Integrated safety monitoring method and system for ship berthing and mooring

Abstract

The present invention relates to the field of ship monitoring technology, and discloses an integrated safety monitoring method and system for ship berthing and mooring. The point cloud data of the berthing and mooring area to be monitored is acquired by radar, and then the point cloud segmentation calculation is performed by plane segmentation, contour extraction, and point cloud point clustering to identify the position and posture of the ship, so as to obtain the monitoring index of the ship berthing and mooring. The point cloud data of the horizontal plane is determined by comparing the horizontal distance of each point cloud with a first distance threshold, and then the point cloud of the non-water surface object is obtained by separating the horizontal plane point cloud. By comparing the horizontal distance between the point cloud points with the second distance threshold, the ship and other obstacles are accurately separated. Accurate and real-time integrated safety monitoring of ship berthing and mooring is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of ship monitoring, and in particular to a method and system for integrated safety monitoring of ship berthing and mooring. Background Art

[0002] Berthing is the process of a ship approaching and contacting a dock or other fixed facilities, aiming to stabilize the ship and facilitate cargo loading and unloading, personnel embarkation and disembarkation, and other operations. Mooring is to firmly fix the ship to a dock or other fixed object to prevent movement or drift caused by natural factors such as water flow and wind. By simultaneously monitoring the motion status of the ship's berthing and mooring, we can fully grasp the real-time situation of each ship in the port, promptly discover and deal with potential safety hazards, and ensure the safety of ships and port facilities.

[0003] However, when monitoring the motion status of a ship while berthing and mooring, the following problems need to be overcome:

[0004] 1. The port environment is complex, with various types of obstacles and interference factors, such as waves, other ships, dock facilities, etc. During the berthing and mooring process, these obstacles and interference factors may block the ships, resulting in misjudgment or omission when identifying the target ship due to missing or deformed data, reducing the accuracy of the final monitoring results.

[0005] 2. During the simultaneous monitoring of ships while berthing or mooring, the monitoring range is wide and there are many objects to be identified. Data needs to be acquired and processed in real time. The amount of data is huge, which brings challenges to the computing power of the monitoring method, resulting in delayed monitoring results or failure to reflect the actual situation in a timely manner.

[0006] Therefore, there is an urgent need for an integrated safety monitoring method and system for ship berthing and mooring, which can accurately, real-time and efficiently monitor the berthing and system of the ship at the same time. Summary of the invention

[0007] In order to solve the above technical problems, the present invention provides, on one hand, a method for integrated safety monitoring of ship berthing and mooring, comprising the following steps:

[0008] S1: Acquire point cloud data of the mooring area to be monitored for safety through radar;

[0009] S2: Perform point cloud segmentation calculation based on the point cloud data to identify the position and posture of the ship, specifically:

[0010] S21: determining the point cloud data of the horizontal plane by comparing the horizontal distance between each point cloud point with a first distance threshold according to the point cloud data, and separating and obtaining the point cloud data of the non-horizontal plane objects in the mooring area;

[0011] S22: obtaining point cloud clusters of each object in the non-horizontal plane object by comparing the horizontal distance between the point cloud points with a second distance threshold value using a clustering method according to the point cloud data of the non-horizontal plane object;

[0012] The relationship between the first distance threshold and the second distance threshold is as follows:

[0013] d 2 = β × d 1× f(L ship ，L osb , σ env ，k) ;

[0014] Where d1 represents the first distance threshold, d2 represents the second distance threshold, β is the proportional coefficient, and L ship Indicates the length of the ship, L osb represents the length of the non-ship obstacle, σ env represents the standard deviation of environmental noise, k is the adjustment system, and f represents the function;

[0015] S23: fitting the point cloud clusters of each object in the non-horizontal plane objects to obtain the position and attitude of the ship;

[0016] S3: Obtain monitoring indicators of the ship's berthing through the position and posture of the ship, and perform visual display.

[0017] Preferably, the function f is specifically:

[0018] ;

[0019] In the formula, α is the exponential parameter and ln represents the natural logarithm.

