Method and system for monitoring and early warning of canal water surface oil spill, and electronic device

Abstract

The application discloses a kind of canal water surface oil spill monitoring and early warning method and system, electronic equipment, it is related to canal monitoring field, wherein, the method comprises: obtaining the multi-source data set of canal water area, the spatial position and geometric feature of oil film at different time points are identified based on multiple oil film detection images in unmanned aerial vehicle monitoring data, oil concentration distribution change is determined in combination with the real-time monitoring data of shore-based fixed monitoring station and oil film diffusion area is evaluated, the water area data where the ship is located collected by ship self-monitoring system is analyzed, the water body oil concentration parameter and oil droplet size parameter of the water area where the ship is located are obtained, oil film thickness is determined in combination with unmanned aerial vehicle monitoring data, real-time monitoring data of shore-based fixed monitoring station, water body oil concentration parameter and oil droplet size parameter, and canal oil spill monitoring and early warning report is generated.The application solves the technical problem that in the related art, when monitoring canal ship oil spill, the diffusion of oil spill cannot be captured, and the accuracy of oil spill pollution assessment is low.

Description

Technical Field

[0001] This invention relates to the field of canal monitoring technology or other related fields. Specifically, it relates to a monitoring and early warning method and system, and electronic equipment for oil spills on the surface of canals. Background Technology

[0002] Oil spills and pollutant discharges from ships have become serious environmental problems in busy canal shipping, posing a significant threat to the ecological balance of water bodies, water quality safety, and even human health. Large ships, in particular, are prone to oil spills when navigating narrow canals due to operational errors, equipment malfunctions, or severe weather. Once an oil slick forms, it spreads rapidly due to its fast diffusion, wide pollution area, and difficulty in cleanup, seriously affecting the canal's ecology and shipping safety.

[0003] Existing monitoring technologies have revealed several limitations in addressing this issue. On the one hand, traditional monitoring methods, such as manual patrols and fixed-point water sampling, suffer from low efficiency, narrow coverage, and slow response, making it difficult to promptly and accurately detect the occurrence and spread of oil spills. On the other hand, while advanced technologies such as drone monitoring and ship self-monitoring systems have emerged, in practical applications, drone monitoring, although capable of rapid and wide-area coverage, suffers from limited image recognition accuracy due to factors such as cloud cover and changes in lighting conditions, especially at night or in adverse weather conditions, significantly reducing monitoring efficiency. Ship self-monitoring systems provide relatively accurate monitoring of the ship's own emissions, but lack the ability to directly observe external environmental factors such as oil slick spread, failing to provide details on the distribution of the oil slick on the water surface.

[0004] Furthermore, data acquired using different technologies differ in format, temporal and spatial resolution. The lack of an effective mechanism to integrate this heterogeneous data into consistent monitoring information results in low data utilization and hinders the construction of comprehensive and accurate oil spill event models. For example, images captured by drones do not match water quality data from shore-based monitoring stations in time and space, making effective correlation impossible and resulting in a lack of depth and breadth in predicting oil film diffusion trends.

[0005] Furthermore, current technologies are too simplistic in oil film analysis, often only considering the diffusion area of ​​the oil film while neglecting the intrinsic relationship between the oil film's thickness, shape, and other multi-dimensional characteristics and diffusion behavior. This results in an incomplete assessment and early warning of oil spill events, making it difficult to effectively guide emergency response and pollution control efforts.

[0006] There is currently no effective solution to the above problems. Summary of the Invention

[0007] This invention provides a method, system, and electronic equipment for monitoring and early warning of oil spills on canal surfaces, in order to at least solve the technical problems in related technologies where the spread of oil spills cannot be captured when monitoring oil spills from ships in canals, resulting in low accuracy in assessing oil pollution.

[0008] According to one aspect of the present invention, a method for monitoring and early warning of oil spills on a canal surface is provided, comprising: acquiring a multi-source data set of a target canal water area, wherein the multi-source data set includes at least: UAV monitoring data, real-time monitoring data from shore-based fixed monitoring stations, and data on the water area where a vessel is located collected by a vessel self-monitoring system; identifying the spatial location and geometric features of the oil film at different time points based on multiple oil film detection images in the UAV monitoring data; determining the oil concentration distribution change based on the spatial location and geometric features of the oil film, combined with the real-time monitoring data from the shore-based fixed monitoring stations, and assessing the oil film diffusion area based on the oil concentration distribution change; analyzing the water area data of the vessel located collected by the vessel self-monitoring system to obtain water oil concentration parameters and oil droplet size parameters of the water area where the vessel is located, and determining the oil film thickness by combining the UAV monitoring data, the real-time monitoring data from the shore-based fixed monitoring stations, the water oil concentration parameters, and the oil droplet size parameters; and generating a canal oil spill monitoring and early warning report by comprehensively considering the spatial location and geometric features of the oil film at different time points, the oil film diffusion area, and the oil film thickness.

[0009] According to another aspect of the present invention, a monitoring and early warning system for oil spills on a canal surface is also provided, comprising: a multi-source data acquisition unit, used to acquire a multi-source data set of a related target canal water area, wherein the multi-source data set includes at least: UAV monitoring data, real-time monitoring data from shore-based fixed monitoring stations, and data on the water area where the vessel is located collected by a vessel self-monitoring system; an oil film shape analysis unit, used to identify the spatial location and geometric features of the oil film at different time points based on multiple oil film detection images in the UAV monitoring data; and an oil film diffusion area assessment unit, used to assess the spatial location and geometric features of the oil film, combined with the data from shore-based fixed monitoring stations. The system uses real-time monitoring data from fixed monitoring stations to determine changes in oil concentration distribution and assess the oil film diffusion area based on these changes. An oil film thickness analysis unit analyzes data from the ship's self-monitoring system to obtain water oil concentration parameters and oil droplet size parameters. This data, combined with UAV monitoring data, real-time monitoring data from shore-based fixed monitoring stations, the water oil concentration parameters, and the oil droplet size parameters, determines the oil film thickness. A monitoring report generation unit integrates the spatial location and geometric characteristics of the oil film at different time points, the oil film diffusion area, and the oil film thickness to generate a canal oil spill monitoring and early warning report.

[0010] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the above-described method for monitoring and early warning of oil spills on the canal surface.

[0011] According to another aspect of the present invention, an electronic device is also provided, including one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the above-described method for monitoring and early warning of oil spills on the canal surface.

[0012] According to another aspect of the present invention, a computer program product is also provided, comprising a computer program that, when executed by a processor, implements the steps of the monitoring and early warning method for oil spills on the canal surface as described in any of the above embodiments.

[0013] This disclosure enables the establishment of an accurate prediction model based on a multi-source dataset, which comprehensively analyzes changes in oil film shape, diffusion area, and thickness. This allows for the accurate assessment of the diffusion, thickness, and shape of oil film in canal spill areas. Through accurate prediction and rapid response, the environmental damage caused by oil spills is effectively reduced. This achieves effective analysis between oil film characteristics and environmental factors, thereby solving the technical problem in related technologies where the diffusion of oil spills cannot be captured when monitoring oil spills from canal vessels, resulting in low accuracy in assessing oil spill pollution. Attached Figure Description

[0014] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0015] Figure 1 This is a flowchart of an optional method for monitoring and early warning of oil spills on the surface of a canal according to an embodiment of the present invention;

[0016] Figure 2 This is a schematic diagram of an optional monitoring and early warning system for oil spills on the canal surface according to an embodiment of the present invention;

[0017] Figure 3 This is a hardware structure block diagram of an electronic device (or mobile device) for implementing a method for monitoring and early warning of oil spills on the canal surface according to an embodiment of the present invention. Detailed Implementation

[0018] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0019] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0020] To facilitate understanding of the present invention by those skilled in the art, some terms or nouns involved in the various embodiments of the present invention are explained below:

[0021] A multispectral camera (MC) can acquire spectral information in different wavelength bands, which is crucial for analyzing the composition and thickness of oil films.

[0022] LiDAR, or Light Detection and Ranging, uses laser pulses to emit and receive reflected signals to measure information such as water level and topography, which helps determine the coverage and thickness changes of oil films.

[0023] An oil film sensor (OFS) uses optical or electrical principles to detect the presence of an oil film on the water surface and is one of the core components of a shore-based fixed monitoring station.

[0024] Oil-Water Separator Monitoring Device (OWSD) is a key component of a ship's self-monitoring system. It monitors in real time whether the oily wastewater discharged from ships meets the standards.

[0025] Marine Exhaust Gas Monitoring Device (MEGMD) is used to detect the levels of pollutants in ship exhaust, such as sulfur oxides and nitrogen oxides, to monitor the compliance of ship emissions.

[0026] A Raman spectrometer (RS) estimates oil film thickness and provides quantitative analysis of oil film properties by measuring the ratio of Raman spectral intensities and combining this with a model showing the relationship between oil film thickness and the Raman spectral intensity ratio.

[0027] Coordinate Unification Processing (CUP) transforms data from UAVs, shore-based monitoring stations, and ship self-monitoring systems into the same coordinate system to ensure accurate spatial correspondence of the data.

[0028] The Sauvola algorithm, or Sauvola Binarization Algorithm (SBA) for short, is a local adaptive thresholding method used to dynamically adjust the threshold in local regions of an image, thereby improving background segmentation.

[0029] It should be noted that the information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, and displayed data) collected in this public disclosure are information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of related data all comply with the relevant laws, regulations, and standards of the relevant regions, necessary confidentiality measures have been taken, and they do not violate public order and good morals. Corresponding operation entry points are provided for users to choose to authorize or refuse. For example, this system has interfaces with relevant users or organizations. Before obtaining relevant information, a request to obtain the information needs to be sent to the aforementioned user or organization through the interface, and the relevant information is obtained only after receiving consent from the aforementioned user or organization.

[0030] It should be noted that in this disclosure, customer information is collected and analyzed, and users are provided with corresponding operation entry points to choose whether to agree to or reject the automated decision results; if the user chooses to reject, the process will proceed to the expert decision-making process.

[0031] The following embodiments of the present invention can be applied to various systems for monitoring and early warning of oil spills on canal surfaces. The present invention is applicable to scenarios such as environmental monitoring and protection, and intelligent shipping, especially for monitoring and early warning of ship oil spills and pollutant emissions in large canals. For example, in environmental supervision and emergency response, the present invention can be used to quickly locate the source of the oil spill, assess the scope of pollution, initiate emergency response measures, and reduce the risk of environmental pollution.

[0032] This invention achieves comprehensive and high-precision monitoring of oil spills from ships in canals by integrating data acquired from drones, shore-based fixed monitoring stations, and ship-based self-monitoring systems. The mobility of drones and the continuous monitoring capabilities of shore-based stations, combined with the direct monitoring of pollution sources by ship-based self-monitoring systems, significantly improve the response speed and data reliability of the monitoring system. Furthermore, this invention can establish accurate predictive models based on multi-source data sets, comprehensively analyzing changes in oil film shape, diffusion area, and thickness, enabling intelligent early warning and providing decision-making support for relevant departments.

