Safety monitoring method, device and equipment for hoisting container based on gantry crane

Abstract

The embodiment of the invention provides a safety monitoring method, device and equipment based on container hoisting of a gantry crane. The method comprises the following steps: acquiring initial point cloud data of a container on a field bridge; wherein the initial point cloud data comprises point cloud data of at least one container; in the initial point cloud data, positioning target point cloud data of each container in the point cloud data; fitting the horizontal edge of the target point cloud data of the container to obtain an edge straight line; and determining whether the hoisting state of the container is abnormal or not according to the edge straight line. The method is used for achieving the effect of accurately identifying whether the hoisting state of the container is abnormal or not.

Description

Technical Field

[0001] This application relates to the field of engineering machinery technology, and in particular to a safety monitoring method, device and equipment based on a yard crane lifting a container. Background Technology

[0002] In a yard crane, containers need to be lifted using spreader equipment. Specifically, while the spreader is lifting the container to the target location, it's necessary to monitor in real time whether the lifting is successful.

[0003] In existing technology, people manually observe whether the container is being lifted normally, and then manually determine whether the lifting status of the container is abnormal.

[0004] However, the manual method mentioned above is inefficient and cannot accurately determine whether the container's lifting status is abnormal. Summary of the Invention

[0005] This application provides a method, apparatus, and equipment for safety monitoring of containers lifted by a yard crane, which can accurately identify whether the lifting status of the container is abnormal.

[0006] In a first aspect, embodiments of this application provide a safety monitoring method based on container lifting by a yard crane, including:

[0007] Acquire initial point cloud data of containers on the yard crane; wherein the initial point cloud data includes point cloud data of at least one container;

[0008] In the initial point cloud data, the target point cloud data of each container in the point cloud data is located;

[0009] The horizontal edges of the target point cloud data of the container are fitted to obtain straight edge lines; and based on the straight edge lines, it is determined whether the lifting status of the container is abnormal.

[0010] In one possible implementation, fitting the horizontal edges of the target point cloud data of the container to obtain straight edge lines includes:

[0011] If the data volume of the target point cloud data of the container is greater than or equal to the preset data volume, then an edge detection algorithm is used to detect the horizontal edge of the target point cloud data of the container.

[0012] The horizontal edge is fitted to obtain a straight edge line.

[0013] In one possible implementation, determining whether the container's lifting status is abnormal based on the edge line includes:

[0014] Determine the angle between the edge line and the horizontal plane;

[0015] If the included angle is determined to be greater than or equal to the preset included angle, then the lifting status of the container is determined to be abnormal, and the container is determined to be at risk of falling.

[0016] In one possible implementation, the method further includes:

[0017] If it is determined that the included angle is less than the preset included angle, then the lifting state of the container is determined to be that the container is lifted at a normal angle.

[0018] In one possible implementation, the method further includes:

[0019] If the amount of target point cloud data of the container is less than the preset amount of data, then the lifting status of the container is determined to be abnormal, and the lifting status of the container is determined to be that the container has not been lifted.

[0020] In one possible implementation, acquiring the initial point cloud data of the containers on the yard crane includes:

[0021] Acquire point cloud data collected by at least one lidar in the field bridge; wherein the at least one lidar is located at a diagonal position of the vehicle in the field bridge;

[0022] The point cloud data collected by the lidar is subjected to coordinate correction to obtain corrected point cloud data;

[0023] Based on a preset origin and a preset region size, the initial point cloud data is determined from the corrected point cloud data.

[0024] In one possible implementation, locating the target point cloud data for each container in the initial point cloud data includes:

[0025] Based on at least one preset centerline, initial point cloud data within a preset range on each side of the preset centerline are determined, which are the target point cloud data for each container.

[0026] Secondly, embodiments of this application provide a safety monitoring device based on a yard crane lifting a container, the device comprising:

[0027] An acquisition module is used to acquire initial point cloud data of containers on a yard crane; wherein the initial point cloud data includes point cloud data of at least one container;

[0028] The positioning module is used to locate the target point cloud data of each container in the initial point cloud data;

[0029] The determination module is used to fit the horizontal edge of the target point cloud data of the container to obtain an edge straight line; and to determine whether the lifting status of the container is abnormal based on the edge straight line.

