CN115880844B - Ship security intelligent management system based on multi-source perception - Google Patents
Ship security intelligent management system based on multi-source perception Download PDFInfo
- Publication number
- CN115880844B CN115880844B CN202310139387.8A CN202310139387A CN115880844B CN 115880844 B CN115880844 B CN 115880844B CN 202310139387 A CN202310139387 A CN 202310139387A CN 115880844 B CN115880844 B CN 115880844B
- Authority
- CN
- China
- Prior art keywords
- ship
- personnel
- module
- data
- monitoring
- 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.)
- Active
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Alarm Systems (AREA)
Abstract
The invention discloses a ship security intelligent management system based on multi-source perception, which comprises: the system comprises a ship monitoring unit, a ship management unit and a background control center; the ship monitoring unit is used for sensing and monitoring the condition information on and around the ship in real time and processing the condition information; the ship management unit is used for processing the condition information monitored by the ship monitoring unit, and the background control center is used for analyzing and judging the information processed by the ship management unit and making a corresponding strategy. According to the invention, the personnel in the ship area are rapidly identified and verified through the multi-hash similarity weighting method, so that the processing speed is improved, non-ship personnel can be accurately and rapidly found out, dangerous attacks on the ship by the non-ship personnel are prevented, the risk in the ship navigation process is accurately judged through the gray correlation algorithm, and further the safety of the ship in the navigation process and intelligent management of the ship can be improved.
Description
Technical Field
The invention relates to the technical field of ship monitoring, in particular to a ship security intelligent management system based on multi-source perception.
Background
With the continuous development of shipping industry and the breakthrough of intelligent ship construction in China, the national importance is placed on the protection of ship navigation safety and the personal safety of ship personnel. However, in the traditional ship safety protection, although the ship can realize all-weather uninterrupted monitoring by installing a high-definition camera, a thermal imaging night vision device and infrared equipment, the imaging requirements on the clearly and accurately monitored area can not be met in environments such as the night, heavy fog and the like or when the imaging distance is far; aiming at articles carried by ship personnel, a security inspection instrument is generally adopted for article detection, but a device for rapidly and intelligently detecting, identifying and reasonably disposing portable dangerous explosive articles is lacking; for the identification and early warning of the external invasion targets of the ship, radar is generally adopted to sense the surrounding environment of the ship, but intelligent identification, early warning and tracking systems for the suspicious targets on the water are lacking.
Wherein, chinese patent CN108227606B is a boats and ships security protection intelligent management system based on multisource perception, includes: the system comprises a ship emergency response unit, a data transfer satellite and a shore-based emergency guiding unit. The ship emergency response unit monitors the access condition information of personnel on the ship, the condition information of whether dangerous articles exist on the ship and the condition information of whether dangerous targets exist on the sea surface in real time, and the shore-based emergency guiding unit receives the data information transmitted by the ship emergency response unit to make an optimization scheme for avoiding risk navigation of the ship. However, in the process of collecting, transmitting and processing data, the management system may cause abnormal conditions of the data due to the problems of faults of collecting equipment, noise interference of a transmission channel and the like, the management system does not process the collected data, the abnormal data can affect subsequent judgment and cannot make accurate judgment, and meanwhile, due to the complex environment of a ship in the sailing process, risks encountered in the sailing process of the ship cannot be well judged, so that proper strategies are difficult to formulate to deal with risks encountered in the sailing process of the ship.
For the problems in the related art, no effective solution has been proposed at present.
Disclosure of Invention
Aiming at the problems in the related art, the invention provides a ship security intelligent management system based on multi-source perception, which aims to overcome the technical problems existing in the related art.
For this purpose, the invention adopts the following specific technical scheme:
a ship security intelligent management system based on multi-source perception comprises: the system comprises a ship monitoring unit, a ship management unit and a background control center, wherein the ship monitoring unit is connected with the background control center through the ship management unit;
the ship monitoring unit is used for sensing and monitoring the condition information on and around the ship in real time and processing the condition information;
the ship management unit is used for processing the condition information monitored by the ship monitoring unit;
the background control center is used for analyzing and judging the information processed by the ship management unit and making a corresponding strategy.