[0033] This invention effectively reduces the environmental damage caused by oil spills through accurate prediction and rapid response, reduces subsequent cleanup and repair costs, and avoids high equipment investment and maintenance costs by making reasonable use of different monitoring methods.

[0034] This invention integrates data acquired from UAVs, shore-based fixed monitoring stations, and ship self-monitoring systems, and performs coordinate unification processing on data from different sources. Detailed coordinate transformation steps are developed for both UAVs (mobile sensors) and shore-based fixed monitoring stations (fixed sensors), while also addressing data format differences. Data from different sources is converted into a unified format, facilitating subsequent integration, processing, and analysis. A complete dataset is formed and stored in a database, ensuring data consistency and integrity and providing a reliable foundation for subsequent analysis.

[0035] In the prediction and analysis of oil film diffusion areas, this invention combines data from shore-based fixed monitoring stations to select influencing factors and establish an oil film diffusion equation, comprehensively considering multiple effects such as convection, diffusion, degradation, and buoyancy. Simultaneously, it uses multi-source data sets to assess and refine the oil film diffusion area. Unmanned aerial vehicles (UAVs) can analyze the overall morphology and diffusion trend of the oil film and adjust the diffusion coefficient; ship-based self-monitoring systems can provide oil concentration data and water flow information at different locations, assisting in correcting the parameters of the oil film diffusion equation. In the prediction and analysis of oil film thickness, Raman spectral reference information is introduced to establish a relationship model between oil film thickness and the ratio of Raman spectral intensity. This model, combined with the spatial location and geometric characteristics of the oil film and the prediction information of the oil film diffusion area, corrects and predicts the oil film thickness, achieving effective analysis between oil film characteristics and environmental factors.

[0036] The present invention will now be described in detail with reference to various embodiments.

[0037] Example 1

[0038] According to an embodiment of the present invention, an embodiment of a method for monitoring and early warning of oil spills on the surface of a canal is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0039] This invention utilizes intelligent monitoring and early warning systems for oil spills and pollutants from ships in canals to monitor and accurately predict oil spills and pollutant emissions from ships in the canals in real time, and to issue timely warnings in order to reduce the risk of environmental pollution in the canals and ensure the safety of the canal's ecological environment. The specific monitoring and early warning methods are illustrated below.

[0040] Figure 1 This is a flowchart of an optional monitoring and early warning method for oil spills on a canal surface according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps S101 to S105, and each step is described in detail below.

[0041] Step S101: Obtain a multi-source data set of the associated target canal waters. The multi-source data set includes at least: UAV monitoring data, real-time monitoring data from shore-based fixed monitoring stations, and data on the waters where the ship is located collected by the ship self-monitoring system.

[0042] Optionally, the steps of acquiring a multi-source data set of the associated target canal waterway include: equipping the UAV with a high-definition camera, a multispectral camera, and a lidar; controlling the UAV to fly along a preset route in the target canal waterway; using the high-definition camera to take real-time water surface photos of the target canal waterway; using the multispectral camera to acquire spectral information of different bands; and using the lidar to measure water surface height and terrain information to obtain UAV monitoring data; installing multiple types of sensors at fixed bank-based locations on both banks of the target canal waterway; and using the multiple types of sensors to collect data of the target canal waterway waterway to obtain real-time monitoring data from the fixed bank-based monitoring stations. The multiple types of sensors include at least one of the following: oil film sensors, water... Water quality sensors and meteorological sensors are used. Oil film sensors detect the optical or electrical properties of the water surface. Water quality sensors monitor the content of petroleum substances and chemical oxygen demand in the canal water. Meteorological sensors collect meteorological data, which includes at least one of the following: wind speed, wind direction, and temperature data. Oil-water separator monitoring equipment and ship exhaust gas monitoring equipment are installed on the ship. The oil-water separator monitoring equipment is used to monitor the oily wastewater discharge indicators of the ship in real time. The ship exhaust gas monitoring equipment is used to detect the pollutant content in the ship exhaust gas. The ship's operating status is recorded, and the data of the water area where the ship is located is obtained by the ship's self-monitoring system. Among them, the oily wastewater discharge indicators include at least one of the following: oil content and suspended solids content.

[0043] First, drone monitoring.

[0044] By equipping drones with high-definition cameras, multispectral cameras, and lidar, low-altitude flight monitoring of the canal can be carried out according to a preset route. The cameras can capture real-time images of the water surface, the multispectral cameras can acquire spectral information in different bands, and the lidar can measure the water surface height and topography. By analyzing this data, the oil spill area can be identified.

[0045] Its high flexibility allows for adjustments to monitoring areas and routes based on the needs of canal vessels, enabling detailed monitoring of key areas. For example, upon discovering a suspected oil spill area, drones can quickly fly to the scene for close-up observation and photography. Moreover, drones are relatively inexpensive and easy to operate, and drone monitoring data is helpful in determining the initial location and general spread trend of the oil slick.

[0046] Secondly, shore-based fixed monitoring stations.

[0047] Various sensors, such as oil film sensors, water quality sensors, and meteorological sensors, are installed on both sides of the canal. In this embodiment, the oil film sensor detects the optical properties (such as reflectivity and transmittance) or electrical properties (such as dielectric constant) of the water surface to identify the oil film; the water quality sensor can monitor indicators such as the content of petroleum substances and chemical oxygen demand in the water; and the meteorological sensor provides meteorological data such as wind speed, wind direction, and temperature, which helps to analyze the direction and speed of oil spill diffusion.

[0048] The sensors provide accurate and reliable monitoring data, enabling real-time and continuous acquisition of water surface and water quality information. They can also acquire the optical properties of the oil film (such as reflectivity and color) and water quality parameters (such as oil concentration and dissolved oxygen content), which is beneficial for subsequent analysis of the oil film diffusion process and thickness changes. However, the monitoring range of shore-based fixed monitoring stations is limited, covering only a certain area around them.

[0049] Thirdly, the ship's self-monitoring system.

[0050] This embodiment can install oil-water separator monitoring equipment and ship exhaust gas monitoring equipment on the ship. The oil-water separator monitoring equipment can monitor in real time whether the oily wastewater discharged by the ship meets the standards, and determine whether there is any illegal discharge by detecting indicators such as oil content and suspended solids content in the wastewater. The ship exhaust gas monitoring equipment can detect the content of pollutants in the ship exhaust gas, such as sulfur oxides and nitrogen oxides, and can obtain the ship's own operating status and oil spill-related information in real time, such as the time, amount, and location of the oil spill. The ship's self-monitoring system helps to determine the source and initial situation of the oil spill, but the ship's self-monitoring system can only reflect the ship's own information and lacks the ability to directly monitor the diffusion and shape changes of the oil film on the water surface.

[0051] It can also directly obtain information on ship pollutant emissions, enabling real-time monitoring of ship pollution sources, which helps to promptly detect illegal emissions from ships and strengthen shipping management.

[0052] This embodiment further integrates data acquired from UAVs, shore-based fixed monitoring stations, and ship self-monitoring systems. Optionally, after acquiring the multi-source data set of the associated target canal waters, the process further includes: using the ship self-monitoring system as a coordinate reference point; calculating the planar rotation axis angle and planar rotation angle of the motion sensor based on the roll angle and forward tilt angle of the motion sensor in the UAV equipment; calculating the corresponding matrix elements based on the planar rotation axis angle and planar rotation angle, combined with the north azimuth angle of the ship self-monitoring system; converting the motion sensor coordinates based on the target azimuth, pitch angle, and distance measurements of the motion sensor; transforming the motion sensor coordinates based on the matrix elements to obtain the motion sensor spatial coordinates under the ship self-monitoring system; unifying the coordinates of the UAV monitoring data and the waters where the ship is located collected by the ship self-monitoring system based on the transformed motion sensor spatial coordinates under the ship self-monitoring system; using the ship self-monitoring system as a coordinate reference point, transforming the coordinate system of the fixed shore-based monitoring stations on both sides of the canal in the real-time monitoring data of the shore-based fixed monitoring stations to the ship self-monitoring system, thus completing the data coordinate unification of the multi-source data set; and performing data format conversion based on the unified multi-source data set to obtain a multi-source data set with a unified data format.

[0053] In this embodiment, the ship's self-monitoring system is used as a coordinate reference point. The monitoring data from the UAV and the shore-based fixed monitoring station need to be combined with the ship's self-monitoring system to improve the accuracy and precision of oil spill identification. Through data fusion, the advantages of various monitoring methods can be fully utilized to make up for their respective shortcomings.

[0054] When performing coordinate unification processing on multi-source data, UAVs, shore-based fixed monitoring stations, and ship self-monitoring systems use different coordinate systems. It is necessary to unify the coordinates of the three types of detection data into the same coordinate system. In this embodiment, the coordinate system of the ship self-monitoring system is used as the reference coordinate to ensure that the source data can be accurately corresponded in spatial location.

[0055] Firstly, the coordinate transformation steps for a drone (mobile sensor, movable sensor) include:

[0056] Step 1: Obtain the tilt angle θ of the motion sensor. b and lean angle θ a The planar rotation axis angle α and planar rotation angle β of the moving sensor can be calculated.

[0057] Wherein, the roll angle θ b and the lean angle θ aThe planar rotation axis angle α and planar rotation angle β of the motion sensor are determined, and the relationship is as follows;

[0058] The planar rotation axis angle α of the motion sensor satisfies the following relationship:

[0059]

[0060] Where α represents the planar rotation axis angle of the motion sensor, θ a θ represents the forward tilt angle of the movable sensor. b This indicates the tilt angle of the movable sensor.

[0061]

[0062] Where β represents the planar rotation angle of the motion sensor, θ a θ represents the forward tilt angle of the movable sensor. b This indicates the tilt angle of the movable sensor.

[0063] Step 2. After obtaining the planar rotation axis angle α and the planar rotation angle β, calculate the corresponding matrix element H based on the north azimuth angle σ of the ship's self-monitoring system.

[0064] Step 3. Based on the target orientation, pitch angle and distance measurement values ​​(w0, f0, l0) of the motion sensor, the coordinates (x, y, z) of the motion sensor can be calculated.

[0065] The target azimuth (azimuth angle w0), pitch angle (pitch angle f0), and distance measurement value (l0) of the moving sensor are converted to obtain the moving sensor coordinates (x, y, z). In this embodiment, a right-handed rectangular coordinate system is used as the origin, with due east as the positive x-axis, due north as the positive y-axis, and vertical upward as the positive z-axis. The conversion formula and derivation process of the moving sensor coordinates (x, y, z) are as follows:

[0066]

[0067] Where (x, y, z) represent the coordinates of the moving sensor, and (w0, f0, l0) represent the target azimuth, pitch angle and distance measurement values ​​of the moving sensor.

[0068] The azimuth angle refers to the angle at which the target rotates clockwise relative to the sensor's true north direction (positive y-axis direction), typically ranging from 0 to 360 degrees.

[0069] The pitch angle refers to the angle of elevation of the target relative to the horizontal plane (xy plane) where the sensor is located. Upward is positive and downward is negative, and the range is usually from -90 degrees to 90 degrees.

