AI visual identification algorithm for monitoring floating objects on water surface

Abstract

The invention relates to the technical field of computer vision, and discloses an AI visual recognition algorithm for water surface floating object monitoring, which comprises the following steps: step 1, establishing a water surface monitoring data module, a water surface monitoring data calculation module, a water surface monitoring equipment optimization module and a floating object monitoring management module; 2, a water surface monitoring data module collects water surface data in real time in a non-contact mode through various sensors; step 3, a water surface monitoring data calculation module calculates the monitoring data; 4, a water surface monitoring equipment optimization module optimizes monitoring equipment parameters according to the calculation result of the water surface monitoring data calculation module; and 5, arranging a newly added monitoring task by the floating object monitoring management module according to a calculation result of the water surface monitoring data calculation module, establishing an algorithm model by taking the steps as a basic framework, and supervising the monitoring efficiency of the system. The problems of low monitoring efficiency, lack of an early warning mechanism and high operation and maintenance cost in a traditional monitoring means are solved.

Description

Technical Field

[0001] The present invention relates to the field of computer vision technology, and in particular to an AI visual recognition algorithm for monitoring floating objects on water surfaces. Background Art

[0002] As the global water pollution problem becomes increasingly serious, floating objects on the water surface have become an environmental issue that cannot be ignored. These floating objects not only affect the beauty of the water body, but also damage the aquatic ecosystem and even threaten human health. Therefore, it is particularly important to monitor and clean up garbage on the water surface in a timely and effective manner. However, in actual operation, traditional monitoring methods have the limitations of low monitoring efficiency, lack of early warning mechanism and high operation and maintenance costs. In order to overcome the above challenges, intelligent monitoring systems based on artificial intelligence (AI) visual recognition technology have emerged. Summary of the invention

[0003] 1. Technical issues to be resolved

[0004] In view of the shortcomings of the prior art, the present invention provides an AI visual recognition algorithm for monitoring floating objects on the water surface, which has the advantages of high monitoring efficiency, early warning mechanism and low operation and maintenance cost, and solves the problems of low monitoring efficiency, lack of early warning mechanism and high operation and maintenance cost in traditional monitoring methods.

[0005] (II) Technical solution

[0006] To achieve the above object, the present invention provides the following technical solution: an AI visual recognition algorithm for monitoring floating objects on the water surface, comprising the following steps:

[0007] Step 1: Establish a water surface monitoring data module, a water surface monitoring data calculation module, a water surface monitoring equipment optimization module and a floating object monitoring management module;

[0008] Step 2: The water surface monitoring data module collects water surface data in real time and non-contactly through various sensors;

[0009] Step 3: The water surface monitoring data calculation module calculates the monitoring data;

[0010] Step 4: The water surface monitoring equipment optimization module optimizes the monitoring equipment parameters according to the calculation results of the water surface monitoring data calculation module;

[0011] Step 5: The floating object monitoring management module arranges new monitoring tasks according to the calculation results of the water surface monitoring data calculation module.

[0012] Preferably, steps one to five are used as a basic framework to establish an algorithm model to supervise the monitoring efficiency of the system of the present invention, and the water surface monitoring data module includes a water surface floating object automation processing data unit, a water surface monitoring and early warning processing data unit and a system automation operation and maintenance cost data unit. The water surface floating object automation processing data unit obtains water surface floating object automation processing data through monitoring equipment and an Internet terminal, the water surface monitoring and early warning processing data unit obtains water surface monitoring and early warning processing data through an Internet terminal, and the system automation operation and maintenance cost data unit obtains system automation operation and maintenance cost data through an Internet terminal. The water surface floating object automation processing data unit, the water surface monitoring and early warning processing data unit and the system automation operation and maintenance cost data unit classify and number the internal data of the unit and then connect to the water surface monitoring data calculation module through a network.

