A Multi-Dimensional Spatial Fusion-Guided Active Measurement Method and System for Ship Altitude

By constructing a world coordinate system on the bridge structure, performing multi-source data fusion and dynamic compensation of flight paths, and combining vision, radar, and AIS systems, high precision, low false alarm rate, and all-weather operation capability of bridge anti-ship collision ultra-high detection were achieved, solving the problem of data being difficult to utilize uniformly in existing technologies.

CN123111104APending Publication Date: 2026-11-17GUANGDONG INSTITUTE OF SAFETY PRODUCTION & EMERGENCY MANAGEMENT SCIENCE & TECHNOLOGY +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611610686.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-10-19
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

Existing bridge collision prevention methods for detecting excessive height are either too simple or have large errors, and data from multiple sensors are difficult to effectively integrate, resulting in the inability to achieve precise positioning, accurate measurement, and identification. Consequently, the detection efficiency is low, the accuracy is poor, and the false alarm rate is high.

Method used

By constructing a world coordinate system based on the bridge structure, coordinate unification and dynamic compensation track fusion of multi-source heterogeneous data are carried out. Combining visual measurement and radar measurement, directional scanning is performed using a single-line laser ranging unit. In conjunction with the AIS system, identity association and early warning are performed, thereby realizing active measurement of ship altitude guided by multi-dimensional spatial fusion.

Benefits of technology

It achieves high-precision positioning, improves measurement efficiency, reduces false alarm rate, ensures all-weather operation capability, has adaptive intelligent data processing capability, and enhances system robustness and reliability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123111104A_ABST
    Figure CN123111104A_ABST
Patent Text Reader

Abstract

This invention discloses a multi-dimensional spatial fusion-guided active ship height measurement method and system. It constructs a world coordinate system based on the bridge structure, and maps the position data of the visual measurement unit, radar measurement unit, and automatic ship identification system to this coordinate system through coordinate transformation. At the synchronous moment, a fusion reference position is determined and the compensation amounts of each measurement source are calibrated. At the asynchronous moment when the data is not updated, two geometric constraint circles are constructed with the visual and radar measurement positions as geometric centers and the calibrated compensation amounts as constraint radii. The ship fusion position is determined by the intersection of the two circles. Based on this fusion position, the target direction of the single-line laser ranging unit is determined. A candidate scanning area is generated using the target image area of ​​the ship to be measured as a constraint, and directional scanning is performed to obtain the height measurement value. This value is then matched with a preset over-altitude judgment condition and spatiotemporally fused with the ship's static attribute information to determine the identity of the target ship triggering the over-altitude alarm and issue a warning. The method features high measurement accuracy, high efficiency, and a low false alarm rate.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of bridge safety monitoring and waterway traffic management technology, specifically to a multi-dimensional spatial fusion-guided active measurement method and system for ship height. Background Technology

[0002] Existing methods for detecting excessive height on bridges to prevent ship collisions are typically limited to single sources. They may rely on static data reported by AIS (Automatic Identification System), which can be prone to errors or deception; or on visual measurement, whose accuracy is easily affected by environmental factors; or on radar, which struggles to accurately identify specific vessels. The failure to effectively integrate data from multiple sensors hinders the achievement of precise positioning, accurate height measurement, and precise identification of ship targets. In short, the problems with existing technologies are: 1) Data from the same sensors (cameras, radar, AIS) exists in different coordinate systems and at different time frequencies, making direct and unified utilization difficult. 2) Single sensors have limitations, failing to simultaneously meet the requirements of high-precision positioning, all-weather operation, and identification. 3) The lack of a method to effectively integrate multi-source heterogeneous data and actively and accurately guide the height measurement device results in low detection efficiency, poor accuracy, and a high false alarm rate. Summary of the Invention

[0003] To overcome the shortcomings of existing technologies, this invention provides a multi-dimensional spatial fusion-guided active measurement method and system for ship altitude, which achieves a closed loop from "coarse screening" to "precise measurement" through coordinate unification, data fusion and active guidance.

[0004] A multi-dimensional spatial fusion-guided active method for measuring ship altitude includes the following steps:

[0005] S1. Construct a world coordinate system based on the bridge structure: acquire multi-source heterogeneous ship position data from visual measurement unit, radar measurement unit and automatic identification system, and map the ship position data to the world coordinate system through coordinate transformation;

[0006] S2. Dynamic compensation track fusion is adopted: At the time of data synchronization from each data source, the fusion reference position of the ship is determined, and the compensation amount of the measurement position of the visual measurement unit and the measurement position of the radar measurement unit relative to the fusion reference position is respectively calibrated; at the time of asynchronous data when the ship automatic identification system data is not updated, two geometric constraint circles are constructed with the current visual measurement position and radar measurement position as geometric centers and the corresponding compensation amount calibrated at the most recent synchronization time as constraint radii, and the ship fusion position at the current time is determined based on the intersection of the two geometric constraint circles.