[0070] In this embodiment, the distance measurement value mentioned is the straight-line distance between the sensor and the target detection position.

[0071] Step 4. Transform the coordinates (x, y, z) of the moving sensor to obtain the spatial coordinates of the moving sensor under the ship's self-monitoring system.

[0072] Because the mobile sensor is affected by attitude changes and motion, a coordinate transformation is required between its coordinate system and the spatial coordinate system of the ship's self-monitoring system. That is, considering the influence of attitude changes and motion, the coordinate measurement information of the sensor is transformed into the spatial coordinate system of the ship's self-monitoring system. The transformation relationship satisfies the following relationship.

[0073]

[0074] Among them, (x ′ y ′ , z ′ H represents the spatial coordinates of the mobile sensor in the ship's self-monitoring system. mn The elements represent distinct elements in the matrix, and (x, y, z) represent the coordinates of the moving sensor. Since ship sensors are usually in a three-dimensional coordinate system, m = 3 and n = 3 are set.

[0075] Furthermore, based on the planar rotation axis angle α and planar rotation angle β of the motion sensor, and the north azimuth angle σ of the monitoring system, the results of calculating different elements H in the matrix are as follows:

[0076] H 11 =sin(a-σ)sina+cos(a-σ)cosacosβ

[0077] H 12 =-sin(a-σ)cosa+sina cos(a-σ)cosβ

[0078] H 13 =cos(a-σ)sinβ

[0079] H 21 =-sinacos(a-σ)+sin(a-σ)sinacosβ

[0080] H 22 =cos(a-σ)cosa+sin(a-σ)sinacosβ

[0081] H 23 =sin(a-σ)sinβ

[0082] H 31 =-cosasinβ

[0083] H32 =-sinasinβ

[0084] H 33 =cosβ

[0085] Substituting the results of different elements in the above matrix, we can obtain the spatial coordinates (x, y) of the mobile sensor under the ship's self-monitoring system. ′ y ′ , z ′ ).

[0086]

[0087] Drones are highly maneuverable and have a wide monitoring range, enabling them to quickly acquire large-scale images of the canal and clearly show the macroscopic morphology of the oil slick, including its overall shape and approximate diffusion area. For example, in the event of a sudden oil spill, drones can reach the scene in a short time to monitor a large area of ​​water. However, they are greatly affected by weather conditions (such as clouds, fog, and strong winds) and flight altitude, making it difficult to accurately measure the thickness of the oil slick.

[0088] After integrating the coordinates, UAV data can be used to determine the initial location and general diffusion trend of the oil film, providing a macro framework for subsequent detailed analysis.

[0089] The coordinate transformation steps for shore-based fixed monitoring stations (fixed sensors) are explained below:

[0090] The shore-based fixed monitoring station (fixed sensor) is unaffected by attitude changes or motion. Coordinate transformation is performed between the shore-based fixed monitoring station coordinate system and the ship's self-monitoring system coordinate system. This transformation primarily involves mapping the detection data from the shore-based fixed monitoring station to the relevant data from the ship's self-monitoring system. The transformation formula is as follows:

[0091]

[0092] Where (x″, y″, z″) represent the coordinates of the shore-based fixed monitoring station under the ship's self-monitoring system, ρ represents the yaw angle of the shore-based fixed monitoring station relative to the ship's self-monitoring system, and (x, y, z) represent the coordinates of the shore-based fixed monitoring station.

[0093] In ship self-monitoring systems, shore-based fixed monitoring stations typically operate within a fixed coordinate system. However, a ship's course changes during navigation. To accurately match the ship's sensor data (such as position and speed) with the shore-based fixed monitoring station's coordinate system, the heading angle between the ship and the monitoring station needs to be considered. By applying the aforementioned coordinate transformation matrix, the shore-based fixed monitoring station's coordinate system can be transformed to the ship's self-monitoring system, thereby achieving data unification and fusion.

[0094] Meanwhile, due to the differences in equipment and technology among drones, shore-based fixed monitoring stations, and ship self-monitoring systems, data formats may vary. Drone data may be in JPG or LAS format, and professional data processing software such as ENVI and Global Mapper can be used to convert detection data from different sources into a unified format, facilitating subsequent integration, processing, and analysis.

[0095] Furthermore, the process involves integrating and analyzing multi-source data after coordinate transformation to obtain a multi-source dataset. Data from UAVs, shore-based fixed monitoring stations, and ship-based self-monitoring systems, after unified coordinate processing, are integrated to form a complete dataset. This fused dataset is stored in a database for convenient subsequent querying, retrieval, and analysis. Relational or non-relational databases can be used to store the data, aiding in the extraction of valuable information. Subsequent analysis of the oil spill area's shape, size, diffusion rate, and other characteristics allows for the assessment of the spill's impact range and severity.

[0096] By correlating and analyzing data from UAV monitoring with data from shore-based fixed monitoring stations, we can analyze the different optical reflection characteristics of oil slicks of various shapes, thereby improving the completeness and accuracy of both UAV images and monitoring station data. Furthermore, by combining this data with oil spill information from the ship's self-monitoring system, we can further determine whether changes in the shape of the oil slick on the ship are related to the source and volume of the oil spill.

[0097] The shore-based fixed monitoring station is equipped with various sensors, such as optical sensors and water quality sensors, enabling real-time and continuous monitoring of specific areas. It can also acquire the optical characteristics of oil films (such as reflectivity and color) and water quality parameters (such as oil concentration and dissolved oxygen content), and has a certain monitoring capability for oil film diffusion processes and thickness changes. However, the monitoring range is limited, only covering a certain surrounding area.

[0098] Based on the integrated coordinates, combined with shore-based data, the diffusion details and thickness variations of the oil film in specific areas are precisely analyzed, supplementing the lack of UAV data.

[0099] Meanwhile, this invention can acquire real-time information on ship operating status and oil spill related information, such as spill time, spill volume, and spill location, which is crucial for determining the source and initial situation of the oil spill. However, it only reflects information about the ship itself and lacks the ability to directly monitor the spread and shape changes of the oil slick on the water surface. Based on coordinate location integration, the ship's self-monitoring data is used as the starting point for analysis, combined with UAV and shore-based data, to comprehensively understand the occurrence and development process of the oil spill event.

[0100] Step S102: Identify the spatial location and geometric features of the oil film at different time points based on multiple oil film detection images from UAV monitoring data.

[0101] Optionally, the step of identifying the spatial location and geometric features of oil film at different time points based on multiple oil film detection images from UAV monitoring data includes: preprocessing the oil film detection images acquired by the UAV, wherein the preprocessing operations include at least one of the following: image denoising, median filtering, and contrast enhancement; using an image segmentation algorithm to separate the oil film region from the background in the oil film detection image; performing geometric feature analysis on the oil film detection image after background separation to extract multiple types of oil film features, wherein the multiple types of oil film features include at least one of the following: oil film area, oil film perimeter, oil film aspect ratio, and oil film circularity; and performing dynamic shape analysis on the multiple types of oil film features of the oil film detection images at different time points based on the time series of the acquired images, and combining the geographic positioning information of the UAV images to obtain the spatial location and geometric features of the oil film at different time points.

[0102] Because oil droplets can be transported and diffused, and also have the characteristic of floating, once a ship spills oil in a large canal, it is very easy for an oil film to form on the water surface because oil is lighter than water and has low solubility.

[0103] Based on a multi-source data set (UAV monitoring data, shore-based fixed monitoring station monitoring data, and ship self-monitoring system monitoring data), the shape, diffusion area, and thickness of oil film in large canals are predicted and analyzed.

[0104] This embodiment primarily relies on the identification and prediction of oil film shape based on images detected by the UAV. First, the oil film detection images acquired by the UAV are subjected to denoising and contrast enhancement operations to improve image quality. In an optional embodiment, to improve image quality, the oil film detection images are smoothed and denoised. Median filtering is a non-linear signal processing method that effectively protects edges from blurring while suppressing random noise. Different median filters of varying specifications are selected based on the canal environment to smooth the oil film detection images, resulting in better processing.

[0105] After denoising the UAV detection image, an image segmentation algorithm (RGB thresholding method and brightness value method for background segmentation) is used to separate the oil film area from the background. In this embodiment of the invention, the RGB thresholding method is used for illustration.

[0106] Optionally, the step of separating the oil film region from the background in the oil film detection image using an image segmentation algorithm includes: using a local adaptive thresholding algorithm to detect the mean and standard value of a local region in the oil film detection image, wherein the mean of the local region refers to the average gray value of all pixels centered on each sub-region in the oil film detection image, and the standard deviation of the local region is used to measure the dispersion of pixel gray values ​​within the local region; based on the mean and standard value of the local region in the oil film detection image, using an RGB thresholding algorithm to process the color channels of the oil film detection image, calculating the gray-level histogram data corresponding to multiple color channels, and obtaining the target threshold corresponding to each color channel; based on the target threshold, performing threshold segmentation processing on each color channel, and synthesizing the images of the three color channels to obtain a threshold-segmented color image; and separating the oil film region from the background in the oil film detection image based on the threshold-segmented color image.

[0107] Since the oil film detection image is a color image, the color image can be represented by three color channels: red (R), green (G), and blue (B), while the image of each channel is a grayscale image.

[0108] First, calculate the grayscale histogram data for the R, G, and B channels; then, based on the iterative algorithm described above, obtain the optimal thresholds for the three color channels: red (R), green (G), and blue (B), denoted as η. R η G η B Finally, the following processing is performed on the 3-color component image.

[0109]

[0110] R(i, j) ′ G(i,j) ′ B(i,j) ′ These represent the grayscale values ​​of pixels (i, j) in the three channels after background segmentation.

[0111] R(i,j), G(i,j), and B(i,j) represent the gray values ​​of pixel (i,j) in the three channels before background segmentation, respectively.

[0112] η R η G η B These represent the threshold values ​​for background segmentation in the three color channels: red (R), green (G), and blue (B), respectively.

[0113] After thresholding the three channels, the three-channel images are synthesized to obtain the color image after thresholding.

[0114] However, threshold selection mainly relies on iterative algorithms, which may fail to accurately capture the complex boundary between the oil film and the background, especially under uneven lighting conditions or when the oil film color is similar to the background. Therefore, in this embodiment, the threshold η obtained by the iterative algorithm... R η G η B It has been optimized.

[0115] It should be noted that this embodiment introduces a local adaptive thresholding method, which can use the Sauvola algorithm and dynamically adjust the threshold according to the gray-scale distribution of the local area of ​​the oil film detection image, thus better handling problems such as uneven lighting in the canal environment.

[0116] It should be noted that this embodiment can also obtain the mean and standard values ​​of the local area based on the oil film detection image. The mean of the local area refers to the average gray value of all pixels in a small window centered at (i, j) in the image. This mean reflects the brightness level of the local area of ​​the oil film detection image. The standard deviation of the local area is mainly used to measure the dispersion of pixel gray values ​​in the local area. The larger the standard deviation, the greater the difference in pixel values ​​in the canal detection area.

