A bridge anti-collision early warning method and device, a storage medium and an electronic device

Abstract

The application provides a bridge anti-collision early warning method and device, a storage medium and an electronic device, and relates to the technical field of bridge anti-collision. The method comprises the following steps: acquiring first time and first heading information when a ship reaches a first monitoring position, and acquiring a second monitoring position where the ship is located at second time; determining second heading information of the ship from the first monitoring position to the second monitoring position; acquiring multiple image information between the first time and the second time, extracting multiple ship height data in the multiple image information respectively, and arranging the multiple ship height data in the order from the first time to the second time; inputting the first heading information, the second heading information and the multiple ship height data into a trained traffic probability prediction model to obtain a traffic probability; and when the traffic probability is lower than a set probability threshold, sending a warning signal to the ship. The method can accurately predict the probability of the ship passing through the bridge, and accurately warn the ship when the risk of collision is predicted to be high.

Description

Technical Field

[0001] This application relates to the field of bridge collision avoidance technology, specifically to a bridge collision avoidance early warning method, device, storage medium, and electronic equipment. Background Technology

[0002] With the continuous increase in ship traffic and the number of bridges being built, bridges, as important transportation hubs, are increasingly prone to ship collisions, which can even lead to serious accidents such as bridge collapses and ship sinkings.

[0003] To address the aforementioned bridge collision incidents, relevant technologies often employ sensors such as infrared and lidar to monitor the silhouettes of vessels approaching the bridge. The goal is to determine whether the vessel can pass smoothly without a collision and to issue an early warning when the silhouette cannot pass through the underpass. This serves as a safety reminder. However, under adverse weather conditions such as wind, waves, or rain, changes in water levels, the impact of waves on the vessel's movement, and course deviations can affect the accuracy of these monitoring methods, thus hindering accurate early warnings. Summary of the Invention

[0004] This application provides a bridge collision avoidance early warning method, device, storage medium, and electronic device. It considers the impact of wind and waves on the horizontal heading of a ship, as well as the vertical impact of hull pitching and water level changes on its height. By using a passage probability prediction model to calculate the passage probability, an early warning signal is issued to the ship when the communication probability is below a probability threshold. This method can accurately predict the probability of a ship passing over the bridge, and thus provide accurate early warnings when a high risk of collision is predicted.

[0005] In a first aspect, this application provides a bridge collision avoidance early warning method, the method comprising: Obtain the first moment and first heading information when the vessel arrives at the first monitoring position, and obtain the second monitoring position of the vessel at the second moment; Determine the second heading information of the vessel from the first monitoring position to the second monitoring position; Acquire multiple image information of the ship between the first time and the second time, and extract multiple ship height data from the multiple image information respectively. The multiple ship height data are arranged in order from the first time to the second time. The first heading information, the second heading information, and the multiple ship altitude data are input into the trained passage probability prediction model to obtain the passage probability. When the probability of passage is lower than the set probability threshold, a warning signal is issued to the vessel.

[0006] By adopting the above technical solution, considering the impact of wind and waves on the horizontal course of a ship, and the vertical impact of hull rolling and water level changes on its height, a passage probability prediction model is used to calculate the passage probability. When the communication probability falls below a probability threshold, a warning signal is issued to the ship. This allows for accurate prediction of the probability of a ship passing under a bridge, and thus provides accurate warnings when a high risk of collision is predicted.

[0007] Optionally, when a ship is detected to have just entered the monitoring area, an intelligent laser rangefinder is used to collect the ship's first monitoring position and the ship's first heading information. Two intelligent laser rangefinders are respectively set at both ends of the bridge, and the laser beams emitted by the intelligent laser rangefinders form an angle with the bridge and intersect horizontally in the monitoring area. At the second moment, the second monitoring position of the vessel as it sails to the monitoring area is obtained.

[0008] By adopting the above technical solution, the intelligent laser rangefinder uses the laser ranging principle and has high measurement accuracy and resolution. It can accurately measure the distance and relative position between ships and bridges, effectively avoiding measurement errors caused by visual errors or weather conditions. At the same time, the intelligent laser rangefinder has strong anti-interference capabilities and adaptability. In adverse weather conditions such as wind, waves, and rain, it can effectively avoid the influence of visual obstruction on the measurement results.