[0007] S3. Perform visual constraint orientation height measurement: Determine the target direction of the single-line laser ranging unit pointing to the ship under test based on the ship fusion position, and generate candidate scanning areas of the single-line laser ranging unit using the target image area of ​​the ship under test detected by the visual measurement unit as a constraint, so that the single-line laser ranging unit only performs orientation scanning within the candidate scanning area to obtain the height measurement value of the ship under test.

[0008] S4. Ultra-high altitude discrimination and identity association warning: The height measurement value is matched with the preset ultra-high altitude judgment conditions, and the matching result is spatiotemporally matched and data fused with the ship static attribute information provided by the Automatic Identification System to determine the identity of the target ship that triggers the ultra-high altitude alarm, and a warning command is generated to drive the warning module to execute the warning.

[0009] A multi-dimensional spatial fusion-oriented active ship altitude measurement system, comprising:

[0010] Data acquisition module: includes camera, aerial survey radar, AIS receiver, single-line laser rangefinder and radar level gauge;

[0011] A data processing and control center is used to receive and process data from the data acquisition module, execute the multi-dimensional spatial fusion-guided active ship altitude measurement method as described above, and includes:

[0012] The spatial reference unification module is configured to construct a world coordinate system based on the bridge structure, and to map the ship position data obtained by the camera, the aerial survey radar and the AIS to the world coordinate system through coordinate transformation;

[0013] The dynamic compensation track fusion module is configured to determine the fusion reference position of the ship at the data synchronization moment and calibrate the compensation amount of each measurement source relative to the fusion reference position. At the asynchronous moment when the AIS data is not updated, two geometric constraint circles are constructed with the ship position measured by the camera at the current moment and the ship position measured by the aerial survey radar at the current moment as the geometric center and the corresponding compensation amount calibrated at the most recent synchronization moment as the constraint radius. The ship fusion position at the current moment is determined based on the intersection of the two geometric constraint circles.

[0014] The visual constraint orientation height measurement module is configured to determine the target direction of the single-line laser rangefinder pointing at the ship under test based on the ship fusion position, and generate a candidate scanning area of ​​the single-line laser rangefinder using the target image area of ​​the ship under test detected by the camera as a constraint, so that the single-line laser rangefinder performs orientation scanning only within the candidate scanning area to obtain the height measurement value of the ship under test;

[0015] The ultra-high altitude identification and identity association early warning module is configured to match the measured altitude value with preset ultra-high altitude judgment conditions, and perform spatiotemporal matching and data fusion with the ship static attribute information provided by AIS to determine the identity of the target ship that triggers the ultra-high altitude alarm and generate an early warning command;

[0016] The early warning module is used to issue an ultra-high alarm in response to the early warning command.

[0017] The multi-dimensional spatial fusion-guided active ship altitude measurement method and system provided by this invention have the following advantages compared with the prior art:

[0018] 1) High-precision positioning: By combining radar water level gauge height information, multi-source sensor coordinate fusion and dynamic compensation track fusion method, the error of a single sensor is overcome, and the ship's position is accurately positioned, providing a foundation for subsequent orientation and height measurement.

[0019] 2) High-efficiency measurement: By actively guiding the single-line laser target with the fusion of ship position, and combining the ship target image area provided by the camera to limit the scanning range, the full-field scanning of traditional area array lidar is avoided, which greatly improves the measurement efficiency and realizes accurate measurement of "point and shoot".

[0020] 3) High-reliability identification: By combining the ship's fusion position, continuous track, AIS identity information and single-line laser altimetry results, the association between the altimetry results and the specific ship's identity can be realized; when multiple ships pass in close parallel, intersecting or passing continuously, the ambiguity between the association between the altimetry results and the AIS ship's identity can be reduced, and the reliability of identifying and alarming over-height ships can be improved.

[0021] 4) All-weather, all-time working capability: It combines the characteristics of vision (daytime advantage), radar (nighttime and severe weather advantage) and AIS (identity recognition advantage), forming a complementary advantage and improving the overall robustness and availability of the system.

[0022] 5) Adaptive and intelligent: The proposed dynamic compensation trajectory fusion method can adaptively process data of different frequencies and accuracies, enabling the system to have a certain intelligent data processing capability, and the trajectory output is smoother and more continuous. Attached Figure Description

[0023] Figure 1 This invention presents the overall structure of the multi-dimensional spatial fusion-guided active ship altitude measurement system and its three main devices (camera, aerial survey radar, and AIS).