[0117] The threshold adjustment formula is as follows:

[0118]

[0119] Where f(i,j) represents the threshold adjustment result, p(i,j) represents the average pixel gray value in the local area, c represents the adjustment parameter, b(i,j) represents the standard deviation of pixel gray value in the local area, and a represents the maximum possible value in the standard deviation b(i,j).

[0120] Furthermore, this embodiment can determine whether the current pixel belongs to the oil film region or the background based on the threshold prediction result. For example, setting the above adjustment parameter between 0 and 1 is mainly used to control the sensitivity of threshold adjustment. A larger c value will make the threshold more sensitive to changes in local standard deviation, thereby increasing the sensitivity of segmentation.

[0121] 'a' is a constant, which in this embodiment is set to the maximum possible value in the standard deviation b(i,j). It can be adjusted according to the grayscale range of the image and is mainly used to normalize the influence of the standard deviation.

[0122] Then, combining the threshold information from the R, G, and B channels with the threshold prediction formula, a weighted fusion method is used to obtain the adjusted threshold η. R * η G * η B * .

[0123] R(i,j), G(i,j), and B(i,j) represent the gray values ​​of pixel (i,j) in the three channels before background segmentation, respectively.

[0124]

[0125] Where, η R * λ represents the threshold result after R-channel adjustment. R p represents the weighting coefficient of the R channel. R (i, j) represents the average gray value of the R channel within a local region, c represents the adjustment parameter, and b R (i, j) represents the standard deviation of the R channel within a local region, a R The standard deviation b R The maximum possible value in (i, j).

[0126]

[0127] Where, η G * λ represents the threshold result after G channel adjustment. G p represents the weighting coefficient of the G channel. G (i, j) represents the average gray value of the G channel within a local region, c represents the adjustment parameter, and b G (i, j) represents the standard deviation of channel G within a local region, a G The standard deviation b G The maximum possible value in (i, j).

[0128]

[0129] Where, η B * This represents the threshold result after adjustment for channel B, λ. B p represents the weighting coefficient of channel B. B (i, j) represents the average gray value of channel B within a local region, c represents the adjustment parameter, and b B (i, j) represents the standard deviation of channel B within a local region, a B Indicates standard deviation b B The maximum possible value in (i, j).

[0130] Finally, based on the adjusted threshold η R * η G * η B * Background segmentation is performed on the oil film detection image.

[0131]

[0132] R(i, j) ′ G(i,j) ′ B(i,j) ′ These represent the grayscale values ​​of pixels (i, j) in the three channels after background segmentation.

[0133] R(i,j), G(i,j), and B(i,j) represent the gray values ​​of pixel (i,j) in the three channels before background segmentation, respectively.

[0134] η R * η G * η B * These represent the threshold values ​​for background segmentation in the three color channels: red (R), green (G), and blue (B), respectively.

[0135] After thresholding the three channels, the three-channel images are synthesized to obtain the oil film detection image (color image) after thresholding.

[0136] Then, geometric feature analysis is performed on the oil film detection image after background segmentation. Specifically, this embodiment can extract shape features such as area, perimeter, aspect ratio, and circularity of the oil film image in the canal. At the same time, dynamic shape analysis and change monitoring are performed by combining oil film detection images at different time points. By combining UAV images at continuous time points, the dynamic change trend of the oil film shape can be analyzed. By combining the geolocation information of the UAV images with the area, perimeter, aspect ratio, and circularity of the oil film image, the spatial location and geometric features of the oil film at different time points can be further determined.

[0137] Finally, the spatial location and geometric characteristics of the oil slick at different time points were verified and predicted based on multi-source datasets. This involved correlating the geometric feature analysis results of the oil slick obtained from UAV-detected images with the optical characteristics of the oil slick monitored by shore-based fixed monitoring stations. Different shapes of oil slicks exhibit different optical reflection characteristics, and the accuracy of UAV image recognition was verified through comparison. Furthermore, by combining oil spill information from the ship's self-monitoring system and comprehensively considering factors such as the oil spill source and spill volume, the predicted trend of oil slick shape was obtained, thus yielding the predictive analysis results for the oil slick shape.

[0138] Step S103: Based on the spatial location and geometric characteristics of the oil film, and combined with real-time monitoring data from shore-based fixed monitoring stations, determine the changes in oil concentration distribution, and assess the oil film diffusion area based on the changes in oil concentration distribution.

[0139] Optionally, step S103 includes: selecting factors influencing oil film diffusion based on real-time monitoring data from shore-based fixed monitoring stations, wherein the factors influencing oil film diffusion include: the water flow velocity and direction of the canal; calculating the rising velocity of oil droplets in the oil film based on the correlation coefficient of water flow velocity, water flow direction, oil droplets rising uniformly in still water in laminar flow, water density, oil density, water dynamic viscosity coefficient, and oil droplet size in the oil film; calculating the diffusion coefficient of the oil film in the mainstream direction of the water flow based on the water flow velocity, water flow direction, and oil droplet rising velocity; calculating the rate of change of oil film concentration in the mainstream direction based on the water flow velocity, water flow direction, oil film diffusion coefficient in the mainstream direction of the water flow, oil film diffusion flux perpendicular to the mainstream direction of the water flow, oil droplet degradation coefficient in water, and estimated oil film concentration; determining the oil concentration distribution change based on the spatial location and geometric characteristics of the oil film and the rate of change of oil film concentration in the mainstream direction; and assessing the oil film diffusion area based on the oil concentration distribution change.

[0140] Because the water in the canal is often in a state of flow, or due to the external environment or external forces, fluctuations and turbulence on the surface of the canal are common. After the oil droplets enter the water, they are transported with the flow and continue to spread downwards under the action of the canal water flow. On the other hand, the oil droplets will float up due to their own buoyancy. The two work together to form the transport and diffusion of oil droplets. The oil film (or at the oil-water interface) will eventually form dispersed oil droplets. The water flow not only causes the oil droplets that have entered the water to continue to spread downwards, but also continuously breaks up large oil droplets into smaller oil droplets or emulsified oil droplets.

[0141] In this embodiment, the spatial location and geometric features of the oil film at different time points are first obtained by combining images detected by UAVs; then, the oil film diffusion area is predicted and judged mainly based on real-time monitoring data from shore-based fixed monitoring stations, the changes in oil concentration monitored by shore-based stations are analyzed, the oil film diffusion intensity and range are judged, and the oil concentration distribution in the oil film diffusion area is predicted.

[0142] First, this embodiment selects the factors affecting oil film diffusion based on data from shore-based fixed monitoring stations. These factors mainly include the water flow velocity and direction of the canal.

[0143] By combining the water flow data (flow velocity, flow direction) of the canal, we can obtain parameters such as the rising velocity of oil droplets in the oil film and the diffusion coefficient in different water flow directions, and further analyze the influence of canal water flow on oil film diffusion.

[0144] The parameter information is as follows:

[0145] 1.V w This represents the rising velocity of the oil droplets in the oil film. In this embodiment, the Stokes velocity formula, which describes the uniform laminar rise of oil droplets in still water, is used to calculate it.

[0146]

[0147] Among them, V w ρ represents the rising velocity of the oil droplets in the oil film, b represents the correlation coefficient of the oil droplets rising uniformly in still water in laminar flow, ρ2 represents the density of water, ρ1 represents the density of oil, μ2 represents the dynamic viscosity coefficient of water, g represents the acceleration due to gravity, and l represents the estimated particle size of the oil droplets in the oil film.

[0148] 2. Direction setting:

[0149] The main direction of the water flow is x (x direction);

[0150] The direction perpendicular to the main flow of water is y (y direction);

[0151] The upward direction perpendicular to the bottom of the canal is z (z direction).

[0152] 3.K x The diffusion coefficient of the oil film in the direction of the mainstream water flow (x direction).

[0153] K y The diffusion coefficient of the oil film in the direction perpendicular to the main water flow direction (y direction).

[0154] The diffusion coefficient reflects the diffusion capacity of an oil film in water due to molecular motion and turbulence. K x and K y The size of the diffusion coefficient depends mainly on factors such as the degree of water turbulence and the properties of the oil film. A larger diffusion coefficient means that the oil film is more likely to diffuse in the corresponding direction.

[0155] Subsequently, this embodiment can analyze the impact of canal flow conditions (flow velocity, flow direction) on the oil film diffusion area based on parameter information. That is, in the canal environment, the oil film diffusion process is affected by a combination of factors, among which the flow conditions (flow velocity, flow direction) are one of the key factors. In order to further explore the impact of canal flow on the oil film diffusion area, this embodiment combines the rising velocity and direction setting information of oil droplets in the oil film, as well as the diffusion coefficient in different directions, and establishes the oil film diffusion equation through the following steps:

[0156] The velocity component of water flow in a canal along the main flow direction, expressed in m / s. Water flow velocity is a crucial factor influencing oil film diffusion; a higher velocity accelerates oil film transport along the main flow direction, allowing it to diffuse downstream more quickly. Convection along the main flow direction is also a significant driving force for oil film diffusion.

[0157] The diffusion capacity of the oil film in the direction of the mainstream water flow (x direction) and perpendicular to the direction of the mainstream water flow (y direction) is further reflected by the coefficients, which reflect the degree of diffusion of the oil film in the corresponding directions due to factors such as turbulent mixing.

[0158] Since oil droplets are less dense than water, they tend to rise to the surface. This velocity needs to be considered in the 3D model to account for the effect of the concentration gradient in the direction perpendicular to the bottom of the canal on the oil film diffusion.

[0159] The rate coefficient of natural degradation of oil film in water can reflect the rate at which the oil film decreases due to biodegradation, volatilization, or chemical decomposition.

[0160] The oil film predicted concentration can provide feedback on the concentration distribution of the oil film in space, and the unit is usually mg / L or g / m3.

[0161] Based on the above analysis of the physical meaning of each parameter, and considering the combined effects of convection, diffusion, degradation, and buoyancy, an oil film diffusion equation can be established in this embodiment, with the water flow velocity as v and the diffusion coefficient as K. x With K y The degradation coefficient of oil droplets in water is j, the predicted concentration of oil film is C, and the oil film diffusion equation is:

[0162]

[0163] The oil film concentration C is estimated based on the geometric characteristics of the oil film, and the unit is usually mg / L or g / m.

[0164] The velocity component of the water flow in the canal along the mainstream direction, expressed in m / s, is a key factor influencing oil film diffusion. A higher flow velocity accelerates oil film transport along the mainstream direction, causing it to diffuse downstream more quickly. In the equation, where... This represents the rate of change of oil film concentration in the direction of the mainstream water flow due to convection. Water flow dominates the migration of oil film in the mainstream direction; the higher the flow velocity, the faster the oil film is transported.

[0165] In the oil film diffusion equation, and The terms represent the diffusion flux of the oil film in the direction of the mainstream water flow (x direction) and perpendicular to the direction of the mainstream water flow (y direction), respectively.

[0166] Convection along the mainstream direction of water flow is one of the important driving forces for oil film diffusion. In the oil film diffusion equation, This represents the rate of change of oil film concentration in the direction of the mainstream water flow due to convection. It describes the migration of the oil film dominated by water flow in the mainstream direction. The greater the flow velocity v, the faster the oil film is transported, that is, the faster the oil film diffuses in the mainstream direction.

