CN112394349A - Intelligent security monitoring method, device and system for ocean buoy and storage medium - Google Patents

Intelligent security monitoring method, device and system for ocean buoy and storage medium Download PDF

Info

Publication number
CN112394349A
CN112394349A CN202011229254.2A CN202011229254A CN112394349A CN 112394349 A CN112394349 A CN 112394349A CN 202011229254 A CN202011229254 A CN 202011229254A CN 112394349 A CN112394349 A CN 112394349A
Authority
CN
China
Prior art keywords
radar sensor
moving
moving object
buoy
suspicious object
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.)
Granted
Application number
CN202011229254.2A
Other languages
Chinese (zh)
Other versions
CN112394349B (en
Inventor
覃朝东
范光伟
杨跃
陈伟昌
韦三刚
张兵
赖杭
张彬培
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Pearl River Hydraulic Research Institute of PRWRC
Original Assignee
Pearl River Hydraulic Research Institute of PRWRC
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Pearl River Hydraulic Research Institute of PRWRC filed Critical Pearl River Hydraulic Research Institute of PRWRC
Priority to CN202011229254.2A priority Critical patent/CN112394349B/en
Publication of CN112394349A publication Critical patent/CN112394349A/en
Application granted granted Critical
Publication of CN112394349B publication Critical patent/CN112394349B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/02—Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
    • G01S13/50—Systems of measurement based on relative movement of target
    • G01S13/58—Velocity or trajectory determination systems; Sense-of-movement determination systems
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/02—Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
    • G01S13/50—Systems of measurement based on relative movement of target
    • G01S13/58—Velocity or trajectory determination systems; Sense-of-movement determination systems
    • G01S13/583—Velocity or trajectory determination systems; Sense-of-movement determination systems using transmission of continuous unmodulated waves, amplitude-, frequency-, or phase-modulated waves and based upon the Doppler effect resulting from movement of targets
    • G01S13/584—Velocity or trajectory determination systems; Sense-of-movement determination systems using transmission of continuous unmodulated waves, amplitude-, frequency-, or phase-modulated waves and based upon the Doppler effect resulting from movement of targets adapted for simultaneous range and velocity measurements
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/02—Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
    • G01S13/50—Systems of measurement based on relative movement of target
    • G01S13/58—Velocity or trajectory determination systems; Sense-of-movement determination systems
    • G01S13/62—Sense-of-movement determination
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/86—Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/88—Radar or analogous systems specially adapted for specific applications
    • G01S13/886—Radar or analogous systems specially adapted for specific applications for alarm systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • 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

Abstract

The invention discloses an intelligent security monitoring method, device and system for an ocean buoy and a storage medium, wherein the method comprises the following steps: reading the electronic compass in real time, and acquiring the current posture of the buoy; when the buoy is kept at a horizontal position, the radar sensor is opened at a fixed time to detect the movement speed and the movement direction of the moving object and the distance between the moving object and the radar sensor; calculating the self movement speed of the radar sensor at the current moment, and correcting the movement speed of the moving object; judging whether the moving object is a suspicious object or not according to the moving speed and the moving direction of the moving object, and if so, starting a camera to shoot the suspicious object; and identifying the suspicious object image, judging whether the suspicious object is an invading ship or not, if so, sending alarm information and the ship image to a remote server, and starting an audible and visual alarm to warn on site. The invention can obtain evidence through shooting on one hand, and ensure the reliability and accuracy of the detection result on the other hand.