[0024] Figure 2 This is a schematic diagram of the transformation model and parameters from the camera coordinate system to the world coordinate system in an embodiment of the present invention;

[0025] Figure 3 This is a schematic diagram of the transformation model and parameters from the aerial survey radar coordinate system to the world coordinate system in an embodiment of the present invention;

[0026] Figure 4 This is a schematic diagram of the transformation model and parameters from the AIS planar coordinate system to the world coordinate system in an embodiment of the present invention;

[0027] Figure 5 This invention provides the target matching process and judgment logic for three types of device data in the world coordinate system in this embodiment.

[0028] Figure 6 This is a schematic diagram illustrating the trajectory fusion problem of three different frequency data (camera, radar, AIS) in an embodiment of the present invention;

[0029] Figure 7 This is a schematic diagram of the fused position obtained using the "dynamic compensation" track fusion method in an embodiment of the present invention (i.e., finding the intersection point using the current position and historical deviation (radius) of the camera and radar).

[0030] Figure 8 This is a schematic diagram of a complete closed-loop scheme from multi-source data fusion, active laser altimetry to final early warning in an embodiment of the present invention. Detailed Implementation

[0031] To make the technical problems to be solved, the technical solutions, and the beneficial effects of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present invention and are not intended to limit the present invention.

[0032] A multi-dimensional spatial fusion-guided active measurement method and system for ship altitude is provided, wherein the system includes:

[0033] The data acquisition module, including a camera, aerial survey radar, AIS receiver, single-line laser rangefinder, and radar level gauge, is responsible for acquiring visual images, radar echoes, ship identification messages, laser ranging data, and real-time water level data.

[0034] The data processing and control center receives and processes data from the data acquisition module. Internally, it is divided into four modules: a spatial reference unification module, responsible for constructing the bridge's world coordinate system and completing coordinate mapping of three types of location data; a dynamic compensation track fusion module, responsible for reference calibration at synchronous times and geometric calculation at asynchronous times; a visual constraint orientation altimetry module, responsible for obtaining the ship's altitude by constraining laser ranging with the fused location and visual target area; and an over-altitude discrimination and identity association early warning module, responsible for spatiotemporally matching the measured altitude with AIS static information, locking the target ship's identity, and generating early warning commands.

[0035] The early warning module is used to issue an ultra-high alarm in response to early warning commands.

[0036] The data processing and control center is used to execute a multi-dimensional spatial fusion-guided active ship altitude measurement method, which includes the following steps:

[0037] S1. Construct a world coordinate system based on the bridge structure: acquire multi-source heterogeneous ship position data from visual measurement units, radar measurement units, and automatic identification systems, and map the ship position data to the world coordinate system through coordinate transformation;

[0038] S2. Dynamic compensation track fusion is adopted: At the time of data synchronization from each data source, the fusion reference position of the ship is determined, and the compensation amount of the measurement position of the visual measurement unit and the measurement position of the radar measurement unit relative to the fusion reference position is calibrated respectively; at the time of asynchronous data when the ship's automatic identification system data is not updated, two geometric constraint circles are constructed with the current visual measurement position and radar measurement position as geometric centers and the corresponding compensation amount calibrated at the most recent synchronization time as constraint radii, and the ship's fusion position at the current time is determined based on the intersection of the two geometric constraint circles.

[0039] S3. Perform visual constraint orientation height measurement: Determine the target direction of the single-line laser ranging unit pointing to the ship under test based on the ship fusion position, and generate candidate scanning areas of the single-line laser ranging unit using the target image area of ​​the ship under test detected by the visual measurement unit as a constraint, so that the single-line laser ranging unit only performs orientation scanning within the candidate scanning area to obtain the height measurement value of the ship under test.

[0040] S4. Over-height detection and identity association warning: Match the height measurement value with the preset over-height judgment conditions, and perform spatiotemporal matching and data fusion with the ship static attribute information provided by the Automatic Identification System (AIS) to determine the identity of the target ship that triggers the over-height alarm, and generate a warning command to drive the warning module to execute the warning.

[0041] The visual measurement unit is a camera, the radar measurement unit is an aerial survey radar, the automatic identification system for ships is AIS, and the data reported by AIS is received through an AIS receiver, and the single-line laser ranging unit is a single-line laser rangefinder.

[0042] The following further explanation is provided regarding the world coordinate system constructed in S1 with the bridge structure as the reference:

[0043] S11, Mapping of visual measurement data: Based on the imaging model of the visual measurement unit and combined with the reference height difference between the visual measurement unit and the water surface measured by the radar water level gauge, the two-dimensional image coordinates output by the visual measurement unit are converted into the water surface position coordinates in the world coordinate system.

[0044] S12, Mapping of radar measurement data: The spherical coordinate measurement output by the radar measurement unit is transformed into coordinates in the world coordinate system through rotation and translation transformations;

[0045] S13, Mapping of Automatic Identification System (AIS) Data: The geodetic coordinates reported by the AIS are transformed into Cartesian coordinates via map projection, and the vertical offset of the ship relative to the bridge reference axis is determined based on the Cartesian coordinates, and then mapped to the world coordinate system.

