Navigation channel navigation mark collision monitoring method and system based on multi-sensor fusion

Abstract

The invention relates to the technical field of marine navigation collision avoidance, in particular to a navigation channel navigation mark collision monitoring method and system based on multi-sensor fusion. The method comprises the following steps: acquiring ship data and water surface data; the navigation direction angle is determined, and the collision risk degree is determined according to the direction angle, the distance between the ship and the navigation mark and the ship speed; determining a collision trend performance index according to the numerical change trend of the collision risk degree; determining an inertial parameter influence index according to the total weight of the ship and the speed of the ship; determining a channel curve influence index according to the flowing direction of the water and the flow velocity of the water; determining the danger avoidance degree by combining the collision trend performance index, the inertial parameter influence index and the channel curve influence index; and carrying out collision early warning on the ship and the navigation mark at the current moment in combination with the collision risk degree and the avoidance risk degree. According to the invention, based on multi-dimensional data analysis, a more accurate navigation mark collision monitoring and early warning result is provided, and the accuracy of navigation mark collision detection is improved.

Description

Technical Field

[0001] The present invention relates to the field of marine navigation collision avoidance technology, and in particular to a waterway beacon collision monitoring method and system based on multi-sensor fusion. Background Art

[0002] Navigation marks can provide ships with clear navigation paths, helping them to safely pass through complex waters and avoid running aground, stranding or other navigation hazards. However, improper operation or adverse weather and sea conditions during navigation may cause a ship to collide with a navigation mark, which may in turn cause damage and displacement of the ship and the navigation mark.

[0003] In the traditional navigation mark collision monitoring method, the navigation mark obtains the Euclidean distance between the ship and it within the monitoring range according to the AIS identification and positioning system, as well as the attitude angle information and acceleration information of the ship's navigation, and determines the danger distance. When the distance of the ship within the navigation mark monitoring range is lower than the danger distance, the communication system sends an early warning to the ship. This traditional monitoring method only analyzes the operating status of the ship itself to obtain the distance information, resulting in a relatively simple collision detection condition, limited monitoring precision, and insufficient monitoring accuracy. Summary of the invention

[0004] In order to solve the technical problem that the traditional monitoring method in the related art only analyzes the running status of the ship itself to obtain the distance information, resulting in a relatively single collision detection condition, limited monitoring accuracy, and insufficient monitoring accuracy, the present invention provides a waterway beacon collision monitoring method and system based on multi-sensor fusion, and the technical scheme adopted is as follows: The present invention proposes a waterway beacon collision monitoring method based on multi-sensor fusion, the method comprising: At different sampling times, obtaining ship data during the navigation process and water surface data at the navigation mark, wherein the ship data includes the position, speed, gross weight and navigation direction of the ship, and the water surface data includes the navigation mark position, the flow velocity and flow direction of the water body at the navigation mark position; A straight line connects the ship position and the navigation mark position, and the angle between the ship's sailing direction and the connected straight line at each sampling moment is taken as the direction angle, and the facing index of the ship's heading direction at each sampling moment is determined according to the direction angle; the collision risk degree between the ship and the navigation mark at each sampling moment is determined according to the Euclidean distance between the ship and the navigation mark, the speed of the ship, and the facing index of the ship's heading direction at each sampling moment; According to the numerical changes of the collision risk degree at all sampling moments, the collision trend performance index is determined; according to the total weight of the ship and the speed of the ship at the current moment, the inertia parameter influence index is determined; according to the angle between the navigation direction and the flow direction of the water body at the current moment, and the flow rate of the water body, the channel curve influence index is determined; the avoidance danger degree of the ship at the current moment is determined by combining the collision trend performance index, the inertia parameter influence index and the channel curve influence index; Based on the degree of collision risk and the degree of avoidance danger, a collision warning is issued for the ship and the navigation mark at the current moment.

[0005] Further, the determining the facing index of the ship heading direction at each sampling moment according to the direction angle includes: The opposite number of the direction angle is normalized to the maximum and minimum values ​​to obtain the facing index of the ship's heading direction.

[0006] Furthermore, the step of determining the collision risk between the ship and the navigation mark at each sampling moment according to the Euclidean distance between the ship and the navigation mark, the speed of the ship, and the facing index of the ship's heading direction at each sampling moment includes: Calculating the ratio of the Euclidean distance between the ship and the navigation mark to the speed of the ship to obtain an estimated collision time; The maximum and minimum values ​​of the ratio of the heading index of the ship to the estimated collision time are normalized to obtain the collision risk degree between the ship and the navigation mark.