Description

Intelligent security monitoring method, device and system for ocean buoy and storage medium
Technical Field
The invention relates to an intelligent security monitoring method, device and system for an ocean buoy and a storage medium, and belongs to the field of security monitoring of ocean buoys.
Background
The marine buoy is an automatic marine hydrographic water quality meteorological observation station which is mainly composed of an observation buoy anchored on the sea, can continuously perform online measurement for a long time by observation, can collect meteorological and hydrological data, particularly can collect data of severe weather and sea conditions which are difficult to collect by an investigation ship, and collects marine hydrographic water quality meteorological data required by marine scientific research, marine oil (gas) development, port construction and national defense construction.
The ocean buoy is usually loaded with scientific measuring instruments such as water quality monitoring, relies on solar energy and battery power supply, works in an unattended state for a long time, cannot use means such as video control, meets emergencies such as ship collision, maliciously steals, can't obtain relevant information in time, causes measured data to break, and even equipment loses.
Disclosure of Invention
In view of the above, the invention provides an intelligent security monitoring method, an intelligent security monitoring device, an intelligent security monitoring system and a storage medium for an ocean buoy, which are characterized in that a suspicious object is rapidly scanned by a radar sensor, then a camera is started to shoot, and whether an intruding ship exists is judged by a main control board, so that on one hand, evidence can be obtained by shooting, and on the other hand, the reliability and the accuracy of a detection result are ensured.
The invention aims to provide an intelligent security monitoring method for an ocean buoy.
The invention also provides an intelligent security monitoring device for the ocean buoy.
The invention also provides an intelligent security monitoring system for the ocean buoy.
It is a fourth object of the present invention to provide a computer-readable storage medium.
The first purpose of the invention can be achieved by adopting the following technical scheme:
an intelligent security monitoring method for an ocean buoy, comprising the following steps:
reading the electronic compass in real time, and acquiring the current posture of the buoy;
when the buoy is kept at a horizontal position, the radar sensor is opened at a fixed time so as to enable the radar sensor to detect the movement speed and the movement direction of the moving object and the distance between the moving object and the radar sensor;
calculating the self movement speed of the radar sensor at the current moment according to the three-dimensional inclination angle and the swing period of the buoy;
correcting the motion speed of the moving object according to the motion speed of the radar sensor at the current moment;
judging whether the moving object is a suspicious object or not according to the moving speed and the moving direction of the moving object;
if the moving object is judged to be a suspicious object, starting a camera so that the camera shoots the suspicious object;
receiving a suspicious object image sent by a camera, identifying the suspicious object image, and judging whether the suspicious object is an invading ship or not;
and if the suspicious object is judged to be an invading ship, sending the alarm information and the ship image to a remote server, and starting an audible and visual alarm to carry out on-site warning.
Further, the detecting the moving speed and the moving direction of the moving object and the distance between the moving object and the radar sensor specifically includes:
when an object moves relative to the radar sensor, the Doppler effect generates Doppler frequency shift, and the moving speed and the moving direction of the moving object and the distance between the moving object and the radar sensor are calculated according to the frequency of a difference frequency signal obtained by mixing a transmitting signal and a receiving signal of the radar sensor; and the frequencies of the transmitting signal and the receiving signal are symmetrical triangles.
Further, the moving speed of the moving object and the distance between the moving object and the radar sensor are as follows:
Figure BDA0002764618560000021
Figure BDA0002764618560000022
where v denotes the moving speed of the moving object, R denotes the distance between the moving object and the radar sensor, fdiff_upRepresenting the frequency of the difference signal, f, in the forward direction after mixing of the transmitted and received signalsdiff_downRepresenting the frequency of the difference signal, c, in the negative tone range after mixing of the transmitted and received signals0The speed of light is represented, T represents the modulation period of the transmitted signal, and Δ F represents the variation range of the transmitting frequency of the voltage-controlled oscillator.
Further, the determining, according to the moving speed and the moving direction of the moving object, whether the moving object is a suspicious object specifically includes:
if the moving speed of the moving object is within the normal speed range of the ship and the moving direction of the moving object is close to the buoy direction, judging that the moving object is a suspicious object; otherwise, the moving object is judged not to be a suspicious object.
Further, the identifying the suspicious object image and the judging whether the suspicious object is an intruding ship specifically comprise:
preprocessing the suspicious object image;
and adopting a pre-trained target detection model to identify the preprocessed suspicious object image and judging whether the suspicious object is an invading ship or not.
Further, the training process of the target detection model includes:
determining a target detection model and a deep learning framework;
acquiring a ship image in a network and/or actual application scene;
screening ship images, and marking ships in the ship images;
and performing iterative training on the target detection model according to the marked ship image until the accuracy reaches the actual application requirement.
Further, the preprocessing the suspicious object image specifically includes:
graying and filtering the suspicious object image, and zooming to a fixed size.
The second purpose of the invention can be achieved by adopting the following technical scheme:
the utility model provides an ocean buoy intelligent security monitoring device, the device includes:
the reading unit is used for reading the electronic compass in real time and acquiring the current posture of the buoy;
the detection unit is used for opening the radar sensor at regular time when the buoy is kept at the horizontal position so as to enable the radar sensor to detect the movement speed, the movement direction and the distance of the moving object;
the computing unit is used for computing the self motion speed of the radar sensor at the current moment according to the three-dimensional inclination angle and the swing period of the buoy;
the correction unit is used for correcting the motion speed of the moving object according to the motion speed of the radar sensor at the current moment;
the first judgment unit is used for judging whether the moving object is a suspicious object or not according to the moving speed and the moving direction of the moving object;
the shooting unit is used for starting the camera if the moving object is judged to be a suspicious object, so that the camera shoots the suspicious object;
the second judgment unit is used for receiving the suspicious object image sent by the camera, identifying the suspicious object image and judging whether the suspicious object is an invading ship or not;
