Ship image identification fusion AIS data positioning display method and system

Through camera calibration and AIS data matching, combined with video image recognition and AIS data, the problem of fusion of video surveillance system and AIS data is solved, real-time fusion of ship status information is achieved, and maritime supervision efficiency and positioning accuracy are improved.

CN118968431APending Publication Date: 2024-11-15MINGFEI WEIYE TECH CO LTD

Patent Information

Application Number
CN202410970152.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-19
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

The existing video surveillance system and automatic identification system (AIS) data are difficult to effectively integrate, resulting in the inability of surveillance personnel to directly obtain key information on the ship, reducing the efficiency of maritime supervision.

Method used

Through camera calibration and AIS data matching, combined with video image recognition and AIS data, real-time ship status information fusion is achieved to provide more comprehensive and accurate ship information.

Benefits of technology

It improves the accuracy of ship positioning, realizes the real-time fusion of video surveillance and AIS data, provides more accurate ship information, improves maritime supervision efficiency, and reduces the possibility of mismatch.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118968431A_ABST
    Figure CN118968431A_ABST
Patent Text Reader

Abstract

The invention provides a ship image identification fusion AIS data positioning display method and system, and belongs to the field of ship positioning, and the method comprises the steps: S1, deploying a camera for monitoring a ship, calibrating the camera, and obtaining a calibration camera and the position information of the calibration camera; s2, acquiring target ship video information by using a calibration camera, and identifying the target ship video information to obtain a first target ship information set; s3, calculating first position information of the target ship according to the position information of the calibration camera and the first target ship information; s4, acquiring an AIS data sequence of the target ship, and analyzing the AIS data sequence to obtain a second target ship information set; and S5, matching and associating the first position information of the target ship with the second target ship information set to obtain positioning information of the target ship. Through camera calibration and AIS data matching, the ship positioning precision is improved, video image recognition and AIS data are combined, real-time fusion of video monitoring and AIS data is achieved, real-time ship state information is provided, and more comprehensive and accurate ship information is provided.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of ship positioning, and in particular to a method and system for ship image recognition, fusion of AIS data, positioning and display. Background Art

[0002] As maritime traffic becomes increasingly busy and complex, the requirements for ship monitoring systems are also getting higher and higher. Traditional video monitoring systems play an important role in maritime supervision, which can capture the visual information of ships in real time and provide intuitive reference for maritime management. At the same time, the automatic identification system (AIS), as another important maritime safety technology, can provide detailed information of ships, including key data such as ship position, speed, and heading.

[0003] However, in the existing technology, most video surveillance systems operate independently and are not effectively integrated with AIS data. This results in the monitoring personnel being unable to directly obtain key information about the ship, such as the ship name, call sign, and precise location, when watching the video. In addition, the existing system also has difficulty automatically identifying whether the ship has turned on the AIS system or whether there is any illegal behavior, resulting in the inability to effectively integrate video surveillance information and AIS data, reducing regulatory efficiency and making it difficult to fully cover all regulatory needs.

[0004] Therefore, finding a positioning method that can integrate video surveillance and AIS data and improve the efficiency of maritime supervision is a technical problem that needs to be urgently solved by technical personnel in this field. Summary of the invention

[0005] In view of this, the present invention proposes a method and system for ship image recognition fusion AIS data positioning display, which improves the accuracy of ship positioning through camera calibration and AIS data matching, and combines video image recognition and AIS data to achieve real-time fusion of video monitoring and AIS data, providing real-time ship status information, and providing more comprehensive and accurate ship information.

[0006] The technical solution of the present invention is achieved in this way:

[0007] In a first aspect, the present invention provides a method for ship image recognition fusion AIS data positioning display, comprising the following steps:

[0008] S1. Deploy a camera to monitor the ship, calibrate the camera, and obtain the calibrated camera and location information of the calibrated camera;

[0009] S2. Using a calibrated camera to obtain target ship video information, and identifying the target ship video information to obtain a first target ship information set;

[0010] S3, calculating the first position information of the target ship according to the position information of the calibration camera and the first target ship information;

[0011] S4, obtaining the AIS data sequence of the target ship, and respectively parsing the AIS data sequence to obtain a second target ship information set;

[0012] S5. Match and associate the first position information of the target ship with the second target ship information set to obtain positioning information of the target ship.