[0009] Optionally, determining the vessel's second heading information from the first monitoring position to the second monitoring position includes: By connecting the first monitoring position and the second monitoring position with a straight line, the second heading information of the ship can be obtained.

[0010] By adopting the above technical solution, it is possible to quickly obtain the course deviation of a ship in severe weather conditions, thereby enabling timely prediction of whether the ship can safely pass under the bridge.

[0011] Optionally, acquiring multiple image information of the ship between the first time and the second time includes: The shooting position of the image acquisition device and the shooting parameters of the image acquisition device are determined based on the first monitoring position. The image acquisition device is used to capture multiple images of the ship between the first time and the second time.

[0012] By adopting the above technical solution, when using image acquisition equipment to obtain the height of a ship, the accuracy of the subsequent image information can be improved, which facilitates the accurate prediction of the ship's passage probability.

[0013] Optionally, the step of extracting multiple ship height data from the multiple image information includes: Using image processing techniques, the edge contours of the ship in the plurality of image information are determined respectively; Based on the scaling ratio of the image information, multiple ship height data are determined from the edge contour of the ship.

[0014] By adopting the above technical solutions, the altitude information of ships can be accurately extracted, providing more accurate data support for the passage probability prediction model and improving the accuracy and reliability of the prediction.

[0015] Optionally, the step of inputting the first heading information, the second heading information, and the plurality of vessel altitude data into the trained passage probability prediction model to obtain the passage probability includes: Based on the first heading information and the second heading information, the route deviation data of the ship between the first time and the second time are calculated; The multiple ship height data were fitted using a linear regression equation to obtain height change data. The route deviation data and the altitude change data are input into the trained passage probability prediction model to obtain the passage probability.

[0016] By adopting the above technical solutions and acquiring and analyzing ship heading and altitude data, the probability of ship passage can be predicted more accurately, thereby providing timely early warnings to ships.

[0017] Optionally, the step of inputting the route deviation data and the altitude change data into the trained passage probability prediction model to obtain the passage probability includes: The ship is profiled using the heading deviation data and the altitude change data to obtain ship profile data. The trainable traffic probability prediction model is used to compare the ship profile data with the bridge traffic data to obtain the traffic probability.

[0018] By adopting the above technical solution, this method improves the safety and efficiency of vessel passage. Through profiling technology and model comparison, the probability of vessel passage can be predicted more accurately. Secondly, this application provides a bridge collision warning device, the device comprising: The first data acquisition module is used to acquire the first moment and first heading information when the ship arrives at the first monitoring position, and to acquire the second monitoring position of the ship at the second moment. The heading information acquisition module is used to determine the second heading information of the vessel from the first monitoring position to the second monitoring position; The second data acquisition module is used to acquire multiple image information of the ship between the first time and the second time, and extract multiple ship height data from the multiple image information respectively, wherein the multiple ship height data are arranged in order from the first time to the second time. The probability prediction module inputs the first heading information, the second heading information, and the multiple ship altitude data into the trained passage probability prediction model to obtain the passage probability. The early warning module issues an early warning signal to the vessel when the probability of passage is lower than a set probability threshold.

[0019] Thirdly, this application provides a computer storage medium storing a plurality of instructions adapted for loading by a processor and executing any of the methods described above.

[0020] Fourthly, this application provides an electronic device including a processor, a memory, and a transceiver, wherein the memory is used to store instructions, the transceiver is used to communicate with other devices, and the processor is used to execute the instructions stored in the memory to cause the electronic device to perform any of the methods described above.

[0021] In summary, the beneficial effects of the technical solution of this application include: Considering the impact of wind and waves on a ship's horizontal heading, and the vertical impact of hull pitching and water level changes on its height, a passage probability prediction model is used to calculate the passage probability. When the communication probability falls below a probability threshold, a warning signal is issued to the ship. This model can accurately predict the probability of a ship passing under a bridge, and thus provide accurate warnings when a high risk of collision is predicted. Attached Figure Description

[0022] Figure 1 This is a schematic flowchart of a bridge collision avoidance early warning method according to an embodiment of this application; Figure 2 This is a structural schematic diagram of a bridge collision warning device according to an embodiment of this application; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0023] Explanation of reference numerals in the attached drawings: 201, First data acquisition module; 202, Heading information acquisition module; 203, Second data acquisition module; 204, Probability prediction module; 205, Early warning module; 300, Electronic device; 301, Processor; 302, Communication bus; 303, User interface; 304, Network interface; 305, Memory. Detailed Implementation

[0024] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0025] In the description of the embodiments of this application, words such as "illustrative," "for example," or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "illustrative," "for example," or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Rather, the use of words such as "illustrative," "for example," or "for example" is intended to present the relevant concepts in a specific manner.