[0167] In the oil film diffusion equation, J represents the rate coefficient of natural degradation of the oil film in water, where jC represents the rate at which the oil film decreases due to biodegradation, volatilization, or chemical decomposition. The larger J is, the faster the oil film concentration decays, and consequently the slower the diffusion area grows. This is because the oil film is continuously degraded during the diffusion process, leading to a decrease in its concentration and thus limiting the diffusion range.

[0168] In the oil film diffusion equation, The calculations show that turbulent mixing causes the oil film to spread in both the mainstream water flow direction (x-direction) and perpendicular to the mainstream water flow direction (y-direction).

[0169] In the oil film diffusion equation, The calculations show that oil droplets, due to their lower density than water, float to the surface and form an oil film. This requires considering the concentration gradient perpendicular to the bottom of the canal in the 3D model. In this embodiment, the concentration gradient in this direction is considered based on a 3D model method. The rising of oil droplets causes changes in the vertical distribution of the oil film, which in turn affects the diffusion area of ​​the oil film on the horizontal plane.

[0170] Furthermore, this embodiment can determine the oil film diffusion area based on the output results of the oil film diffusion equation, while also combining monitoring data from multiple sources (UAVs, shore-based fixed monitoring stations, and ship self-monitoring systems).

[0171] This embodiment combines the spatial location and geometric characteristics of the oil film at different time points, real-time monitoring data from shore-based fixed monitoring stations, and multi-source data collection including monitoring data from UAVs and ship self-monitoring systems to predict and determine the oil film diffusion area. By analyzing the changes in oil concentration monitored by the data sources, the intensity and range of oil film diffusion are determined, thereby predicting the oil concentration distribution in the oil film diffusion area.

[0172] Following this, based on the output of the oil film diffusion equation, and combined with multi-source data sets (monitoring data from UAVs, shore-based fixed monitoring stations, and ship-based self-monitoring systems), the relevant judgment and analysis of the oil film diffusion area were improved and supplemented. UAVs have the advantage of high-altitude observation; based on the spatial location and geometric characteristics of the oil film at different time points, they can analyze the overall morphology, area, and diffusion trend of the oil film in different directions. Simultaneously, based on UAV monitoring data, the diffusion coefficient in different water flow directions can be adjusted, which helps to further analyze the degradation of the oil film and the particle size distribution of oil droplets, thereby correcting the relevant parameters in the oil film diffusion equation. Ship-based self-monitoring systems can acquire oil concentration data at different locations, providing more detailed information for predicting the oil film diffusion area. At the same time, ship-based self-monitoring systems can also monitor the water flow around the ship, complementing the data from shore-based fixed monitoring stations and improving the accuracy of judging the water flow velocity v and direction. Furthermore, the oil droplet size data recorded by the ship-based self-monitoring system is of great significance for calculating and correcting the oil droplet rising velocity.

[0173] By comprehensively analyzing monitoring data from drones, shore-based fixed monitoring stations, and ship self-monitoring systems, the output results of the oil film diffusion equation can be verified and corrected. This allows for a more accurate prediction of the oil concentration distribution, diffusion intensity, and range in the oil film diffusion area, providing a scientific basis for the prevention and control of oil pollution in canals.

[0174] Step S104: Analyze the water area data collected by the ship's self-monitoring system to obtain the water oil concentration parameters and oil droplet size parameters of the water area where the ship is located. Combine the monitoring data of the UAV, the real-time monitoring data of the shore-based fixed monitoring station, the water oil concentration parameters and the oil droplet size parameters to determine the oil film thickness.

[0175] Optionally, the steps for determining the oil film thickness by combining UAV monitoring data, real-time monitoring data from shore-based fixed monitoring stations, water oil concentration parameters, and oil droplet size parameters include: collecting Raman spectral data of the water area where the ship is located using the ship's self-monitoring system, and recording the ship's navigation trajectory and time information; extracting the Raman spectral intensities at the first and second wavelengths based on the Raman spectral data collected by the ship's self-monitoring system, and calculating the ratio of the two Raman spectral intensities; calling the correlation model between the Raman spectral intensities ratio and the oil film thickness, inputting the first wavelength and its corresponding first constant, the second wavelength and its corresponding second constant, and the ratio of the two Raman spectral intensities into the correlation model, and outputting the initial oil film thickness; analyzing the spatial location and geometric characteristics of the oil film to obtain the oil film morphology; analyzing the color distribution information of the oil film based on real-time monitoring data from shore-based fixed monitoring stations; and adjusting the initial oil film thickness based on the oil film morphology, the color distribution information of the oil film, water oil concentration parameters, and oil droplet size parameters to determine the final oil film thickness.

[0176] The ship self-monitoring system can obtain information such as the oil concentration and oil droplet size in the water at the ship's location in real time. In this embodiment, the oil film thickness is mainly determined based on the monitoring data of the ship self-monitoring system. During the ship's navigation, it can pass through the oil film area, thereby obtaining oil film data at different locations, providing more detailed information for the prediction of the oil film thickness range.

[0177] The ship's self-monitoring system can acquire information such as oil concentration and oil droplet size in the water at the ship's location in real time. In this embodiment, the oil film thickness is comprehensively judged mainly based on the monitoring data of the ship's self-monitoring system, combined with data from UAVs and shore-based fixed monitoring stations. As the ship navigates through the oil film area, oil film data at different locations can be obtained, providing more detailed information for predicting the oil film thickness.

[0178] To more accurately predict and analyze oil film thickness, Raman spectral reference information for different types of oil was introduced in the examples. Based on this, the Raman spectral characteristics of different oils, as well as the Raman spectral response characteristics under different oil film thicknesses, can be obtained.

[0179] The Raman peaks and corresponding Raman wavenumber shifts of water excited at typical excitation wavelengths are shown in the table. Different excitation wavelengths produce different Raman peaks in water. With increasing excitation wavelength, the redshift of the Raman peak position becomes more pronounced, but the Raman wavenumber shift remains essentially unchanged (at 3400 cm⁻¹). -1 about).

[0180] Furthermore, this embodiment can estimate the oil film thickness based on optical properties. During navigation, the ship uses a self-monitoring system to collect real-time data on water oil concentration, oil droplet size, and Raman spectral density at their location. Simultaneously, the ship's navigation trajectory and time information are recorded to facilitate subsequent location and analysis of the oil film thickness at different positions.

[0181] Furthermore, this embodiment determines the relationship between the Raman spectral intensity ratio and the oil film thickness. Based on data from the ship's self-monitoring system, the Raman spectral intensities at wavelengths λ1 and λ2 are extracted, and the ratio μ of the two water Raman spectral intensities is calculated. l .

[0182] Raman spectral intensities at different wavelengths were measured using a Raman spectrometer in a self-monitoring system. By varying the oil film thickness and recording the corresponding Raman spectral intensity ratios, a relationship model between oil film thickness and the Raman spectral intensity ratio was established.

[0183]

[0184] Where d represents the oil film thickness, k(λ1) represents the constant corresponding to λ1, k(λ2) represents the constant corresponding to λ2, λ1 represents one wavelength, λ2 represents another wavelength, r0 represents the ratio of the two Raman spectral intensities at wavelengths λ1 and λ2 when using pure water, and μ l This represents the ratio of the intensities of the two Raman spectra.

[0185] Furthermore, this embodiment can combine the relationship model between oil film thickness and Raman spectral intensity ratio with multi-source data to correct and predict oil film thickness. Specifically, by combining the obtained spatial location and geometric features of the oil film, the morphology and color distribution information of the oil film can be quickly obtained. When a region of darker oil film color may correspond to a thicker oil film, the oil film thickness estimation result output by the oil film thickness-Raman spectral intensity ratio relationship model can be supplemented or verified. Then, based on the aforementioned oil film diffusion region prediction and judgment information, the diffusion trend and thickness variation law of the oil film are analyzed. Combining the oil film thickness estimation results and real-time monitoring data, the oil film thickness for a future period can be predicted.

[0186] This embodiment can ultimately combine multi-source data sets (UAV monitoring data, shore-based fixed monitoring station monitoring data, and ship self-monitoring system monitoring data), oil film spatial location and geometric shape analysis results, oil film diffusion area prediction results, and oil film thickness analysis results to intelligently monitor oil spills and pollutants from ships in the canal. This enables real-time monitoring, accurate prediction, and scientific assessment of oil spills and pollutant emissions from ships in the canal, and timely issuance of early warnings to reduce the risk of environmental pollution in the canal and ensure the ecological safety of the canal.

[0187] Step S105: Based on the spatial location and geometric characteristics of the oil film at different time points, the oil film diffusion area and the oil film thickness, a canal oil spill monitoring and early warning report is generated.

[0188] Optionally, the steps for generating a canal oil spill monitoring and early warning report by integrating the spatial location and geometric characteristics of the oil film at different time points, the oil film diffusion area, and the oil film thickness include: determining the location of the oil spill area in the target canal waterway using a geographic information system based on the spatial location and geometric characteristics of the oil film at different time points; simulating the diffusion trajectory of the oil film based on the oil film diffusion area and thickness, and obtaining the oil film diffusion trend by combining canal flow data and oil film diffusion prediction results; analyzing the canal pollutant diffusion results based on the oil spill area location, oil film diffusion area, and oil film diffusion trend, combined with meteorological and hydrological data; determining the early warning level based on the canal pollutant diffusion results; and generating a canal oil spill monitoring and early warning report based on the early warning level, canal pollutant diffusion results, oil spill area location, and oil film diffusion area.

[0189] This embodiment utilizes the spatial location and geometric shape analysis of the oil slick to obtain detailed images and video information of the oil spill area, clearly presenting the morphology, color, and other characteristics of the oil slick, providing an intuitive basis for rapid location and preliminary confirmation of the oil spill area. Through comprehensive analysis of UAV monitoring images and data from shore-based fixed monitoring stations, the spatial location and geometric shape information of the oil slick are extracted, facilitating the calculation of its area, perimeter, aspect ratio, circularity, and other shape characteristics. Combined with geographic information system (GIS) technology, the specific location of the oil slick within the canal can be determined. The spatial location and geometric shape analysis results of the oil slick enable rapid and accurate location of the oil spill area, providing emergency response personnel with intuitive on-site information to help them quickly formulate appropriate response plans. Simultaneously, dynamic analysis of the oil slick shape at different time points allows for understanding the diffusion trend and change patterns of the oil slick, providing important reference for pollution assessment.

[0190] Furthermore, the predicted oil film diffusion area is helpful in simulating the diffusion trajectory of the oil film. By analyzing canal flow data and oil film diffusion prediction results, the oil spill situation and the predicted oil film diffusion trend can be further verified, providing basic data support for subsequent pollution assessment. Based on the oil film diffusion equation, combined with canal flow data (flow velocity, flow direction), the rising velocity of oil droplets in the oil film, and the diffusion coefficient in different flow directions, the diffusion area of ​​the oil film can be accurately predicted. By continuously updating real-time monitoring data, the prediction model can be dynamically adjusted and optimized to improve the accuracy and reliability of the prediction. The predicted oil film diffusion area is helpful in simulating the diffusion trajectory of the oil film under different environmental conditions and predicting the potential range of pollution in advance.