[0013] On the basis of the above technical solution, preferably, the elements of the second target ship information set include ship attributes and status information of the target ship, wherein the status information includes ship position, ship name, ship speed, heading and ship number.

[0014] On the basis of the above technical solution, preferably, step S5 specifically includes:

[0015] Calculate the similarity between the first position information of the target ship and the position of the ship in the second target ship information set respectively;

[0016] The ship position with the highest similarity is selected as the best matching AIS data;

[0017] The first ship information is fused with the best matching AIS data to obtain the positioning information of the target ship.

[0018] On the basis of the above technical solution, preferably, the calculation formula of the similarity is:

[0019]

[0020] Among them, S(i,j) represents the similarity between the first position information j of the target ship and the position i of the second target ship information set, (x i ,y i ) represents the position of the ship in the second target ship information set, (x j ,y j ) represents the first position information of the target ship, v i Indicates the speed of the second target ship information set, v j represents the first speed of the target ship, θ i represents the first heading of the target ship, θ j represents the heading of the second target ship information set, σ po represents the standard deviation of the position error, σ ve represents the standard deviation of velocity error, σ he Represents the standard deviation of the heading error.

[0021] More preferably, in step S2, identifying the target ship video information specifically includes:

[0022] Decompose the target ship video information frame by frame to obtain several frames of target ship images;

[0023] Performing image recognition on each frame of the target ship image to obtain first ship information;

[0024] Perform image cropping on the identified target ship image to obtain a target ship picture;

[0025] Perform text recognition on the target ship image to obtain the second ship information.

[0026] On the basis of the above technical solution, preferably, step S3 specifically includes:

[0027] Determine the height and angle of the camera based on the camera's position information, and calculate the vertical position of the target ship within the camera's field of view;

[0028] Calculate the horizontal position of the target ship in the target ship image according to the target ship size in the first ship information and the target ship size in the target ship image;

[0029] Calculate the distance of the target ship relative to the camera according to the position and angle of the camera;

[0030] According to the horizontal position of the target ship in the target ship image and the parameters of the camera, the angle of the target ship relative to the camera is calculated;

[0031] The longitude and latitude coordinates of the target ship are obtained by combining the position of the camera, the distance of the target ship relative to the camera, and the angle of the target ship relative to the camera.

[0032] On the basis of the above technical solution, preferably, the calculation formula of the latitude and longitude coordinates of the target ship is:

[0033] lat p =lat c +(D / R)×cosα;

[0034] lon p =lon c +(D / (R×coslat c ))×sinα;

[0035] Among them, (lat c ,lon c ) represents the latitude and longitude of the camera, (lat p ,lon p ) represents the latitude and longitude coordinates of the target ship, D represents the distance of the target ship relative to the camera, α represents the angle of the target ship relative to the camera, and R represents the radius of the earth.

[0036] In a second aspect, the present invention provides a ship image recognition fusion AIS data positioning display system, which adopts the ship image recognition fusion AIS data positioning display method as described above, including:

[0037] A calibration module is configured to deploy a camera for monitoring a ship and calibrate the camera to obtain the calibration camera and position information of the calibration camera;

[0038] A video recognition module is configured to use a calibrated camera to obtain target ship video information, and recognize the target ship video information to obtain a first target ship information set;

[0039] A first calculation module is configured to calculate first position information of the target ship according to the position information of the calibration camera and the first target ship information;

[0040] A data parsing module, configured to obtain an AIS data sequence of a target ship, and parse the AIS data sequence to obtain a second target ship information set;

[0041] The second calculation module is configured to match and associate the first position information of the target ship with the second target ship information set to obtain the positioning information of the target ship.

[0042] In a third aspect, the present invention provides an electronic device, comprising: at least one processor, at least one memory, a communication interface and a bus; wherein:

[0043] The processor, memory, and communication interface communicate with each other via the bus;

[0044] The memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to implement the ship image recognition fusion AIS data positioning display method as described above.

[0045] In a fourth aspect, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions enable the computer to implement the ship image recognition fusion AIS data positioning and display method as described above.

[0046] Compared with the prior art, the ship image recognition fusion AIS data positioning display method of the present invention has the following beneficial effects:

[0047] (1) The accuracy of ship positioning is improved through camera calibration and AIS data matching. In addition, the real-time fusion of video surveillance and AIS data is achieved by combining video image recognition and AIS data, providing real-time ship status information and more comprehensive and accurate ship information.