[0046] Among them, the reference height difference is the height of the visual measurement unit above the current water surface as measured by the radar level gauge; the spherical coordinate measurement is the spherical coordinate output by the radar measurement unit; the map projection transformation is Gauss-Kruger projection; and the vertical offset is the vertical distance from the ship to the bridge reference axis.

[0047] The following further explanation is provided regarding the dynamic compensation track fusion used in S2:

[0048] S21: At the moment of data synchronization update between the visual measurement unit, the radar measurement unit, and the automatic identification system, the ship position coordinates output by the three are statistically fused in the world coordinate system, and the obtained statistical center quantity is used as the fusion reference position of the ship; and the compensation amount of the measurement position of the visual measurement unit, the measurement position of the radar measurement unit, and the position reported by the automatic identification system relative to the fusion reference position is calibrated and recorded as the current calibration value.

[0049] S22: When the data of the Automatic Identification System (AIS) is not updated, but the visual measurement unit and the radar measurement unit have obtained the current ship position asynchronously, the current visual measurement position and the radar measurement position are respectively used as geometric centers, and the compensation amount corresponding to the visual measurement unit and the compensation amount corresponding to the radar measurement unit are respectively used as constraint parameters to construct two geometric constraints, and solve the intersection of the two geometric constraints to determine the ship's fused position at the current moment.

[0050] S23: When the data from the visual measurement unit, radar measurement unit, and automatic identification system are synchronized and updated again, the fusion reference position is redefined, and the compensation amounts corresponding to the positions reported by the visual measurement unit, radar measurement unit, and automatic identification system are updated accordingly for use in subsequent asynchronous ship position fusion.

[0051] Furthermore, in S21, statistical fusion is the average value of the ship's position output by the computer vision measurement unit, the radar measurement unit, and the automatic identification system in the world coordinate system; the resulting statistical center quantity is the fusion reference position, which is the ship's center position; the compensation quantity is the distance from the ship's position measured by each measurement source to the ship's center position.

[0052] Furthermore, in S22, the geometric constraint is a circle, that is, two geometric constraint circles; the geometric center is the center of the circle, the constraint parameter is the radius of the circle, and the intersection of the geometric constraints is the intersection of the two circles; the ship fusion position at the current moment determined based on the intersection of the two circles is the ship center position after the ship under test is fused.

[0053] The following further explanation is provided regarding the execution of visually constrained orientation and altimetry in S3:

[0054] S31: The optical axis direction of the single-line laser ranging unit is controlled in real time by the ship's fused position;

[0055] S32: The scanning area of ​​the single-line laser ranging unit is determined by the target image area of ​​the ship under test in the image provided by the vision measurement unit.

[0056] Furthermore, in S3, the height measurement value is the actual height of the ship to be measured obtained by the single-line laser ranging unit; in S4, the ship's static attribute information includes the ship name and reported height provided by AIS; the spatiotemporal matching and data fusion are as follows: the laser-measured height data and the ship identity information provided by AIS are aligned in time and space and then matched to determine the identity of the target ship that triggers the over-altitude alarm.

[0057] For ease of understanding, see Figures 1 to 8 This paper describes the multi-dimensional spatial fusion-guided active measurement method and system for ship altitude provided by the present invention.

[0058] like Figure 1 As shown, the ship's position is measured using three different devices—camera, aerial survey radar, and AIS—in their respective reference coordinate systems, designated as D1, D2, and D3. The difference E between each pair of the three measurements is then calculated. 12 E 13 E 23 According to the preset distance error threshold T hreshold If T hreshold > max (E 12 E 13 E 23 If we can determine that the measured ships are at the same location, then we can match the three locations together.

[0059] Figure 2 This shows the pixel coordinates of the ship in the image in the camera coordinate system. A schematic diagram of the parameters for the bridge's coordinates in the world coordinate system. Among them, For the camera focal length, internal parameters were calibrated using Zhang's chessboard calibration method. These are the coordinates of the center point of the image plane. The angle between the camera's optical axis and the horizontal plane (water surface) is called the downward angle (positive) and the upward angle (negative). Bridge monitoring typically uses the downward angle. The vertical height of the camera's optical center above the water surface is measured using a radar level gauge. (Camera coordinate system origin) In the light center, The axis points in front of the lens along the optical axis. Axis to the right, The axis points downwards. The world coordinate system defines it on the water surface. Origin. The projection point on the water surface directly below the camera's optical center. The axis points in the direction of the projection onto the horizontal plane directly in front of the camera. The axis is perpendicular to the water surface and upwards (opposite to the direction of gravity). The axis is determined according to the right-hand rule. The goal of this invention is to solve for a single pixel in an image. The corresponding actual position in the world coordinate system {W} (water surface) Since {W} is defined on the water surface, the point... The coordinates are always 0.