[0020] Preferably, in S21, according to the point cloud data, by comparing the horizontal distance between each point cloud point with a first distance threshold, the point cloud data of the horizontal plane is determined, and the point cloud data of the non-horizontal plane objects in the mooring area are separated and obtained, comprising the following steps:

[0021] S211: randomly selecting a point cloud point in the point cloud data as an initial point cloud point;

[0022] S212: Calculate the difference between the ordinates of the initial point cloud point and each of its connected point cloud points, and take the point cloud point whose ordinate difference is not greater than the coordinate difference threshold as the primary point cloud point;

[0023] S213: Calculate the horizontal distance between each of the preliminarily selected point cloud points and the initial point cloud point, and compare each horizontal distance with a first distance threshold:

[0024] If the horizontal distance exceeds the first distance threshold, the initial point cloud point is reselected and steps S211 to S213 are executed;

[0025] If the horizontal distance does not exceed the first distance threshold, the point cloud point corresponding to the current horizontal distance is determined as a horizontal plane point cloud point and used as a new initial point cloud point;

[0026] And so on, traverse all point cloud points to obtain all horizontal point cloud points;

[0027] S214: Divide all the horizontal plane point cloud points into N regions and perform fitting respectively to determine the point cloud points corresponding to the horizontal plane;

[0028] S215: Separate all point cloud points corresponding to the horizontal plane from the point cloud data to obtain point cloud data of non-horizontal plane objects in the mooring area.

[0029] Preferably, in S22, based on the point cloud data of the non-horizontal surface object, by comparing the horizontal distance between the point cloud points with the second distance threshold, a clustering method is used to obtain a point cloud cluster of each object in the non-horizontal surface object, specifically:

[0030] S221: Calculating the horizontal distance between the point cloud points corresponding to each non-horizontal surface object through the point cloud data of the non-horizontal surface object;

[0031] S222: comparing the horizontal distance between the point cloud points with a second distance threshold, and taking the point cloud points that do not exceed the second distance threshold as point cloud points of non-horizontal surface objects;

[0032] S223: Clustering the point cloud points of the non-horizontal plane objects to obtain point cloud clusters of each object in the non-horizontal plane objects.

[0033] Preferably, in S23, the point cloud clusters of each object in the non-horizontal plane are fitted to obtain the position and attitude of the ship as follows:

[0034] According to the point cloud clusters of each object in the non-horizontal plane object, a ship is identified by using a contour extraction algorithm;

[0035] The point cloud cluster of the ship is subjected to a bounding box fitting method to obtain bounding box data of the ship; the bounding box data is output in the form of a group, and each group of the bounding box data includes time, length, width, height, coordinate position of the center point and heading angle;

[0036] The position and attitude of the ship are calculated based on the bounding box data of the ship.

[0037] Preferably, the monitoring indicators of the ship berthing include the distance of the ship from the embankment, the speed and angle of the ship.

[0038] Preferably, the monitoring indicators of the ship's mooring include the ship's sway, surge, heave, roll, pitch and bow pitch.

[0039] Preferably, in S3, monitoring indicators of the berthing of the ship are obtained through the position and posture of the ship, and are visualized, and further include:

[0040] The monitoring indicators of the ship berthing will be obtained and compared with the corresponding warning thresholds:

[0041] If the warning threshold is exceeded, the alarm function will be triggered, and the abnormal monitoring indicators and warnings will be prompted during the visual display.