[0007] Furthermore, the determination of the collision trend performance index according to the numerical changes of the collision risk levels at all sampling moments includes: A two-dimensional rectangular coordinate system is constructed with time as the horizontal coordinate and the collision risk degree as the vertical coordinate; sample points of the collision risk degree at all sampling moments are determined in the two-dimensional rectangular coordinate system; Based on the least squares straight line fitting method, a straight line fitting is performed on the sample points in the two-dimensional rectangular coordinate system, the slope of the fitted straight line is calculated, and the slope of the fitted straight line is normalized to the maximum and minimum values ​​as a slope influence index; The numerical mean of the collision risk level at all sampling moments is used as the collision impact indicator; The product of the slope influence index and the collision influence index is calculated to obtain a collision trend performance index.

[0008] Furthermore, the inertia parameter influencing index is determined according to the total weight of the ship and the speed of the ship at the current moment, including: The product value of the total weight of the ship and the speed of the ship at the current moment is calculated to obtain the inertia parameter influence index.

[0009] Furthermore, the determining of the channel curve influence index according to the angle between the navigation direction and the flow direction of the water body at the current moment, and the flow velocity of the water body, includes: Calculate the ratio of the angle formed by the navigation direction and the flow direction of the water body at the current moment to 180 degrees to obtain the water body flow angle impact index; The product of the inverse of the water body flow angle influence index and the flow velocity of the water body is used as the channel curve influence index.

[0010] Furthermore, the combination of the collision tendency performance index, the inertia parameter influence index and the channel curve influence index to determine the avoidance risk level of the ship at the current moment includes: The product of the collision tendency performance index, inertia parameter influence index and channel curve influence index of the ship at the current moment is calculated to obtain the avoidance danger degree.

[0011] Furthermore, the collision risk level and the avoidance risk level are combined to provide a collision warning for the ship and the navigation mark at the current moment, including: Calculate the product of the collision risk level and the avoidance risk level, and normalize the maximum and minimum values ​​to obtain a warning indicator; Determine whether to perform a collision warning according to the warning indicator.

[0012] Further, determining whether to perform a collision warning according to the warning indicator includes: When the warning indicator is greater than a preset warning threshold, it is determined to perform a collision warning, otherwise, no collision warning is performed.

[0013] On the other hand, a waterway beacon collision monitoring system based on multi-sensor fusion is also provided, the system comprising a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the steps of any of the methods described above when executing the computer program.

[0014] The present invention has the following beneficial effects: The present invention acquires multi-dimensional data, including ship data and water surface data at the buoy, so as to facilitate subsequent analysis of the multi-dimensional data; through the connection line between the ship position and the buoy position, as well as the speed and navigation direction of the ship, the collision risk analysis between the ship and the buoy is carried out, so as to obtain an accurate degree of collision risk, which takes into account information such as the direction, speed and position of the ship at different sampling times, so as to make collision predictions in advance, so that the collision risk degree can have a more accurate prediction effect; then, based on the collision trend performance index, the inertial parameter influence index and the channel curve influence index, the avoidance risk degree is analyzed, and the avoidance risk is mainly based on the control effect of the ship itself. Therefore, the total weight of the ship, the numerical change trend of the collision risk degree, the speed of the ship and the speed and direction of the water flow are combined to perform the avoidance risk analysis, and a more accurate and reliable degree of avoidance risk is obtained; in summary, in combination with the collision risk degree and the avoidance risk degree, a collision warning is given to the ship and the buoy at the current moment. The present invention can effectively conduct multi-angle and multi-dimensional data analysis on the ship's operating status and water flow status, thereby combining the ship's operating status, ship collision risk analysis and seawater thrust conditions to obtain more accurate navigation mark collision monitoring and early warning results, thereby improving the accuracy of waterway navigation mark collision detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 A flow chart of a waterway beacon collision monitoring method based on multi-sensor fusion provided by an embodiment of the present invention; Figure 2 A schematic diagram of a waterway navigation mark provided by an embodiment of the present invention; Figure 3 A structural diagram of a waterway beacon collision monitoring system based on multi-sensor fusion provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, features and effects of a waterway beacon collision monitoring method and system based on multi-sensor fusion proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0018] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0019] The specific scheme of the waterway beacon collision monitoring method based on multi-sensor fusion provided by the present invention is described in detail below with reference to the accompanying drawings.