[0060] The specific steps are as follows:

[0061] Step S201: Ray direction from pixel coordinates to camera coordinate system

[0062] First, the pixel coordinates are transformed into a normalized direction vector in the camera coordinate system using the camera model.

[0063] 1) Convert pixel coordinates to normalized planar coordinates in the camera coordinate system (in...) (on the plane)

[0064] (1)

[0065] At this moment, in the camera coordinate system, the coordinates of this point are: This point defines the path from the optical center. The direction of the ray that originates from it.

[0066] 2) This direction vector is in the camera coordinate system {C} as .

[0067] Step S202: Establish the transformation relationship between the camera coordinate system {C} and the world coordinate system {W}.

[0068] According to the definition of the {W} system (with the origin directly below the optical center and the Z-axis pointing upwards):

[0069] The {C} system has a loop relative to the {W} system. axis The rotation (because the camera tilted downwards) horn).

[0070] Translation: The coordinates of the origin of the {C} system in the {W} system are... .

[0071] Therefore, the transformation from {C} to {W} is:

[0072] Rotation:

[0073] (2)

[0074] Translation:

[0075] (3)

[0076] The transformation formula for a point from the {C} system to the {W} system is:

[0077] (4)

[0078] Step S203: Find the intersection point of the ray and the water surface.

[0079] In the camera coordinate system {C}, the coordinates of any point on the ray can be represented as:

[0080] (5)

[0081] in It is a scale factor greater than 0, representing the distance from the optical center along the ray direction.

[0082] Now we will Transform to world coordinate system {W}:

[0083] (6)

[0084] This intersection must be located on the water surface. We use this condition to solve for... :

[0085] but , .

[0086] The obtained Substitute return The coordinates of the ship target in the water surface coordinate system {W} can be obtained from the expression. :

[0087] (7)

[0088] in, .

[0089] Figure 3This demonstrates the 3D point cloud sphere coordinates of the ship in the aerial survey radar coordinate system. Coordinates in the bridge world coordinate system A parameter diagram. Wherein, the origin... This is the phase center of the radar. The axis points upwards (related to the orientation of the radar antenna). The forward detection direction of the axis radar. The axis is determined by the right-hand rule. The world coordinate system defines it on the water surface. Origin. The water surface projection point directly below the radar installation point. The axis is parallel to the direction of bridge extension. The axis is perpendicular to the water surface and pointing upwards. The axis is perpendicular to the bridge and points towards the center of the river. The vertical height of the radar origin above the water surface. The spherical coordinates of the target vessel as measured by radar. Slant range. Azimuth (In the XY plane, from) (starting from axis), pitch angle (Starting from the XY plane, upwards is positive). The specific steps are as follows:

[0090] Step S301: Convert radar spherical coordinates to radar rectangular coordinates {R}

[0091] First, the rectangular coordinates of a point in the radar coordinate system , by its spherical coordinates The conversion formula is determined to be:

[0092] (8)

[0093] Step S302: Transform the radar coordinate system {R} to the world coordinate system {W}

[0094] Since the radar is installed on the side pier, its coordinate system {R} is rotated and translated from the world coordinate system {W}.

[0095] Translation vector: Assuming the origin of the world coordinate system At the radar origin The water surface directly below. Then the translation vector... In the {W} system:

[0096] (9)

[0097] Rotation matrix: The rotation matrix describes how to rotate the coordinate axes of the {R} frame to align with the {W} frame. Typically, radar... The axis points horizontally towards the center of the river channel (i.e., in relation to {W}). (Axial direction consistent), radar The axis is vertically upward (relative to the {W} system). (The axes are aligned), but the equipment used in this invention has a certain angle during installation. Further rotation is required. Therefore, rotation is ultimately achieved through two transformation processes.

[0098] (10)

[0099] The general formula for transforming a point from radar coordinate system {R} to world coordinate system {W} is:

[0100] (11)

[0101] Step S303: Combining the formulas from steps S301 and S302, we obtain the value directly from radar measurements. Calculate the coordinates of the target in the water surface world coordinate system {W} The complete formula:

[0102] (12)

[0103] This specifies the ship's height relative to the water surface. For ships on the water surface, its... It should be close to 0 (considering the ship's freeboard height and measurement errors). The value can be used as a validation parameter for data. If... A value much greater than 0 could indicate a bird in flight or a false detection; a value much less than 0 would suggest the target is underwater, which is unreasonable.