[0013] Preferably, the water surface monitoring data calculation module includes a water surface floating object monitoring efficiency unit, a water surface monitoring and early warning efficiency unit and a system automation operation and maintenance cost efficiency unit. The water surface floating object monitoring efficiency unit calculates the water surface floating object monitoring efficiency Asl according to the water surface floating object automation processing data. The water surface monitoring and early warning efficiency unit calculates the water surface monitoring and early warning efficiency Bsl according to the water surface monitoring and early warning processing data. The system automation operation and maintenance cost efficiency unit calculates the system automation operation and maintenance cost efficiency index Zvl according to the system automation operation and maintenance cost data. The water surface floating object monitoring efficiency unit, the water surface monitoring and early warning efficiency unit and the system automation operation and maintenance cost efficiency unit are connected to the water surface monitoring equipment optimization module through a network.

[0014] Preferably, the water surface floating object automated processing data includes recording the amount of water surface floating objects processed per unit time, the accuracy ratio of the amount of water surface floating objects obtained by cross-validation of the system algorithm, the amount of water surface floating objects ideally processed per unit time and the accuracy ratio of the amount of water surface floating objects ideally processed per unit time, and numbering the data, the amount of water surface floating objects processed per unit time, the accuracy ratio of the amount of water surface floating objects obtained by cross-validation of the system algorithm, the amount of water surface floating objects ideally processed per unit time and the accuracy ratio of the amount of water surface floating objects ideally processed per unit time are numbered M respectively. r ,α,M x ,

[0015] Preferably, the water surface floating object monitoring efficiency unit calculates the water surface floating object monitoring efficiency Asl according to the water surface floating object automatic processing data, and the calculation formula is:

[0016]

[0017] In the formula, Asl represents the monitoring efficiency of floating objects on the water surface, M r,α,M x , They respectively represent the amount of floating objects on the water surface treated per unit time, the accuracy ratio of the amount of floating objects on the water surface obtained by cross-validation of the system algorithm, the amount of floating objects on the water surface ideally treated per unit time, and the accuracy ratio of the amount of floating objects on the water surface ideally treated per unit time.

[0018] Preferably, the water surface monitoring and early warning processing data includes recording the number of times that floating objects actually enter the ship channel area after the early warning, the total number of early warnings issued by the system, the average time from the issuance of the early warning of floating objects entering the ship channel area to the response action, and the early warning signal coverage rate, and the recorded information is numbered, and the number of times that floating objects actually enter the ship channel area after the early warning, the total number of early warnings issued by the system, the average time from the issuance of the early warning of floating objects entering the ship channel area to the response action, and the early warning signal coverage rate are numbered F respectively. c 、F s , t, θ.

[0019] Preferably, the water surface monitoring and early warning efficiency unit calculates the water surface monitoring and early warning efficiency Bsl according to the water surface monitoring and early warning processing data, and the calculation formula is:

[0020]

[0021] In the formula, Bsl represents the efficiency of water surface monitoring and early warning, F c 、F s , t, and θ represent the number of actual occurrences of floating objects entering the ship channel area after the warning, the total number of warnings issued by the system, the average time from the issuance of the warning of floating objects entering the ship channel area to the response action, and the warning signal coverage rate, respectively.

[0022] Preferably, the system automated operation and maintenance cost data includes statistics on the cost after automated operation and maintenance, the operation and maintenance time after automated operation and maintenance, the cost before automated operation and maintenance, and the operation and maintenance time before automated operation and maintenance, and the statistical information is numbered, and the cost after automated operation and maintenance, the operation and maintenance time after automated operation and maintenance, the cost before automated operation and maintenance, and the operation and maintenance time before automated operation and maintenance are numbered W respectively. h 、T h , W q 、T q .

[0023] Preferably, the system automation operation and maintenance cost efficiency unit calculates the system automation operation and maintenance cost efficiency index Zvl according to the system automation operation and maintenance cost data, and the calculation formula is:

[0024]

[0025] In the formula, Zvl represents the system automation operation and maintenance cost efficiency index, W h 、T h , W q 、T q They represent the cost after automated operation and maintenance, the operation and maintenance time after automated operation and maintenance, the cost before automated operation and maintenance, and the operation and maintenance time before automated operation and maintenance, respectively. h , g h They represent the weighted coefficients of system cost and operation and maintenance time after automated operation and maintenance, k q , g q They respectively represent the weighted coefficients of system cost and operation and maintenance time before automated operation and maintenance.