[0048] (2) By matching and associating the first position information of the target ship with the second target ship information set, the limitation of a single data source is overcome, more comprehensive and accurate ship information is provided, and similarity is used to ensure that the AIS data and image recognition results can accurately correspond to the same ship, reducing the possibility of mismatching and improving the efficiency of maritime supervision;

[0049] (3) By combining the camera’s location information and the target ship’s image information, the target ship’s latitude and longitude coordinates can be accurately calculated. By comparing the actual ship size with the size in the image, the error caused by the perspective effect can be corrected, the positioning accuracy can be improved, and the ship’s position can be quickly calculated, thus achieving real-time tracking and updating of the ship’s position. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0051] Figure 1 The present invention is a flow chart of the method for positioning and displaying ship image recognition fused with AIS data. DETAILED DESCRIPTION

[0052] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] like Figure 1 As shown, the present invention provides a method for positioning and displaying ship image recognition fusion AIS data, comprising the following steps:

[0054] S1. Deploy a camera to monitor the ship, calibrate the camera, and obtain the calibrated camera and location information of the calibrated camera.

[0055] Among them, the focal length, sensor size, position (latitude and longitude), altitude (relative to the ground or reference plane) and angle (pitch and yaw) of the camera are recorded when the camera is deployed.

[0056] It is understandable that the focal length and sensor size of the camera can be obtained from the camera product specification. The camera can be installed at different positions and angles to suit different types of ships and application requirements.

[0057] In one embodiment of the present application, when calibrating the camera, a checkerboard calibration method may be used for calibration.

[0058] This application does not impose any specific restrictions on the camera calibration method, which can be set according to actual needs.

[0059] S2. Use a calibrated camera to obtain target ship video information, and identify the target ship video information to obtain a first target ship information set.

[0060] In one embodiment of the present application, the calibration camera includes a high-definition network camera and a low-light camera. The high-definition network camera and the low-light camera are used to obtain video information of the target ship in the monitoring area.

[0061] Specifically, step S2 specifically includes:

[0062] Decompose the target ship video information frame by frame to obtain several frames of target ship images;

[0063] Performing image recognition on each frame of the target ship image to obtain first ship information;

[0064] Perform image cropping on the identified target ship image to obtain a target ship picture;

[0065] Perform text recognition on the target ship image to obtain the second ship information.

[0066] The first ship information includes the size of the target ship, the flag hoisting situation (whether the national flag is hoisted), the cargo lock situation (whether the cargo is locked), and the crew wearing life jackets (whether the lifeguard wears life jackets), etc. The second ship information includes the name of the target ship, waterline, and other information.

[0067] In one embodiment of the present application, a YOLOv8 model is used to perform image recognition on a target ship image to obtain first ship information.

[0068] S3, calculating the first position information of the target ship according to the position information of the calibration camera and the first target ship information;

[0069] Specifically, step S3 specifically includes:

[0070] Determine the height and angle of the camera based on the camera's position information, and calculate the vertical position of the target ship within the camera's field of view;

[0071] Calculate the horizontal position of the target ship in the target ship image according to the target ship size in the first ship information and the target ship size in the target ship image;

[0072] Calculate the distance of the target ship relative to the camera according to the position and angle of the camera;

[0073] According to the horizontal position of the target ship in the target ship image and the parameters of the camera, the angle of the target ship relative to the camera is calculated;

[0074] The longitude and latitude coordinates of the target ship are obtained by combining the position of the camera, the distance of the target ship relative to the camera, and the angle of the target ship relative to the camera.

[0075] By combining the camera's location information and the target ship's image information, the actual geographic location (latitude and longitude coordinates) of the target ship can be accurately calculated, and by comparing the actual ship size with the size in the image, the error caused by the perspective effect can be corrected, the positioning accuracy can be improved, and the ship's position can be quickly calculated to achieve real-time tracking and updating of the ship's position.

[0076] In an embodiment of the present application, step S3 further includes:

[0077] When an error occurs in calculating the latitude and longitude coordinates of the target ship, the latitude and longitude coordinates of the target ship are further calculated using the percentage difference.

[0078] Among them, percentage error = |(measured value - reference value) / reference value|*100,

[0079] Then the actual accurate value of the target ship = measured value / (1-percent error / 100).

[0080] The measured value is the latitude and longitude position of the target ship in the first target ship information, and the reference value is the reference point coordinate of the known position.