and the alarm unit is used for sending alarm information and ship images to the remote server and starting the audible and visual alarm to carry out on-site warning if the suspicious object is judged to be an invading ship.
The third purpose of the invention can be achieved by adopting the following technical scheme:
an intelligent security monitoring system for an ocean buoy comprises an electronic compass, a radar sensor, a camera, an audible and visual alarm and a main control board, wherein the electronic compass and the main control board are arranged in an instrument bin of the buoy, and the electronic compass, the radar sensor, the camera and the audible and visual alarm are respectively connected with the main control board;
the electronic compass is used for measuring the posture of the buoy;
the radar sensor is used for detecting the movement speed and the movement direction of the moving object and the distance between the moving object and the radar sensor;
the camera is used for shooting the suspicious object when the moving object is judged to be the suspicious object;
the acousto-optic alarm is used for carrying out on-site warning when the suspicious object is judged to be an invading ship;
the main control board is used for executing the intelligent security monitoring method for the ocean buoy.
Further, radar sensor and camera are four, and radar sensor and camera one-to-one, and four radar sensor lay in four outside instrument storehouse directions of east, south, west, north respectively, and every radar sensor's detection angle reaches 90 degrees, and every radar sensor's detection distance is greater than 120m, and every camera setting is on the radar sensor that corresponds.
The fourth purpose of the invention can be achieved by adopting the following technical scheme:
a storage medium stores a program, and when the program is executed by a processor, the intelligent security monitoring method for the ocean buoy is realized.
Compared with the prior art, the invention has the following beneficial effects:
the main control board of the invention obtains the current posture of the buoy by reading the electronic compass, and when the buoy is kept in a horizontal position, the radar sensor is opened at regular time to detect the movement speed and the movement direction of the moving object and the distance between the moving object and the radar sensor, the three-dimensional inclination angle and the swing period of the buoy can be obtained by the electronic compass, and the movement speed of the radar sensor at the current moment is calculated, so that the movement speed of the moving object is corrected, the suspicious object is rapidly scanned according to the movement speed and the movement direction of the moving object, then the camera is started to shoot, whether the suspicious object is an invading ship is judged by the main control board, after the suspicious object is judged to be the invading ship, the alarm information and the ship image are sent to the remote server, and the audible and visual alarm is started to carry out on-, and on the other hand, the reliability and the accuracy of the detection result are ensured.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the structures shown in the drawings without creative efforts.
Fig. 1 is a block diagram of a structure of an intelligent security monitoring system for an ocean buoy according to embodiment 1 of the present invention.
Fig. 2 is a front view of a buoy according to embodiment 1 of the present invention.
Fig. 3 is a plan view of a float according to embodiment 1 of the present invention.
Fig. 4 is a frequency graph of a transmission signal and a reception signal of the radar sensor according to embodiment 1 of the present invention.
Fig. 5 is a flowchart of image recognition according to embodiment 1 of the present invention.
Fig. 6 is a flowchart of an intelligent security monitoring method for an ocean buoy according to embodiment 1 of the present invention.
Fig. 7 is a block diagram of a structure of an intelligent security monitoring device for an ocean buoy according to embodiment 2 of the present invention.
101-a buoy body, 102-an instrument bin, 103-an electronic compass, 104-a radar sensor, 105-a camera, 106-an audible and visual alarm, 107-a main control board, 108-a power supply control module, 109-a communication module, 110-a remote server and 111-a vibration sensor.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer and more complete, the technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some embodiments of the present invention, but not all embodiments, and all other embodiments obtained by a person of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the protection scope of the present invention.
Example 1:
as shown in fig. 1 to fig. 3, the embodiment provides an intelligent security monitoring system for an ocean buoy, wherein the buoy includes a buoy body 101 and an instrument chamber 102, the system includes an electronic compass 103, a radar sensor 104, a camera 105, an audible and visual alarm 106, a main control board 107, a power control module 108 and a communication module 109, the electronic compass 103 and the main control board 107 are disposed in the instrument chamber 102 of the buoy, the electronic compass 103, the radar sensor 104, the camera 105, the audible and visual alarm 106 and the power control module 108 are respectively connected with the main control board 107, the main control board 107 is further connected with a remote server 110 through the communication module 109, and a radar detection algorithm and an image recognition algorithm are disposed in the main control board 107; the electronic compass 103 can measure the posture of the buoy, and the audible and visual alarm 106 can warn in the field when the suspicious object is judged to be an intruding ship.
The main control board 107 adopts a 32-bit embedded main control chip, which has a 32-bit processor, runs a high-performance embedded operating system, supports multi-thread low-power-consumption running, in an idle state, only runs a main thread, closes other peripheral devices and related threads, and adopts a timed dormancy wakeup working mode, wherein the related device threads include: the system comprises a power supply management thread, a radar detection thread, an image processing thread, an image intelligent identification thread, an electronic compass processing thread, an acousto-optic warning thread and a communication processing thread.
The radar sensors 104 can simultaneously detect the moving speed and distance information of a moving object, the modulation signal adopts triangular waves, the moving speed, the moving direction and the distance between the moving object and the radar sensors 104 are obtained according to difference frequency signals of an ascending section and a descending section of the triangular waves, one radar sensor 104 is respectively arranged in the east, south, west and north directions outside the instrument bin 102 to form a 360-degree dead-angle-free monitoring range, the detection angle of each radar sensor 104 reaches 90 degrees, and the detection distance of each radar sensor 104 is larger than 120m, so that when the moving object approaches, the system has enough reaction time to take a snapshot and warn, the radar sensors 104 are simultaneously started at regular time, when a certain direction finds that the moving object approaches a buoy, the snapshot is immediately carried out, and the moving speed, the moving direction and the distance between the moving object and the radar sensors 104, which are detected by the radar sensors 104, are transmitted to the communication module 109, the data is transmitted by the communication module 109 to the remote server 110.