[0026] Preferably, the water surface monitoring equipment optimization module optimizes the monitoring equipment parameters according to the water surface floating object monitoring efficiency Asl, the water surface monitoring early warning efficiency Bsl and the system automation operation and maintenance cost efficiency index Zvl calculated by the water surface monitoring data calculation module. When the water surface floating object monitoring efficiency Asl, the water surface monitoring early warning efficiency Bsl and the system automation operation and maintenance cost efficiency index Zvl are all lower than 1, the system is automatically prompted to switch to a high camera resolution and increase the number of sensors, while improving the data transmission speed;

[0027] The floating object monitoring management module arranges new monitoring tasks according to the calculation results of the water surface monitoring data calculation module, and the tasks include adding monitoring points, adjusting monitoring frequency or introducing new monitoring technologies.

[0028] Compared with the prior art, the present invention provides an AI visual recognition algorithm for monitoring floating objects on the water surface, which has the following beneficial effects:

[0029] 1. The present invention calculates the surface floating object monitoring efficiency Asl. In the formula, the amount of surface floating objects processed per unit time is compared with the amount of surface floating objects ideally processed per unit time, which can directly reflect the working efficiency of the monitoring system of the present invention. When the surface floating object monitoring efficiency Asl is too low, the monitoring efficiency can be improved by optimizing the monitoring equipment and increasing the processing speed of the system algorithm, thereby meeting the demand for real-time monitoring of the movement of floating objects, ensuring the authenticity of the monitoring data, and reducing the situation of system false alarms and omissions.

[0030] 2. The present invention calculates the system automation operation and maintenance cost efficiency index Zvl and compares the costs before and after the automation operation and maintenance, so as to intuitively see the economic benefits brought by automation and reduce the investment of human and material resources.

[0031] 3. The present invention calculates the water surface monitoring and early warning efficiency Bsl through the water surface monitoring and early warning efficiency unit, and monitors the water surface monitoring and early warning efficiency Bsl in real time through the system. When the water surface monitoring and early warning efficiency Bsl is lower than 1, it indicates that the early warning performance of the system is low. By correcting and optimizing the system monitoring equipment parameters, the early warning performance of the system can be increased, so that the system can detect abnormal conditions in the first time and send out early warning signals in time, thereby taking measures in advance to prevent the occurrence of disasters. This adjustment method not only solves the problem of lack of early warning mechanism in traditional monitoring means, but also improves the performance of the entire monitoring and early warning system by improving the accuracy, response speed and coverage of the early warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a schematic diagram of the structure of the present invention. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] See also Figure 1 , an AI visual recognition algorithm for monitoring floating objects on the water surface, including the following steps:

[0035] Step 1: Establish a water surface monitoring data module, a water surface monitoring data calculation module, a water surface monitoring equipment optimization module and a floating object monitoring management module;

[0036] Step 2: The water surface monitoring data module collects water surface data in real time and non-contactly through various sensors;

[0037] Step 3: The water surface monitoring data calculation module calculates the monitoring data;

[0038] Step 4: The water surface monitoring equipment optimization module optimizes the monitoring equipment parameters according to the calculation results of the water surface monitoring data calculation module;

[0039] Step 5: The floating object monitoring management module arranges new monitoring tasks according to the calculation results of the water surface monitoring data calculation module.