[0020] See also Figure 1 , which shows a flow chart of a waterway beacon collision monitoring method based on multi-sensor fusion provided by an embodiment of the present invention, the method comprising: S101: At different sampling times, the ship data during the navigation process and the water surface data at the navigation mark are obtained, the ship data including the position, speed, total weight and navigation direction of the ship, and the water surface data including the navigation mark position, the flow velocity and flow direction of the water body at the navigation mark position.

[0021] The scenario of the embodiment of the present invention is a ship navigation scenario. The channel beacons in the scenario can provide navigation guidance for ships, helping them to safely pass through complex waters and avoid running aground, stranding or other navigation hazards. Figure 2 , Figure 2 A schematic diagram of a waterway navigation mark provided by an embodiment of the present invention.

[0022] In the traditional navigation mark collision monitoring method, a threshold value (such as 1 nautical mile) is set for the distance between the navigation mark and the ship, and the threshold value is adjusted according to the navigation status of the ship. When the distance is less than the threshold, the navigation mark issues an early warning to the ship. However, in actual scenarios, there are differences in the operating status of the ship within the navigation mark monitoring range, the inertial drift performance of the ship, and the thrust and resistance of the seawater current to the hull. These differences will affect the accuracy of navigation mark collision monitoring, making the monitoring accuracy of the traditional monitoring method that only analyzes the distance between the navigation mark and the ship insufficient. Therefore, the embodiment of the present invention combines the actual scenario and the data collected by the navigation mark multi-sensor to perform collision monitoring and early warning on the ship and the navigation mark within the navigation mark monitoring range.

[0023] In the embodiment of the present invention, the identity of the ship can be specifically identified through the AIS identification and positioning system, and real-time basic information of the ship can be obtained through the VHF marine communication system, including: 1. The ship's position, direction and speed data; 2. The track curve data of the route the ship has traveled; 3. Euclidean distance data between the ship and the navigation mark; 4. Model parameters of the vessel, including the weight and size information of the vessel.

[0024] Then, the basic information of the ship is sorted to obtain the ship data, which mainly includes the ship's position, speed, total weight and sailing direction. Among them, the ship's position can be specifically the GPS position information of the ship at different sampling times, the speed is meters per second, the total weight is the weight of the ship itself plus the weight of the cargo, which can be replaced by the draft, and the sailing direction is the instantaneous direction of the ship's sailing at different sampling times.

[0025] Among them, the real-time water flow velocity data of the seawater can be read through the water flow velocity sensor set underwater at the navigation beacon, and the real-time water flow direction of the seawater can be read through the water flow direction sensor set underwater at the navigation beacon, so as to obtain the flow velocity and flow direction of the water body at the navigation beacon position.

[0026] In the embodiment of the present invention, when there is a ship within the monitoring range of the navigation mark, the above multi-dimensional data is collected and uploaded to the data collection system, and thus the pre-preparation and multi-sensor data collection work are completed.

[0027] S102: A straight line is used to connect the ship position and the navigation mark position, and the angle between the ship's sailing direction and the connected straight line at each sampling moment is used as the direction angle. The facing index of the ship's heading direction at each sampling moment is determined according to the direction angle. The collision risk degree between the ship and the navigation mark at each sampling moment is determined according to the Euclidean distance between the ship and the navigation mark, the speed of the ship, and the facing index of the ship's heading direction at each sampling moment.

[0028] In the embodiment of the present invention, in order to facilitate collision monitoring, it is necessary not only to conduct a specific analysis of the distance between the ship and the navigation mark, but also to analyze the current action state of the ship, wherein the collision risk degree represents the probability information of the collision risk generated by the ship during the action process, that is, the larger the value of the collision risk degree, the more likely the collision risk is. Based on this, it is necessary to conduct a specific analysis of the position of the ship and the navigation mark, the sailing direction of the ship and the speed of the ship.

[0029] Among them, the direction angle is the angle between the ship's sailing direction and the line connecting the ship's navigation mark. The angle is a non-obtuse angle, that is, the smaller the angle value of the direction angle, the more consistent the ship's sailing direction is with the direction of the line connecting the ship's navigation mark, that is, the more likely the ship is to move toward the navigation mark, and the greater the probability of collision during the movement. It should be noted that since the detection range of the navigation mark is a circular range on the plane, that is, the smaller the direction angle, the ship may be close to the navigation mark or far away from the navigation mark. At this time, further analysis is required based on the distance between the ship and the navigation mark. Here, only the collision effect caused by the direction angle is analyzed.