[0026] In the description of the embodiments of this application, the term "multiple" means two or more. For example, multiple systems means two or more systems, and multiple screen terminals means two or more screen terminals. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature. The terms "comprising," "including," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0027] First, a brief description of the specific scenario of this application is provided. With the increase in ship traffic and the number of bridges constructed, ship collisions with bridges occur frequently, posing a serious threat to people's lives and property. To effectively prevent and reduce bridge collision accidents, related technologies typically use sensors such as infrared and lidar to monitor the silhouette of ships approaching bridges. These sensors can capture the silhouette information of ships, thereby determining whether the ship can pass through the bridge smoothly without a collision. When the system detects that the ship's silhouette cannot pass through the bridge arch, it will issue a warning signal to remind the ship's navigator to pay attention to safety and take timely evasive action. However, under severe weather conditions such as wind, waves, and rain, the changes in water level and the impact of wind and waves on the ship's turbulence and course deviation are significant. This can affect the accuracy of the monitoring methods in related technologies, making accurate warnings impossible. Specifically, when the wind and waves are large, the ship will be affected by the wind force, causing it to sway and turbulent, which changes the ship's course and speed, making it impossible to accurately determine whether the ship can pass through the bridge smoothly. At the same time, wind and waves also cause fluctuations in water level, further affecting the accuracy of the monitoring methods. Rainy weather causes water level fluctuations and ship rocking due to rainwater accumulation, affecting the accuracy of monitoring methods. Furthermore, rainwater can cause errors and biases in sensors such as lidar, reducing the reliability of monitoring methods. Therefore, to address bridge collision prevention under severe weather conditions such as wind, waves, and rain, it is necessary to research and develop more reliable and accurate monitoring technologies and methods.

[0028] Please see Figure 1 This is a flowchart illustrating a bridge collision avoidance early warning method provided in an embodiment of this application. This method can be implemented using a computer program, a microcontroller, or run on a bridge collision avoidance early warning device based on the von Neumann architecture. The computer program can be integrated into the application or run as a standalone utility application. The specific steps of the bridge collision avoidance early warning method are described in detail below.

[0029] Step S101: Obtain the first moment and first heading information when the ship arrives at the first monitoring position, and obtain the second monitoring position where the ship is at the second moment.

[0030] The first monitoring position is the starting point for vessel monitoring under this application, when a vessel enters the first monitoring position. The first monitoring position is a preset location, typically situated at the entrance to a bridge, port, or other key waterway, recording the first moment of entry. The first heading information refers to the vessel's direction of travel when it enters the monitoring area from the first monitoring position. The first heading information can be obtained by acquiring the vessel's bow heading.

[0031] The second moment refers to the time after the vessel has been sailing in the monitored area for a certain period of time. Data from the first moment to the second moment is used as a sample to analyze the degree of impact of severe weather on the vessel, thereby determining whether it can safely pass under the bridge. The vessel's position in the monitored area at the second moment is the second monitoring position.

[0032] Specifically, the methods for obtaining the first monitoring position, the first heading information, and the second monitoring position are as follows: When the ship enters the monitoring area at the first moment, the first monitoring position and the first heading information of the ship are collected using an intelligent laser rangefinder. Two intelligent laser rangefinders are respectively set at both ends of the bridge, and the laser beams emitted by the intelligent laser rangefinders form an angle with the bridge and intersect horizontally in the monitoring area; the second monitoring position of the ship when it sails into the monitoring area is obtained at the second moment.

[0033] The laser beam emitted by the intelligent laser rangefinder forms an angle with the bridge and intersects horizontally within the monitored area. This setup ensures accurate monitoring and data collection of vessels. By observing the angle and intersection point between the laser beam and the bridge, the vessel's position and heading information within the monitored area can be determined.