[0030] In one possible implementation, the determining module includes:

[0031] If the data volume of the target point cloud data of the container is greater than or equal to the preset data volume, then an edge detection algorithm is used to detect the horizontal edge of the target point cloud data of the container.

[0032] The horizontal edge is fitted to obtain a straight edge line.

[0033] In one possible implementation, the determining module includes:

[0034] Determine the angle between the edge line and the horizontal plane;

[0035] If the included angle is determined to be greater than or equal to the preset included angle, then the lifting status of the container is determined to be abnormal, and the container is determined to be at risk of falling.

[0036] In one possible implementation, the device further includes:

[0037] If it is determined that the included angle is less than the preset included angle, then the lifting state of the container is determined to be that the container is lifted at a normal angle.

[0038] In one possible implementation, the device further includes:

[0039] If the amount of target point cloud data of the container is less than the preset amount of data, then the lifting status of the container is determined to be abnormal, and the lifting status of the container is determined to be that the container has not been lifted.

[0040] In one possible implementation, the acquisition module includes:

[0041] Acquire point cloud data collected by at least one lidar in the field bridge; wherein the at least one lidar is located at a diagonal position of the vehicle in the field bridge;

[0042] The point cloud data collected by the lidar is subjected to coordinate correction to obtain corrected point cloud data;

[0043] Based on a preset origin and a preset region size, the initial point cloud data is determined from the corrected point cloud data.

[0044] In one possible implementation, the positioning module includes:

[0045] Based on at least one preset centerline, initial point cloud data within a preset range on each side of the preset centerline are determined, which are the target point cloud data for each container.

[0046] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0047] The memory stores computer-executed instructions;

[0048] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0049] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0050] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0051] This application provides a safety monitoring method, apparatus, and equipment for container lifting based on a yard crane. It acquires initial point cloud data of containers on the yard crane, comprehensively covering the point cloud information of at least one container, providing a rich and accurate data foundation for subsequent analysis. Next, the target point cloud data of each container is precisely located within the initial point cloud data. This step effectively eliminates irrelevant data interference, making subsequent processing more focused and efficient. Subsequently, the horizontal edges of the target point cloud data of the containers are fitted to obtain straight edge lines. This fitting process utilizes advanced algorithms to accurately capture the geometric features of the container edges. Finally, based on the edge lines, it is determined whether the container's lifting status is abnormal. Analysis of the edge lines allows for timely detection of potential tilting, offset, or other abnormalities that may occur during container lifting. This series of technical means works in tandem and progressively addresses the technical problems of inaccurate monitoring and low efficiency in traditional monitoring methods. It achieves real-time and accurate monitoring of the container lifting status by the yard crane, thereby ensuring operational safety, preventing safety accidents caused by abnormal container lifting, improving operational efficiency, and reducing operating costs. Attached Figure Description

[0052] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0053] Figure 1 A flowchart illustrating a safety monitoring method for container lifting based on a yard crane, provided in this application embodiment. Figure 1 ;

[0054] Figure 2 A flowchart illustrating a safety monitoring method for container lifting based on a yard crane, provided in this application embodiment. Figure 2 ;

[0055] Figure 3 A schematic diagram of a container linear fitting provided in an embodiment of this application;

[0056] Figure 4 A schematic diagram of the structure of a safety monitoring device based on a yard crane lifting a container, provided in this application embodiment. Figure 1 ;

[0057] Figure 5 A schematic diagram of the structure of a safety monitoring device for container lifting by a yard crane, provided in this application embodiment. Figure 2 ;

[0058] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0059] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0060] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0061] In yard crane operations, spreader arms play a crucial role in lifting containers, transporting them to their target locations. During this process, real-time monitoring of container lifting is essential. Current technology relies primarily on manual methods, where workers visually inspect the container to determine if it's being lifted correctly and to identify any abnormalities. However, this manual method has significant drawbacks. Firstly, it's extremely inefficient, failing to meet the demands of high-efficiency yard crane operations. Secondly, human judgment is highly subjective, making it difficult to accurately determine whether the container's lifting status is truly abnormal.

[0062] Therefore, this application provides a safety monitoring method based on a yard crane lifting a container, which can solve the above problems.

[0063] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0064] Figure 1 A flowchart illustrating a safety monitoring method for container lifting based on a yard crane, provided in this application embodiment. Figure 1 ,like Figure 1 As shown, the method includes:

[0065] S101. Obtain the initial point cloud data of the containers on the yard crane; wherein the initial point cloud data includes the point cloud data of at least one container.