[0104] Figure 4 This demonstrates the two-dimensional plane coordinates of a ship in the AIS plane coordinate system. Coordinates in the bridge world coordinate system A parameter diagram. Wherein, the origin... The water surface projection point at the center of points A and B on the selected bridge axis. The axis is parallel to the direction of bridge extension. The axis is perpendicular to the water surface and pointing upwards. The axis is perpendicular to the bridge and points towards the center of the river channel. The target vessel information received by AIS includes longitude (LG) and latitude (LA). Slant range Azimuth (In the XY plane, from) (starting from axis), pitch angle (Starting from the XY plane, upwards is positive). The specific steps are as follows:

[0105] Step S401: Establish the bridge's planar coordinate reference and convert the ship's coordinates in real time.

[0106] 1) Define the key points of the bridge

[0107] Obtain the geodetic coordinates of the two endpoints A and B of the bridge: Point A: Latitude ,longitude Point B: Latitude ,longitude .

[0108] 2) Convert latitude and longitude coordinates using the Gauss-Kruger projection forward calculation formula.

[0109] The latitude and longitude coordinates of points A and B are transformed to their respective plane coordinate systems using the Gauss-Kruger projection forward calculation formula. The specific calculations are performed using a GIS database to complete the entire coordinate transformation. , Then, by using A and B conversions to calculate the same parameters, the ship's latitude and longitude coordinates are converted in real time. .

[0110] Step S402: Calculate the position of the ship relative to the bridge

[0111] The bridge endpoints are now known. , and ship position .

[0112] 1) Calculate the vertical distance to the bridge axis.

[0113] Treat the bridge axis as a direction vector .

[0114] Define a vector:

[0115] (13)

[0116] Projection parameters:

[0117] (14)

[0118] Perpendicular coordinates:

[0119] (15)

[0120] Vertical distance:

[0121] (16)

[0122] 2) Calculate the perpendicular distance to the axis that is perpendicular to the bridge axis and passes through the two endpoints A and B.

[0123] like Figure 4 As shown, the calculations obtained from the above steps Ships in the world coordinate system of the bridges we constructed Axis coordinates. Similarly, we construct a direction vector perpendicular to the bridge's axis vector, whose direction is relative to the bridge's world coordinate system. The axial directions are consistent, that is... As shown in the diagram, the center points of the two endpoints A and B are the center points of the bridge's world coordinate system. Similarly, we can obtain vectors. Repeating the calculation process in step 1 above, we can obtain the ship's coordinates in the bridge's world coordinate system. Axis coordinates .

[0124] Through the above calculations, the ship's latitude and longitude coordinates are finally determined. Transform to planar coordinates in the bridge world coordinate system we have constructed. .

[0125] Figure 5 This diagram illustrates the matching process of three devices transformed into the bridge's world coordinate system. Ideally, regardless of whether the camera coordinate system is transformed into the ship's coordinate system... Ship coordinates after radar coordinate system transformation Or the ship coordinates after AIS coordinate system transformation The three values ​​should be identical. However, in actual transformations, both the calculation method and the precision of the equipment itself can introduce some deviation. Therefore, to correlate the three coordinates, we set a target matching threshold. The following method is proposed to determine whether they are the same coordinates.

[0126] Step S501: Ship target matching calculation

[0127] 1) Calculate the coordinates of the midpoint of the three points.

[0128] (17)

[0129] 2) Calculate the distances from the three points to the midpoint.

[0130] (18)

[0131] 3) Based on the set threshold, determine whether the deviations of the three distances exceed the range. If all are less than the threshold, it proves that they are the same ship target point.

[0132] (19)

[0133] Figure 6 This diagram illustrates the transformation of the ship's target trajectory points when viewed in the bridge's world coordinate system using three different devices. Ideally, we would want the data collected by the three devices to have the same frequency. However, in reality, the AIS device's receiving frequency... It is lower than the camera frequency and radar frequency Therefore, we propose a high-precision trajectory fusion method based on dynamic compensation.

[0134] Step S601: Timestamp synchronization and frequency setting

[0135] First, synchronize the timestamps of the three devices to the same time zone and time base. Then, set the camera frequency and radar frequency to be the same, and their values ​​to be integer multiples of the AIS device frequency.

[0136] Step S602: As we know from step S501, we can obtain the coordinates of the center point ship by calculating the average of the three monitored ship position data. While matching the three together, we also obtained a set of distances. Based on the above information, we propose a track fusion method based on dynamic compensation.

[0137] First, at the initial moment, we obtain a set of distances. At the next moment, we can only obtain the ship's position as monitored by the cameras. and the location of ships monitored by radar We take these two locations as the center, and the distance from each location to the center point... Draw a circle with a radius, such as Figure 7 As shown. The center point can be obtained by calculating the intersection of the two circles. .

[0138] (20)

[0139] Step S603: Continue the above calculation process until the three parties match and synchronize to obtain data again, then update the distance. Continue the calculation process of formula (20). By performing the above steps, the ship trajectory can be obtained effectively and accurately.