[0034] As the ship navigates within the monitored area, at a second moment, the intelligent laser rangefinder acquires data showing the ship's position at a second monitoring location within the area. This data reflects the ship's trajectory and course changes over a period of time.

[0035] Additionally, accidental contact with the laser beam by birds or other objects could lead to false alarms from the laser rangefinder. However, by setting two horizontally emitted laser beams, each forming a certain angle with the bridge, this false alarm can be effectively avoided. When a ship enters the monitored area, it will sequentially contact both laser beams. Because the laser beams form an angle with the bridge and the two beams intersect horizontally, both beams will only be contacted simultaneously when the ship is within the monitored area. This allows the system to more accurately determine the ship's position and heading, improving the accuracy and reliability of the monitoring. By simultaneously acquiring data from both laser beams, the data can also be cross-checked, further reducing the possibility of false alarms. If the data measured by the two laser beams are inconsistent, the system will perform anomaly processing and judgment to avoid false alarms caused by inaccurate data from a single source.

[0036] Step S102: Determine the second heading information of the vessel from the first monitoring position to the second monitoring position.

[0037] Secondary heading information refers to the actual direction and trajectory of a vessel as it navigates from the first monitoring position to the second monitoring position within the monitored area. This information reflects course deviations caused by severe weather. By using the secondary heading information from the first to the second monitoring position as a sample, it is possible to predict subsequent vessel deviations when passing under bridges, thereby determining whether safe passage is possible.

[0038] One possible implementation is to connect the first monitoring position and the second monitoring position in a straight line to obtain the ship's second heading information.

[0039] Because timely and accurate early warnings are crucial in severe weather conditions, the straight-line path between the first and second monitoring positions, with its short interval between the two points in time, can be considered, to some extent, the actual heading information. This allows for the rapid acquisition of heading samples, facilitating subsequent prediction of passage probability.

[0040] Step S103: Acquire multiple image information of the ship between the first time and the second time, extract multiple ship height data from the multiple image information respectively, and arrange the multiple ship height data in the order from the first time to the second time.

[0041] When it is necessary to obtain information on the changes in a ship's height caused by wind, waves, or water level fluctuations in the vertical direction, acquiring images of the ship in the monitored area and extracting multiple ship height data from multiple images is a highly efficient method when time is limited. This allows for timely assessment of the probability that the ship can safely pass under the bridge.

[0042] In one feasible implementation, the shooting position and shooting parameters of the image acquisition device are determined based on the first monitoring position; the image acquisition device is used to capture multiple image information of the ship between the first moment and the second moment.

[0043] The primary monitoring position determines the optimal shooting location for capturing clear images of the vessel. Shooting parameters include, but are not limited to, exposure time, aperture, ISO sensitivity, and focal length. These parameters need to be determined based on shooting requirements and information from the primary monitoring position. For example, if the vessel is traveling at a high speed, a faster shutter speed may be needed to capture its movement; if the vessel is large or far away, a larger aperture or higher ISO sensitivity may be required to obtain a clearer image.

[0044] Between the first and second moments, image acquisition equipment takes multiple photographs of the ship to obtain various image data. The purpose is to record the ship's navigation status and changes between the first and second moments. Through multiple photographs, information such as the ship's position, heading, and speed at different points in time can be obtained, and this information can then be analyzed and processed, such as for trajectory tracking, speed calculation, and heading determination.

[0045] Specifically, image processing techniques are used to determine the edge contours of the ship in multiple image data; based on the scaling ratio of the image data, multiple ship height data are determined from the ship's edge contours.

[0046] Image processing techniques are used to analyze multiple images to determine the edge contours of the ship in each image. Specific image processing techniques may include, but are not limited to, edge detection, binarization, and morphological processing. These techniques extract the ship's edges from the images, forming its edge contours. By scaling the image information, the ship's size in the image can be converted to its actual size. Then, the ship's height data can be extracted from its edge contours.

[0047] Step S104: Input the first heading information, the second heading information, and multiple ship altitude data into the trained passage probability prediction model to obtain the passage probability.

[0048] The traffic probability prediction model is a pre-trained model that uses historical data as both the training and testing sets. It is trained and optimized by analyzing actual ship passage data from the past and manually labeled traffic probabilities. Traffic probability is quantified data used to evaluate bridge collision avoidance; it is used to determine whether collision warnings are needed for ships about to pass over the bridge.

[0049] Specifically, based on the first and second heading information, the ship's course deviation data between the first and second moments is calculated; multiple ship height data are fitted using a linear regression equation to obtain height change data; the course deviation data and height change data are input into the trained passage probability prediction model to obtain the passage probability.

[0050] The first and second heading information are converted into angle values. The heading angles at the two times are subtracted to obtain the course deviation angle. The course deviation angle is then converted into corresponding course deviation data. The course deviation data is the ship's course deviation angle during the time between the first and second times.

[0051] By fitting multiple ship height data points using a linear regression equation, we can obtain ship height variation data. Multiple ship height data points are extracted from multiple image datasets. The actual ship height is calculated based on the height of the ship's edge contour in each image, according to the image scaling ratio. By fitting these height data using a linear regression equation, the trend of ship height variation can be obtained. Based on the results of the linear regression equation, ship height variation data can be obtained. This data can be represented as the height value at each moment or as the rate of change of height over time. Using the height variation data, we can predict the maximum height a ship will reach when passing under a bridge, thereby determining its probability of successful bridge passage.

[0052] By inputting the calculated route deviation data and altitude change data into the already trained passage probability prediction model, the probability of ship passage can be obtained.

[0053] Specifically, the ship profile is created using heading deviation data and altitude change data; the passage probability is obtained by comparing the ship profile data with the bridge passage data using a pre-trained passage probability prediction model.

[0054] Ship profile data is obtained by using heading deviation data and altitude change data to characterize the vessel. This profile can include various features such as the vessel's navigation status, trajectory, and altitude changes when passing under a bridge. The constructed vessel profile is then converted into a corresponding data format to obtain vessel portrait data. This data can be used for subsequent comparison with a traffic probability prediction model. Specifically, based on the vessel's status and area when passing under the bridge, a pre-trained traffic probability prediction model is used to compare the vessel profile data with the bridge traffic data to determine the probability of vessel passage.

[0055] Step S105: When the probability of passage is lower than the set probability threshold, issue a warning signal to the ship.

[0056] Based on the bridge's collision safety requirements and actual weather conditions, a threshold for the probability of passage is set. This threshold can be a fixed value or a value that is dynamically adjusted based on various factors.

[0057] If the calculated probability of passage is lower than the set probability threshold, then the vessel is considered to pose a risk of passage, and a warning signal needs to be issued to remind the vessel's navigator to take appropriate evasive action. This warning signal can take various forms, such as sound, light, or radio signals, and is not specifically limited to any particular form.

[0058] The following are embodiments of the apparatus of this application, which can be used to execute the embodiments of the method of this application. For details not disclosed in the embodiments of the apparatus of this application, please refer to the embodiments of the method of this application.

[0059] Please see Figure 2 This illustration shows a structural schematic diagram of a bridge collision avoidance early warning device provided in an exemplary embodiment of this application. The device can be implemented as all or part of a whole through software, hardware, or a combination of both. The device includes a first data acquisition module 201, a heading information acquisition module 202, a second data acquisition module 203, a probability prediction module 204, and an early warning module 205.

[0060] The first data acquisition module 201 is used to acquire the first moment and first heading information when the ship arrives at the first monitoring position, and to acquire the second monitoring position where the ship is at the second moment. The heading information acquisition module 202 is used to determine the second heading information of the vessel from the first monitoring position to the second monitoring position; The second data acquisition module 203 is used to acquire multiple image information of the ship between the first time and the second time, and extract multiple ship height data from the multiple image information respectively. The multiple ship height data are arranged in order from the first time to the second time. The probability prediction module 204 is used to input the first heading information, the second heading information, and multiple ship altitude data into the trained passage probability prediction model to obtain the passage probability. The early warning module 205 is used to issue an early warning signal to the ship when the probability of passage is lower than the set probability threshold.

[0061] Optionally, the first data acquisition module 201 may also include a laser ranging unit.

[0062] The laser ranging unit is used to monitor the ship when it first enters the monitoring area. It uses an intelligent laser rangefinder to collect the ship's first monitoring position and first heading information. Two intelligent laser rangefinders are set up at both ends of the bridge. The laser beams emitted by the intelligent laser rangefinders form an angle with the bridge and intersect horizontally in the monitoring area. The second monitoring position of the ship when it sails into the monitoring area is obtained at the second moment.

[0063] Optionally, the heading information acquisition module 202 may also include a straight-line navigation unit.

[0064] The straight-line navigation unit is used to connect the first monitoring position and the second monitoring position in a straight line to obtain the ship's second heading information.

[0065] Optionally, the second data acquisition module 203 may also include a shooting adjustment unit and a height extraction unit.

[0066] The shooting adjustment unit is used to determine the shooting position and shooting parameters of the image acquisition device based on the first monitoring position; and to use the image acquisition device to capture multiple image information of the ship between the first moment and the second moment.

[0067] The height extraction unit is used to determine the edge contours of ships in multiple image information using image processing techniques; and to determine multiple ship height data from the edge contours of the ships based on the scaling ratio of the image information.

[0068] Optionally, the probability prediction module 204 may also include a probability calculation unit and a profile comparison unit.

[0069] The probability calculation unit is used to calculate the ship's route deviation data between the first and second time points based on the first and second course information; to fit multiple ship height data using a linear regression equation to obtain height change data; and to input the route deviation data and height change data into the trained passage probability prediction model to obtain the passage probability.

[0070] The image comparison unit is used to create a portrait of the ship using heading deviation data and altitude change data to obtain ship portrait data; it then compares the ship portrait data with bridge passage data using a pre-trained passage probability prediction model to obtain the passage probability.

[0071] This application also provides a computer storage medium that can store multiple instructions, which are adapted to be loaded and executed by a processor as described above. Figure 1 The bridge collision avoidance early warning method shown in the embodiment can be further explained in the following steps: Figure 1 The specific details of the illustrated embodiments will not be elaborated here.

[0072] Please see Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 3 As shown, the electronic device 300 may include: at least one processor 301, at least one network interface 304, user interface 303, memory 305, and at least one communication bus 302.

[0073] The communication bus 302 is used to enable communication between these components.

[0074] The user interface 303 may include a standard wired interface and a wireless interface.

[0075] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0076] The processor 301 may include one or more processing cores. The processor 301 connects to various parts of the server using various interfaces and lines, and performs various server functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in memory 305, and by calling data stored in memory 305. Optionally, the processor 301 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 301 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 301 and may be implemented as a separate chip.

[0077] The memory 305 may include random access memory (RAM) or read-only memory. Optionally, the memory 305 may include a non-transitory computer-readable storage medium. The memory 305 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 305 may also be at least one storage device located remotely from the aforementioned processor 301. Figure 3 As shown, the memory 305, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for a bridge collision avoidance and early warning method.

[0078] exist Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and to obtain the user input data; while the processor 301 can be used to call an application program stored in the memory 305 for a bridge collision avoidance warning method. When executed by one or more processors, the electronic device executes one or more methods as described in the above embodiments.

[0079] An electronic device readable storage medium stores instructions that, when executed by one or more processors, cause the electronic device to perform one or more methods as described in the above embodiments.

[0080] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0081] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0082] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the shown or discussed mutual couplings or direct couplings or communication connections may be through some service interfaces; indirect couplings or communication connections between apparatuses or units may be electrical or other forms.

[0083] 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 network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0084] Furthermore, the functional units in the various embodiments of this application 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.

[0085] 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 device (CMD). Based on this understanding, the technical solution of this application, 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 memory 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 of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0086] The above are merely exemplary embodiments of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Those skilled in the art will readily conceive of other embodiments of this disclosure upon considering the specification and the disclosure of practical truths. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described in this disclosure.