Specifically, the radar sensor 104 adopting triangular wave modulation transmits signals with a symmetrical triangular frequency, wherein in a single period, the first half period is positive frequency modulation, and the second half period is negative frequency modulation; in fig. 4, the axis of abscissa indicates time T, the axis of ordinate indicates frequency F, the solid line indicates a transmission signal, the broken line indicates a reception signal, T indicates a modulation period of the transmission signal, Δ F indicates a variation range of the transmission frequency of the voltage-controlled oscillator, i.e., a bandwidth of modulation, and when an object moves relative to the radar sensor 104, the doppler shift is observedThe doppler shift is produced by the doppler effect; f. ofdiff_upRepresenting the frequency of the difference signal, f, in the forward direction after mixing of the transmitted and received signalsdiff_downThe difference frequency signal frequency of the transmitting signal and the receiving signal after frequency mixing in a negative frequency modulation band is represented; r represents the distance between the moving object and the radar sensor 104, c0Represents the speed of light; f. ofDoppIndicating the frequency of the doppler shift.
The number of the cameras 105 is four, the cameras 105 correspond to the radar sensors 104 one by one, each camera 105 is arranged on the corresponding radar sensor 104, when the main control board 107 judges that the moving object is a suspicious object, the suspicious object can be shot, the camera 105 adopts a digital camera interface (DCMI), after being powered on, the camera 105 completes shooting and image compression processing within hundreds of milliseconds, image data in a JPG format is directly output, after the main control board 107 acquires an image file, the file is stored in a memory, an image recognition thread is started for image recognition, the shot suspicious object is preprocessed by using an image recognition algorithm, image recognition is performed by using a pre-trained model, image recognition can be quickly realized on the main control board 107, and the flow of the image recognition is shown in fig. 5.
Further, the intelligent security monitoring system for the ocean buoy of the embodiment may further include a vibration sensor 111, where the vibration sensor 111 is connected to the main control board 107, and can detect that the buoy is suddenly impacted by an external force, and further initiate emergency alarm information; the whole system is powered by solar energy and a storage battery, and in an idle state, the main control panel 107 is in a dormant state, other sensors are in a closed state, so that electric quantity is not consumed, and power consumption of a power supply is saved.
As shown in fig. 6, this embodiment further provides an intelligent security monitoring method for an ocean buoy, which is implemented based on the main control board 107 and includes the following steps:
and S101, reading the electronic compass in real time and acquiring the current posture of the buoy.
S102, when the buoy is kept at a horizontal position, the radar sensor is opened at a fixed time, and the radar detection result is prevented from being influenced by the reflection signal of the ocean surface, so that the radar sensor can detect the movement speed and the movement direction of the moving object and the distance between the moving object and the radar sensor.
Doppler shift fdoppThe relationship with the moving speed v of the moving object is as follows:
Figure BDA0002764618560000071
wherein f isdoppRepresenting the Doppler shift (Hz), f0Representing the transmission frequency (Hz) of the radar sensor, v representing the speed of movement (m/s) of the moving object, c0Representing the speed of light (m/s) and alpha representing the angle (°) between the line from the radar sensor to the moving object and the direction of motion of the moving object
In this embodiment, α is 0, and the following can be simplified:
Figure BDA0002764618560000072
from fig. 4, it can be found that:
fdiff_up＝fDelay-fDopp
fdiff_down＝fDelay+fDopp
therefore, the moving speed of the moving object and the distance between the moving object and the radar sensor are as follows:
Figure BDA0002764618560000073
Figure BDA0002764618560000074
s103, the three-dimensional inclination angle of the buoy and the swing period of the buoy can be obtained through the data of the electronic compass, and the motion speed of the radar sensor at the current moment is calculated according to the three-dimensional inclination angle and the swing period of the buoy.
And S104, correcting the motion speed of the moving object according to the motion speed of the radar sensor at the current moment.
And S105, judging whether the moving object is a suspicious object or not according to the moving speed and the moving direction of the moving object.
Specifically, if the moving speed of the moving object is within the normal speed range of the ship and the moving direction of the moving object is close to the buoy, the moving object is judged to be a suspicious object; otherwise, the moving object is judged not to be a suspicious object.
And S106, if the moving object is judged to be a suspicious object, starting the camera so that the camera shoots the suspicious object.
S107, receiving the suspicious object image sent by the camera, identifying the suspicious object image by using an image identification algorithm, and judging whether the suspicious object is an invading ship.
The target detection model of this embodiment adopts a convolutional neural network model for target detection, which takes tiny-yolo3 as an example in this embodiment, and other convolutional neural network models, such as yolo-nano, Mobilenet and the like, may also be used in practical applications, and it can be understood that, for those skilled in the art, the replacement of the target detection model does not bring about a great influence on the implementation of the technical scheme of this embodiment; secondly, according to the actual application scenario, a deep learning frame is selected, in this embodiment, a tensrflow machine learning frame is selected, and corresponding tensrflow-Lite and tensrflow-Mobile are tensrflow versions optimized specifically for Mobile end devices, and a corresponding conversion tool is provided, so that the common model can be optimized and cut into a model used on the Mobile end device.
After the target detection model and the deep learning framework of the target detection model are determined, corresponding target detection model training can be carried out; firstly, data collection and preparation work is carried out, ship images on a network and/or in an actual application scene are collected, the ship images are screened, and then ships in the ship images are marked; then, dividing the marked ship images into three groups, namely a training group, a verification group and an evaluation group, and performing iterative training on a target detection model by using the marked images until the accuracy of the target detection model meets the actual application requirement, wherein the ship can be detected in an official pre-training model of yolo3(tiny-yolo3), so that the pre-trained model is further subjected to enhanced training only by using pictures in an actual application scene, and the detection accuracy of the ship in the actual application scene is improved; in the embodiment, 2000 actually shot images are collected and marked, wherein 1000 images are taken as training samples, 500 images are taken as verification samples, and 500 images are taken as evaluation samples; the number of marked samples in this embodiment does not represent any claim, and the number of marked samples can be adjusted according to the detection result precision of the target detection model, and if the result precision is not enough, the number of marked samples can be increased correspondingly.
After the target detection model is trained, the mobile terminal can be deployed; firstly, a trained target detection model needs to be converted into a TensorFlow Lite file format by using a TensorFlow Lite Converter tool; then, compiling the corresponding image processing program into a binary file by using a TensorFlow Lite tool; and finally, uploading the model file, the program file and the corresponding tag file to a main control board to finish the deployment of the mobile terminal of the detection program.