[0030] Furthermore, in some embodiments of the present invention, the facing index of the ship's heading direction at each sampling moment is determined based on the direction angle, including: normalizing the opposite number of the direction angle to the maximum and minimum values ​​to obtain the facing index of the ship's heading direction.

[0031] Since the smaller the value of the direction angle is, the more likely the ship is facing the navigation mark, the opposite value of the direction angle is directly normalized to the maximum and minimum values ​​to obtain the facing index of the ship's heading direction. This facing index can be used for subsequent collision impact analysis.

[0032] After performing angle analysis to obtain the facing index, a collision analysis can be performed in multiple dimensions combining angle, speed, and distance. Further, in some embodiments of the present invention, the collision risk level between the ship and the navigation mark at each sampling moment is determined based on the Euclidean distance between the ship and the navigation mark, the speed of the ship, and the facing index of the ship's heading direction at each sampling moment, including: calculating the ratio of the Euclidean distance between the ship and the navigation mark to the speed of the ship to obtain an estimated collision time; normalizing the maximum and minimum values ​​of the ratio of the facing index of the ship's heading direction to the estimated collision time to obtain the collision risk level between the ship and the navigation mark.

[0033] In the embodiment of the present invention, all data are in standard units for the convenience of calculation and analysis, among which the ratio of the Euclidean distance between the ship and the navigation mark to the speed of the ship can be used as the estimated collision time to be produced, that is, the smaller the Euclidean distance between the ship and the navigation mark and the greater the speed of the ship, the shorter the corresponding estimated collision time, the easier it is for the ship to collide with the navigation mark and the greater the collision risk.

[0034] Furthermore, the smaller the angle value of the direction angle, the more consistent the direction of the ship's navigation direction is with the direction of the ship's navigation mark, that is, the larger the facing index is, the more likely the ship is to move toward the navigation mark, and the greater the probability of a collision during the movement, indicating that the facing index is positively correlated with the degree of collision risk, and the estimated collision time is negatively correlated with the degree of collision risk. Therefore, the ratio of the facing index of the ship's heading direction to the estimated collision time is directly calculated, and the maximum and minimum values ​​are normalized to obtain the degree of collision risk between the ship and the navigation mark.

[0035] The degree of collision risk represents the greater the probability of collision with navigation marks when the ship is sailing at the speed and direction at the corresponding sampling time. The analysis here is based on the operating status of the ship itself.

[0036] The avoidance state of the ship is subsequently analyzed, and the specific analysis process is shown in the subsequent embodiments.

[0037] S103: Determine the collision trend performance index according to the numerical changes of the collision risk degree at all sampling moments; determine the inertia parameter influence index according to the total weight of the ship and the speed of the ship at the current moment; determine the channel curve influence index according to the angle between the navigation direction and the flow direction of the water body at the current moment, and the flow rate of the water body; determine the avoidance danger degree of the ship at the current moment by combining the collision trend performance index, the inertia parameter influence index and the channel curve influence index.

[0038] It should be noted that the factors affecting avoidance mainly include the inertia of the ship itself, that is, the greater the inertia of the ship, the more difficult it is to avoid. Similarly, the avoidance process is also affected by the water flow at the corresponding sampling time. Therefore, separate analysis is required.

[0039] Firstly, a specific analysis is made on the collision trend, and the collision trend performance index is determined according to the numerical changes of the collision risk degree at all sampling moments, including: constructing a two-dimensional rectangular coordinate system with time as the horizontal axis and the collision risk degree as the vertical axis; determining the sample points of the collision risk degree at all sampling moments in the two-dimensional rectangular coordinate system; performing straight line fitting on the sample points in the two-dimensional rectangular coordinate system based on the least squares straight line fitting method, calculating the slope of the fitting straight line, and normalizing the slope of the fitting straight line to the maximum and minimum values ​​as the slope influence index; taking the numerical mean of the collision risk degree at all sampling moments as the collision influence index; calculating the product of the slope influence index and the collision influence index to obtain the collision trend performance index.