[0191] Furthermore, the oil film thickness analysis results, combined with the ship's position in the canal and the discharge time, can preliminarily estimate the oil spill volume and oil film type. In this embodiment, a model is established to establish the relationship between oil film thickness and the ratio of Raman spectral intensity by introducing Raman spectral reference information for different types of oil. During the ship's navigation, the Raman spectral data of the water body is collected in real time using a self-monitoring system, and the oil film thickness is estimated in conjunction with this model. The oil film thickness analysis results provide basic data for simulating the oil film diffusion area. Oil films of different thicknesses exhibit different characteristics during diffusion. By accurately analyzing the oil film thickness, the diffusion process of the oil film can be simulated more precisely, and the severity of pollution can be assessed. At the same time, oil film thickness information also helps to determine the source and nature of the oil spill, providing clues for pollution tracing.

[0192] Effective monitoring of pollutant emissions can be achieved using multi-source data sets (data from UAV monitoring, shore-based fixed monitoring stations, and ship self-monitoring systems). UAVs, shore-based fixed monitoring stations, and ship self-monitoring systems not only monitor oil spills but also other pollutant emissions from ships. Ship self-monitoring systems acquire real-time data on the levels of pollutants such as sulfur oxides and nitrogen oxides in ship exhaust, comparing this data with preset emission standards to promptly detect violations of emission regulations. Combining meteorological data (such as wind speed, wind direction, temperature, and air pressure) and hydrological data (such as water flow velocity, water level, and flow direction), in-depth analysis of the factors influencing pollutant diffusion is conducted. Based on these parameters, the diffusion trajectory of pollutants is simulated, predicting the diffusion range and impact, providing a scientific and accurate basis for pollution prevention and control decisions.

[0193] Real-time data from the ship's self-monitoring system is used to monitor oil spills in real time. When the system detects excessive levels of oily wastewater or an oil spill, it immediately transmits the information to the real-time monitoring platform. Combined with data from drones and shore-based fixed monitoring stations, the oil spill area is quickly located and confirmed. Drones can rapidly reach the spill site to acquire detailed images and video information; shore-based fixed monitoring stations can monitor water quality changes in the spill area in real time, providing auxiliary support for oil spill monitoring.

[0194] Furthermore, based on real-time monitoring data and forecast results, a scientifically sound and reasonable tiered early warning mechanism is established. For example, this embodiment can divide the early warning levels into four levels—blue, yellow, orange, and red—based on factors such as the severity, scope of impact, and duration of oil spills and pollutant emissions, clearly defining the triggering conditions and corresponding response measures for each level. For instance, when a minor oil spill or excessive pollutant emissions is detected with a small impact area, a blue warning is triggered, alerting relevant departments to strengthen monitoring and attention; when the oil spill is large-scale, the pollution spread trend is obvious, and it may have a significant impact on the canal's ecological environment, a red warning is triggered, initiating the highest-level emergency response procedure.

[0195] When monitoring data reaches the warning threshold, the real-time monitoring platform automatically issues a warning and promptly and accurately conveys the warning information to relevant departments and personnel through various channels, such as SMS, email, and app push notifications. The warning information should include detailed information such as the location, scale, impact range, warning level, and response measures for oil spills or pollutant emissions, ensuring that recipients can quickly understand the situation and take appropriate action.

[0196] Through the above steps, a multi-source data set of the associated target canal water area can be obtained. This multi-source data set includes at least: UAV monitoring data, real-time monitoring data from shore-based fixed monitoring stations, and data on the water area where the vessel is located collected by the vessel's self-monitoring system. Based on multiple oil film detection images from the UAV monitoring data, the spatial location and geometric features of the oil film at different time points are identified. Based on the spatial location and geometric features of the oil film, combined with real-time monitoring data from shore-based fixed monitoring stations, the changes in oil concentration distribution are determined, and the oil film diffusion area is assessed based on these changes. The data on the water area where the vessel is located collected by the vessel's self-monitoring system are analyzed to obtain the water oil concentration parameters and oil droplet size parameters of the water area where the vessel is located. Combining the UAV monitoring data, real-time monitoring data from shore-based fixed monitoring stations, water oil concentration parameters, and oil droplet size parameters, the oil film thickness is determined. Finally, by comprehensively analyzing the spatial location and geometric features of the oil film at different time points, the oil film diffusion area, and the oil film thickness, a canal oil spill monitoring and early warning report is generated. In this embodiment, based on a multi-source dataset, the shape, diffusion area, and thickness changes of the oil film can be comprehensively analyzed to establish an accurate prediction model. This enables accurate assessment of the diffusion of oil spills in canal areas, the thickness of the oil film, and the shape of the oil film. Through accurate prediction and rapid response, the environmental damage caused by oil spills is effectively reduced. This achieves effective analysis between oil film characteristics and environmental factors, thereby solving the technical problem in related technologies where the diffusion of oil spills cannot be captured when monitoring oil spills from canal vessels, resulting in low accuracy in assessing oil spill pollution.

[0197] The following is a detailed description with reference to another embodiment.

[0198] Example 2

[0199] The oil spill monitoring and early warning system provided in this embodiment includes multiple implementation units, each of which corresponds to a specific implementation step in Embodiment 1 above.

[0200] Figure 2 This is a schematic diagram of an optional oil spill monitoring and early warning system for a canal according to an embodiment of the present invention, as shown below. Figure 2 As shown, the monitoring and early warning system for oil spills on the canal surface may include: a multi-source data acquisition unit 21, an oil film shape analysis unit 22, an oil film diffusion area assessment unit 23, an oil film thickness analysis unit 24, and a monitoring report generation unit 25.

[0201] The multi-source data acquisition unit 21 is used to acquire a multi-source data set of the associated target canal waters. The multi-source data set includes at least: UAV monitoring data, real-time monitoring data from shore-based fixed monitoring stations, and data on the waters where the ship is located collected by the ship self-monitoring system.

[0202] The oil film shape analysis unit 22 is used to identify the spatial location and geometric features of the oil film at different time points based on multiple oil film detection images from UAV monitoring data.

[0203] The oil film diffusion area assessment unit 23 is used to determine the oil concentration distribution change based on the spatial location and geometric characteristics of the oil film, combined with real-time monitoring data from shore-based fixed monitoring stations, and to assess the oil film diffusion area based on the oil concentration distribution change.

[0204] The oil film thickness analysis unit 24 is used to analyze the water area data collected by the ship's self-monitoring system to obtain the water oil concentration parameters and oil droplet size parameters of the water area where the ship is located. Combined with UAV monitoring data, real-time monitoring data from shore-based fixed monitoring stations, water oil concentration parameters, and oil droplet size parameters, the oil film thickness is determined.

[0205] The monitoring report generation unit 25 is used to generate a canal oil spill monitoring and early warning report by comprehensively considering the spatial location and geometric characteristics of the oil film at different time points, the oil film diffusion area and the oil film thickness.

[0206] The aforementioned oil spill monitoring and early warning system for the canal canal can acquire a multi-source data set of the associated target canal water area through the multi-source data acquisition unit 21. The multi-source data set includes at least: UAV monitoring data, real-time monitoring data from shore-based fixed monitoring stations, and data on the water area where the vessel is located collected by the vessel's self-monitoring system. The oil film shape analysis unit 22 identifies the spatial location and geometric features of the oil film at different time points based on multiple oil film detection images from the UAV monitoring data. The oil film diffusion area assessment unit 23 determines the oil concentration distribution change based on the spatial location and geometric features of the oil film, combined with real-time monitoring data from shore-based fixed monitoring stations, and assesses the oil film diffusion area based on the oil concentration distribution change. The oil film thickness analysis unit 24 analyzes the water area data of the vessel's location collected by the vessel's self-monitoring system to obtain the water oil concentration parameters and oil droplet size parameters of the water area where the vessel is located. The oil film thickness is determined by combining the UAV monitoring data, real-time monitoring data from shore-based fixed monitoring stations, water oil concentration parameters, and oil droplet size parameters. The monitoring report generation unit 25 integrates the spatial location and geometric features of the oil film at different time points, the oil film diffusion area, and the oil film thickness to generate a canal oil spill monitoring and early warning report. In this embodiment, based on a multi-source dataset, the shape, diffusion area, and thickness changes of the oil film can be comprehensively analyzed to establish an accurate prediction model. This enables accurate assessment of the diffusion of oil spills in canal areas, the thickness of the oil film, and the shape of the oil film. Through accurate prediction and rapid response, the environmental damage caused by oil spills is effectively reduced. This achieves effective analysis between oil film characteristics and environmental factors, thereby solving the technical problem in related technologies where the diffusion of oil spills cannot be captured when monitoring oil spills from canal vessels, resulting in low accuracy in assessing oil spill pollution.

[0207] Optionally, the multi-source data acquisition unit includes: an equipment configuration module, used to equip the UAV with a high-definition camera, a multispectral camera, and a lidar, controlling the UAV to fly along a preset route in the target canal area, using the high-definition camera to take real-time water surface photos of the target canal area, using the multispectral camera to acquire spectral information of different bands, and using the lidar to measure water surface height and terrain information to obtain UAV monitoring data; and a shore-based fixed monitoring module, used to install various types of sensors at fixed shore-based locations on both sides of the target canal area, using these sensors to collect data from the target canal area to obtain real-time monitoring data from the shore-based fixed monitoring station, wherein the various types of sensors include at least one of the following: an oil film sensor, a water quality sensor, etc. The system includes sensors and meteorological sensors; oil film sensors detect the optical or electrical properties of the water surface; water quality sensors monitor the content of petroleum substances and chemical oxygen demand in the canal water; meteorological sensors collect meteorological data, including at least one of the following: wind speed, wind direction, and temperature data; and a ship self-monitoring module, used to install oil-water separator monitoring equipment and ship exhaust gas monitoring equipment on the ship. The oil-water separator monitoring equipment is used to monitor the oily wastewater discharge indicators of the ship in real time, and the ship exhaust gas monitoring equipment is used to detect the pollutant content in the ship exhaust gas. The system records the ship's operating status and obtains the water area data collected by the ship self-monitoring system, wherein the oily wastewater discharge indicators include at least one of the following: oil content and suspended solids content.

[0208] Optionally, the monitoring and early warning system for oil spills on the canal surface also includes: a coordinate reference determination unit, used to use the ship's self-monitoring system as a coordinate reference point after acquiring a multi-source data set of the associated target canal water area; a sensor rotation angle calculation unit, used to calculate the planar rotation axis angle and planar rotation angle of the mobile sensor based on the roll angle and forward tilt angle of the mobile sensor in the UAV equipment; a matrix element calculation unit, used to calculate the corresponding matrix elements based on the planar rotation axis angle and planar rotation angle, combined with the north azimuth angle of the ship's self-monitoring system; and to convert the mobile sensor coordinates based on the target azimuth, pitch angle, and distance measurement values ​​of the mobile sensor; and a coordinate transformation unit, used to transform the mobile sensor coordinates based on the matrix elements. The system employs several methods: a first, a conversion unit to obtain the spatial coordinates of the mobile sensors under the ship's self-monitoring system; a second, a coordinate unification unit to unify the coordinates of the UAV monitoring data with the ship's location data collected by the ship's self-monitoring system based on the converted spatial coordinates of the mobile sensors under the ship's self-monitoring system; a third, a multi-source data coordinate unification unit to use the ship's self-monitoring system as a coordinate reference point to convert the coordinate system of the fixed shore-based monitoring stations on both sides of the canal in the real-time monitoring data of the shore-based fixed monitoring stations to the ship's self-monitoring system, thus completing the data coordinate unification of the multi-source data set; and a fourth, a data format conversion unit to perform data format conversion based on the unified multi-source data set, resulting in a multi-source data set with a unified data format.

[0209] Optionally, the oil film shape analysis unit includes: an oil film detection image preprocessing module for preprocessing the oil film detection image acquired by the UAV, wherein the preprocessing operations include at least one of the following: image denoising, median filtering, and contrast enhancement; a background separation module for separating the oil film region from the background in the oil film detection image using an image segmentation algorithm; an oil film feature extraction module for performing geometric feature analysis on the background-separated oil film detection image and extracting multiple types of oil film features, wherein the multiple types of oil film features include at least one of the following: oil film area, oil film perimeter, oil film aspect ratio, and oil film circularity; and an oil film dynamic shape analysis unit for performing dynamic shape analysis on the multiple types of oil film features of the oil film detection image at different time points based on the time series of the acquired images, and obtaining the spatial location and geometric features of the oil film at different time points by combining the geographic positioning information of the UAV image.

[0210] Optionally, the background separation module includes: a local region numerical detection submodule, used to detect the mean and standard values ​​of local regions in the oil film detection image using a local adaptive thresholding algorithm, wherein the mean of the local region refers to the average gray value of all pixels centered on each sub-region in the oil film detection image, and the standard deviation of the local region is used to measure the dispersion of pixel gray values ​​within the local region; a color channel processing submodule, used to perform color channel processing on the oil film detection image based on the mean and standard values ​​of local regions in the oil film detection image using an RGB thresholding algorithm, calculating the gray-level histogram data corresponding to multiple color channels, and obtaining the target threshold corresponding to each color channel; a threshold segmentation submodule, used to perform threshold segmentation processing on each color channel based on the target threshold, and synthesize the images of the three color channels to obtain a threshold-segmented color image; and a background separation submodule, used to separate the oil film region from the background in the oil film detection image based on the threshold-segmented color image.

[0211] Optionally, the oil film diffusion area assessment unit includes: a diffusion factor selection module, used to select oil film diffusion influencing factors based on real-time monitoring data from shore-based fixed monitoring stations, wherein the oil film diffusion influencing factors include: the canal's water flow velocity and direction; an oil droplet rising velocity calculation module, used to calculate the rising velocity of oil droplets in the oil film based on the correlation coefficient of water flow velocity, water flow direction, oil droplets rising uniformly in still water in laminar flow, water density, oil density, water dynamic viscosity coefficient, and oil droplet size in the oil film; and a diffusion coefficient calculation module, used to calculate the rising velocity of oil droplets in the oil film based on water flow velocity, water flow direction, and... The module calculates the oil film diffusion coefficient in the direction of the mainstream water flow based on the rising velocity of the oil droplets; the oil film change rate calculation module calculates the rate of change of oil film concentration in the direction of the mainstream water flow based on the water flow velocity, water flow direction, oil film diffusion coefficient in the direction of the mainstream water flow, oil film diffusion flux perpendicular to the direction of the mainstream water flow, oil droplet degradation coefficient in water, and estimated oil film concentration; the oil concentration distribution change determination module determines the oil concentration distribution change based on the spatial location and geometric characteristics of the oil film and the rate of change of oil film concentration in the direction of the mainstream water flow, and evaluates the oil film diffusion area based on the oil concentration distribution change.

[0212] Optionally, the oil film thickness analysis unit includes: a Raman spectroscopy acquisition module, used to acquire Raman spectral data of the waters where the ship is located using the ship's self-monitoring system, and record the ship's navigation trajectory and time information; a Raman spectral intensity ratio calculation module, used to extract the Raman spectral intensities at the first wavelength and the second wavelength based on the Raman spectral data acquired by the ship's self-monitoring system, and calculate the ratio of the two Raman spectral intensities; a model calculation module, used to call the correlation model between the Raman spectral intensity ratio and the oil film thickness, inputting the first wavelength and the corresponding first constant, the second wavelength and the corresponding second constant, and the two Raman spectral intensity ratios into the correlation model, and outputting the initial oil film thickness; an oil film morphology analysis module, used to analyze the spatial location and geometric characteristics of the oil film to obtain the oil film morphology; and to analyze the color distribution information of the oil film based on real-time monitoring data from shore-based fixed monitoring stations; and an oil film thickness adjustment module, used to adjust the initial oil film thickness based on the oil film morphology, the color distribution information of the oil film, the water oil concentration parameters, and the oil droplet size parameters to determine the final oil film thickness.

[0213] Optionally, the monitoring report generation unit includes: an oil spill area location determination module, used to determine the location of the oil spill area in the target canal waterway based on the spatial location and geometric characteristics of the oil slick at different time points using a geographic information system; an oil slick diffusion trend determination module, used to simulate the diffusion trajectory of the oil slick based on the oil slick diffusion area and thickness, and obtain the oil slick diffusion trend by combining canal flow data and oil slick diffusion prediction results; a canal pollutant diffusion analysis module, used to analyze the canal pollutant diffusion results based on the oil spill area location, oil slick diffusion area, and oil slick diffusion trend, combined with meteorological and hydrological data; and to determine the early warning level based on the canal pollutant diffusion results; and an oil spill monitoring and early warning report generation module, used to generate a canal oil spill monitoring and early warning report based on the early warning level, canal pollutant diffusion results, oil spill area location, and oil slick diffusion area.

[0214] The aforementioned monitoring and early warning system for oil spills on the canal surface may also include a processor and a memory. The aforementioned multi-source data acquisition unit 21, oil film shape analysis unit 22, oil film diffusion area assessment unit 23, oil film thickness analysis unit 24, monitoring report generation unit 25, etc., are all stored in the memory as program units, and the processor executes the aforementioned program units stored in the memory to realize the corresponding functions.

[0215] The aforementioned processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and adjusting kernel parameters enables intelligent monitoring and early warning of oil spills and pollutants from canal vessels.

[0216] The aforementioned memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0217] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored computer program, wherein, when the computer program is running, it controls the device where the computer-readable storage medium is located to execute the monitoring and early warning method for oil spills on the canal surface according to any one of the above embodiments.

[0218] According to another aspect of the present invention, an electronic device is also provided, including one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the monitoring and early warning method for oil spills on the canal surface as described in any of the above embodiments.

[0219] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the monitoring and early warning method for oil spills on the canal surface described in various embodiments of this application.

[0220] This application also provides a computer program product, including a non-volatile computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the monitoring and early warning method for oil spills on the canal surface described in various embodiments of this application.

[0221] Figure 3 This is a hardware structure block diagram of an electronic device (or mobile device) for implementing a method for monitoring and early warning of oil spills on a canal surface, according to an embodiment of the present invention. Figure 3 As shown, an electronic device may include one or more ( Figure 3 The processor (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and memory 304 for storing data are illustrated using 302a, 302b, ..., 302n. In addition, it may include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports in the I / O interface), a network interface, a keyboard, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 3 The structure shown is for illustrative purposes only and does not limit the structure of the electronic system described above. For example, the electronic device may also include... Figure 3 The more or fewer components shown, or having the same Figure 3 The different configurations shown.

[0222] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0223] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0224] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The system embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection of units or modules may be electrical or other forms.

[0225] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0226] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0227] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0228] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for monitoring and early warning of oil spills on the surface of a canal, characterized in that, include: Acquire a multi-source data set of the associated target canal waters, wherein the multi-source data set includes at least: UAV monitoring data, real-time monitoring data from shore-based fixed monitoring stations, and data on the waters where the ship is located collected by the ship's self-monitoring system; The steps for obtaining a multi-source data set of the associated target canal waterway include: installing multiple types of sensors at fixed shore-based locations on both banks of the target canal waterway; collecting data from the target canal waterway using the multiple types of sensors to obtain real-time monitoring data from the fixed shore-based monitoring stations; wherein the multiple types of sensors include at least one of the following: oil film sensors, water quality sensors, and meteorological sensors; the oil film sensors detect the optical or electrical characteristics of the water surface; the water quality sensors monitor the content of petroleum substances and chemical oxygen demand in the canal water; and the meteorological sensors collect meteorological data, which includes at least one of the following: wind speed, wind direction, and temperature data; installing oil-water separator monitoring equipment and ship exhaust gas monitoring equipment on the ship; using the oil-water separator monitoring equipment to monitor the oily wastewater discharge indicators of the ship in real time; using the ship exhaust gas monitoring equipment to detect the pollutant content in the ship exhaust gas; recording the ship's operating status; and obtaining the waterway data of the ship's location collected by the ship's self-monitoring system; wherein the oily wastewater discharge indicators include at least one of the following: oil content and suspended solids content. Based on multiple oil film detection images from the UAV monitoring data, the spatial location and geometric features of the oil film at different time points are identified; Based on the spatial location and geometric characteristics of the oil film, and combined with real-time monitoring data from the shore-based fixed monitoring station, the oil concentration distribution change is determined. The oil film diffusion area is then assessed based on this change, including: selecting influencing factors for oil film diffusion based on real-time monitoring data from the shore-based fixed monitoring station, wherein these influencing factors include: the canal's water flow velocity and direction; and calculating the rising velocity of oil droplets in the oil film based on the water flow velocity, the water flow direction, the correlation coefficient of oil droplets rising uniformly in still water in laminar flow, the density of water, the density of oil, the dynamic viscosity coefficient of water, and the droplet size in the oil film. The following steps are taken: First, the diffusion coefficient of the oil film in the mainstream water flow direction is calculated based on the water flow velocity, the water flow direction, and the rising velocity of the oil droplets. Second, the rate of change of oil film concentration in the mainstream water flow direction is calculated based on the water flow velocity, the water flow direction, the diffusion coefficient of the oil film in the mainstream water flow direction, the diffusion flux of the oil film perpendicular to the mainstream water flow direction, the degradation coefficient of the oil droplets in water, and the estimated concentration of the oil film. Third, the change in oil concentration distribution is determined based on the spatial location and geometric characteristics of the oil film and the rate of change of oil film concentration in the mainstream water flow direction. Finally, the oil film diffusion area is evaluated based on the change in oil concentration distribution. By analyzing the water area data collected by the ship's self-monitoring system, the oil concentration parameters and oil droplet size parameters of the water area where the ship is located are obtained. The oil film thickness is determined by combining the monitoring data of the UAV, the real-time monitoring data of the shore-based fixed monitoring station, the water oil concentration parameters, and the oil droplet size parameters. The step of determining the oil film thickness by combining the monitoring data from the UAV, the real-time monitoring data from the shore-based fixed monitoring station, the water oil concentration parameter, and the oil droplet size parameter includes: collecting Raman spectral data of the water area where the ship is located using the ship's self-monitoring system, and recording the ship's navigation trajectory and time information; extracting the Raman spectral intensities at a first wavelength and a second wavelength based on the Raman spectral data collected by the ship's self-monitoring system, and calculating the ratio of the two Raman spectral intensities; calling the correlation model between the Raman spectral intensities ratio and the oil film thickness, inputting the first wavelength and its corresponding first constant, the second wavelength and its corresponding second constant, and the two Raman spectral intensities ratio into the correlation model, and outputting the initial oil film thickness; analyzing the spatial location and geometric characteristics of the oil film to obtain the oil film morphology; analyzing the color distribution information of the oil film based on the real-time monitoring data from the shore-based fixed monitoring station; and adjusting the initial oil film thickness based on the oil film morphology, the oil film color distribution information, the water oil concentration parameter, and the oil droplet size parameter to determine the final oil film thickness. By combining the spatial location and geometric characteristics of the oil film at different time points, the oil film diffusion area, and the oil film thickness, a canal oil spill monitoring and early warning report is generated.