[0042] As another aspect of the present invention, a ship berthing and mooring integrated safety monitoring system is also provided, which is used to execute any of the above-mentioned ship berthing and mooring integrated safety monitoring methods, and the system comprises: a data acquisition module, a ship position and posture recognition module, and an output module;

[0043] The data acquisition module is used to acquire point cloud data of the berthing area to be safely monitored by radar;

[0044] The ship position and posture recognition module is connected to the data acquisition module and is used to perform point cloud segmentation calculation according to the point cloud data to recognize the position and posture of the ship, specifically:

[0045] According to the point cloud data, by comparing the horizontal distance between each point cloud point with a first distance threshold, the point cloud data of the horizontal plane is determined, and the point cloud data of the non-horizontal plane objects in the mooring area are separated and obtained;

[0046] According to the point cloud data of the non-horizontal object, by comparing the horizontal distance between the point cloud points with the second distance threshold, using a clustering method, a point cloud cluster of each object in the non-horizontal object is obtained;

[0047] Fitting the point cloud clusters of each object in the non-horizontal plane objects to obtain the position and attitude of the ship;

[0048] The output module is connected to the ship position and posture recognition module, and is used to obtain monitoring indicators of the ship's berthing and mooring through the position and posture of the ship, and to perform visual display.

[0049] The embodiments of the present invention have the following technical effects:

[0050] 1. The integrated safety monitoring method for berthing and mooring of ships provided by the present invention obtains point cloud data of the berthing and mooring area to be monitored by radar, and then performs point cloud segmentation calculation through plane segmentation, contour extraction, and point cloud point clustering to identify the position and posture of the ship, so as to obtain monitoring indicators of the berthing and mooring of ships. As a whole, accurate and real-time integrated safety monitoring of berthing and mooring of ships is achieved together.

[0051] 2. When identifying the position and posture of a ship through the point cloud segmentation method, the water surface area is separated by comparing the horizontal distance of each point cloud with the first distance threshold; then, based on the point cloud data of non-horizontal objects, the horizontal distance between the point cloud points is compared with the second distance threshold to identify the point cloud corresponding to the ship. After layer-by-layer comparison, the amount of data processing is greatly reduced. In the subsequent point cloud cluster fitting, only the data corresponding to the ship is processed, which improves the data processing efficiency and further improves the real-time nature of the monitoring results.

[0052] 3. The first distance threshold and the second distance threshold need to satisfy a certain relationship, and comprehensively consider the length of the ship, the length of non-ship obstacles and the influence of environmental noise, so that the ship identification is more accurate, the monitoring accuracy is improved, and the robustness of the system in complex port environments is enhanced, thereby providing more reliable safety protection for ship berthing and mooring. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0054] Figure 1 is a flow chart of a method for integrated safety monitoring of ship berthing and mooring provided by an embodiment of the present invention;

[0055] Figure 2 is a flow chart of a method for obtaining point cloud data of non-horizontal objects in the mooring area provided by an embodiment of the present invention;

[0056] Figure 3 It is a flow chart of a method for obtaining point cloud clusters of each object in a non-horizontal plane provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0058] In view of the problem of low accuracy and delayed results in integrated monitoring of ship berthing and mooring, the present invention provides an integrated safety monitoring method for ship berthing and mooring, which realizes accurate and real-time integrated safety monitoring of ship berthing and mooring. Figure 1 The integrated safety monitoring method for ship berthing and mooring provided by the embodiment of the present invention specifically comprises the following steps:

[0059] S1: Acquire point cloud data of the mooring area to be monitored for safety through radar;

[0060] For example, based on the actual topography and ship distribution of the port to be inspected, laser radars are reasonably deployed to collect point cloud data of the berthing area. It can provide comprehensive coverage of the area, capture three-dimensional information of the entire monitoring area, and monitor around the clock without being restricted by light conditions. It can work in bad weather and nighttime environments, provide accurate input for subsequent processing, and ensure the accuracy of monitoring results.

[0061] S2: Perform point cloud segmentation calculation based on the point cloud data to identify the position and posture of the ship, specifically:

[0062] S21: determining the point cloud data of the horizontal plane by comparing the horizontal distance between each point cloud point with a first distance threshold according to the point cloud data, and separating and obtaining the point cloud data of the non-horizontal plane objects in the mooring area;

[0063] Preferably, in order to ensure data consistency and calculation accuracy, the point cloud data acquired by each radar is unified in coordinates in combination with the layout positions of each radar, so that the coordinates of each point cloud point are at the same coordinate.