[0066] For example, a yard crane, also known as a yard crane, is an important piece of equipment used in container terminals for loading and unloading containers. It can move on specific tracks to move containers between different locations.

[0067] The initial point cloud data is a collection of a large number of discrete points obtained by scanning the lifted container using 3D scanning equipment such as LiDAR and depth cameras. These points have specific coordinate information in three-dimensional space and together constitute the three-dimensional model of the container, which can accurately describe the container's shape, size, position and other characteristics.

[0068] A suitable location needs to be selected for the installation of the 3D laser scanning equipment. Typically, the lidar is installed in a suitable position on the crane, such as under a crossbeam or under a trolley, ensuring that its scanning range covers the lifted containers. Lidar utilizes the principle of laser pulse ranging. It emits a laser beam towards the target object, measures the time it takes for the beam to travel from emission to reflection back to the receiver, and calculates the distance to the target object by combining this with the speed of light. Simultaneously, by combining this information with the lidar's own angle encoder, the coordinates of each measurement point in 3D space can be determined.

[0069] This technology has the advantages of high precision, high speed and non-contact measurement, which can quickly and accurately acquire surface point cloud data of containers without causing any damage to the containers, providing a reliable data foundation for subsequent container processing.

[0070] S102. In the initial point cloud data, locate the target point cloud data of each container in the point cloud data.

[0071] For example, target point cloud data refers to a set of point clouds separated from the initial point cloud data that specifically corresponds to each individual container. It can accurately describe the shape, size, and location of the container, providing accurate data support for subsequent operations on individual containers.

[0072] For example, the initial point cloud data is denoised to remove noise points caused by factors such as equipment errors and environmental interference, thereby improving data quality. Common denoising methods include statistical filtering and radius filtering. Statistical filtering calculates the statistical characteristics of points in the neighborhood of each point, such as the average distance, and removes points that deviate significantly from the statistical characteristics as noise points. Radius filtering sets a radius threshold; if the number of neighboring points within a certain radius of a point is less than the set value, the point is removed as a noise point.

[0073] Feature information that helps distinguish different containers is extracted from the preprocessed point cloud data, such as the normal vector and curvature of the points. The normal vector of a point reflects the orientation of the surface on which the point is located, and the distribution of normal vectors on the surfaces of different containers has different characteristics; the curvature describes the degree of curvature of the surface on which the point is located, and the edges and corners of containers usually have larger curvature values.

[0074] In the initial point cloud data, the target point cloud data of each container in the point cloud data is located.

[0075] S103. Fit the horizontal edges of the target point cloud data of the container to obtain edge lines; and determine whether the lifting status of the container is abnormal based on the edge lines.

[0076] For example, point cloud data representing the horizontal edges is extracted from the target point cloud data of a container. Horizontal edge points can be filtered by setting appropriate normal vector ranges and curvature thresholds. Since the normal vectors of points at the horizontal edges of a container are typically close to the horizontal direction and have relatively small curvature, these characteristics can be used to separate horizontal edge points from the target point cloud. For instance, by setting conditions such as the vertical component of the normal vector being between -0.1 and 0.1 (assuming the vertically upward direction is positive) and curvature being less than 0.05, points that meet these conditions are extracted as horizontal edge point cloud data.

[0077] For example, the extracted horizontal edge point cloud data is preprocessed to remove noise points and outliers. A distance-based outlier removal method can be used, where a distance threshold is set, and for each point, the average distance to its surrounding neighbors is calculated. If the average distance is greater than the set threshold, the point is considered an outlier and removed. Alternatively, the point cloud data can be downsampled to reduce the amount of data and improve the efficiency of subsequent fitting processes. Downsampling can employ methods such as random sampling or voxel grid filtering to uniformly distribute the point cloud data in three-dimensional space, retaining only one point within each voxel grid.