[0040] In the embodiment of the present invention, the collision risk degree indicates the probability of the collision risk. As time changes, the greater the mean value of the collision risk degree is, the stronger the collision trend is, and the greater the value of the collision trend performance index is.

[0041] In the embodiment of the present invention, the greater the slope of the fitting straight line is, the more dramatic the increase in the collision risk value is, the more likely a collision is to occur, and the more uncontrollable the situation is, the greater the collision trend performance index is.

[0042] Based on the above analysis, combined with the mean value of the collision risk degree and the slope of the fitted straight line, the product of the slope influence index and the collision influence index is directly calculated to obtain the collision trend performance index.

[0043] Among them, the collision trend performance index represents the index information of the collision trend. The larger the value of the collision trend performance index is, the greater the overall collision possibility is, which leads to a greater degree of danger for the ship when avoiding navigation marks.

[0044] Then, the inertia is specifically analyzed. Further, in some embodiments of the present invention, the inertia parameter influence index is determined according to the total weight of the ship and the speed of the ship at the current moment, including: calculating the product value of the total weight of the ship and the speed of the ship at the current moment to obtain the inertia parameter influence index.

[0045] Since inertia affects the stopping of the ship, the factor affecting inertia is mainly the mass of the ship, so the inertia is determined by the total weight of the ship. However, in the actual navigation process, the faster the ship speed, the weaker the ship's stopping control ability, and the longer the sliding navigation distance when the ship speed stops at 0. Therefore, the speed of the ship at the current moment is also used as an inertia influence indicator.

[0046] That is to say, the inertial parameter influence index in the embodiment of the present invention is not equivalent to the inertial information of the ship, but characterizes the inertial control effect when the ship stops from the sailing speed to 0 speed, that is, the larger the value of the inertial parameter influence index, the longer the distance the ship sails when it stops from the sailing speed, and the more difficult it is to perform the stop control, which further indicates that the subsequent avoidance ability of the navigation mark is worse.

[0047] Afterwards, the water flow and the impact on the channel are analyzed. Furthermore, in some embodiments of the present invention, the channel curve impact index is determined based on the angle between the navigation direction and the flow direction of the water body at the current moment, and the flow velocity of the water body, including: calculating the ratio of the angle formed by the navigation direction and the flow direction of the water body at the current moment to 180 degrees, to obtain the water flow angle impact index; taking the product of the opposite of the water flow angle impact index and the water flow velocity as the channel curve impact index.

[0048] Among them, the angle formed by the navigation direction and the flow direction of the water body at the current moment is a non-obtuse angle, that is to say, the smaller the angle formed by the navigation direction and the flow direction of the water body at the current moment, the more consistent the flow direction and the navigation direction, that is, the channel curve is more susceptible to the ocean current. Similarly, the greater the flow velocity of the water body, the more susceptible the channel curve is to the ocean current speed. Therefore, the product of the inverse of the water body flow angle influence index and the water body flow velocity is directly calculated to obtain the channel curve influence index.

[0049] The larger the value of the channel curve impact index, the more consistent the navigation curve is with the water flow direction, and the more susceptible the ship's navigation is to the ocean current, resulting in a greater degree of danger for the ship when avoiding navigation marks.

[0050] Furthermore, in some embodiments of the present invention, the collision tendency performance index, the inertia parameter influence index and the channel curve influence index are combined to determine the avoidance danger degree of the ship at the current moment, including: calculating the product value of the collision tendency performance index, the inertia parameter influence index and the channel curve influence index of the ship at the current moment to obtain the avoidance danger degree.

[0051] Among them, the larger the value of the collision trend performance index, the greater the overall possibility of collision, which leads to a greater degree of danger for the ship when avoiding navigation marks; the larger the value of the inertial parameter influence index, the longer the distance the ship has sailed when it stops from the navigation speed, and the more difficult it is to control the stop, which means the worse the subsequent ability to avoid navigation marks; and the larger the value of the channel curve influence index, the more consistent the navigation curve is with the water flow direction, and the more susceptible the ship's navigation is to the navigation current, which leads to a greater degree of danger for the ship when avoiding navigation marks.

[0052] From the logical analysis, it can be seen that the values ​​of the collision trend performance index, the inertia parameter influence index and the channel curve influence index are all positively correlated with the degree of avoidance danger. Therefore, the product value of the collision trend performance index, the inertia parameter influence index and the channel curve influence index of the ship at the current moment can be directly calculated to obtain the degree of avoidance danger.