In the actual use process, after the main control board is started, the whole initialization program is started, the image processing program is initialized, the model and the tag file in the storage are loaded, the initialization of the target detection model is completed, and then the main control board can be waited for calling; after the main control board receives the image identification instruction, the processing flow of the image processing program is as follows: firstly, reading an image from a memory; secondly, preprocessing the image such as graying, filtering, zooming to a fixed size and the like; then, calling a target detection model interface to identify the preprocessed image; and finally, returning the identification result to the main control board, wherein the identification result comprises whether the target is detected and the coordinate position (xmin, ymin, xmax, ymax) of the target bounding box, and the main control board receives the corresponding identification result and then carries out the next processing.
It can be understood that, in this embodiment, after receiving the suspicious object image sent by the camera, the main control board performs preprocessing such as graying, filtering, scaling to a fixed size, and the like on the suspicious object image, and identifies the preprocessed suspicious object image by using a pre-trained target detection model to determine whether the suspicious object is an intruding ship.
And S108, if the suspicious object is judged to be an invading ship, sending the alarm information and the ship image to a remote server, and starting an audible and visual alarm to carry out on-site warning.
It should be noted that although the method operations described above are depicted in the drawings in a particular order, this does not require or imply that these operations must be performed in this particular order, or that all of the illustrated operations must be performed, to achieve desirable results. Rather, the depicted steps may change the order of execution. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions.
Example 2:
as shown in fig. 7, the present embodiment provides an intelligent security monitoring device for an ocean buoy, which includes a reading unit 701, a detecting unit 702, a calculating unit 703, a correcting unit 704, a first judging unit 705, a shooting unit 706, a second judging unit 707, and an alarming unit 708, and the specific functions of each unit are as follows:
and the reading unit 701 is used for reading the electronic compass in real time and acquiring the current posture of the buoy.
And the detection unit 702 is used for opening the radar sensor at regular time when the buoy is kept at the horizontal position, so that the radar sensor detects the movement speed, the movement direction and the distance of the moving object.
And the calculating unit 703 is configured to calculate the motion speed of the radar sensor at the current time according to the three-dimensional inclination angle and the swing period of the buoy.
And a correcting unit 704, configured to correct the moving speed of the moving object according to the moving speed of the radar sensor at the current time.
The first judging unit 705 is configured to judge whether the moving object is a suspicious object according to the moving speed and the moving direction of the moving object.
The shooting unit 706 is configured to start the camera if the moving object is determined to be a suspicious object, so that the camera shoots the suspicious object.
The second judging unit 707 is configured to receive the suspicious object image sent by the camera, identify the suspicious object image, and judge whether the suspicious object is an intruding ship.
And the alarm unit 708 is used for sending alarm information and a ship image to the remote server and starting an audible and visual alarm to warn on site if the suspicious object is judged to be an intruding ship.
It should be noted that the apparatus provided in this embodiment is only illustrated by the division of the above functional units, and in practical applications, the above function allocation may be performed by different functional units according to needs, that is, the internal structure is divided into different functional units to perform all or part of the functions described above.
Example 3:
the present embodiment provides a storage medium, which is a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the computer program implements the following operations:
reading the electronic compass in real time, and acquiring the current posture of the buoy;
when the buoy is kept at a horizontal position, the radar sensor is opened at a fixed time so as to enable the radar sensor to detect the movement speed and the movement direction of the moving object and the distance between the moving object and the radar sensor;
calculating the self movement speed of the radar sensor at the current moment according to the three-dimensional inclination angle and the swing period of the buoy;
correcting the motion speed of the moving object according to the motion speed of the radar sensor at the current moment;
judging whether the moving object is a suspicious object or not according to the moving speed and the moving direction of the moving object;
if the moving object is judged to be a suspicious object, starting a camera so that the camera shoots the suspicious object;
receiving a suspicious object image sent by a camera, identifying the suspicious object image, and judging whether the suspicious object is an invading ship or not;
and if the suspicious object is judged to be an invading ship, sending the alarm information and the ship image to a remote server, and starting an audible and visual alarm to carry out on-site warning.
It should be noted that the computer readable storage medium of the present embodiment may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
In the present embodiment, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this embodiment, however, a computer readable signal medium may include a propagated data signal with a computer readable program embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable storage medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program embodied on the computer readable storage medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
In summary, the main control board of the present invention obtains the current posture of the buoy by reading the electronic compass, and when the buoy is kept in the horizontal position, the radar sensor is turned on at regular time to detect the moving speed and the moving direction of the moving object and the distance between the moving object and the radar sensor, and the three-dimensional tilt angle and the swing period of the buoy can be obtained by the electronic compass, so as to calculate the moving speed of the radar sensor at the current moment, thereby correcting the moving speed of the moving object, rapidly scanning the moving object according to the moving speed and the moving direction of the moving object to obtain the suspicious object, then starting the camera to shoot, judging whether the suspicious object is an intruding ship by the main control board, after judging the suspicious object is an intruding ship, sending the alarm information and the ship image to the remote server, and starting the audible and visual alarm to warn in the field, and on the other hand, the reliability and the accuracy of the detection result are ensured.
The above description is only for the preferred embodiments of the present invention, but the protection scope of the present invention is not limited thereto, and any person skilled in the art can substitute or change the technical solution and the inventive concept of the present invention within the scope of the present invention.