[0064] According to the difference of the horizontal coordinates of each point cloud point in the point cloud data of the same coordinate system, the horizontal distance between each point cloud is obtained, and then the horizontal distance of each point cloud is compared with the first distance threshold to determine the point cloud data of the horizontal plane, so that the water surface area can be identified, and then the point cloud of non-surface objects can be obtained by separating the horizontal plane point cloud, which provides a basis for accurately identifying the position of the ship. At the same time, it also greatly reduces the amount of data processing in subsequent ship identification, improves the calculation efficiency while ensuring high recognition accuracy, and improves the real-time monitoring.

[0065] Preferably, in S21, according to the point cloud data, by comparing the horizontal distance between each point cloud point with the first distance threshold, the point cloud data of the horizontal plane is determined, and the point cloud data of the non-horizontal plane objects in the mooring area are separated and obtained. Figure 2 It can be seen that the following steps are included:

[0066] S211: randomly selecting a point cloud point in the point cloud data as an initial point cloud point;

[0067] S212: Calculate the difference between the ordinates of the initial point cloud point and each of its connected point cloud points, and take the point cloud point whose ordinate difference is not greater than the coordinate difference threshold as the primary point cloud point;

[0068] The size of the coordinate difference threshold can be determined according to the wave conditions at the scene. If the waves are violent, the coordinate difference threshold is increased; if the sea level is relatively calm and the waves are small, the coordinate difference threshold is reduced.

[0069] S213: Calculate the horizontal distance between each of the preliminarily selected point cloud points and the initial point cloud point, and compare each horizontal distance with a first distance threshold:

[0070] If the horizontal distance exceeds the first distance threshold, the initial point cloud point is reselected and steps S211 to S213 are executed;

[0071] If the horizontal distance does not exceed the first distance threshold, the point cloud point corresponding to the current horizontal distance is determined as a horizontal plane point cloud point and used as a new initial point cloud point;

[0072] And so on, traverse all point cloud points to obtain all horizontal point cloud points;

[0073] S214: Divide all the horizontal plane point cloud points into N regions and perform fitting respectively to determine the point cloud points corresponding to the horizontal plane;

[0074] The setting of the value N should be a balance between computational efficiency and fitting quality. The higher the density of the point cloud data, the more regions may be needed to accurately fit different plane parts. If the distribution of point cloud data is uneven, the region division may need to be adjusted according to the number of dense regions. However, more regions means that more computing resources and time may be required to process the data. Therefore, the specific value of region N should be determined based on different application scenarios and the requirements for accuracy and efficiency.

[0075] S215: Separate all point cloud points corresponding to the horizontal plane from the point cloud data to obtain point cloud data of non-horizontal plane objects in the mooring area.

[0076] S22: obtaining point cloud clusters of each object in the non-horizontal plane object by comparing the horizontal distance between the point cloud points with a second distance threshold value using a clustering method according to the point cloud data of the non-horizontal plane object;

[0077] The first distance threshold is used to separate the horizontal point cloud data from the point cloud data to determine the point cloud data of non-horizontal objects in the mooring area. This threshold should be large enough to exclude noise points that are very close to the radar, but not too large to exclude useful point cloud data. The setting of the first distance threshold should also take into account the size of the ship and the expected docking location.

[0078] The second distance threshold is used to identify individual obstacles by clustering in the point cloud data of the identified non-horizontal objects. This threshold determines which points in the point cloud are considered to be part of the same obstacle. The second distance threshold needs to be set based on the typical size of ships and other obstacles to ensure the accuracy of the clustering results.

[0079] Therefore, in order to more accurately identify each object, it is necessary to set the first distance threshold and the second distance threshold so that they satisfy the following relationship:

[0080] d 2 = β × d 1× f(L ship ，L osb , σ env ，k) ;

[0081] Where d1 represents the first distance threshold, d2 represents the second distance threshold, β is the proportional coefficient, and L ship Indicates the length of the ship, L osb represents the length of the non-ship obstacle, σ env represents the standard deviation of environmental noise, k is the adjustment system, and f represents the function.