[0040] Based on steps 1 to 5 as the basic framework, an algorithm model is established to supervise the monitoring efficiency of the system of the present invention, solving the problems of low monitoring efficiency, lack of early warning mechanism and high operation and maintenance cost in traditional monitoring methods;

[0041] The water surface monitoring data module includes a water surface floating object automation processing data unit, a water surface monitoring and early warning processing data unit and a system automation operation and maintenance cost data unit. The water surface floating object automation processing data unit obtains water surface floating object automation processing data through monitoring equipment and Internet terminals, the water surface monitoring and early warning processing data unit obtains water surface monitoring and early warning processing data through Internet terminals, and the system automation operation and maintenance cost data unit obtains system automation operation and maintenance cost data through Internet terminals. The water surface floating object automation processing data unit, the water surface monitoring and early warning processing data unit and the system automation operation and maintenance cost data unit classify and number the internal data of the units and then connect them to the water surface monitoring data calculation module through the network.

[0042] The water surface monitoring data calculation module includes a water surface floating object monitoring efficiency unit, a water surface monitoring and early warning efficiency unit and a system automation operation and maintenance cost efficiency unit. The water surface floating object monitoring efficiency unit calculates the water surface floating object monitoring efficiency Asl according to the water surface floating object automation processing data. The water surface monitoring and early warning efficiency unit calculates the water surface monitoring and early warning efficiency Bsl according to the water surface monitoring and early warning processing data. The system automation operation and maintenance cost efficiency unit calculates the system automation operation and maintenance cost efficiency index Zvl according to the system automation operation and maintenance cost data. The water surface floating object monitoring efficiency unit, the water surface monitoring and early warning efficiency unit and the system automation operation and maintenance cost efficiency unit are connected to the water surface monitoring equipment optimization module through a network.

[0043] The data of automatic processing of floating objects on the water surface include recording the amount of floating objects on the water surface processed per unit time, the accuracy ratio of the amount of floating objects on the water surface obtained by cross-validation of the system algorithm, the amount of floating objects on the water surface ideally processed per unit time and the accuracy ratio of the amount of floating objects on the water surface ideally processed per unit time, and numbering the data. The amount of floating objects on the water surface processed per unit time, the accuracy ratio of the amount of floating objects on the water surface obtained by cross-validation of the system algorithm, the amount of floating objects on the water surface ideally processed per unit time and the accuracy ratio of the amount of floating objects on the water surface ideally processed per unit time are numbered M, respectively. r ,α,M x , By monitoring and recording data through AI digital-visual fusion technology, real-time monitoring and identification of floating objects on the water surface can be achieved, avoiding the time delay of manual inspections in traditional methods.

[0044] The water surface floating object monitoring efficiency unit calculates the water surface floating object monitoring efficiency Asl according to the water surface floating object automatic processing data, and the calculation formula is:

[0045]

[0046] In the formula, Asl represents the monitoring efficiency of floating objects on the water surface, M r ,α,M x , They respectively represent the amount of floating objects on the water surface treated per unit time, the accuracy ratio of the amount of floating objects on the water surface obtained by cross-validation of the system algorithm, the amount of floating objects on the water surface ideally treated per unit time, and the accuracy ratio of the amount of floating objects on the water surface ideally treated per unit time.

[0047] The advantages are: by calculating the water surface floating object monitoring efficiency Asl, the amount of water surface floating objects processed per unit time is compared with the amount of water surface floating objects ideally processed per unit time in the formula, which can directly reflect the working efficiency of the monitoring system of the present invention. When the water surface floating object monitoring efficiency Asl is too low, the monitoring efficiency can be improved by optimizing the monitoring equipment and increasing the processing speed of the system algorithm, thereby meeting the needs of real-time monitoring of the movement of floating objects, ensuring the authenticity of the monitoring data, and reducing the situation of system false alarms and omissions.

[0048] The surface monitoring and early warning processing data includes the number of actual occurrences of floating objects entering the ship channel area after the warning, the total number of warnings issued by the system, the average time from the issuance of the warning of floating objects entering the ship channel area to the response action, and the warning signal coverage rate. The recorded information is numbered, and the number of actual occurrences of floating objects entering the ship channel area after the warning, the total number of warnings issued by the system, the average time from the issuance of the warning of floating objects entering the ship channel area to the response action, and the warning signal coverage rate are numbered F respectively. c 、F s ,t,θ,Using intelligent video analysis and machine learning technology, the system can automatically identify different types of floating objects, classify and count them, improving the pertinence and effectiveness of early warning.