Claims (10)

1. An intelligent security monitoring method for an ocean buoy is characterized by comprising the following steps:
reading the electronic compass in real time, and acquiring the current posture of the buoy;
when the buoy is kept at a horizontal position, the radar sensor is opened at a fixed time so as to enable the radar sensor to detect the movement speed and the movement direction of the moving object and the distance between the moving object and the radar sensor;
calculating the self movement speed of the radar sensor at the current moment according to the three-dimensional inclination angle and the swing period of the buoy;
correcting the motion speed of the moving object according to the motion speed of the radar sensor at the current moment;
judging whether the moving object is a suspicious object or not according to the moving speed and the moving direction of the moving object;
if the moving object is judged to be a suspicious object, starting a camera so that the camera shoots the suspicious object;
receiving a suspicious object image sent by a camera, identifying the suspicious object image, and judging whether the suspicious object is an invading ship or not;
and if the suspicious object is judged to be an invading ship, sending the alarm information and the ship image to a remote server, and starting an audible and visual alarm to carry out on-site warning.
2. The intelligent security monitoring method for the ocean buoy according to claim 1, wherein the detection of the moving speed and the moving direction of the moving object and the distance between the moving object and the radar sensor specifically comprises the following steps:
when an object moves relative to the radar sensor, the Doppler effect generates Doppler frequency shift, and the moving speed and the moving direction of the moving object and the distance between the moving object and the radar sensor are calculated according to the frequency of a difference frequency signal obtained by mixing a transmitting signal and a receiving signal of the radar sensor; and the frequencies of the transmitting signal and the receiving signal are symmetrical triangles.
3. The intelligent security monitoring method for the ocean buoy according to claim 2, wherein the moving speed of the moving object and the distance between the moving object and the radar sensor are as follows:
Figure FDA0002764618550000011
Figure FDA0002764618550000012
where v denotes the moving speed of the moving object, R denotes the distance between the moving object and the radar sensor, fdiff_upRepresenting the frequency of the difference signal, f, in the forward direction after mixing of the transmitted and received signalsdiff_downRepresenting the frequency of the difference signal, c, in the negative tone range after mixing of the transmitted and received signals0The speed of light is represented, T represents the modulation period of the transmitted signal, and Δ F represents the variation range of the transmitting frequency of the voltage-controlled oscillator.
4. The intelligent security monitoring method for the ocean buoy according to claim 1, wherein whether the moving object is a suspicious object is judged according to the moving speed and the moving direction of the moving object, and specifically:
if the moving speed of the moving object is within the normal speed range of the ship and the moving direction of the moving object is close to the buoy direction, judging that the moving object is a suspicious object; otherwise, the moving object is judged not to be a suspicious object.
5. The intelligent security monitoring method for the ocean buoy according to any one of claims 1-4, wherein the identifying the image of the suspicious object and the determining whether the suspicious object is an intruding ship specifically comprises:
preprocessing the suspicious object image;
and adopting a pre-trained target detection model to identify the preprocessed suspicious object image and judging whether the suspicious object is an invading ship or not.
6. The intelligent security monitoring method for ocean buoys according to claim 5, wherein the training process of the target detection model comprises the following steps:
determining a target detection model and a deep learning framework;
acquiring a ship image in a network and/or actual application scene;
screening ship images, and marking ships in the ship images;
and performing iterative training on the target detection model according to the marked ship image until the accuracy reaches the actual application requirement.
7. The utility model provides an ocean buoy intelligent security monitoring device which characterized in that, the device includes:
the reading unit is used for reading the electronic compass in real time and acquiring the current posture of the buoy;
the detection unit is used for opening the radar sensor at regular time when the buoy is kept at the horizontal position so as to enable the radar sensor to detect the movement speed, the movement direction and the distance of the moving object;
the computing unit is used for computing the self motion speed of the radar sensor at the current moment according to the three-dimensional inclination angle and the swing period of the buoy;
the correction unit is used for correcting the motion speed of the moving object according to the motion speed of the radar sensor at the current moment;
the first judgment unit is used for judging whether the moving object is a suspicious object or not according to the moving speed and the moving direction of the moving object;
the shooting unit is used for starting the camera if the moving object is judged to be a suspicious object, so that the camera shoots the suspicious object;
the second judgment unit is used for receiving the suspicious object image sent by the camera, identifying the suspicious object image and judging whether the suspicious object is an invading ship or not;
and the alarm unit is used for sending alarm information and ship images to the remote server and starting the audible and visual alarm to carry out on-site warning if the suspicious object is judged to be an invading ship.
8. An intelligent security monitoring system for an ocean buoy is characterized by comprising an electronic compass, a radar sensor, a camera, an audible and visual alarm and a main control board, wherein the electronic compass and the main control board are arranged in an instrument bin of the buoy, and the electronic compass, the radar sensor, the camera and the audible and visual alarm are respectively connected with the main control board;
the electronic compass is used for measuring the posture of the buoy;
the radar sensor is used for detecting the movement speed and the movement direction of the moving object and the distance between the moving object and the radar sensor;
the camera is used for shooting the suspicious object when the moving object is judged to be the suspicious object;
the acousto-optic alarm is used for carrying out on-site warning when the suspicious object is judged to be an invading ship;
the main control board is used for executing the intelligent security monitoring method for the ocean buoy according to any one of claims 1 to 6.
9. The intelligent security monitoring system for the ocean buoy according to claim 8, wherein the number of the radar sensors and the number of the cameras are four, the radar sensors correspond to the cameras one by one, the four radar sensors are respectively arranged in the east, south, west and north directions outside the instrument bin, the detection angle of each radar sensor reaches 90 degrees, the detection distance of each radar sensor is larger than 120m, and each camera is arranged on the corresponding radar sensor.
10. A storage medium storing a program, wherein the program, when executed by a processor, implements the method for intelligent security monitoring of a marine buoy according to any one of claims 1 to 6.
CN202011229254.2A 2020-11-06 2020-11-06 Intelligent security monitoring method, device and system for ocean buoy and storage medium Active CN112394349B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011229254.2A CN112394349B (en) 2020-11-06 2020-11-06 Intelligent security monitoring method, device and system for ocean buoy and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011229254.2A CN112394349B (en) 2020-11-06 2020-11-06 Intelligent security monitoring method, device and system for ocean buoy and storage medium