[0081] In one embodiment of the present application, the calculation formula for the distance of the target ship relative to the camera is:

[0082]

[0083] Among them, (x1, y1) represents the horizontal distance of the target ship relative to the camera, and (x2, y2) represents the vertical distance of the target ship relative to the camera.

[0084] In one embodiment of the present application, the angle of the target ship relative to the camera is calculated according to the horizontal position of the target ship in the target ship image and the parameters of the camera, specifically including:

[0085] The pixel coordinates of the target ship in the target ship image are (u, v), the optical center of the calibration camera is (Cx, Cy), and the intrinsic parameter matrix of the calibration camera is:

[0086]

[0087] Where fx and fy represent the focal length of the calibration camera in the x-direction and y-direction respectively;

[0088] The pixel coordinates (u, v) of the target ship in the target ship image are converted to camera coordinates. The calculation formula is as follows:

[0089]

[0090] Among them, (Xc, Yc) represents the camera coordinates of the target ship, K -1 Represents the inverse matrix of the calibration camera intrinsic parameter matrix K;

[0091] Then the angle of the target ship relative to the camera is:

[0092] α=atan 2 (-Yc, Xc)

[0093] It can be understood that the intrinsic parameters of the calibration camera are determined when the camera is calibrated.

[0094] Furthermore, the calculation formula of the latitude and longitude coordinates of the target ship is:

[0095] lat p =lat c +(D / R)×cosα

[0096] lon p =lon c +(D / (R×coslat c ))×sinα

[0097] Among them, (lat c ,lon c ) represents the latitude and longitude of the camera, (lat p ,lon p ) represents the latitude and longitude coordinates of the target ship, D represents the distance of the target ship relative to the camera, α represents the angle of the target ship relative to the camera, and R represents the radius of the earth.

[0098] S4. Acquire the AIS data sequence of the target ship, and parse the AIS data sequence to obtain a second target ship information set; wherein the status information includes the ship position, ship name, ship speed, heading and ship number.

[0099] In one embodiment of the present application, obtaining the AIS data sequence of the target ship specifically includes:

[0100] Use the AIS receiver to obtain the receiving latitude and longitude (lat, lon) of the target ship;

[0101] The distance p between the ship position identified by the image and the ship position acquired by the AIS receiver is obtained according to the receiving longitude and latitude coordinates and the longitude and latitude coordinates of the target ship;

[0102] Calculate the distance between the ship position identified by the image and the ship position received by all nearby AIS receivers;

[0103] The minimum distance is taken as the AIS information of the target ship.

[0104] The calculation formula of distance p is as follows:

[0105]

[0106] In an embodiment of the present application, parsing the AIS data sequence specifically includes:

[0107] Obtain the original data stream through the AIS receiving device and confirm whether the original data stream conforms to the NMEA 0183 standard format:

[0108] If it matches, the data stream is split into independent NMEA sentences, and the checksum of each NMEA sentence is calculated;

[0109] Compare the calculated checksum with the checksum provided in the statement to ensure data integrity;

[0110] Parse the prefix of the NMEA sentence, determine the specific AIS message type, and decode the payload portion of the NMEA sentence into raw binary data;

[0111] According to the specifications of different message types, the values ​​of each field are extracted from the binary data according to the predefined field length and position, and the binary data is converted into readable text. The value of the field can be an integer (such as MMSI number), a floating point number (such as latitude and longitude, speed), a string (such as ship name), a date and time (such as a timestamp), etc.

[0112] S5. Match and associate the first position information of the target ship with the second target ship information set to obtain positioning information of the target ship.

[0113] It can be understood that the second target ship information set provided by AIS data can supplement the deficiencies of image recognition, and image recognition can verify and supplement AIS data to improve the accuracy of the overall information.

[0114] In the embodiment of the present application, by matching and associating the first position information of the target ship and the second target ship information set, a connection between the AIS data and the image recognition data is established, and it is determined that the results of the AIS data and the image recognition refer to the same ship.

[0115] Specifically, step S5 specifically includes:

[0116] Calculate the similarity between the first position information of the target ship and the position of the ship in the second target ship information set respectively;

[0117] The ship position with the highest similarity is selected as the best matching AIS data;

[0118] The first ship information is fused with the best matching AIS data to obtain the positioning information of the target ship.