[0078] For example, the least squares method is used to fit a straight line to the preprocessed horizontal edge point cloud data. Let the equation of the fitted line be y = kx + b, where k is the slope and b is the intercept. This is achieved by minimizing the sum of the squares of the perpendicular distances from all points to the line. (in, Let k be the coordinates of a point in the point cloud data, and n be the number of points. Taking the partial derivatives of k and b with respect to k and setting them to 0, we obtain a system of equations about k and b. Solving this system of equations yields the parameters k and b for the fitted line. For horizontal edge point clouds in 3D space, if the edge is roughly in a plane, we can first project the point cloud onto a 2D plane (such as a plane perpendicular to the approximate direction of the edge) and then perform 2D line fitting. If the edge has a certain curvature in 3D space, we can consider using a piecewise fitting method, dividing the edge into multiple small segments and performing line fitting on each segment separately.

[0079] Based on the fitted edge line parameters, it is determined whether the container's lifting status is abnormal. This can be done by comparing parameters such as the slope and position of the edge lines with theoretical values ​​under normal conditions. For example, for the horizontal edge lines on the side of the container, under normal lifting conditions, their slope should be close to 0 (i.e., vertical). If the absolute value of the slope of the fitted line is greater than a set threshold (e.g., 0.1), it may indicate that the container is tilted. For the horizontal edge lines at the top and bottom of the container, the distance between them can be compared with the standard height of the container to determine whether there are abnormalities such as compression or tensile deformation. If the parameters of the edge lines are found to be outside the normal range, the container's lifting status is determined to be abnormal, and an alarm is issued promptly.

[0080] This application provides a safety monitoring method for container lifting based on a yard crane. It acquires initial point cloud data of containers on the yard crane, comprehensively covering the point cloud information of at least one container, providing a rich and accurate data foundation for subsequent analysis. Next, the target point cloud data of each container is precisely located within the initial point cloud data. This step effectively eliminates irrelevant data interference, making subsequent processing more focused and efficient. Subsequently, the horizontal edges of the target point cloud data of the containers are fitted to obtain straight lines. This fitting process utilizes advanced algorithms to accurately capture the geometric features of the container edges. Finally, based on the straight lines, it is determined whether the container's lifting status is abnormal. Analysis of the straight lines allows for timely detection of potential tilting, offset, or other abnormalities that may occur during container lifting. This series of techniques works in tandem, effectively solving the technical problems of inaccurate monitoring and low efficiency in traditional monitoring methods. It achieves real-time and accurate monitoring of the container lifting status by the yard crane, thereby ensuring operational safety, preventing safety accidents caused by abnormal container lifting, improving operational efficiency, and reducing operating costs.

[0081] Figure 2 A flowchart illustrating a safety monitoring method for container lifting based on a yard crane, provided in this application embodiment. Figure 2 ,like Figure 2 As shown, the method includes:

[0082] S201. Obtain point cloud data collected by at least one lidar in the field bridge; wherein, at least one lidar is located at the diagonal position of the vehicle in the field bridge; perform coordinate correction on the point cloud data collected by the lidar to obtain corrected point cloud data; determine the initial point cloud data from the corrected point cloud data based on the preset origin and preset area size.

[0083] For example, at least one lidar can be a single lidar or multiple lidars. Placing the lidars diagonally across the trolley is because the relative positions of different parts of the trolley to surrounding objects are complex when it moves and operates within the yard. The diagonal position allows the lidar's scanning range to cover a wider and more critical spatial area around the trolley, thereby acquiring more comprehensive information about the surrounding environment and providing richer data support for subsequent operation control and safety monitoring.

[0084] Coordinate correction is necessary because installation errors during the actual installation of LiDAR, or factors such as vibrations during the operation of the field bridge, can cause deviations between the coordinates of the collected point cloud data and the actual scene coordinates. By using known reference points or specific algorithm models, coordinate transformation and adjustment are performed on the original point cloud data. This allows the corrected point cloud data to more accurately reflect the position and shape of objects in the actual scene, improving the accuracy and reliability of the data and providing a solid foundation for subsequent analysis and processing based on this data.

[0085] First, a reference coordinate system for correction is determined. This reference coordinate system can be the fixed coordinate system of the field bridge or a pre-defined global coordinate system. Then, the raw point cloud data collected by the lidar is collected, and the installation position and attitude information of the lidar in the reference coordinate system are recorded. Next, using this information, coordinate transformation algorithms, such as rotation matrices and translation vectors, are used to transform the coordinates of each point in the raw point cloud data from the lidar's own coordinate system to the reference coordinate system, thereby obtaining the corrected point cloud data. For example, assuming there is a transformation relationship between the lidar's own coordinate system and the reference coordinate system, involving a rotation angle θ around the Z-axis and a translation dx along the X-axis and a translation dy along the Y-axis, then for any point P(x1,y1,z1) in the raw point cloud data, the new coordinates P'(x2,y2,z2) obtained after correction can be calculated using the following formulas: x2=x1×cosθ-y1×sinθ+dx; y2=x1×sinθ+y1×cosθ+dy; z2=z1.