[0082] The first distance threshold and the second distance threshold need to satisfy a certain relationship, and comprehensively consider the length of the ship, the length of non-ship obstacles and the influence of environmental noise, so as to make the ship identification more accurate, improve the accuracy of monitoring, and enhance the robustness of the system in complex port environments, thereby providing more reliable safety protection for ship berthing and mooring.

[0083] Preferably, the function f is specifically:

[0084] ;

[0085] Where α is an exponential parameter that can adjust the weight of the relationship between the length of the non-ship obstacle and the length of the ship; ln represents the natural logarithm, which is used to simulate the influence of the standard deviation of ambient noise on the determination of the threshold.

[0086] Preferably, in S22, based on the point cloud data of the non-horizontal surface object, by comparing the horizontal distance between the point cloud points with the second distance threshold, a clustering method is used to obtain the point cloud clusters of each object in the non-horizontal surface object, such as Figure 3 As shown, specifically:

[0087] S221: Calculating the horizontal distance between the point cloud points corresponding to each non-horizontal surface object through the point cloud data of the non-horizontal surface object;

[0088] Exemplarily, the method for calculating the horizontal distance between the point cloud points corresponding to each non-horizontal surface object is the same as the horizontal distance of each point cloud in S21.

[0089] S222: comparing the horizontal distance between the point cloud points with a second distance threshold, and taking the point cloud points that do not exceed the second distance threshold as point cloud points of non-horizontal surface objects;

[0090] S223: Clustering the point cloud points of the non-horizontal plane objects to obtain point cloud clusters of each object in the non-horizontal plane objects.

[0091] By comparing the horizontal distance between point cloud points with the second distance threshold, the ship can be accurately separated from other obstacles, the accuracy of the monitoring results can be improved, the point cloud data can be organized into meaningful clusters, structured data can be provided for subsequent analysis, the data processing efficiency can be improved, and the real-time nature of the monitoring results can be further improved.

[0092] S23: fitting the point cloud clusters of each object in the non-horizontal plane object to obtain the position and attitude of the ship, specifically:

[0093] S231: identifying the ship by using a contour extraction algorithm according to the point cloud clusters of each object in the non-horizontal plane object;

[0094] For example, first, the principal component analysis (PCA) is performed on the point cloud clusters of each object in the non-horizontal plane object to determine the major axis, minor axis and main direction of the point cloud, so as to identify the outline of the ship. Then, starting from the predefined seed point, according to a certain growth criterion, it is expanded to the neighborhood until the entire ship outline is covered. Finally, the active contour model (snakes) or the geodesic active contour model (geodesic active contours) is used to extract the boundary of the ship through iterative evolution.

[0095] S232: obtaining bounding box data of the ship by a bounding box fitting method for the point cloud cluster of the ship; the bounding box data is output in the form of groups, and each group of the bounding box data includes time, length, width, height, coordinate position of the center point and heading angle;

[0096] Exemplarily, the bounding box fitting of Lshape or the minimum rectangular area circumscription method is used to fit the point cloud cluster of the ship to obtain the bounding box data of the ship.

[0097] When identifying the position and posture of a ship through the point cloud segmentation method, the water surface area is separated by comparing the horizontal distance of each point cloud with the first distance threshold; then, based on the point cloud data of non-horizontal objects, the horizontal distance between the point cloud points is compared with the second distance threshold to identify the point cloud corresponding to the ship. After layer-by-layer comparison, the amount of data processing is greatly reduced. In the subsequent point cloud cluster fitting, only the data corresponding to the ship is processed, which improves the data processing efficiency and further improves the real-time nature of the monitoring results.

[0098] S233: Calculate the position and posture of the ship based on the bounding box data of the ship.

[0099] For example, the position of the ship at each time can be determined based on the time, length, width, height, and coordinate position of the center point in each set of bounding box data. The heading angle in each set of bounding box data is then used as the posture of the ship at each time.

[0100] S3: Obtain monitoring indicators of the ship's berthing through the position and posture of the ship, and perform visual display.