[0119] By matching and associating the first position information of the target ship with the second target ship information set, the limitation of a single data source is overcome, more comprehensive and accurate ship information is provided, and similarity is used to ensure that AIS data and image recognition results can accurately correspond to the same ship, reducing the possibility of mismatching and improving the efficiency of maritime supervision.

[0120] Furthermore, the calculation formula of the similarity is:

[0121]

[0122] Among them, S(i,j) represents the similarity between the first position information j of the target ship and the position i of the second target ship information set, (x i ,y i ) represents the position of the ship in the second target ship information set, (x j ,y j ) represents the first position information of the target ship, v i Indicates the speed of the second target ship information set, v j represents the first speed of the target ship, θ i represents the first heading of the target ship, θ j represents the heading of the second target ship information set, σ po represents the standard deviation of the position error, σ ve represents the standard deviation of velocity error, σ he Represents the standard deviation of the heading error.

[0123] The standard deviation of position error, speed error and heading error are obtained by analyzing historical data.

[0124] This application improves the accuracy of ship positioning through camera calibration and AIS data matching, and combines video image recognition and AIS data to achieve real-time fusion of video surveillance and AIS data, providing near real-time ship status information and more comprehensive and accurate ship information.

[0125] In one embodiment of the present application, the method for ship image recognition fusion AIS data positioning display further includes:

[0126] S6. Display the positioning information of the target ship in the video image of the target ship by superimposing characters, so as to realize data visualization and sharing.

[0127] By visualizing the positioning information of the target ship, the instant combination of visual information and data information is achieved, the real-time monitoring capability is enhanced, and through intuitive data display, regulators can quickly obtain and understand ship information, more easily identify abnormal situations, and improve supervision efficiency.

[0128] In one embodiment of the present application, the position information in the positioning information of the target ship is superimposed on the video screen of the target ship through video processing technology to ensure that the text and the video screen are synchronized, and the superimposed information is updated in real time according to the real-time positioning information of the target ship to reflect the changes in the position, speed, etc. of the target ship, and ensure the smoothness of the information update to avoid screen jitter or flickering.

[0129] The present invention also provides a ship image recognition fusion AIS data positioning display system, which adopts the ship image recognition fusion AIS data positioning display method as described above, and comprises:

[0130] A calibration module is configured to deploy a camera for monitoring a ship and calibrate the camera to obtain the calibration camera and position information of the calibration camera;

[0131] A video recognition module is configured to use a calibrated camera to obtain target ship video information, and recognize the target ship video information to obtain a first target ship information set;

[0132] A first calculation module is configured to calculate first position information of the target ship according to the position information of the calibration camera and the first target ship information;

[0133] A data parsing module, configured to obtain an AIS data sequence of a target ship, and parse the AIS data sequence to obtain a second target ship information set;

[0134] The second calculation module is configured to match and associate the first position information of the target ship with the second target ship information set to obtain the positioning information of the target ship.

[0135] The present invention also provides an electronic device, comprising: at least one processor, at least one memory, a communication interface and a bus; wherein the processor, the memory and the communication interface communicate with each other through the bus; the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to implement the ship image recognition fusion AIS data positioning display method as described above.

[0136] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions enable the computer to implement the ship image recognition fusion AIS data positioning display method as described above.

[0137] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for ship image recognition and AIS data positioning display, It is characterized in that The following steps are involved: S1. Deploy a camera to monitor the ship, calibrate the camera, and obtain the calibrated camera and location information of the calibrated camera; S2. Using a calibrated camera to obtain target ship video information, and identifying the target ship video information to obtain a first target ship information set; S3, calculating the first position information of the target ship according to the position information of the calibration camera and the first target ship information; S4, obtaining the AIS data sequence of the target ship, and respectively parsing the AIS data sequence to obtain a second target ship information set; S5. Match and associate the first position information of the target ship with the second target ship information set to obtain positioning information of the target ship.

2. A method for ship image recognition fusion AIS data positioning display as claimed in claim 1, It is characterized in that The elements of the second target ship information set include ship attributes and status information of the target ship, wherein the status information includes ship position, ship name, ship speed, heading and ship number.

3. A method for ship image recognition fusion AIS data positioning display as claimed in claim 2, It is characterized in that Step S5 specifically includes: Calculate the similarity between the first position information of the target ship and the position of the ship in the second target ship information set respectively; The ship position with the highest similarity is selected as the best matching AIS data; The first ship information is fused with the best matching AIS data to obtain the positioning information of the target ship.