[0086] The preset origin is a manually set reference point that serves as the starting point for defining the spatial range of the point cloud data to be extracted. The preset region size specifies the spatial dimensions of the region to be extracted from the corrected point cloud data; for example, it can be a cuboid region whose length, width, and height are determined by preset length, width, and height values, respectively. By setting the preset origin and preset region size, point cloud data from specific regions can be extracted from a large amount of corrected point cloud data as initial point cloud data, reducing the amount of data processing, improving processing efficiency, and meeting the analysis needs of specific regions of data in different application scenarios.

[0087] First, determine the coordinate position of the preset origin in the reference coordinate system according to the actual application requirements. For example, a specific point on a certain fixed structure of the quay crane is used as the origin. Then, determine the size of the preset area. For example, a cuboid area with a length of 5 meters, a width of 3 meters, and a height of 2 meters is set. Next, traverse each point in the corrected point cloud data and calculate the distance between this point and the preset origin in the three coordinate axis directions. Finally, determine whether these distances are respectively less than the sizes of the preset area in the corresponding coordinate axis directions. If the conditions are met, this point belongs to the initial point cloud data; otherwise, it is not included. For example, for a point Q(xq, yq, zq) in the corrected point cloud data, the preset origin is O(x0, y0, z0), the length of the preset area is L, the width is W, and the height is H. If |xq - x0| < L / 2 and |yq - y0| < W / 2 and |zq - z0| < H / 2, then point Q belongs to the initial point cloud data.

[0088] S202. Based on at least one preset center line, determine the initial point cloud data within the preset range on each side of the preset center line as the target point cloud data for each container.

[0089] Exemplarily, according to the container layout plan in the quay crane operation area, use measuring tools (such as laser rangefinders, total stations, etc.) or based on a pre-established three-dimensional model of the quay crane to determine the center line position of the container stacking area and record it in the coordinate system of the quay crane. These center lines can be straight lines parallel to the length direction of the container or straight lines parallel to the width direction, specifically depending on the subsequent data processing and analysis requirements.

[0090] According to the standard dimensions of the container (such as length, width, height) and the error range in actual applications, determine the preset range around both sides of the preset center line. For example, for a standard 20-foot container with a length of about 6 meters and a width of about 2.4 meters, considering the installation error and the acquisition accuracy of the point cloud data, it can be set that each side extends 0.5 meters along the length direction and 0.3 meters along the width direction as the preset range.

[0091] Traverse each point in the initial point cloud data and calculate the distance from this point to the preset center line. For the preset center line parallel to the length direction of the container, calculate the perpendicular distance from the point to the line; for the preset center line parallel to the width direction of the container, also calculate the perpendicular distance from the point to the line. Then, determine whether this distance is within the preset range. If it is within the preset range, classify this point as the target point cloud data of the corresponding container; if it is not within the preset range, exclude this point. In this way, the initial point cloud data is screened according to the preset center line and the preset range to obtain the target point cloud data of each container.

[0092] In one possible implementation, if the yard crane operation is a double-container operation (meaning lifting two containers), the initial point cloud data of the containers is obtained; and the left and right containers are determined based on a preset centerline.

[0093] In one possible implementation, if the yard crane operation is a three-container operation (referring to lifting three containers), the initial point cloud data of the containers is obtained; and based on two preset centerlines, the left container, the middle container and the right container are determined.

[0094] S203. If the amount of target point cloud data of the container is greater than or equal to the preset amount of data, then the edge detection algorithm is used to detect the horizontal edge of the target point cloud data of the container; the horizontal edge is fitted to obtain the edge straight line.

[0095] For example, the amount of target point cloud data for the current container is counted and compared with a preset amount of data. If the amount of target point cloud data is less than the preset amount of data, it means that the collected data is insufficient to accurately reflect the surface features of the container. In this case, no further edge detection and fitting processing is performed, and it may be necessary to re-collect point cloud data or take other supplementary measures. If the amount of target point cloud data is greater than or equal to the preset amount of data, proceed to the next step.