[0101] Preferably, the monitoring indicators of the ship berthing include the distance of the ship from the embankment, the speed and angle of the ship.

[0102] During the berthing process, these monitoring indicators are key factors in ensuring safety and efficiency. Distance of the ship from the embankment: This refers to the horizontal distance between the ship and the dock or embankment. During the berthing process, it is necessary to ensure that there is enough space between the ship and the dock to complete the berthing operation while avoiding collision. Speed ​​of the ship: The speed of the ship during berthing usually needs to be reduced to ensure that the ship can smoothly approach the dock. Speed ​​control is essential to prevent collision with the dock and ensure the safety of the crew. Angle of the ship: This refers to the relative position angle of the ship to the dock or embankment during the berthing process. Ideally, the ship should be as parallel to the dock as possible at the moment of contact with the dock, which helps to reduce friction and collision during berthing.

[0103] The method of obtaining monitoring indicators of ship berthing through the position and posture of the ship is relatively mature and is not limited here.

[0104] For example, the distance between the ship and the embankment can be determined by combining the coordinate position of the center point of the ship with the location of the embankment. The speed of the ship can be calculated by performing a time series analysis on the center point coordinates, that is, the speed is estimated by dividing the continuously recorded coordinate position change by the time change. The angle of the ship can be calculated using trigonometric functions using the center point coordinates, length, width, height of the ship, combined with the location of the dock.

[0105] Preferably, the monitoring indicators of the ship's mooring include the ship's sway, surge, heave, roll, pitch and bow pitch.

[0106] Sway refers to the left-right reciprocating motion of a ship along its transverse axis (i.e. horizontal direction). Surge refers to the forward-backward reciprocating motion of a ship along its longitudinal axis (i.e. the direction from bow to stern). Heave, also known as heave, refers to the reciprocating motion of a ship in a direction perpendicular to the water surface (i.e. up and down direction). Roll refers to the reciprocating rocking of a ship around its longitudinal axis (i.e. from one side of the ship to the other). Pitch: refers to the reciprocating rocking of a ship around its transverse axis (i.e. from bow to stern direction). Yaw: refers to the reciprocating rocking of a ship around its vertical axis (i.e. horizontal axis), which is the yaw motion of the ship. These movements are usually caused by natural forces such as wind, waves, and currents acting on the ship. When the ship is moored, these movements are monitored in real time to ensure the safety of the ship and the efficiency of cargo loading and unloading.

[0107] There are many methods for obtaining monitoring indicators of ship mooring through the position and posture of the ship, and they are not limited here as long as they can be calculated.

[0108] Exemplarily, the ship's sway can be obtained by dividing the change in the horizontal axis coordinate of the center point coordinate position in the ship's position over time by the change in time, that is, it is estimated by dividing the change in the horizontal axis of the continuously recorded center point coordinate position by the change in time.

[0109] Similarly, the ship's longitudinal motion can be obtained by dividing the change in the longitudinal coordinate of the center point coordinate position in the ship's position over time by the change in time, that is, it can be estimated by dividing the change in the longitudinal coordinate position of the continuously recorded center point by the change in time.

[0110] The vertical swing of the ship can be obtained by dividing the change of the vertical axis coordinate of the center point coordinate position in the ship's position over time by the change over time, that is, it can be estimated by dividing the change of the vertical axis coordinate position of the continuously recorded center point by the change over time.

[0111] The position of the ship at each moment can be determined based on the time, length, width, height, and coordinate position of the center point in each set of bounding box data. The heading angle in each set of bounding box data is then used as the posture of the ship at each moment.

[0112] The roll of a ship can be estimated by the change in the position of the center point of the ship in continuous time frames, combined with the changes in the length, width, height and direction of the ship. The pitch of a ship can be estimated by the change in the longitudinal coordinates of the ship over time. The bow roll of a ship can be obtained by calculating the change in the heading angle between two consecutive time points.