[0049] The water surface monitoring and early warning efficiency unit calculates the water surface monitoring and early warning efficiency Bsl according to the water surface monitoring and early warning processing data. The calculation formula is:

[0050]

[0051] In the formula, Bsl represents the efficiency of water surface monitoring and early warning, F c 、F s , t, and θ represent the number of actual occurrences of floating objects entering the ship channel area after the warning, the total number of warnings issued by the system, the average time from the issuance of the warning of floating objects entering the ship channel area to the response action, and the warning signal coverage rate, respectively.

[0052] The advantages are: the water surface monitoring and early warning efficiency Bsl calculated by the water surface monitoring and early warning efficiency unit is monitored in real time by the system. When the water surface monitoring and early warning efficiency Bsl is lower than 1, it means that the early warning performance of the system is low. By correcting and optimizing the system monitoring equipment parameters, the early warning performance of the system can be increased, so that the system can detect abnormal situations in the first time and send out early warning signals in time, so as to take measures in advance to prevent the occurrence of disasters. This adjustment method not only solves the problem of lack of early warning mechanism in traditional monitoring means, but also improves the performance of the entire monitoring and early warning system by improving the accuracy, response speed and coverage of the early warning.

[0053] The system automated operation and maintenance cost data includes the cost after automated operation and maintenance, the operation and maintenance time after automated operation and maintenance, the cost before automated operation and maintenance, and the operation and maintenance time before automated operation and maintenance. The statistical information is numbered, and the cost after automated operation and maintenance, the operation and maintenance time after automated operation and maintenance, the cost before automated operation and maintenance, and the operation and maintenance time before automated operation and maintenance are numbered W respectively. h 、T h , W q 、T q .

[0054] The system automation operation and maintenance cost efficiency unit calculates the system automation operation and maintenance cost efficiency index Zvl according to the system automation operation and maintenance cost data. The calculation formula is:

[0055]

[0056] In the formula, Zvl represents the system automation operation and maintenance cost efficiency index, W h 、T h , W q 、T q They represent the cost after automated operation and maintenance, the operation and maintenance time after automated operation and maintenance, the cost before automated operation and maintenance, and the operation and maintenance time before automated operation and maintenance, respectively. h , g h They represent the weighted coefficients of system cost and operation and maintenance time after automated operation and maintenance, k q , g q They respectively represent the weighted coefficients of system cost and operation and maintenance time before automated operation and maintenance.

[0057] The advantage is that by calculating the system automation operation and maintenance cost efficiency index Zvl and comparing the costs before and after automated operation and maintenance, the economic benefits brought by automation can be intuitively seen, reducing the investment in human and material resources.

[0058] The water surface monitoring equipment optimization module optimizes the monitoring equipment parameters according to the water surface floating object monitoring efficiency Asl, water surface monitoring early warning efficiency Bsl and system automation operation and maintenance cost efficiency index Zvl calculated by the water surface monitoring data calculation module. When the water surface floating object monitoring efficiency Asl, water surface monitoring early warning efficiency Bsl and system automation operation and maintenance cost efficiency index Zvl are all lower than 1, the system is automatically prompted to switch to high camera resolution and increase the number of sensors, while improving the data transmission speed;

[0059] The advantages are: through real-time analysis of the water surface monitoring data calculation module, the water surface monitoring equipment optimization module can immediately discover the problem of low monitoring efficiency and automatically prompt the system to make necessary adjustments, such as switching to high camera resolution or increasing the number of sensors. This real-time performance ensures that the monitoring system can respond quickly to environmental changes and improve the accuracy and efficiency of monitoring.

[0060] The floating object monitoring management module arranges new monitoring tasks according to the calculation results of the water surface monitoring data calculation module. The tasks include adding monitoring points, adjusting the monitoring frequency or introducing new monitoring technologies to ensure the comprehensiveness and accuracy of the monitoring.