2. The monitoring and early warning method according to claim 1, characterized in that, The steps for obtaining a multi-source dataset of data related to the target canal waterway include: The drone is equipped with a high-definition camera, a multispectral camera, and a lidar. The drone is controlled to fly along a preset route in the target canal area. The high-definition camera is used to take real-time photos of the water surface of the target canal area. The multispectral camera is used to acquire spectral information of different bands. The lidar is used to measure the water surface height and terrain information to obtain the monitoring data of the drone.

3. The monitoring and early warning method according to claim 2, characterized in that, After acquiring the multi-source dataset of the associated target canal waters, the process also includes: Use the ship's self-monitoring system as a coordinate reference point; Based on the tilt angle and forward tilt angle of the motion sensor in the UAV device, calculate the planar rotation axis angle and planar rotation angle of the motion sensor; Based on the plane rotation axis angle and the plane rotation angle, and combined with the north azimuth angle of the ship's self-monitoring system, the corresponding matrix elements are calculated. Based on the target azimuth, pitch angle and distance measurements of the mobile sensor, the coordinates of the mobile sensor are calculated. Based on the matrix elements, the coordinates of the moving sensor are transformed to obtain the spatial coordinates of the moving sensor under the ship self-monitoring system; Based on the converted spatial coordinates of the mobile sensors under the ship self-monitoring system, the coordinates of the UAV monitoring data and the ship's location water area data collected by the ship self-monitoring system are unified. Using the ship self-monitoring system as a coordinate reference point, the coordinate system of the fixed shore-based monitoring stations on both sides of the canal in the real-time monitoring data of the shore-based fixed monitoring stations is transformed to the ship self-monitoring system, thereby completing the data coordinate unification of the multi-source data set; Based on the unified multi-source data set, data format conversion is performed to obtain the multi-source data set with a unified data format.

4. The monitoring and early warning method according to claim 1, characterized in that, The steps for identifying the spatial location and geometric features of oil film at different time points based on multiple oil film detection images from the UAV monitoring data include: The oil film detection image acquired by the UAV is preprocessed, wherein the preprocessing operation includes at least one of the following: image denoising, median filtering, and contrast enhancement; An image segmentation algorithm is used to separate the oil film region from the background in the oil film detection image; Geometric feature analysis is performed on the oil film detection image after background separation to extract multiple types of oil film features, wherein the multiple types of oil film features include at least one of the following: oil film area, oil film perimeter, oil film aspect ratio, and oil film circularity. Based on the time series of the acquired images, dynamic shape analysis is performed on the various oil film features of the oil film detection images at different time points. Combined with the geolocation information of the UAV images, the spatial location and geometric features of the oil film at different time points are obtained.

5. The monitoring and early warning method according to claim 4, characterized in that, The step of separating the oil film region from the background in the oil film detection image using an image segmentation algorithm includes: A local adaptive thresholding algorithm is used to detect the mean and standard values ​​of local regions in the oil film detection image. The mean of the local region refers to the average gray value of all pixels centered on each sub-region in the oil film detection image, and the standard deviation of the local region is used to measure the dispersion of pixel gray values ​​within the local region. Based on the mean and standard values ​​of local regions in the oil film detection image, the RGB thresholding algorithm is used to process the color channels of the oil film detection image, calculate the grayscale histogram data corresponding to multiple color channels, and obtain the target threshold corresponding to each color channel. Based on the target threshold, threshold segmentation is performed on each color channel, and the images of the three color channels are synthesized to obtain a color image after threshold segmentation. The oil film region is separated from the background in the oil film detection image based on the color image after threshold segmentation.

6. The monitoring and early warning method according to claim 1, characterized in that, The steps for generating a canal oil spill monitoring and early warning report, based on the spatial location and geometric characteristics of the oil film at different time points, the oil film diffusion area, and the oil film thickness, include: Based on the spatial location and geometric characteristics of the oil slick at different time points, a geographic information system is used to determine the location of the oil spill area in the target canal waterway. Based on the oil film diffusion area and the oil film thickness, the diffusion trajectory of the oil film is simulated. Combined with canal water flow data and oil film diffusion prediction results, the oil film diffusion change trend is obtained. Based on the location of the oil spill area, the oil film diffusion area, and the oil film diffusion trend, combined with meteorological and hydrological data, the results of pollutant diffusion in the canal were analyzed. The early warning level is determined based on the results of the canal pollutant diffusion. Based on the warning level, the results of pollutant diffusion in the canal, the location of the oil spill area, and the area of ​​oil film diffusion, an oil spill monitoring and warning report for the canal is generated.

7. A monitoring and early warning system for oil spills on the surface of a canal, characterized in that, include: A multi-source data acquisition unit is used to acquire a multi-source data set of the associated target canal waters, wherein the multi-source data set includes at least: UAV monitoring data, real-time monitoring data of shore-based fixed monitoring stations, and data on the waters where the ship is located collected by the ship self-monitoring system; The multi-source data acquisition unit includes: a shore-based fixed monitoring module, used to install various types of sensors at fixed shore-based locations on both banks of the target canal waterway, and to collect data from the target canal waterway using the various types of sensors to obtain real-time monitoring data from the shore-based fixed monitoring station. The various types of sensors include at least one of the following: an oil film sensor, a water quality sensor, and a meteorological sensor. The oil film sensor detects the optical or electrical characteristics of the water surface. The water quality sensor monitors the content of petroleum substances and chemical oxygen demand in the canal water. The meteorological sensor collects meteorological data, including at least one of the following: wind speed, wind direction, and temperature data. A ship self-monitoring module is used to install oil-water separator monitoring equipment and ship exhaust gas monitoring equipment on the ship. The oil-water separator monitoring equipment monitors the oily wastewater discharge indicators of the ship in real time, and the ship exhaust gas monitoring equipment detects the pollutant content in the ship exhaust gas, records the ship's operating status, and obtains the waterway data of the ship's location collected by the ship self-monitoring system. The oily wastewater discharge indicators include at least one of the following: oil content and suspended solids content. The oil film shape analysis unit is used to identify the spatial location and geometric features of the oil film at different time points based on multiple oil film detection images in the UAV monitoring data. The oil film diffusion area assessment unit is used to determine the oil concentration distribution change based on the spatial location and geometric characteristics of the oil film, combined with real-time monitoring data from the shore-based fixed monitoring station, and to assess the oil film diffusion area based on the oil concentration distribution change. The oil film diffusion area assessment unit includes: a diffusion factor selection module, used to select oil film diffusion influencing factors based on real-time monitoring data from the shore-based fixed monitoring station, wherein the oil film diffusion influencing factors include: the canal's water flow velocity and direction; an oil droplet rising velocity calculation module, used to calculate the rising velocity of oil droplets in the oil film based on the water flow velocity, the water flow direction, the correlation coefficient of oil droplets rising uniformly in still water in laminar flow, the density of water, the density of oil, the dynamic viscosity coefficient of water, and the oil droplet size in the oil film; and a diffusion coefficient calculation module, used to calculate the rising velocity of oil droplets in the oil film based on the water flow velocity, the water flow direction, and the... The system includes a rising velocity of oil droplets and a diffusion coefficient of the oil film in the direction of the main water flow. An oil film change rate calculation module calculates the rate of change of oil film concentration in the direction of the main water flow based on the water flow velocity, the water flow direction, the diffusion coefficient of the oil film in the direction of the main water flow, the diffusion flux of the oil film perpendicular to the direction of the main water flow, the degradation coefficient of the oil droplets in water, and the estimated oil film concentration. An oil concentration distribution change determination module determines the change in oil concentration distribution based on the spatial location and geometric characteristics of the oil film and the rate of change of oil film concentration in the direction of the main water flow, and evaluates the oil film diffusion area based on the change in oil concentration distribution. The oil film thickness analysis unit is used to analyze the water area data of the ship collected by the ship self-monitoring system to obtain the water oil concentration parameters and oil droplet size parameters of the water area where the ship is located. The oil film thickness is determined by combining the monitoring data of the UAV, the real-time monitoring data of the shore-based fixed monitoring station, the water oil concentration parameters, and the oil droplet size parameters. The oil film thickness analysis unit includes: a Raman spectroscopy acquisition module, used to acquire Raman spectral data of the waters where the ship is located using the ship's self-monitoring system, and record the ship's navigation trajectory and time information; a Raman spectral intensity ratio calculation module, used to extract the Raman spectral intensities at a first wavelength and a second wavelength based on the Raman spectral data acquired by the ship's self-monitoring system, and calculate the ratio of the two Raman spectral intensities; a model calculation module, used to call the correlation model between the Raman spectral intensity ratio and the oil film thickness, inputting the first wavelength and its corresponding first constant, the second wavelength and its corresponding second constant, and the two Raman spectral intensity ratios into the correlation model, and outputting the initial oil film thickness; an oil film morphology analysis module, used to analyze the spatial location and geometric features of the oil film to obtain the oil film morphology; and to analyze the color distribution information of the oil film based on real-time monitoring data from the shore-based fixed monitoring station; and an oil film thickness adjustment module, used to adjust the initial oil film thickness based on the oil film morphology, the color distribution information of the oil film, the water oil concentration parameter, and the oil droplet size parameter to determine the final oil film thickness; The monitoring report generation unit is used to generate a canal oil spill monitoring and early warning report by integrating the spatial location and geometric characteristics of the oil film at different time points, the oil film diffusion area and the oil film thickness.

8. An electronic device, characterized in that, It includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the monitoring and early warning method for oil spills on the canal surface as described in any one of claims 1 to 6.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the monitoring and early warning method for oil spills on the canal surface as described in any one of claims 1 to 6.

Images