[0113] Preferably, in S3, monitoring indicators of the berthing of the ship are obtained through the position and posture of the ship, and are visualized, and further include:

[0114] The monitoring indicators of the ship berthing will be obtained and compared with the corresponding warning thresholds:

[0115] If the warning threshold is exceeded, the alarm function will be triggered, and the abnormal monitoring indicators and warnings will be prompted during the visual display.

[0116] As a whole, they jointly achieve accurate and real-time integrated safety monitoring of ship berthing and mooring.

[0117] As another aspect of the present invention, a ship berthing and mooring integrated safety monitoring system is also provided, which is used to execute any of the above-mentioned ship berthing and mooring integrated safety monitoring methods, and the system comprises: a data acquisition module, a ship position and posture recognition module, and an output module;

[0118] The data acquisition module is used to acquire point cloud data of the berthing area to be safely monitored by radar;

[0119] The ship position and posture recognition module is connected to the data acquisition module and is used to perform point cloud segmentation calculation according to the point cloud data to recognize the position and posture of the ship, specifically:

[0120] According to the point cloud data, by comparing the horizontal distance between each point cloud point with a first distance threshold, the point cloud data of the horizontal plane is determined, and the point cloud data of the non-horizontal plane objects in the mooring area are separated and obtained;

[0121] According to the point cloud data of the non-horizontal object, by comparing the horizontal distance between the point cloud points with the second distance threshold, using a clustering method, a point cloud cluster of each object in the non-horizontal object is obtained;

[0122] Fitting the point cloud clusters of each object in the non-horizontal plane objects to obtain the position and attitude of the ship;

[0123] The output module is connected to the ship position and posture recognition module, and is used to obtain monitoring indicators of the ship's berthing and mooring through the position and posture of the ship, and to perform visual display.

[0124] It should be noted that the terms used in the present invention are only for describing specific embodiments, rather than limiting the scope of the present application. As shown in the present specification, unless the context clearly indicates an exception, the words "one", "a", "a kind of" and / or "the" do not specifically refer to the singular, but may also include the plural. The terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method or device. In the absence of more restrictions, the elements defined by the sentence "include one..." do not exclude the presence of other identical elements in the process, method or device including the elements.