Publications (2)

Publication Number Publication Date
CN112394349A true CN112394349A (en) 2021-02-23
CN112394349B CN112394349B (en) 2021-08-31

Family

ID=74598231

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011229254.2A Active CN112394349B (en) 2020-11-06 2020-11-06 Intelligent security monitoring method, device and system for ocean buoy and storage medium

Country Status (1)

Country Link
CN (1) CN112394349B (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113232785A (en) * 2021-06-09 2021-08-10 湖南农业大学 Long-endurance fishing unmanned yacht for emergency rescue
CN113255827A (en) * 2021-06-17 2021-08-13 广东电网有限责任公司中山供电局 Relay pressure maintaining plate state identification system and method based on YOLO Nano algorithm
CN114487327A (en) * 2022-01-17 2022-05-13 青岛百发海水淡化有限公司 Marine water quality monitoring and suspicious ship evidence obtaining system and method
CN115100808A (en) * 2022-06-29 2022-09-23 广州市声讯电子科技股份有限公司 Acousto-optic intelligent dispersing system
WO2023279786A1 (en) * 2021-07-08 2023-01-12 华为技术有限公司 Perimeter detection method and apparatus, and device and system
CN116935699A (en) * 2023-09-15 2023-10-24 天津港(集团)有限公司 Intelligent seaport channel integrated monitoring system and method

Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1937762A (en) * 2005-09-23 2007-03-28 王凌慧 Image monitoring safety device and method
US20090167592A1 (en) * 2007-12-28 2009-07-02 National Taiwan Ocean University Method for small-scale fishing boat equipped with radar receiver to avoid ship collision and the radar receiver therefor
US20090315756A1 (en) * 2004-02-04 2009-12-24 Hayama Imazu Vessel monitoring system
CN206776488U (en) * 2017-05-24 2017-12-22 青岛欧蓝特环境科技有限公司 Cage culture multi-parameter automatic monitored control system
CN107820058A (en) * 2017-11-21 2018-03-20 宜昌创源中新光电科技有限公司 A kind of device and method for screening buoy saboteur and rodman
CN108152808A (en) * 2017-11-23 2018-06-12 安徽四创电子股份有限公司 A kind of circumference intelligent predicting method for early warning based on millimetre-wave radar
KR101911756B1 (en) * 2018-05-04 2018-10-25 (주)에디넷 The system for real-time remote monitoring buoys on the sea
CN109683149A (en) * 2018-12-14 2019-04-26 深圳市置辰海信科技有限公司 Fusion realization of goal method is calculated by radar and AIS ship oceangoing ship blending algorithm
CN208868257U (en) * 2018-08-30 2019-05-17 山东深海海洋科技有限公司 A kind of marine marker motion state monitoring device
CN110673128A (en) * 2019-11-11 2020-01-10 南京信息工程大学 X-waveband shore-based radar flow measurement method based on intermittent up-down frequency modulation waves
CN110687530A (en) * 2019-09-18 2020-01-14 上海广电通信技术有限公司 Miniature security radar monitoring system
US20200341115A1 (en) * 2019-04-28 2020-10-29 Massachusetts Institute Of Technology Subject identification in behavioral sensing systems
US10823843B1 (en) * 2016-10-20 2020-11-03 Leidos, Inc. Motion extended array synthesis for use in high resolution imaging applications