[0061] The advantages are: the floating object monitoring management module not only focuses on the comprehensiveness of monitoring, but also emphasizes the accuracy of monitoring data based on the calculation results of monitoring data. By adding monitoring points, adjusting the monitoring frequency or introducing new monitoring technologies, it ensures all-round and high-precision monitoring of floating objects on the water surface.

[0062] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An AI visual recognition algorithm for monitoring floating objects on the water surface, characterized in that: The following steps are involved: Step 1: Establish a water surface monitoring data module, a water surface monitoring data calculation module, a water surface monitoring equipment optimization module and a floating object monitoring management module; Step 2: The water surface monitoring data module collects water surface data in real time and non-contactly through various sensors; Step 3: The water surface monitoring data calculation module calculates the monitoring data; Step 4: The water surface monitoring equipment optimization module optimizes the monitoring equipment parameters according to the calculation results of the water surface monitoring data calculation module; Step 5: The floating object monitoring management module arranges new monitoring tasks according to the calculation results of the water surface monitoring data calculation module.

2. The AI ​​visual recognition algorithm for monitoring floating objects on the water surface according to claim 1 is characterized in that: The steps one to five are used as a basic framework to establish an algorithm model to supervise the monitoring efficiency of the system of the present invention. The water surface monitoring data module includes a water surface floating object automation processing data unit, a water surface monitoring and early warning processing data unit and a system automation operation and maintenance cost data unit. The water surface floating object automation processing data unit obtains water surface floating object automation processing data through monitoring equipment and an Internet terminal, the water surface monitoring and early warning processing data unit obtains water surface monitoring and early warning processing data through an Internet terminal, and the system automation operation and maintenance cost data unit obtains system automation operation and maintenance cost data through an Internet terminal. The water surface floating object automation processing data unit, the water surface monitoring and early warning processing data unit and the system automation operation and maintenance cost data unit classify and number the internal data of the unit and then connect to the water surface monitoring data calculation module through a network.

3. The AI ​​visual recognition algorithm for monitoring floating objects on the water surface according to claim 1 is characterized in that: The water surface monitoring data calculation module includes a water surface floating object monitoring efficiency unit, a water surface monitoring and early warning efficiency unit and a system automation operation and maintenance cost efficiency unit. The water surface floating object monitoring efficiency unit calculates the water surface floating object monitoring efficiency Asl according to the water surface floating object automation processing data. The water surface monitoring and early warning efficiency unit calculates the water surface monitoring and early warning efficiency Bsl according to the water surface monitoring and early warning processing data. The system automation operation and maintenance cost efficiency unit calculates the system automation operation and maintenance cost efficiency index Zvl according to the system automation operation and maintenance cost data. The water surface floating object monitoring efficiency unit, the water surface monitoring and early warning efficiency unit and the system automation operation and maintenance cost efficiency unit are connected to the water surface monitoring equipment optimization module through a network.

4. The AI ​​visual recognition algorithm for monitoring floating objects on the water surface according to claim 1 is characterized in that: The water surface floating object automatic processing data includes recording the amount of water surface floating objects processed per unit time, the accuracy ratio of the amount of water surface floating objects obtained by cross-validation of the system algorithm, the amount of water surface floating objects ideally processed per unit time and the accuracy ratio of the amount of water surface floating objects ideally processed per unit time, and numbering the data, the amount of water surface floating objects processed per unit time, the accuracy ratio of the amount of water surface floating objects obtained by cross-validation of the system algorithm, the amount of water surface floating objects ideally processed per unit time and the accuracy ratio of the amount of water surface floating objects ideally processed per unit time are numbered M respectively r ,α,M x , 5. The AI ​​visual recognition algorithm for monitoring floating objects on the water surface according to claim 4 is characterized in that: The water surface floating object monitoring efficiency unit calculates the water surface floating object monitoring efficiency Asl according to the water surface floating object automatic processing data, and the calculation formula is: In the formula, Asl represents the monitoring efficiency of floating objects on the water surface, M r ,α,M x , They respectively represent the amount of floating objects on the water surface treated per unit time, the accuracy ratio of the amount of floating objects on the water surface obtained by cross-validation of the system algorithm, the amount of floating objects on the water surface ideally treated per unit time, and the accuracy ratio of the amount of floating objects on the water surface ideally treated per unit time.