Further, the ship monitoring unit comprises a video monitoring module, a smoke detection module, a radar detection module and a weather detection module;
the video monitoring module is used for monitoring the ship area and the personnel in the ship area through the monitoring camera to acquire facial images of the personnel in the ship area;
the smoke detection module is used for monitoring whether fire conditions exist in the ship area through the smoke sensor;
the radar detection module is used for monitoring whether other ships and other objects exist in the nearby area of the ship through the radar detector;
the weather detection module is used for monitoring weather conditions of the nearby area of the ship through the ship weather instrument.
Further, the ship management unit comprises a data processing module, a personnel identification module and a ship navigation risk assessment module, and the data processing module is sequentially connected with the personnel identification module, the ship navigation risk assessment module, the video monitoring module, the smoke detection module, the radar detection module and the weather detection module;
the data processing module is used for analyzing and processing the data transmitted by the ship monitoring unit;
the personnel identification module is used for identifying and verifying the acquired facial images of the personnel in the ship area;
the ship navigation risk assessment module is used for assessing the ship navigation risk through a gray correlation analysis method.
Further, the analyzing and processing the monitoring data transmitted by the ship monitoring unit includes the following steps:
collecting monitoring data transmitted by the ship monitoring unit, and carrying out induction classification on the monitoring data according to data types to obtain a measurement data set;
calculating a measurement mean value of each set of measurement data
Residual value v i And standard deviation estimate +.>
If the residual value v of the ith measurement data i Satisfy the formula
Then the ith measurement data x i Belonging to abnormal data, otherwise, the ith measurement data x i Belonging to normal data;
and eliminating the abnormal data and storing the normal data.
Further, the measurement mean value
The calculation formula of (2) is as follows:
the v is i The calculation formula of (2) is as follows:
the standard deviation estimate
The calculation formula of (2) is as follows:
where h represents the number of measurement data.
Further, the identifying and verifying the acquired facial image of the personnel in the ship area comprises the following steps:
acquiring facial image information of a ship personnel on a ship and forming a facial information database of the ship personnel;
acquiring facial images of the ship regional personnel and characteristics of the facial images of the ship personnel in the ship regional personnel facial information database through a neural network to form a characteristic diagram of the ship regional personnel and a characteristic diagram of the ship personnel;
performing similarity calculation on the characteristic diagrams of the ship regional personnel and the characteristic diagrams of the ship personnel through a mean value hash algorithm and a perception hash algorithm;
respectively weighting the feature map of the ship regional personnel and the feature map of the ship personnel by using alpha and beta as weighting coefficients of mean value hash and weighting coefficients of perception hash, and obtaining a final similarity value;
when the weighted similarity is greater than or equal to a preset threshold value, judging that the ship regional personnel are ship personnel;
and when the weighted similarity is smaller than a preset threshold value, judging that the ship regional personnel are not ship personnel.
Further, the calculation formula of the final similarity value is as follows:
S(S 1 ，S 2 )＝αS 1 +βS 2 ，0＜α＜1，0＜β＜1
wherein S (S) 1 ，S 2 ) Representing the final similarity value;
alpha represents the weighting coefficient of the mean hash;
beta represents the weighting coefficient of the perceptual hash;
S 1 representing that the similarity value is obtained through calculation of a mean hash algorithm;
S 2 representing that the similarity value is obtained through calculation of a perceptual hash algorithm;
further, the assessment of the ship navigation risk by the gray correlation analysis method comprises the following steps:
acquiring risks existing in the history sailing of the ship;
constructing an evaluation index system according to risks existing in the historical sailing of the ship;
determining a reference data sequence and a comparison sequence of the reference evaluation object;
calculating the association coefficient and the association degree between the evaluation indexes;
and judging the ship navigation risk according to the association degree, wherein if the association degree is larger, the ship navigation risk is safer in the process, and otherwise, the ship navigation risk is more dangerous.
Further, the calculation formula for calculating the association coefficient between the evaluation indexes is as follows:
wherein, xi 0j (k) Representing a correlation coefficient;
X 0 (k) Representing a reference data sequence;
X i (k) Representing a comparison data sequence;
ρ represents a resolution coefficient, and the value range of ρ is 0.1-1.0, and the value is 0.5;
the calculation formula for calculating the association degree between the evaluation indexes is as follows:
wherein P is 0j (k) Representing the degree of association;
ξ 0j (k) Representing a correlation coefficient;
m represents the number of comparison data sequences;
n represents the number of evaluation indexes;
ω k representing the weight, 0 < omega k ≤1，
Further, the background control center comprises a terminal display module and an early warning module, and the terminal display module and the early warning module are sequentially connected with the data processing module;
the terminal display module is used for visually displaying the data processed by the ship management unit;
and the early warning module is used for sending out early warning signals to prompt ship personnel.
The beneficial effects of the invention are as follows:
1. according to the invention, information acquisition is carried out on a ship area and the vicinity of the ship through a multi-source sensing technology, and human face recognition verification is carried out on personnel in the ship area rapidly through a multi-hash similarity weighting method, so that the processing speed is improved, non-ship personnel can be accurately and rapidly found out, dangerous attack on the ship by the non-ship personnel is prevented, and accurate judgment is carried out on risks in the ship navigation process through a gray correlation algorithm, so that the safety of the ship in the navigation process and intelligent management on the ship can be improved.
2. According to the invention, through carrying out abnormal analysis on the acquired data and accurately removing and cleaning the abnormal data, the smooth processing of the acquired data is realized, and further, the guarantee can be provided for the follow-up authentication of personnel in a ship area and the accurate judgment of risks in the ship navigation process.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic block diagram of a ship security intelligent management system based on multi-source perception according to an embodiment of the present invention.
In the figure:
1. a ship monitoring unit; 101. a video monitoring module; 102. a smoke detection module; 103. a radar detection module; 104. a weather detection module; 2. a ship management unit; 201. a data processing module; 202. a personnel identification module; 203. a ship navigation risk assessment module; 3. a background control center; 301. a terminal display module; 302. and an early warning module.
Detailed Description
For the purpose of further illustrating the various embodiments, the present invention provides the accompanying drawings, which are a part of the disclosure of the present invention, and which are mainly used to illustrate the embodiments and, together with the description, serve to explain the principles of the embodiments, and with reference to these descriptions, one skilled in the art will recognize other possible implementations and advantages of the present invention, wherein elements are not drawn to scale, and like reference numerals are generally used to designate like elements.
According to the embodiment of the invention, a ship security intelligent management system based on multi-source perception is provided.
The invention will be further described with reference to the accompanying drawings and detailed description, as shown in fig. 1, a multi-source perception based intelligent management system for ship security according to an embodiment of the invention, the system comprises: the system comprises a ship monitoring unit 1, a ship management unit 2 and a background control center 3, wherein the ship monitoring unit 1 is connected with the background control center 3 through the ship management unit 2;
the ship monitoring unit 1 is used for sensing and monitoring the condition information on and around the ship in real time and processing the condition information;
specifically, the ship monitoring unit 1 includes a video monitoring module 101, a smoke detection module 102, a radar detection module 103 and a weather detection module 104;
the video monitoring module 101 is configured to monitor a ship area and personnel in the ship area through a monitoring camera, and obtain facial images of the personnel in the ship area;
the smoke detection module 102 is used for monitoring whether fire conditions exist in the ship area through a smoke sensor;
the radar detection module 103 is configured to monitor whether other ships and other objects exist in a nearby area of the ship through a radar detector;
the weather detection module 104 is configured to monitor weather conditions of a nearby area of the ship through a ship weather meter.
The ship management unit 2 is used for processing the condition information monitored by the ship monitoring unit 1;
specifically, the ship management unit 2 includes a data processing module 201, a personnel identification module 202, and a ship navigation risk assessment module 203, where the data processing module 201 is sequentially connected to the personnel identification module 202, the ship navigation risk assessment module 203, the video monitoring module 101, the smoke detection module 102, the radar detection module 103, and the weather detection module 104;
the data processing module 201 is configured to analyze and process the data transmitted from the ship monitoring unit 1;
specifically, the problem that the ship is likely to be disturbed by the noise of the transmission channel and the like due to the faults of the acquisition equipment in the operation process can cause abnormal conditions of data, abnormal analysis is carried out on the acquired data, abnormal data can be accurately removed and cleaned, smooth processing on the acquired data is realized, and further guarantee can be provided for follow-up identity verification of personnel in a ship area and accurate judgment on risks in the ship navigation process.
Wherein, the analyzing and processing the monitoring data transmitted by the ship monitoring unit 1 includes the following steps:
collecting monitoring data transmitted by the ship monitoring unit 1, and carrying out induction classification on the monitoring data according to data types to obtain a measurement data set;
calculating a measurement mean value of each set of measurement data
Residual value v i And standard deviation estimate +.>
Wherein the measurement mean value
The calculation formula of (2) is as follows:
the v is i The calculation formula of (2) is as follows:
the standard deviation estimate
The calculation formula of (2) is as follows:
where h represents the number of measurement data.
If the residual value v of the ith measurement data i Satisfy the formula
Then the ith measurement data x i Belonging to abnormal data, otherwise, the ith measurement data x i Belonging to normal data;
and eliminating the abnormal data and storing the normal data.
The personnel identification module 202 is configured to identify and verify the acquired facial image of the personnel in the ship area;
the method for identifying and verifying the acquired facial image of the personnel in the ship area comprises the following steps:
acquiring facial image information of a ship personnel on a ship and forming a facial information database of the ship personnel;
acquiring facial images of the ship regional personnel and characteristics of the facial images of the ship personnel in the ship regional personnel facial information database through a neural network to form a characteristic diagram of the ship regional personnel and a characteristic diagram of the ship personnel;
performing similarity calculation on the characteristic diagrams of the ship regional personnel and the characteristic diagrams of the ship personnel through a mean value hash algorithm and a perception hash algorithm;
specifically, the mean hash algorithm includes the steps of:
1) The feature map is scaled down to a size of 8 x 8 for a total of 64 pixels;
2) Converting the feature map with the size of 8 multiplied by 8 into a gray map;
3) Calculating the gray average value of all 64 pixels;
4) Comparing the gray scales of the pixels, if the gray scale value of each pixel is larger than or equal to the gray scale average value, marking the result as 1, otherwise marking the result as 0, and stringing the result to form binary numbers;
5) Taking 64 binary numbers as hash values of the characteristic images, and calculating the Hamming distance of the hash values of the characteristic images to obtain similarity values;
specifically, the steps of the perceptual hash algorithm include:
1) Shrinking the feature map to a size of 32×32;
2) Converting the feature map with the size of 32×32 into a gray map;
3) Performing discrete cosine transform on the grayscale feature map to obtain a 32×32 discrete cosine transform coefficient matrix;
4) Extracting 8×8 matrix of the upper left corner in the discrete cosine transform coefficient matrix, and calculating average value of 8×8 matrix;
5) Comparing pixel gray scales, if the gray scale value of each pixel in the extracted 8×8 matrix is greater than or equal to the average value, marking the result as 1, otherwise marking the result as 0, and stringing the result to form binary numbers;
6) Taking 64 binary numbers as hash values of the characteristic images, and calculating the Hamming distance of the hash values of the characteristic images to obtain similarity values;
respectively weighting the feature map of the ship regional personnel and the feature map of the ship personnel by using alpha and beta as weighting coefficients of mean value hash and weighting coefficients of perception hash, and obtaining a final similarity value;
the calculation formula of the final similarity value is as follows:
S(S 1 ，S 2 )＝αS 1 +βS 2 ，0＜α＜1，0＜β＜1
wherein S (S) 1 ，S 2 ) Representing the final similarity value;
alpha represents the weighting coefficient of the mean hash;
beta represents the weighting coefficient of the perceptual hash;
S 1 representing that the similarity value is obtained through calculation of a mean hash algorithm;
S 2 representing that the similarity value is obtained through calculation of a perceptual hash algorithm;
when the weighted similarity is greater than or equal to a preset threshold value, judging that the ship regional personnel are ship personnel;
and when the weighted similarity is smaller than a preset threshold value, judging that the ship regional personnel are not ship personnel.
The ship navigation risk assessment module 203 is configured to assess risk of ship navigation through a gray correlation analysis method;
the method for evaluating the ship navigation risk through the gray correlation analysis method comprises the following steps of:
acquiring risks existing in the history sailing of the ship;
constructing an evaluation index system according to risks existing in the historical sailing of the ship;
determining a reference data sequence and a comparison sequence of the reference evaluation object;
specifically, in order to evaluate the evaluation target data sequence, first, an evaluation reference data sequence is determined, which is generally denoted as:
X 0 (k)＝{X 0 (1)，X 0 (2)，…X 0 (n)}，k＝1，2，…，n，
suppose that reference data sequence X 0 (k) The number of the data index sequences for comparison is m, and each data sequence has n indexes, the comparison sequence can be recorded as:
X 1 (k)，X 2 (k)，...X m (k)，k＝1，2，…，n，
when determining the reference sequence, selecting a reference value according to the index type of the comparison sequence;
calculating the association coefficient and the association degree between the evaluation indexes;
wherein, the calculation formula for calculating the association coefficient between the evaluation indexes is as follows:
wherein, xi 0j (k) Representing a correlation coefficient;
X 0 (k) Representing a reference data sequence;
X i (k) Representing a comparison data sequence;
ρ represents a resolution coefficient, and the value range of ρ is 0.1-1.0, and the value is 0.5;
the calculation formula for calculating the association degree between the evaluation indexes is as follows:
wherein P is 0j (k) Representing the degree of association;
ξ 0j (k) Representing a correlation coefficient;
m represents the number of comparison data sequences;
n represents the number of evaluation indexes;
ω k represents weight, 0.ltoreq.ω k ≤1，
And judging the ship navigation risk according to the association degree, wherein if the association degree is larger, the ship navigation risk is safer in the process, and otherwise, the ship navigation risk is more dangerous.
The background control center 3 is used for analyzing and judging the information processed by the ship management unit 2 and making a corresponding strategy;
the background control center 3 comprises a terminal display module 301 and an early warning module 302, and the terminal display module 301 and the early warning module 302 are sequentially connected with the data processing module 201;
the terminal display module 301 is configured to visually display the data processed by the ship management unit 2;
the terminal display module comprises a display screen, a mobile phone, a PC tablet, a PC computer and the like.
The early warning module 302 is configured to send an early warning signal to prompt a marine personnel;
specifically, when the ship personnel receive the early warning sent by the early warning module 302, the ship personnel can make corresponding judgment according to the early warning information, so that unnecessary loss of the ship in the running process is avoided.
In summary, by means of the technical scheme, the information is acquired in the ship area and the vicinity of the ship through the multi-source sensing technology, and the personnel in the ship area are rapidly identified and verified through the multi-hash similarity weighting method, so that the processing speed is improved, non-ship personnel can be accurately and rapidly found out, dangerous attack of the non-ship personnel on the ship is prevented, the risk in the ship sailing process is accurately judged through the gray correlation algorithm, and further the safety of the ship in the sailing process and intelligent management of the ship can be improved; according to the invention, through carrying out abnormal analysis on the acquired data and accurately removing and cleaning the abnormal data, the smooth processing of the acquired data is realized, and further, the guarantee can be provided for the follow-up authentication of personnel in a ship area and the accurate judgment of risks in the ship navigation process.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (7)
1. A ship security intelligent management system based on multi-source perception is characterized in that the system comprises: the system comprises a ship monitoring unit, a ship management unit and a background control center, wherein the ship monitoring unit is connected with the background control center through the ship management unit;
the ship monitoring unit is used for sensing and monitoring the condition information on and around the ship in real time and processing the condition information;
the ship monitoring unit comprises a video monitoring module, a smoke detection module, a radar detection module and a weather detection module;
the video monitoring module is used for monitoring the ship area and the personnel in the ship area through the monitoring camera to acquire facial images of the personnel in the ship area;
the smoke detection module is used for monitoring whether fire conditions exist in the ship area through the smoke sensor;
the radar detection module is used for monitoring whether other ships and other objects exist in the nearby area of the ship through the radar detector;
the weather detection module is used for monitoring weather conditions of the nearby area of the ship through the ship weather instrument;
the ship management unit is used for processing the condition information monitored by the ship monitoring unit;
the ship management unit comprises a data processing module, a personnel identification module and a ship navigation risk assessment module, wherein the data processing module is sequentially connected with the personnel identification module, the ship navigation risk assessment module, the video monitoring module, the smoke detection module, the radar detection module and the weather detection module;
the data processing module is used for analyzing and processing the data transmitted by the ship monitoring unit;
the analysis processing of the monitoring data transmitted by the ship monitoring unit comprises the following steps:
collecting monitoring data transmitted by the ship monitoring unit, and carrying out induction classification on the monitoring data according to data types to obtain a measurement data set;
calculating a measurement mean value of each set of measurement data
Residual value v i And standard deviation estimate +.>
If the residual value v of the ith measurement data i Satisfy the formula
Then the ith measurement data x i Belonging to abnormal data, otherwise, the ith measurement data x i Belonging to normal data;
removing the abnormal data and storing the normal data;
the personnel identification module is used for identifying and verifying the acquired facial images of the personnel in the ship area;
the ship navigation risk assessment module is used for assessing the ship navigation risk through a gray correlation analysis method;
the background control center is used for analyzing and judging the information processed by the ship management unit and making a corresponding strategy.
2. The intelligent management system for ship security based on multi-source perception according to claim 1, wherein the measurement mean value is as follows
The calculation formula of (2) is as follows:
the v is i Is of the meter(s)The calculation formula is as follows:
the standard deviation estimate
The calculation formula of (2) is as follows: />
Where h represents the number of measurement data.
3. The intelligent management system for ship security and protection based on multi-source perception according to claim 2, wherein the identification and verification of the acquired facial image of the personnel in the ship area comprises the following steps:
acquiring facial image information of a ship personnel on a ship and forming a facial information database of the ship personnel;
acquiring facial images of the ship regional personnel and characteristics of the facial images of the ship personnel in the ship regional personnel facial information database through a neural network to form a characteristic diagram of the ship regional personnel and a characteristic diagram of the ship personnel;
performing similarity calculation on the characteristic diagrams of the ship regional personnel and the characteristic diagrams of the ship personnel through a mean value hash algorithm and a perception hash algorithm;
respectively weighting the feature map of the ship regional personnel and the feature map of the ship personnel by using alpha and beta as weighting coefficients of mean value hash and weighting coefficients of perception hash, and obtaining a final similarity value;
when the weighted similarity is greater than or equal to a preset threshold value, judging that the ship regional personnel are ship personnel;
and when the weighted similarity is smaller than a preset threshold value, judging that the ship regional personnel are not ship personnel.
4. The intelligent management system for ship security and protection based on multi-source perception according to claim 3, wherein the calculation formula of the final similarity value is as follows:
S(S 1 ，S 2 )＝αS 1 +βS 2 ，0＜α＜1，0＜β＜1
wherein S (S) 1 ，S 2 ) Representing the final similarity value;
alpha represents the weighting coefficient of the mean hash;
beta represents the weighting coefficient of the perceptual hash;
S 1 representing that the similarity value is obtained through calculation of a mean hash algorithm;
S 2 representing the similarity value calculated by the perceptual hash algorithm.
5. The intelligent management system for ship security based on multi-source perception according to claim 4, wherein the assessment of the risk of ship navigation by gray correlation analysis method comprises the following steps:
acquiring risks existing in the history sailing of the ship;
constructing an evaluation index system according to risks existing in the historical sailing of the ship;
determining a reference data sequence and a comparison sequence of the reference evaluation object;
calculating the association coefficient and the association degree between the evaluation indexes;
and judging the ship navigation risk according to the association degree, wherein if the association degree is larger, the ship navigation risk is safer in the process, and otherwise, the ship navigation risk is more dangerous.
6. The intelligent management system for ship security and protection based on multi-source perception according to claim 5, wherein the calculation formula for calculating the correlation coefficient between the evaluation indexes is as follows:
wherein, xi 0j (k) Representing a correlation coefficient;
X 0 (k) Representing a reference data sequence;
X i (k) Representing a comparison data sequence;
ρ represents a resolution coefficient, and the value range of ρ is 0.1-1.0, and the value is 0.5;
the calculation formula for calculating the association degree between the evaluation indexes is as follows:
wherein P is 0j (k) Representing the degree of association;
ξ 0j (k) Representing a correlation coefficient;
m represents the number of comparison data sequences;
n represents the number of evaluation indexes;
ω k represents weight, 0.ltoreq.ω k ≤1，
7. The intelligent management system for ship security and protection based on multi-source perception according to claim 5, wherein the background control center comprises a terminal display module and an early warning module, and the terminal display module and the early warning module are sequentially connected with the data processing module;
the terminal display module is used for visually displaying the data processed by the ship management unit;
and the early warning module is used for sending out early warning signals to prompt ship personnel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310139387.8A CN115880844B (en) | 2023-02-21 | 2023-02-21 | Ship security intelligent management system based on multi-source perception |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310139387.8A CN115880844B (en) | 2023-02-21 | 2023-02-21 | Ship security intelligent management system based on multi-source perception |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115880844A CN115880844A (en) | 2023-03-31 |
| CN115880844B true CN115880844B (en) | 2023-05-09 |
Family
ID=85761379
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310139387.8A Active CN115880844B (en) | 2023-02-21 | 2023-02-21 | Ship security intelligent management system based on multi-source perception |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115880844B (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108227606B (en) * | 2018-01-29 | 2020-12-08 | 李颖 | Ship security intelligent management system based on multi-source perception |
| CN111091641A (en) * | 2018-10-24 | 2020-05-01 | 大连永航科技有限公司 | Ship security system based on face recognition |
| CN109883496A (en) * | 2019-03-12 | 2019-06-14 | 上海卯瑞船舶设备有限公司 | A kind of monitoring of marine fuel oil and opposite bank management system for internet of things |
| CN111160195A (en) * | 2019-12-23 | 2020-05-15 | 哈尔滨工程大学 | Ship personnel management system based on multi-biometric feature recognition technology |
| CN111340343A (en) * | 2020-02-18 | 2020-06-26 | 广东省标准化研究院 | Unmanned ship safety risk grey correlation degree evaluation method |
-
2023
- 2023-02-21 CN CN202310139387.8A patent/CN115880844B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115880844A (en) | 2023-03-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111739250B (en) | Fire detection method and system combining image processing technology and infrared sensor | |
| Zhang et al. | A recognition technology of transmission lines conductor break and surface damage based on aerial image | |
| CN106934377B (en) | Improved human face detection system | |
| CN112084963B (en) | Monitoring early warning method, system and storage medium | |
| CN111163290A (en) | Device and method for detecting and tracking night navigation ship | |
| CN112183219A (en) | Public safety video monitoring method and system based on face recognition | |
| CN113887324A (en) | Fire point detection method based on satellite remote sensing data | |
| CN114241370A (en) | Intrusion identification method and device based on digital twin transformer substation and computer equipment | |
| CN116797977A (en) | Method and device for identifying dynamic target of inspection robot and measuring temperature and storage medium | |
| CN110728212B (en) | Road well lid monitoring device and monitoring method based on computer vision | |
| CN110428579B (en) | Indoor monitoring system, method and device based on image recognition | |
| CN115049955A (en) | Fire detection analysis method and device based on video analysis technology | |
| CN115880844B (en) | Ship security intelligent management system based on multi-source perception | |
| CN116740649B (en) | Deep learning-based real-time detection method for behavior of crewman falling into water beyond boundary | |
| CN115496803A (en) | Collision warning and evidence obtaining system and method for offshore buoy | |
| CN111429701B (en) | Alarm method, device, equipment and storage medium | |
| CN113516091B (en) | Method for identifying electric spark image of transformer substation | |
| CN115063427A (en) | Pollutant discharge monitoring image processing method for novel ship | |
| CN114708544A (en) | Intelligent violation monitoring helmet based on edge calculation and monitoring method thereof | |
| CN115049988A (en) | Edge calculation method and device for power distribution network monitoring and prejudging | |
| CN111597524B (en) | Verification method and system for seal sample sampling personnel | |
| CN109886133A (en) | A kind of ship detection method and system based on remote sensing image | |
| CN113158725B (en) | Comprehensive engineering vehicle construction action judgment method | |
| CN117788463B (en) | Ship draft detection method based on video AI and multi-mode data fusion | |
| CN117094995B (en) | Reaction kettle gas leakage detection method, device, medium and equipment |
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 |