Intelligent safety supervision system applied to ship

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.