods, systems, equipment and storage media |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117058630A true CN117058630A (en) | 2023-11-14 |
Family
ID=88659737
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310848035.XA Pending CN117058630A (en) | 2023-07-11 | 2023-07-11 | Coastal ship identification methods, systems, equipment and storage media |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117058630A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117876979A (en) * | 2024-01-18 | 2024-04-12 | 亿海蓝（北京）数据技术股份公司 | Image-based ship behavior detection method, device and storage medium |
| CN117975144A (en) * | 2024-02-02 | 2024-05-03 | 北京视觉世界科技有限公司 | Target information identification method, device, equipment and storage medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114140753A (en) * | 2021-11-29 | 2022-03-04 | 广州中科智巡科技有限公司 | Method, device and system for marine ship identification |
-
2023
- 2023-07-11 CN CN202310848035.XA patent/CN117058630A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114140753A (en) * | 2021-11-29 | 2022-03-04 | 广州中科智巡科技有限公司 | Method, device and system for marine ship identification |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117876979A (en) * | 2024-01-18 | 2024-04-12 | 亿海蓝（北京）数据技术股份公司 | Image-based ship behavior detection method, device and storage medium |
| CN117975144A (en) * | 2024-02-02 | 2024-05-03 | 北京视觉世界科技有限公司 | Target information identification method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101995107B1 (en) | Method and system for artificial intelligence based video surveillance using deep learning | |
| Wang et al. | A real-time deep learning forest fire monitoring algorithm based on an improved Pruned+ KD model | |
| EP3673411B1 (en) | Adaptive real-time detection and examination network (arden) | |
| US20220327335A1 (en) | Controlling asynchronous fusion of spatio-temporal multimodal data | |
| US20170032262A1 (en) | Enterprise hypothesis orchestration | |
| CN110309779A (en) | Assemble monitoring method, device and the electronic equipment of part operational motion in scene | |
| CN117058630A (en) | Coastal ship identification methods, systems, equipment and storage media | |
| CN117874678A (en) | Track abnormity judging method based on sliding window algorithm | |
| CN117745758A (en) | Unmanned high-speed boat swarm target tracking method for offshore environment | |
| CN117475266A (en) | Robot visual perception method and device based on multi-expert attention fusion | |
| Toprak et al. | Ship Detection from Optical Satellite Images Using Convolutional Neural Networks | |
| Guggilam et al. | An expert system for privacy-driven vessel detection harnessing YOLOv8 and strengthened by SHA-256 | |
| CN120258329A (en) | A smart fishery supervision method and system based on multi-source data fusion | |
| Tsekhmystro et al. | Investigation of the effect of object size on accuracy of human localisation in images acquired from unmanned aerial vehicles | |
| Ganesh et al. | Real-time video processing for ship detection using transfer learning | |
| Hao et al. | Ship trajectory anomaly detection based on TCN model | |
| CN118228083A (en) | Fishing boat operation behavior recognition method based on 1DCNN-LSTM | |
| Waskito et al. | Comparison of the Use of YOLOv11 Variations in the Empty Parking Spaces Detection System | |
| Nazarkevych et al. | Method of Dataset Filling and Recognition of Moving Objects in Video Sequences based on YOLO. | |
| den Hollander et al. | Vessel classification for naval operations | |
| Sonntag et al. | Transformer-Based State Estimation for Multi-Target Tracking: Sensitivity Analysis against Varying Kinematic Parameters and Clutter Density | |
| Trung | A comparison of YOLO networks for ship detection and classification from optical remote-sensing images | |
| Choudhary et al. | A Robust Machine Learning Model for Forest Fire Detection Using Drone Images | |
| US20250053784A1 (en) | System and method for generating unified goal representations for cross task generalization in robot navigation | |
| Van Tran et al. | Enhancing Inland Waterway Safety and Management through Machine Learning-Based Ship Detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |