Intelligent safety supervision system applied to ship

Patent metadata

Field	Value
Publication number	US-12573186-B2
Application number	US-202318236859-A
Country	US
Kind code	B2
Filing date	Aug 22, 2023
Priority date	Apr 13, 2023
Publication date	Mar 10, 2026
Grant date	Mar 10, 2026

Abstract

An intelligent safety supervision system applied to a ship is provided. An image acquisition module acquires high-definition images in real time. An automatic recognition module obtains ship dynamic and static data. A ship server performs feature recognition on the ship dynamic and static data to obtain a data processing result, transmits the ship dynamic and static data and the data processing result, and receives alarm indication information. An alarm module outputs an alarm. A ship client displays the data processing result, and determines whether to transmit the alarm indication information according to the data processing result. A communication module receives and transmits the ship dynamic and static data and the data processing result. A shore-side supervision system includes a ship safety supervision big data analysis platform for performing secondary feature recognition on the ship dynamic and static data, so as to obtain a secondary data processing result.

First claim

What is claimed is:

1 . An intelligent safety supervision system applied to a ship, comprising a ship-side supervision system and a shore-side supervision system;
the ship-side supervision system comprising: an image acquisition module, configured to acquire high-definition images in real time; an automatic recognition module, configured to obtain ship dynamic data and ship static data by a deep learning algorithm of a convolution neural network at least according to the high-definition images; a ship server, connected to the automatic recognition module, and configured to: perform feature recognition on the ship dynamic data and the ship static data to obtain a data processing result, wherein the feature recognition comprises big data storage analysis and behavior recognition, wherein the data processing result at least comprises: normal temperature data or abnormal temperature data, a normal position or an abnormal position, a normal velocity or an abnormal velocity, a normal course or an abnormal course, normal smoke data or abnormal smoke data, a normal water pressure or an abnormal water pressure, a normal water level or an abnormal water level, a normal depth or an abnormal depth, and normal on-duty or off-post data; transmit the ship dynamic data, the ship static data and the data processing result, and receive alarm indication information; an alarm module, connected to the ship server, and configured to output an alarm according to the alarm indication information; a ship client, connected to the ship server, and configured to: display the data processing result, determine whether to transmit the alarm indication information according to the data processing result, transmit the alarm indication information if a feature value in the data processing result is greater than or equal to a first predetermined threshold value, and transmit normal operation information if the feature value in the data processing result is less than the first predetermined threshold value; and a communication module, connected to the ship server, and configured to transmit and receive the ship dynamic data, the ship static data and the data processing result; and the shore-side supervision system comprising: a ship safety supervision big data analysis platform, configured to: perform secondary feature recognition on the ship dynamic data and the ship static data using the deep learning algorithm of the convolution neural network, so as to obtain a secondary data processing result, a land client, connected to the ship safety supervision big data analysis platform, and configured to: display the ship dynamic data, the ship static data, the data processing result and the secondary data processing result, determine whether to transmit the alarm indication information according to the secondary data processing result, transmit the alarm indication information if a feature value in the secondary data processing result is greater than or equal to the first predetermined threshold value; transmit the normal operation information if the feature value in the secondary data processing result is less than the first predetermined threshold value; and obtaining an overlap rate by comparing a number of times that the ship safety supervision big data analysis platform transmits the alarm indication information with a number of times that the ship client transmits the alarm indication information, wherein in responding to the overlap rate being greater than or equal to a second predetermined threshold, an output alarm is accurate; and in responding to the overlap rate being less than the second preset threshold, the output alarm is inaccurate.

2 . The intelligent safety supervision system according to claim 1 , wherein the ship-side supervision system further comprises:
a fire monitoring module, connected to the ship server, and configured to: obtain the alarm indication information, smoke data, water pressure data and water level data of the ship, and transmit the smoke data, the water pressure data and the water level data of the ship, and perform fire extinguishing according to the alarm indication information.

3 . The intelligent safety supervision system according to claim 1 , wherein the shore-side supervision system further comprises
a land server, connected to the communication module, and configured to: receive the ship dynamic data, the ship static data and the data processing result, and classify and store the ship dynamic data, the ship static data and the data processing result.

4 . The intelligent safety supervision system according to claim 2 , wherein
the ship dynamic data comprises at least one of ship fire data, staff on-duty data, ship position data, ship velocity data, ship course data, the smoke data, the water pressure data and the water level data; the ship static data comprises at least one of a ship name, a call sign, and a ship draft.

5 . The intelligent safety supervision system according to claim 1 , wherein the ship-side supervision system further comprises:
a master clock, connected to the ship server, and configured to provide a unified time reference for a slave clock on the ship and the ship server.

6 . The intelligent safety supervision system according to claim 1 , wherein the ship server comprises:
a feature fusion grading unit, configured to grade fusion features under an influence of different factors in the ship dynamic data and the ship static data according to a character feature fusion method, so as to obtain a feature fusion grading, wherein the different factors comprise: color, illumination, or a pitch angle, and a feature fusion grading function is:

f
j

=

∑

i
=
1

U

⁢

a
i

⁢

η
i

,

j
=
1

,
2
,
3
,
…

,

n
;

wherein a number of feature components under the influence of different factors is U, f i is a fusion feature of a j-th person under the influence of different factors, η i is a feature component prior to fusion, and a i is a weight of a fusion feature component.

7 . The intelligent safety supervision system according to claim 1 , wherein the ship safety supervision big data analysis platform comprises:
a prediction unit, configured to predict a current state value based on a prior state value by using a state prediction equation, so as to obtain a priori state estimate value {circumflex over (x)} k ; and an update unit, configured to optimize and update the priori state estimate value {circumflex over (x)} k using a Kalman gain coefficient equation and a state update equation, so as to obtain a posteriori state estimate value {circumflex over (X)} k , wherein the posteriori state estimate value {circumflex over (X)} k is the secondary data processing result.

Assignees

• Univ Chengdu Technology

Inventors

• Cai Dongsheng
• Huang Qi
• Li Jian

Classifications

• G08B31/00

  Predictive alarm systems characterised by extrapolation or other computation using updated historic data · CPC title

• G08B21/182

  Level alarms, e.g. alarms responsive to variables exceeding a threshold · CPC title

• A62C3/10 Primary

  in ships {(A62C3/0207 takes precedence)} · CPC title

• G06V10/82

  using neural networks · CPC title

• G06V20/52

  Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) · CPC title