[0096] A suitable edge detection algorithm is selected to process the target point cloud data of the container. Taking the edge detection algorithm based on normal vector change as an example, for each point in the point cloud, its normal vector is calculated, and then the change of the normal vector between that point and its neighboring points is analyzed. If the change of the normal vector exceeds a certain threshold, the point is considered to be on an edge. By traversing the entire point cloud data, all edge points that meet the conditions are found, thus obtaining the set of horizontal edge points of the container.

[0097] Since edge detection may yield edge points that include vertical edges and those in other directions, it's necessary to filter these points, retaining only horizontal edge points. This filtering can be done by analyzing the normal vector direction or coordinate information of the edge points. For example, for horizontal edge points, the vertical component of their normal vector should be close to 0. Alternatively, based on the coordinate system of the point cloud data, edge points distributed horizontally within a specific height range can be selected as horizontal edge points.

[0098] The selected horizontal edge points are fitted with a straight line using the least squares method. The principle of the least squares method is to find the best function match for the data by minimizing the sum of squared errors. Specifically, let the coordinates of the horizontal edge points be (xi, yi), i = 1, 2, ..., n, and the equation of the line to be fitted be y = kx + b. According to the least squares method, we need to find the values ​​of k and b that minimize Σ(yi - (kxi + b))². By solving the system of equations, we can obtain the specific values ​​of k and b, thus obtaining the fitted edge line equation.

[0099] Figure 3 This is a schematic diagram of a container linear fitting provided in an embodiment of this application, as shown below. Figure 3 As shown in the figure, the red straight line represents the fitted edge line of the container.

[0100] S204. Determine the angle between the edge line and the horizontal plane; if the angle is greater than or equal to the preset angle, then the container's lifting status is determined to be abnormal, and the container is determined to be at risk of falling.

[0101] For example, the fitted equation of the container edge line is obtained from the previous steps. This equation is usually expressed in the general form Ax + By + C = 0 (in three-dimensional space, the influence of the z-coordinate may need to be considered, but if it is a horizontal edge line and the horizontal plane is used as a reference, it can be simplified to a two-dimensional plane problem). At the same time, the equation of the horizontal plane is determined. When the earth's horizontal plane is used as a reference, the equation of the horizontal plane can be set as z = 0 (assuming that the z-axis is perpendicular to the horizontal plane and upwards).

[0102] For the line Ax + By + C = 0 in a two-dimensional plane, its slope k = -A / B (B ≠ 0). Let the slope of the edge line be k1. The horizontal plane in the two-dimensional plane can be considered as a line with a slope of 0 (y = constant). According to the formula for the angle between two lines, tanθ = |(k1-k2) / (1+k1k2)| (where k2 is the slope of the horizontal plane of 0), we can obtain tanθ = |k1|. Then, we can calculate the angle θ between the edge line and the horizontal plane (the angle range is 0° to 90°) using the arctangent function θ = arctan(|k1|). If it is in three-dimensional space, we need to first project the edge line onto a plane perpendicular to the horizontal plane, and then calculate the angle according to the two-dimensional plane method, or use the vector method. Let the direction vector of the edge line be v1=(x1,y1,z1), and the normal vector of the horizontal plane be v2=(0,0,1). According to the formula for the angle between vectors, cosθ=(v1·v2) / (|v1|×|v2|), and then calculate the angle θ using the inverse cosine function θ=arccos((v1·v2) / (|v1|×|v2|)).

[0103] The calculated included angle θ is compared with the preset included angle α.

[0104] When θ ≥ α, the lifting status of the container is determined to be abnormal, and based on this abnormal status, it is judged that the container is at risk of falling. At this time, the system can trigger the corresponding safety warning mechanism, such as issuing alarm signals to the operators, recording abnormal event information, and stopping the relevant operations of the yard crane, so that the operators can take timely measures to deal with the situation.

[0105] S205. If it is determined that the included angle is less than the preset included angle, then the lifting state of the container is determined to be that the container is lifted at a normal angle.

[0106] For example, in the preceding steps, the angle between the container edge line and the horizontal plane has been calculated using a specific algorithm (such as the two-dimensional plane line slope method or the three-dimensional space vector method), and the angle value is stored in the corresponding variable of the system for later use.