Patent Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090315756A1 (en) * 2004-02-04 2009-12-24 Hayama Imazu Vessel monitoring system
CN1937762A (en) * 2005-09-23 2007-03-28 王凌慧 Image monitoring safety device and method
US20090167592A1 (en) * 2007-12-28 2009-07-02 National Taiwan Ocean University Method for small-scale fishing boat equipped with radar receiver to avoid ship collision and the radar receiver therefor
US10823843B1 (en) * 2016-10-20 2020-11-03 Leidos, Inc. Motion extended array synthesis for use in high resolution imaging applications
CN206776488U (en) * 2017-05-24 2017-12-22 青岛欧蓝特环境科技有限公司 Cage culture multi-parameter automatic monitored control system
CN107820058A (en) * 2017-11-21 2018-03-20 宜昌创源中新光电科技有限公司 A kind of device and method for screening buoy saboteur and rodman
CN108152808A (en) * 2017-11-23 2018-06-12 安徽四创电子股份有限公司 A kind of circumference intelligent predicting method for early warning based on millimetre-wave radar
KR101911756B1 (en) * 2018-05-04 2018-10-25 (주)에디넷 The system for real-time remote monitoring buoys on the sea
CN208868257U (en) * 2018-08-30 2019-05-17 山东深海海洋科技有限公司 A kind of marine marker motion state monitoring device
CN109683149A (en) * 2018-12-14 2019-04-26 深圳市置辰海信科技有限公司 Fusion realization of goal method is calculated by radar and AIS ship oceangoing ship blending algorithm
US20200341115A1 (en) * 2019-04-28 2020-10-29 Massachusetts Institute Of Technology Subject identification in behavioral sensing systems
CN110687530A (en) * 2019-09-18 2020-01-14 上海广电通信技术有限公司 Miniature security radar monitoring system
CN110673128A (en) * 2019-11-11 2020-01-10 南京信息工程大学 X-waveband shore-based radar flow measurement method based on intermittent up-down frequency modulation waves

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
COSTANZA R: "《The ecological,econom ic,and social importance of the oceans》", 《ECOLOGICAL ECONOM ICS》 *
杨燕 等: "《波浪动力滑翔机海洋环境监测系统》", 《海洋技术学报》 *

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113232785A (en) * 2021-06-09 2021-08-10 湖南农业大学 Long-endurance fishing unmanned yacht for emergency rescue
CN113255827A (en) * 2021-06-17 2021-08-13 广东电网有限责任公司中山供电局 Relay pressure maintaining plate state identification system and method based on YOLO Nano algorithm
WO2023279786A1 (en) * 2021-07-08 2023-01-12 华为技术有限公司 Perimeter detection method and apparatus, and device and system
CN114487327A (en) * 2022-01-17 2022-05-13 青岛百发海水淡化有限公司 Marine water quality monitoring and suspicious ship evidence obtaining system and method
CN115100808A (en) * 2022-06-29 2022-09-23 广州市声讯电子科技股份有限公司 Acousto-optic intelligent dispersing system
CN116935699A (en) * 2023-09-15 2023-10-24 天津港(集团)有限公司 Intelligent seaport channel integrated monitoring system and method
CN116935699B (en) * 2023-09-15 2023-12-12 天津港(集团)有限公司 Intelligent seaport channel integrated monitoring system and method

Also Published As

Publication number Publication date
CN112394349B (en) 2021-08-31

Similar Documents

Publication Publication Date Title
CN112394349B (en) Intelligent security monitoring method, device and system for ocean buoy and storage medium
CN110414396B (en) Unmanned ship perception fusion algorithm based on deep learning
CN110246177A (en) Automatic wave measuring method based on vision
CN104267643A (en) Target positioning recognition system of underwater robot
CN108415323A (en) A kind of aquafarm intellectualized management system
CN111650627A (en) Ocean buoy station, intrusion detection evidence obtaining method and system
CN116245916B (en) Unmanned ship-oriented infrared ship target tracking method and device
CN114708217B (en) Early warning method, device and equipment for preventing ultrahigh ship collision of bridge in wide water area
CN114018317B (en) Data acquisition device and method for marine environment
CN111103008A (en) Ocean safety detection method based on sensor
CN114877873A (en) Ocean buoy monitoring system and method, electronic equipment and storage medium
US11808570B2 (en) Sensor and telemetry unit (STU) adapted for securable coupling to a floating object or buoyant aid to navigation (AtoN) to operate as a selectively deployable ocean data acquisition system (ODAS)
CN115206040A (en) Biological invasion early warning method, device and terminal for nuclear power water intake
CN112113541A (en) River and lake environment problem identification method and system
CN114814990B (en) Device for forecasting and monitoring tidal volume of bay and working method thereof
US20190079213A1 (en) Automatic Harbor Surveillance System
CN205898246U (en) Unmanned on duty website tidal level measurement system based on radar is measured
CN115496803A (en) Collision warning and evidence obtaining system and method for offshore buoy
CN115909816A (en) Buoy collision early warning and recording system
CN111879293B (en) Device and method for in-situ measurement of noise characteristics of rainfall on sea
CN210534857U (en) Wave video measuring device
CN210666019U (en) Sea echo-based X-band radar wave measuring system
CN203204151U (en) Buoy type sonar navigation system device
CN107941220B (en) Unmanned ship sea antenna detection and navigation method and system based on vision
CN212623110U (en) Ocean buoy station and intrusion detection evidence obtaining system

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
GR01 Patent grant
GR01 Patent grant