[0053] S104: Based on the collision risk level and the avoidance danger level, a collision warning is issued for the ship and the navigation mark at the current moment.

[0054] Among them, the collision risk degree indicates the possibility of a collision between a ship and a navigation mark. The larger the value, the more likely it is that the ship and the navigation mark will collide. The avoidance risk degree indicates the risk probability of a ship avoiding during navigation. The larger the value, the more difficult it is for the ship to avoid. Therefore, the collision risk degree and the avoidance risk degree can be combined to perform collision warning analysis.

[0055] Furthermore, in some embodiments of the present invention, the product of the collision risk degree and the avoidance danger degree may be directly calculated, and the maximum and minimum values ​​may be normalized to obtain a warning index; and whether to perform a collision warning may be determined based on the warning index.

[0056] The warning indicator represents the value for the warning. When the warning indicator is greater than the preset warning threshold, a collision warning is determined. Otherwise, no collision warning is performed.

[0057] Among them, the preset warning threshold is the threshold value of the warning index. The preset warning threshold can be specifically 0.8, for example, that is, when the warning index is greater than 0.8, the navigation mark issues a collision warning to the ship, and when the warning index is less than or equal to 0.8, the navigation mark does not issue a collision warning to the ship.

[0058] Of course, in other embodiments of the present invention, corresponding threshold information may be set for the collision risk degree and the avoidance danger degree, respectively, so as to analyze them separately and take different warning effects, and there is no limitation on this.

[0059] In the embodiment of the present invention, the collision warning mainly refers to the navigation mark sending a warning notification to the ship through the communication system, such as transmitting a radio warning information to the ship's cab. The navigation mark can also directly use strong light to point to the ship's cab to achieve the warning, or it can also combine multiple warning functions to achieve collision warning, and there is no limitation on this.

[0060] The present invention acquires multi-dimensional data, including ship data and water surface data at the buoy, so as to facilitate subsequent analysis of the multi-dimensional data; through the connection line between the ship position and the buoy position, as well as the speed and navigation direction of the ship, the collision risk analysis between the ship and the buoy is carried out, so as to obtain an accurate degree of collision risk, which takes into account information such as the direction, speed and position of the ship at different sampling times, so as to make collision predictions in advance, so that the collision risk degree can have a more accurate prediction effect; then, based on the collision trend performance index, the inertial parameter influence index and the channel curve influence index, the avoidance risk degree is analyzed, and the avoidance risk is mainly based on the control effect of the ship itself. Therefore, the total weight of the ship, the numerical change trend of the collision risk degree, the speed of the ship and the speed and direction of the water flow are combined to perform the avoidance risk analysis, and a more accurate and reliable degree of avoidance risk is obtained; in summary, in combination with the collision risk degree and the avoidance risk degree, a collision warning is given to the ship and the buoy at the current moment. The present invention can effectively conduct multi-angle and multi-dimensional data analysis on the ship's operating status and water flow status, thereby combining the ship's operating status, ship collision risk analysis and seawater thrust conditions to obtain more accurate navigation mark collision monitoring and early warning results, thereby improving the accuracy of waterway navigation mark collision detection.

[0061] The present invention also provides a navigation channel collision monitoring system based on multi-sensor fusion, see Figure 3 , Figure 3 A structural diagram of a waterway beacon collision monitoring system based on multi-sensor fusion is provided for one embodiment of the present invention. The system 600 includes a memory 601, a processor 602, and a computer program 603 stored in the memory 601 and executable on the processor 602. When the processor 602 executes the computer program 603, the steps of the aforementioned waterway beacon collision monitoring method based on multi-sensor fusion are implemented.

[0062] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0063] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A waterway beacon collision monitoring method based on multi-sensor fusion, characterized in that: The method comprises: At different sampling times, obtaining ship data during the ship's voyage and water surface data at the navigation mark, wherein the ship data includes the ship's position, speed, gross weight, and navigation direction; and the water surface data includes the navigation mark position, the flow velocity, and the flow direction of the water body at the navigation mark position; A straight line is drawn to connect the ship's position and the position of the navigation mark. The angle between the ship's sailing direction and the straight line at each sampling moment is used as the bearing angle. The heading index of the ship's heading at each sampling moment is determined based on the bearing angle. The collision risk level between the ship and the navigation mark at each sampling moment is determined based on the Euclidean distance between the ship and the navigation mark, the ship's speed, and the heading index of the ship's heading at each sampling moment. Based on the numerical changes in the collision risk level at all sampling moments, a collision trend performance index is determined; based on the total weight of the ship and the speed of the ship at the current moment, an inertia parameter impact index is determined; based on the angle between the navigation direction and the flow direction of the water body at the current moment, as well as the flow rate of the water body, a channel curve impact index is determined; and based on the collision trend performance index, the inertia parameter impact index, and the channel curve impact index, the degree of avoidance risk of the ship at the current moment is determined. Based on the degree of collision risk and the degree of avoidance danger, a collision warning is issued for the ship and the navigation mark at the current moment.