[0107] If it is determined that the angle between the straight line of the container's edge and the horizontal plane is less than a preset angle, a flag is set in the system or corresponding status information is output, indicating that the container is being lifted at a normal angle. This flag or status information can be used by subsequent work processes or other related modules to determine whether to continue normal operations. For example, if the flag is true (indicating normal lifting), the yard crane can continue to lift the container to the specified height or move it to the target position; if the flag is false (indicating abnormal lifting), the corresponding abnormal handling mechanism is triggered.

[0108] S206. If the amount of target point cloud data of the container is less than the preset amount of data, then the lifting status of the container is determined to be abnormal, and the lifting status of the container is determined to be that the container has not been lifted.

[0109] For example, the amount of target point cloud data for the current container is counted and compared with a preset amount of data. If the amount of target point cloud data is less than the preset amount of data, the container's lifting status is determined to be abnormal, and the container's lifting status is determined to be that the container has not been lifted.

[0110] This application provides a safety monitoring method for container lifting based on a yard crane. It acquires point cloud data from at least one lidar located diagonally opposite the trolley in the yard crane, a layout that can capture container information from all directions. The acquired point cloud data is then subjected to coordinate correction to eliminate data deviations and obtain accurate corrected data. Initial point cloud data is then determined from the corrected data based on a preset origin and region size. Subsequently, based on at least one preset centerline, the initial point cloud data within a preset range on each side is divided as the target point cloud data for the container. If the target point cloud data volume is greater than or equal to a preset data volume, an edge detection algorithm is used to find the horizontal edge, and a straight line is fitted. By determining the angle between the straight line and the horizontal plane, if the angle is greater than or equal to a preset value, the container lifting is determined to be abnormal and at risk of falling; if it is less than the preset value, it is determined to be a normal lifting. If the target point cloud data volume is less than the preset data volume, the container lifting is directly determined to be abnormal and not lifted. This series of steps is interconnected. From data collection to final status determination, each step provides support for accurately judging the container lifting status, effectively solving the problems of incomplete and inaccurate monitoring by traditional methods. It realizes real-time and accurate monitoring of container lifting status and ensures the safety of yard crane operations.

[0111] Figure 4 A schematic diagram of the structure of a safety monitoring device for container lifting by a yard crane, provided in this application embodiment. Figure 1 ,like Figure 4 As shown, the safety monitoring device 40 based on a yard crane lifting a container provided in this embodiment includes:

[0112] The acquisition module 401 is used to acquire the initial point cloud data of the containers on the yard crane; wherein the initial point cloud data includes the point cloud data of at least one container;

[0113] The positioning module 402 is used to locate the target point cloud data of each container in the initial point cloud data;

[0114] The determination module 403 is used to fit the horizontal edge of the target point cloud data of the container to obtain the edge line; and based on the edge line, to determine whether the lifting status of the container is abnormal.

[0115] This embodiment provides a safety monitoring device based on a yard crane lifting a container, which can execute the method provided in the above-described method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0116] Figure 5 A schematic diagram of the structure of a safety monitoring device for container lifting by a yard crane, provided in this application embodiment. Figure 2 ,like Figure 5As shown, the safety monitoring device 50 based on a yard crane lifting a container provided in this embodiment includes:

[0117] The acquisition module 501 is used to acquire the initial point cloud data of the containers on the yard crane; wherein the initial point cloud data includes the point cloud data of at least one container;

[0118] The positioning module 502 is used to locate the target point cloud data of each container in the initial point cloud data;

[0119] The determination module 503 is used to fit the horizontal edge of the target point cloud data of the container to obtain the edge line; and based on the edge line, to determine whether the lifting status of the container is abnormal.

[0120] In one possible implementation, the determining module 503 includes:

[0121] If the data volume of the target point cloud data of the container is greater than or equal to the preset data volume, then the edge detection algorithm is used to detect the horizontal edge of the target point cloud data of the container.

[0122] The horizontal edges are fitted to obtain straight lines.

[0123] In one possible implementation, the determining module 503 includes:

[0124] Determine the angle between the edge line and the horizontal plane;

[0125] If the included angle is determined to be greater than or equal to the preset included angle, then the container's lifting status is determined to be abnormal, and the container is determined to be at risk of falling.

[0126] In one possible implementation, the device 50 further includes:

[0127] If the included angle is determined to be less than the preset included angle, then the container is determined to be lifted at a normal angle.