[0140] Figure 8 A multi-dimensional spatial fusion-guided active ship altitude measurement scheme was demonstrated. The specific scheme is as follows:

[0141] Step S801: Based on the aforementioned steps and processes, we successfully matched and registered the ship's position information across the three devices, obtaining a precise ship position. Each of the three devices provided us with unique information. The camera provided candidate area information for the ship, AIS provided static information about the ship (such as ship name, altitude, etc.), and the fusion of camera and radar provided a precise ship trajectory. The specific over-altitude detection scheme is as follows:

[0142] 1) Based on the accurate trajectory information obtained, we can pinpoint the ship's location in real time.

[0143] 2) Align the optical axis of the single-line laser with the direction of this position and scan the ship area provided by the camera.

[0144] 3) Match the measured overheight information with the vessel information provided by AIS, record the data, and send it back to the ground control room. Issue relevant warnings to vessels exhibiting overheight based on the pre-established early warning plan.

[0145] 4) Once an over-height situation is detected, the vessel should be tracked in real time until it receives a warning and moves away from the bridge, at which point the tracking should end.

[0146] The above is a description of the present invention to help understand it. However, the implementation of the present invention is not limited to the above embodiments. Any changes, modifications, substitutions, combinations, or simplifications made without departing from the principle of the present invention should be considered equivalent substitutions and are included within the protection scope of the present invention.

Claims

1. A multi-dimensional spatial fusion-guided active measurement method for ship altitude, characterized in that, include: S1. Construct a world coordinate system based on the bridge structure: acquire multi-source heterogeneous ship position data from visual measurement unit, radar measurement unit and automatic identification system, and map the ship position data to the world coordinate system through coordinate transformation; S2. Dynamic compensation track fusion is adopted: At the time of data synchronization from each data source, the fusion reference position of the ship is determined, and the compensation amount of the measurement position of the visual measurement unit and the measurement position of the radar measurement unit relative to the fusion reference position is respectively calibrated; at the time of asynchronous data when the ship automatic identification system data is not updated, two geometric constraint circles are constructed with the current visual measurement position and radar measurement position as geometric centers and the corresponding compensation amount calibrated at the most recent synchronization time as constraint radii, and the ship fusion position at the current time is determined based on the intersection of the two geometric constraint circles. S3. Perform visual constraint orientation height measurement: Determine the target direction of the single-line laser ranging unit pointing to the ship under test based on the ship fusion position, and generate candidate scanning areas of the single-line laser ranging unit using the target image area of ​​the ship under test detected by the visual measurement unit as a constraint, so that the single-line laser ranging unit only performs orientation scanning within the candidate scanning area to obtain the height measurement value of the ship under test. S4. Ultra-high altitude discrimination and identity association warning: The height measurement value is matched with the preset ultra-high altitude judgment conditions, and the matching result is spatiotemporally matched and data fused with the ship static attribute information provided by the Automatic Identification System to determine the identity of the target ship that triggers the ultra-high altitude alarm, and a warning command is generated to drive the warning module to execute the warning.

2. The multi-dimensional spatial fusion-guided active ship altitude measurement method according to claim 1, characterized in that, The construction of a world coordinate system based on the bridge structure, as described in S1, includes: S11, Mapping of visual measurement data: Based on the imaging model of the visual measurement unit and combined with the reference height difference between the visual measurement unit and the water surface measured by the radar water level gauge, the two-dimensional image coordinates output by the visual measurement unit are converted into the water surface position coordinates in the world coordinate system. S12, Mapping of radar measurement data: The spherical coordinate measurement output by the radar measurement unit is transformed into coordinates in the world coordinate system through rotation and translation transformations; S13, Mapping of Automatic Identification System (AIS) data: The geodetic coordinates reported by the AIS are converted into Cartesian coordinates by map projection transformation, and the vertical offset of the ship relative to the bridge reference axis is determined based on the Cartesian coordinates, and then mapped to the world coordinate system.

3. The multi-dimensional spatial fusion-guided active ship altitude measurement method according to claim 1, characterized in that, The dynamic compensation track fusion described in S2 includes: S21: At the moment of data synchronization update of the visual measurement unit, the radar measurement unit, and the automatic identification system, the ship position coordinates output by the three are statistically fused in the world coordinate system, and the resulting statistical center quantity is used as the fusion reference position of the ship; and the compensation amount of the measurement position of the visual measurement unit, the measurement position of the radar measurement unit, and the position reported by the automatic identification system relative to the fusion reference position is calibrated and recorded as the current calibration value. S22: When the data of the Automatic Identification System (AIS) is not updated, but the visual measurement unit and the radar measurement unit have obtained the current ship position asynchronously, the current visual measurement position and the radar measurement position are respectively used as geometric centers. The compensation amount corresponding to the visual measurement unit and the compensation amount corresponding to the radar measurement unit calibrated at the most recent synchronization time are respectively used as constraint parameters to construct two geometric constraints. The intersection of the two geometric constraints is solved to determine the ship's fused position at the current time. S23: When the data of the visual measurement unit, the radar measurement unit and the automatic identification system of the ship are synchronized and updated again, the fusion reference position is re-determined, and the compensation amount corresponding to the position reported by the visual measurement unit, the position reported by the radar measurement unit and the position reported by the automatic identification system of the ship are refreshed accordingly, so as to be used for ship position fusion in subsequent asynchronous moments.