Claims

1. A bridge collision avoidance early warning method, characterized in that, The method includes: Obtain the first moment and first heading information when the vessel arrives at the first monitoring position, and obtain the second monitoring position of the vessel at the second moment; The steps of obtaining the first moment and first heading information when the vessel arrives at the first monitoring position, and obtaining the second monitoring position of the vessel at the second moment, include: When a vessel is detected entering the monitoring area at the first moment, a smart laser rangefinder is used to collect the first monitoring position and the first heading information of the vessel. Two smart laser rangefinders are respectively set at both ends of the bridge, and the laser beams emitted by the smart laser rangefinders form an angle with the bridge and intersect horizontally in the monitoring area. At the second moment, the second monitoring position of the vessel when it sails into the monitoring area is obtained. Determine the second heading information of the vessel from the first monitoring position to the second monitoring position; Acquire multiple image information of the ship between the first time and the second time, and extract multiple ship height data from the multiple image information respectively. The multiple ship height data are arranged in order from the first time to the second time. The first heading information, the second heading information, and the multiple ship altitude data are input into the trained passage probability prediction model to obtain the passage probability. The step of inputting the first heading information, the second heading information, and the multiple vessel altitude data into the trained passage probability prediction model to obtain the passage probability includes: Based on the first heading information and the second heading information, the route deviation data of the vessel between the first time and the second time is calculated; the multiple vessel height data are fitted using a linear regression equation to obtain height change data; the route deviation data and the height change data are input into a pre-trained passage probability prediction model to obtain the passage probability. The step of inputting the route deviation data and the altitude change data into the trained passage probability prediction model to obtain the passage probability includes: The ship is profiled using the heading deviation data and the altitude change data to obtain ship profile data; the ship profile data is compared with the bridge passage data using a trained passage probability prediction model to obtain the passage probability. When the probability of passage is lower than the set probability threshold, a warning signal is issued to the vessel.

2. The method according to claim 1, characterized in that, Determining the second heading information of the vessel from the first monitoring position to the second monitoring position includes: By connecting the first monitoring position and the second monitoring position with a straight line, the second heading information of the ship can be obtained.

3. The method according to claim 1, characterized in that, The acquisition of multiple image information of the ship between the first time and the second time includes: The shooting position of the image acquisition device and the shooting parameters of the image acquisition device are determined based on the first monitoring position. The image acquisition device is used to capture multiple images of the ship between the first time and the second time.

4. The method according to claim 1, characterized in that, The step of extracting multiple ship height data from the multiple image information includes: Using image processing techniques, the edge contours of the ship in the plurality of image information are determined respectively; Based on the scaling ratio of the image information, multiple ship height data are determined from the edge contour of the ship.

5. A bridge collision avoidance early warning device, characterized in that, The device includes: The first data acquisition module is used to acquire the first moment and first heading information when the ship arrives at the first monitoring position, and to acquire the second monitoring position of the ship at the second moment. Acquiring the first moment and first heading information when the ship arrives at the first monitoring position, and acquiring the second monitoring position of the ship at the second moment, includes: when the ship just enters the monitoring area at the first moment, using an intelligent laser rangefinder to collect the first monitoring position and the ship's first heading information, with two intelligent laser rangefinders respectively installed at both ends of the bridge, and the laser beams emitted by the intelligent laser rangefinders forming angles with the bridge and horizontally intersecting within the monitoring area; acquiring the second monitoring position of the ship when it sails into the monitoring area at the second moment. The heading information acquisition module is used to determine the second heading information of the vessel from the first monitoring position to the second monitoring position; The second data acquisition module is used to acquire multiple image information of the ship between the first time and the second time, and extract multiple ship height data from the multiple image information respectively, wherein the multiple ship height data are arranged in order from the first time to the second time. The probability prediction module inputs the first heading information, the second heading information, and the multiple vessel height data into a pre-trained passage probability prediction model to obtain the passage probability. This process includes: calculating the vessel's route deviation data between a first time point and a second time point based on the first and second heading information; fitting the multiple vessel height data using a linear regression equation to obtain height change data; and inputting the route deviation data and the height change data into the pre-trained passage probability prediction model to obtain the passage probability. The process further includes: creating a vessel profile using the heading deviation data and the height change data; and comparing the vessel profile data with bridge passage data using the pre-trained passage probability prediction model to obtain the passage probability. The early warning module issues an early warning signal to the vessel when the probability of passage is lower than a set probability threshold.

6. A computer storage medium, characterized in that, The computer storage medium stores multiple instructions, which are adapted to be loaded by a processor and executed as described in any one of claims 1 to 4.

7. An electronic device, characterized in that, The device includes a processor, a memory, and a transceiver. The memory is used to store instructions, the transceiver is used to communicate with other devices, and the processor is used to execute the instructions stored in the memory to cause the electronic device to perform the method as described in any one of claims 1 to 4.

Images