6. The AI ​​visual recognition algorithm for monitoring floating objects on the water surface according to claim 1 is characterized by: The surface monitoring and early warning processing data includes recording the number of actual occurrences of floating objects entering the ship channel area after the early warning, the total number of early warnings issued by the system, the average time from the issuance of the early warning of floating objects entering the ship channel area to the response action, and the early warning signal coverage rate, and the recorded information is numbered, and the number of actual occurrences of floating objects entering the ship channel area after the early warning, the total number of early warnings issued by the system, the average time from the issuance of the early warning of floating objects entering the ship channel area to the response action, and the early warning signal coverage rate are numbered F and F, respectively. c 、F s , t, θ.

7. The AI ​​visual recognition algorithm for monitoring floating objects on the water surface according to claim 5 is characterized by: The water surface monitoring and early warning efficiency unit calculates the water surface monitoring and early warning efficiency Bsl according to the water surface monitoring and early warning processing data, and its calculation formula is: In the formula, Bsl represents the efficiency of water surface monitoring and early warning, F c 、F s , t, and θ represent the number of actual occurrences of floating objects entering the ship channel area after the warning, the total number of warnings issued by the system, the average time from the issuance of the warning of floating objects entering the ship channel area to the response action, and the warning signal coverage rate, respectively.

8. The AI ​​visual recognition algorithm for monitoring floating objects on the water surface according to claim 1 is characterized by: The system automated operation and maintenance cost data includes the cost after automated operation and maintenance, the operation and maintenance time after automated operation and maintenance, the cost before automated operation and maintenance, and the operation and maintenance time before automated operation and maintenance, and the statistical information is numbered, and the cost after automated operation and maintenance, the operation and maintenance time after automated operation and maintenance, the cost before automated operation and maintenance, and the operation and maintenance time before automated operation and maintenance are numbered W respectively. h , T h , W q , T q .

9. The AI ​​visual recognition algorithm for monitoring floating objects on the water surface according to claim 8 is characterized by: The system automation operation and maintenance cost efficiency unit calculates the system automation operation and maintenance cost efficiency index Zvl according to the system automation operation and maintenance cost data, and the calculation formula is: In the formula, Zvl represents the system automation operation and maintenance cost efficiency index, W h , T h , W q , T q They represent the cost after automated operation and maintenance, the operation and maintenance time after automated operation and maintenance, the cost before automated operation and maintenance, and the operation and maintenance time before automated operation and maintenance, respectively. h , g h They represent the weighted coefficients of system cost and operation and maintenance time after automated operation and maintenance, k q , g q They respectively represent the weighted coefficients of system cost and operation and maintenance time before automated operation and maintenance.

10. The AI ​​visual recognition algorithm for monitoring floating objects on the water surface according to claim 1 is characterized by: The water surface monitoring equipment optimization module optimizes the monitoring equipment parameters according to the water surface floating object monitoring efficiency Asl, the water surface monitoring early warning efficiency Bsl and the system automation operation and maintenance cost efficiency index Zvl calculated by the water surface monitoring data calculation module. When the water surface floating object monitoring efficiency Asl, the water surface monitoring early warning efficiency Bsl and the system automation operation and maintenance cost efficiency index Zvl are all lower than 1, the system is automatically prompted to switch to a high camera resolution and increase the number of sensors, while improving the data transmission speed; The floating object monitoring management module arranges new monitoring tasks according to the calculation results of the water surface monitoring data calculation module, and the tasks include adding monitoring points, adjusting monitoring frequency or introducing new monitoring technologies.

Images