4. The multi-dimensional spatial fusion-guided active ship altitude measurement method according to claim 1, characterized in that, The execution of visual constraint orientation altimetry described in S3 includes: S31: The optical axis direction of the single-line laser ranging unit is controlled in real time by the ship's fusion position; S32: The scanning area of ​​the single-line laser ranging unit is determined by the target image area of ​​the ship under test in the image provided by the visual measurement unit.

5. The multi-dimensional spatial fusion-guided active ship altitude measurement method according to claim 2, characterized in that: The reference elevation difference is the height of the visual measurement unit above the current water surface as measured by the radar level gauge; the spherical coordinate measurement is the spherical coordinate output by the radar measurement unit; the map projection transformation is Gauss-Kruger projection; and the vertical offset is the vertical distance from the ship to the bridge reference axis.

6. The multi-dimensional spatial fusion-guided active ship altitude measurement method according to claim 3, characterized in that: In S21, the statistical fusion is to calculate the average value of the ship position output by the visual measurement unit, the radar measurement unit and the automatic identification system in the world coordinate system; the resulting statistical center quantity is the fusion reference position, which is the ship center position; the compensation quantity is the distance from the ship position measured by each measurement source to the ship center position.

7. The multi-dimensional spatial fusion-guided active ship altitude measurement method according to claim 3, characterized in that: In S22, the geometric constraint is a circle, namely the two geometric constraint circles; the geometric center is the center of the circle, the constraint parameter is the radius of the circle, and the intersection of the geometric constraints is the intersection of the two circles; the ship fusion position at the current moment determined based on the intersection of the two circles is the ship center position after the ship under test is fused.

8. The multi-dimensional spatial fusion-guided active ship altitude measurement method according to claim 1, characterized in that, In S3, the height measurement value is the actual height of the ship to be measured obtained by the single-line laser ranging unit; in S4, the ship static attribute information includes the ship name and reported height provided by AIS; the spatiotemporal matching and data fusion is: the laser-measured height data and the ship identity information provided by AIS are aligned in time and space and then matched to determine the identity of the target ship that triggers the over-altitude alarm.

9. The multi-dimensional spatial fusion-guided active ship altitude measurement method according to any one of claims 1 to 8, characterized in that, The visual measurement unit is a camera, the radar measurement unit is an aerial survey radar, the automatic identification system for ships is AIS, and the data reported by AIS is received via an AIS receiver, and the single-line laser ranging unit is a single-line laser rangefinder.

10. A multi-dimensional spatial fusion-guided active ship altitude measurement system, characterized in that, include: Data acquisition module: includes camera, aerial survey radar, AIS receiver, single-line laser rangefinder and radar level gauge; A data processing and control center is configured to receive and process data from the data acquisition module, execute the multi-dimensional spatial fusion-guided active ship altitude measurement method as described in any one of claims 1 to 9, and includes: The spatial reference unification module is configured to construct a world coordinate system based on the bridge structure, and to map the ship position data obtained by the camera, the aerial survey radar and the AIS receiver to the world coordinate system through coordinate transformation. The dynamic compensation track fusion module is configured to determine the fusion reference position of the ship at the data synchronization moment and calibrate the compensation amount of each measurement source relative to the fusion reference position. At the asynchronous moment when the AIS data is not updated, two geometric constraint circles are constructed with the ship position measured by the camera at the current moment and the ship position measured by the aerial survey radar at the current moment as the geometric center and the corresponding compensation amount calibrated at the most recent synchronization moment as the constraint radius. The ship fusion position at the current moment is determined based on the intersection of the two geometric constraint circles. The visual constraint orientation height measurement module is configured to determine the target direction of the single-line laser rangefinder pointing at the ship under test based on the ship fusion position, and generate a candidate scanning area of ​​the single-line laser rangefinder using the target image area of ​​the ship under test detected by the camera as a constraint, so that the single-line laser rangefinder performs orientation scanning only within the candidate scanning area to obtain the height measurement value of the ship under test; The ultra-high altitude identification and identity association early warning module is configured to match the measured altitude value with preset ultra-high altitude judgment conditions, and perform spatiotemporal matching and data fusion of the matching result with the ship static attribute information provided by AIS, so as to determine the identity of the target ship that triggers the ultra-high altitude alarm and generate an early warning command. The early warning module is used to issue an ultra-high alarm in response to the early warning command.