4. A method for ship image recognition fusion AIS data positioning display as claimed in claim 3, It is characterized in that The calculation formula of the similarity is: Among them, S(i,j) represents the similarity between the first position information j of the target ship and the position i of the second target ship information set, (x i ,y i ) represents the position of the ship in the second target ship information set, (x j ,y j ) represents the first position information of the target ship, v i Indicates the speed of the second target ship information set, v j represents the first speed of the target ship, θ i represents the first heading of the target ship, θ j represents the heading of the second target ship information set, σ po represents the standard deviation of the position error, σ ve represents the standard deviation of velocity error, σ he Represents the standard deviation of the heading error.

5. A method for ship image recognition fusion AIS data positioning display as claimed in claim 1, It is characterized in that In step S2, the target ship video information is identified, specifically including: Decompose the target ship video information frame by frame to obtain several frames of target ship images; Performing image recognition on each frame of the target ship image to obtain first ship information; Perform image cropping on the identified target ship image to obtain a target ship picture; Perform text recognition on the target ship image to obtain the second ship information.

6. A method for ship image recognition fusion AIS data positioning display as claimed in claim 5, It is characterized in that Step S3 specifically includes: Determine the height and angle of the camera based on the camera's position information, and calculate the vertical position of the target ship within the camera's field of view; Calculate the horizontal position of the target ship in the target ship image according to the target ship size in the first ship information and the target ship size in the target ship image; Calculate the distance of the target ship relative to the camera according to the position and angle of the camera; According to the horizontal position of the target ship in the target ship image and the parameters of the camera, the angle of the target ship relative to the camera is calculated; The longitude and latitude coordinates of the target ship are obtained by combining the position of the camera, the distance of the target ship relative to the camera, and the angle of the target ship relative to the camera.

7. A method for ship image recognition fusion AIS data positioning display as claimed in claim 6, It is characterized in that The calculation formula of the latitude and longitude coordinates of the target ship is: years p =years c +(D / R)×cosα; lon p =on c +(D / (R×coslat c ))×sinα; Among them, (lat c ,lon c ) represents the latitude and longitude of the camera, (lat p ,lon p ) represents the latitude and longitude coordinates of the target ship, D represents the distance of the target ship relative to the camera, α represents the angle of the target ship relative to the camera, and R represents the radius of the earth.

8. A ship image recognition fusion AIS data positioning display system, It is characterized in that The method for positioning and displaying ship image recognition and fusion of AIS data as claimed in any one of claims 1 to 7 comprises: A calibration module is configured to deploy a camera for monitoring a ship and calibrate the camera to obtain the calibration camera and position information of the calibration camera; A video recognition module is configured to use a calibrated camera to obtain target ship video information, and recognize the target ship video information to obtain a first target ship information set; A first calculation module is configured to calculate first position information of the target ship according to the position information of the calibration camera and the first target ship information; A data parsing module, configured to obtain an AIS data sequence of a target ship, and parse the AIS data sequence to obtain a second target ship information set; The second calculation module is configured to match and associate the first position information of the target ship with the second target ship information set to obtain the positioning information of the target ship.

9. An electronic device, It is characterized in that include: At least one processor, at least one memory, a communication interface and a bus; wherein, The processor, memory, and communication interface communicate with each other via the bus; The memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to implement the ship image recognition fusion AIS data positioning and display method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions enable the computer to implement the ship image recognition fusion AIS data positioning and display method according to any one of claims 1 to 7.

Citation Information

Patent Citations

  • Remote sensing image automatic data annotation method based on AIS data retrieval

    CN114625911A

  • Ship information display method and system based on computer vision, AIS and radar

    CN114821493A

  • Ship identification method and device based on Beidou satellite navigation system and artificial intelligence video analysis

    CN115205372A

  • Multi-ship target tracking identification method and device, electronic equipment and storage medium

    CN116129332A

  • Ship identity recognition method based on fusion of AIS data and video data

    US20210073573A1

Cited By

  • Ship marine target sensing method and system based on machine vision

    CN119888188A

  • Multi-source data fusion-based radar-assisted camera ship positioning method and device

    CN119936869A

  • Method and apparatus for ship positioning using a radar-assisted camera based on multi-source data fusion

    CN119936869B