[0125] It should also be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. Unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", etc. should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be a connection between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0126] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. A method for integrated safety monitoring of ship berthing and mooring, characterized in that: The steps include: S1: Acquire point cloud data of the mooring area to be monitored for safety through radar; S2: Perform point cloud segmentation calculation based on the point cloud data to identify the position and posture of the ship, specifically: S21: According to the point cloud data, by comparing the horizontal distance between each point cloud point with the first distance threshold, the point cloud data of the horizontal plane is determined, and the point cloud data of the non-horizontal plane objects in the mooring area are separated and obtained, including the following steps: S211: randomly selecting a point cloud point in the point cloud data as an initial point cloud point; S212: Calculate the difference between the ordinates of the initial point cloud point and each of its connected point cloud points, and take the point cloud point whose ordinate difference is not greater than the coordinate difference threshold as the primary point cloud point; S213: Calculate the horizontal distance between each of the preliminarily selected point cloud points and the initial point cloud point, and compare each horizontal distance with a first distance threshold: If the horizontal distance exceeds the first distance threshold, the initial point cloud point is reselected and steps S211 to S213 are executed; If the horizontal distance does not exceed the first distance threshold, the point cloud point corresponding to the current horizontal distance is determined as a horizontal plane point cloud point and used as a new initial point cloud point; And so on, traverse all point cloud points to obtain all horizontal point cloud points; S214: Divide all the horizontal plane point cloud points into N regions and perform fitting respectively to determine the point cloud points corresponding to the horizontal plane; S215: Separating all point cloud points corresponding to the horizontal plane from the point cloud data to obtain point cloud data of non-horizontal plane objects in the mooring area; S22: Based on the point cloud data of the non-horizontal surface object, by comparing the horizontal distance between the point cloud points with the second distance threshold, using a clustering method, obtaining a point cloud cluster of each object in the non-horizontal surface object, specifically: S221: Calculating the horizontal distance between the point cloud points corresponding to each non-horizontal surface object through the point cloud data of the non-horizontal surface object; S222: comparing the horizontal distance between the point cloud points with a second distance threshold, and taking the point cloud points that do not exceed the second distance threshold as point cloud points of non-horizontal surface objects; S223: clustering the point cloud points of the non-horizontal plane objects to obtain point cloud clusters of each object in the non-horizontal plane objects; The relationship between the first distance threshold and the second distance threshold is as follows: d 2 = β × d 1× f(L ship ，L osb , σ env ，k) ; Where d1 represents the first distance threshold, d2 represents the second distance threshold, β is the proportional coefficient, and L ship Indicates the length of the ship, L osb represents the length of the non-ship obstacle, σ env represents the standard deviation of environmental noise, k is the adjustment system, and f represents the function; The function f is specifically: ; In the formula, α is the exponential parameter, and ln represents the natural logarithm; S23: fitting the point cloud clusters of each object in the non-horizontal plane object to obtain the position and attitude of the ship, specifically including: According to the point cloud clusters of each object in the non-horizontal plane object, a ship is identified by using a contour extraction algorithm; The point cloud cluster of the ship is subjected to a bounding box fitting method to obtain bounding box data of the ship; the bounding box data is output in the form of a group, and each group of the bounding box data includes time, length, width, height, coordinate position of the center point and heading angle; Calculating the position and attitude of the ship based on the bounding box data of the ship; S3: Obtain monitoring indicators of the ship's berthing through the position and posture of the ship, and perform visual display; The monitoring indicators of ship mooring include the ship's sway, pitch, heave, roll, pitch and bow pitch; The ship's sway is obtained by dividing the change in the horizontal axis coordinate of the center point of the ship's position over time by the change in time; The ship's heave is obtained by dividing the change in the longitudinal coordinate of the center point of the ship's position over time by the change in time; The vertical swing of the ship is obtained by dividing the change of the vertical axis coordinate of the center point of the ship's position over time by the change over time; The ship's roll is estimated by the change in position of the ship's center point in successive time frames, combined with the changes in the ship's length, width, height, and direction; The pitch of the ship is obtained by changing the longitudinal coordinates of the ship over time. The ship's bow roll is obtained by calculating the change in heading angle between two consecutive time points.

2. The integrated safety monitoring method for ship berthing and mooring according to claim 1 is characterized in that: Monitoring indicators for ship berthing include the distance between the ship and the embankment, the speed and angle of the ship.

3. The integrated safety monitoring method for ship berthing and mooring according to claim 1 is characterized in that: In S3, monitoring indicators of the ship's berthing are obtained through the position and posture of the ship, and are visualized and displayed, which also includes: The monitoring indicators of the ship berthing will be obtained and compared with the corresponding warning thresholds: If the warning threshold is exceeded, the alarm function will be triggered, and the abnormal monitoring indicators and warnings will be prompted during the visual display.

4. A ship berthing and mooring integrated safety monitoring system, used to implement the ship berthing and mooring integrated safety monitoring method according to any one of claims 1 to 3, characterized in that: The system comprises: a data acquisition module, a ship position and posture recognition module, and an output module; The data acquisition module is used to acquire point cloud data of the berthing area to be safely monitored by radar; The ship position and posture recognition module is connected to the data acquisition module and is used to perform point cloud segmentation calculation according to the point cloud data to recognize the position and posture of the ship, specifically: According to the point cloud data, by comparing the horizontal distance between each point cloud point with a first distance threshold, the point cloud data of the horizontal plane is determined, and the point cloud data of the non-horizontal plane objects in the mooring area are separated and obtained; According to the point cloud data of the non-horizontal object, by comparing the horizontal distance between the point cloud points with the second distance threshold, using a clustering method, a point cloud cluster of each object in the non-horizontal object is obtained; Fitting the point cloud clusters of each object in the non-horizontal plane objects to obtain the position and attitude of the ship; The output module is connected to the ship position and posture recognition module, and is used to obtain monitoring indicators of the ship's berthing and mooring through the position and posture of the ship, and to perform visual display.

Images