2. The method for monitoring waterway and navigation mark collision based on multi-sensor fusion according to claim 1, characterized in that: Determining the facing index of the ship's heading direction at each sampling moment according to the direction angle includes: The opposite numbers of the direction angles are normalized to the maximum and minimum values ​​to obtain a facing index of the ship's heading direction.

3. The method for monitoring waterway and navigation mark collision based on multi-sensor fusion according to claim 1, characterized in that: Determining the collision risk level between the ship and the navigation mark at each sampling moment based on the Euclidean distance between the ship and the navigation mark, the speed of the ship, and the heading index of the ship at each sampling moment includes: Calculating the ratio of the Euclidean distance between the ship and the navigation mark to the speed of the ship to obtain an estimated collision time; The maximum and minimum values ​​of the ratio of the heading index of the ship to the estimated collision time are normalized to obtain the collision risk degree between the ship and the navigation mark.

4. The method for monitoring waterway and navigation mark collision based on multi-sensor fusion according to claim 1, characterized in that: The collision trend performance indicator is determined based on the numerical changes in the collision risk levels at all sampling moments, including: A two-dimensional rectangular coordinate system is constructed with time as the horizontal coordinate and the collision risk degree as the vertical coordinate; sample points of the collision risk degree at all sampling moments are determined in the two-dimensional rectangular coordinate system; Performing linear fitting on the sample points in the two-dimensional rectangular coordinate system based on the least squares linear fitting method, calculating the slope of the fitted straight line, and normalizing the maximum and minimum values ​​of the slope of the fitted straight line as a slope influence index; The numerical mean of the collision risk level at all sampling moments is used as the collision impact index; The product of the slope influence index and the collision influence index is calculated to obtain a collision trend performance index.

5. The method for monitoring waterway and navigation mark collision based on multi-sensor fusion according to claim 1, characterized in that: Determining the inertia parameter influencing index based on the total weight of the ship and the speed of the ship at the current moment includes: The product value of the total weight of the ship and the speed of the ship at the current moment is calculated to obtain the inertia parameter influence index.

6. The method for monitoring waterway and navigation mark collision based on multi-sensor fusion according to claim 1, characterized in that: The channel curve impact index is determined based on the angle between the navigation direction and the flow direction of the water body at the current moment, as well as the flow velocity of the water body, including: Calculate the ratio of the angle between the current navigation direction and the water flow direction to 180 degrees to obtain the water flow angle impact index; The product of the inverse of the water body flow angle influence index and the flow velocity of the water body is used as the channel curve influence index.

7. The method for monitoring waterway and navigation mark collision based on multi-sensor fusion according to claim 1, characterized in that: The method of combining the collision tendency performance index, the inertia parameter influence index, and the channel curve influence index to determine the avoidance risk level of the ship at the current moment includes: The product of the collision tendency performance index, inertia parameter influence index and channel curve influence index of the ship at the current moment is calculated to obtain the avoidance risk degree.

8. The method for monitoring waterway and navigation mark collision based on multi-sensor fusion according to claim 1, characterized in that: The above mentioned method combines the collision risk level and the avoidance risk level to issue a collision warning for the current moment between the ship and the navigation mark, including: Calculating the product of the collision risk level and the avoidance risk level, and normalizing the maximum and minimum values ​​to obtain a warning indicator; Determine whether to perform a collision warning based on the warning indicator.

9. The method for monitoring waterway and navigation mark collision based on multi-sensor fusion according to claim 8, characterized in that: The determining whether to perform a collision warning according to the warning indicator includes: When the warning indicator is greater than a preset warning threshold, it is determined to perform a collision warning; otherwise, no collision warning is performed.

10. A waterway and navigation mark collision monitoring system based on multi-sensor fusion, the system comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 9 are implemented.

Images