[0128] In one possible implementation, the device 50 further includes:

[0129] If the amount of target point cloud data for the container is less than the preset amount, the container's lifting status is determined to be abnormal, and the container's lifting status is determined to be that the container has not been lifted.

[0130] In one possible implementation, the acquisition module 501 includes:

[0131] Acquire point cloud data collected by at least one lidar in the field bridge; wherein at least one lidar is located at a diagonal position of the vehicle in the field bridge;

[0132] The point cloud data collected by the lidar is subjected to coordinate correction to obtain the corrected point cloud data;

[0133] Based on the preset origin and preset region size, the initial point cloud data is determined from the corrected point cloud data.

[0134] In one possible implementation, the positioning module 502 includes:

[0135] Based on at least one preset centerline, the initial point cloud data within a preset range on each side of the preset centerline is determined, which is the target point cloud data for each container.

[0136] This embodiment provides a safety monitoring device based on a yard crane lifting a container, which can execute the method provided in the above-described method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0137] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 6 As shown, the electronic device 60 provided in this embodiment includes at least one processor 601 and a memory 602. Optionally, the device 60 further includes a communication component 603. The processor 601, memory 602, and communication component 603 are connected via a bus 604.

[0138] In a specific implementation, at least one processor 601 executes computer execution instructions stored in memory 602, causing at least one processor 601 to perform the above-described method.

[0139] The specific implementation process of processor 601 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0140] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0141] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0142] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0143] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0144] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0145] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0146] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0147] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0148] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0149] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0150] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0151] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0152] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A safety monitoring method based on container lifting by a yard crane, characterized in that, The method includes: Acquire initial point cloud data of containers on the yard crane; wherein the initial point cloud data includes point cloud data of at least one container; In the initial point cloud data, the target point cloud data of each container in the point cloud data is located; The horizontal edges of the target point cloud data of the container are fitted to obtain straight edge lines; and based on the straight edge lines, it is determined whether the lifting status of the container is abnormal.

2. The method according to claim 1, characterized in that, The horizontal edges of the target point cloud data of the container are fitted to obtain straight edge lines, including: If the data volume of the target point cloud data of the container is greater than or equal to the preset data volume, then an edge detection algorithm is used to detect the horizontal edge of the target point cloud data of the container. The horizontal edge is fitted to obtain a straight edge line.

3. The method according to claim 1, characterized in that, Based on the straight edge line, determine whether the lifting status of the container is abnormal, including: Determine the angle between the edge line and the horizontal plane; If the included angle is determined to be greater than or equal to the preset included angle, then the lifting status of the container is determined to be abnormal, and the container is determined to be at risk of falling.

4. The method according to claim 3, characterized in that, The method further includes: If it is determined that the included angle is less than the preset included angle, then the lifting state of the container is determined to be that the container is lifted at a normal angle.

5. The method according to claim 1, characterized in that, The method further includes: If the amount of target point cloud data of the container is less than the preset amount of data, then the lifting status of the container is determined to be abnormal, and the lifting status of the container is determined to be that the container has not been lifted.

6. The method according to any one of claims 1-5, characterized in that, The acquisition of initial point cloud data of containers on the yard crane includes: Acquire point cloud data collected by at least one lidar in the field bridge; wherein the at least one lidar is located at a diagonal position of the vehicle in the field bridge; The point cloud data collected by the lidar is subjected to coordinate correction to obtain corrected point cloud data; Based on a preset origin and a preset region size, the initial point cloud data is determined from the corrected point cloud data.

7. The method according to any one of claims 1-5, characterized in that, In the initial point cloud data, the target point cloud data for each container in the point cloud data is located, including: Based on at least one preset centerline, initial point cloud data within a preset range on each side of the preset centerline are determined, which are the target point cloud data for each container.

8. A safety monitoring device based on container lifting by a yard crane, characterized in that, The method includes: An acquisition module is used to acquire initial point cloud data of containers on a yard crane; wherein the initial point cloud data includes point cloud data of at least one container; The positioning module is used to locate the target point cloud data of each container in the initial point cloud data; The determination module is used to fit the horizontal edge of the target point cloud data of the container to obtain an edge straight line; and to determine whether the lifting status of the container is abnormal based on the edge straight line.

9. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-7.

Images