Container rotating method, device and equipment applied to container door machine and medium

Abstract

The embodiment of the invention provides a container rotating method, device and equipment applied to a container door machine and a medium. The invention relates to the field of container door machines, and discloses a container door machine lifting method which comprises the steps that in response to a container rotating request of a user side, a lifting tool on a container door machine is lifted; if it is determined that the lifting height of the lifting appliance on the container door machine meets the rotating condition, the rotating area of the container is determined; scanning the rotating area of the container according to a scanning instrument to obtain a scanning result; if the scanning result shows that the obstacle exists, a lifting appliance on the container door machine is lifted according to the scanning result until the rotating area of the container does not have the obstacle; and if the scanning result shows that no obstacle exists, the container is rotated. The method is used for achieving the technical effect of improving the efficiency of rotating the container.

Description

Technical Field

[0001] This application relates to the field of container door machines, and more particularly to a container rotation method, apparatus, equipment and medium applied to container door machines. Background Technology

[0002] In port container handling operations, the container door crane (also known as a fixed crane) is one of the core pieces of equipment. Its main function is to control the rotation of containers to adjust the orientation of the container doors to match the loading and unloading needs of the trucks. The container doors usually need to be aligned with the cargo box of the truck to achieve efficient loading and unloading.

[0003] Traditional container door cranes typically require the container to be raised to a preset safe height before rotating the door to ensure that it does not collide with trucks or surrounding equipment during the rotation.

[0004] However, in actual operation, the container may have already met the conditions for rotation before it reaches the preset safe height. Therefore, the existing technology has the technical problem of low efficiency in controlling the rotation of the container. Summary of the Invention

[0005] This application provides a container rotation method, apparatus, equipment, and medium applied to a container door crane, in order to achieve the technical effect of improving the efficiency of rotating containers.

[0006] In a first aspect, embodiments of this application provide a container rotation method applied to a container door crane, comprising:

[0007] In response to a container rotation request from the user, the spreader on the container door operator is raised; the spreader on the container door operator is connected to the container.

[0008] If it is determined that the lifting height of the spreader on the container door crane meets the rotation conditions, then the rotation area of ​​the container is determined.

[0009] The rotating area of ​​the container is scanned using a scanning instrument to obtain the scan results;

[0010] If the scan results show that there is an obstacle, the spreader on the container door operator will be raised according to the scan results until there is no obstacle in the rotation area of ​​the container; if the scan results show that there is no obstacle, the container will be rotated.

[0011] In one possible implementation, if it is determined that the height to which the spreader on the container door operator rises satisfies the rotation condition, then the rotation zone of the container is determined, including:

[0012] Raise the spreader on the container door operator until the height of the container is higher than the height of the truck bed;

[0013] Obtain the container's dimensions and determine the container's rotation radius based on those dimensions.

[0014] Based on the container's surface, obtain the coordinates of the container's rotation center point;

[0015] Obtain the location information of the container, and determine the location range of the container based on the location information;

[0016] The rotation area of ​​the container is obtained based on the radius of its rotation range, the coordinates of its rotation center point, and its position range.

[0017] In one possible implementation, the rotation area of ​​the container is obtained based on the container's rotation radius, the coordinates of the container's rotation center point, and the container's position range, including:

[0018] The first rotation area is determined based on the rotation radius of the container and the coordinates of the rotation center point of the container; wherein, the first rotation area is used to characterize the rotation area with respect to the rotation radius of the container.

[0019] Based on the first rotation region, the area is expanded by a preset amount to obtain the second rotation region;

[0020] Based on the location range of the container, the container-occupied area is obtained; the container-occupied area is used to characterize the area occupied by the container in the second rotation area before rotation.

[0021] Subtract the container's occupied area from the second rotation area to obtain the container's rotation area.

[0022] In one possible implementation, a high-definition camera is mounted on the hanger of the door operator, and after the scan results indicate the presence of an obstacle, the following is included:

[0023] Images of obstacles are obtained using a high-definition camera;

[0024] Input the image and scan results of the obstacle into a pre-trained prediction model to obtain the predicted type of the obstacle;

[0025] Based on the mapping relationship, the predicted height corresponding to the predicted type of obstacle is determined; where the mapping relationship is the correspondence between the predicted type and the predicted height.

[0026] Based on the predicted height, the spreader on the container door crane is raised until there are no obstructions in the container's rotation area.

[0027] In one possible implementation, the hanger on the gate operator is equipped with two single-line laser scanners, and a three-dimensional laser scanner is located beside the lane where the gate operator is situated, including:

[0028] The rotating area of ​​the container is scanned using a single-line laser scanner and a 3D laser scanner to obtain point cloud data of the rotating area.

[0029] Data analysis is performed on the point cloud data to obtain the scanning results.

[0030] In one possible implementation, data analysis is performed on the point cloud data to obtain scanning results, including:

[0031] Density calculation and contour detection are performed on point cloud data to identify suspected obstacles in the point cloud data;

[0032] Based on statistical filtering and radius filtering methods, determine whether a suspected obstacle is a real obstacle;

[0033] If yes, the scan result indicates the presence of an obstacle; otherwise, the scan result indicates the absence of an obstacle.

[0034] Secondly, embodiments of this application provide a container rotating device applied to a container door crane, comprising:

[0035] The control module is used to raise the spreader on the container door operator in response to the container rotation request from the user terminal; wherein the spreader on the container door operator is connected to the container;

[0036] The acquisition module is used to determine the rotation area of ​​the container if it is determined that the height of the spreader on the container door crane meets the rotation conditions.

[0037] The scanning module is used to scan the rotating area of ​​the container using a scanning instrument to obtain the scanning results;

[0038] The processing module is used to raise the spreader on the container door operator according to the scan results if the scan results show that there are obstacles, until there are no obstacles in the rotation area of ​​the container; if the scan results show that there are no obstacles, the container is rotated.

[0039] In one possible implementation, the acquisition module is further configured to:

[0040] Raise the spreader on the container door operator until the height of the container is higher than the height of the truck bed;

[0041] Obtain the container's dimensions and determine the container's rotation radius based on those dimensions.

[0042] Based on the container's surface, obtain the coordinates of the container's rotation center point;

[0043] Obtain the location information of the container, and determine the location range of the container based on the location information;

[0044] The rotation area of ​​the container is obtained based on the radius of its rotation range, the coordinates of its rotation center point, and its position range.

[0045] In one possible implementation, the acquisition module is further configured to:

[0046] The first rotation area is determined based on the rotation radius of the container and the coordinates of the rotation center point of the container; wherein, the first rotation area is used to characterize the rotation area with respect to the rotation radius of the container.

[0047] Based on the first rotation region, the area is expanded by a preset amount to obtain the second rotation region;

[0048] Based on the location range of the container, the container-occupied area is obtained; the container-occupied area is used to characterize the area occupied by the container in the second rotation area before rotation.

[0049] Subtract the container's occupied area from the second rotation area to obtain the container's rotation area.

[0050] In one possible implementation, the processing module is further configured to:

[0051] Images of obstacles are obtained using a high-definition camera;

[0052] Input the image and scan results of the obstacle into a pre-trained prediction model to obtain the predicted type of the obstacle;

[0053] Based on the mapping relationship, the predicted height corresponding to the predicted type of obstacle is determined; where the mapping relationship is the correspondence between the predicted type and the predicted height.

[0054] Based on the predicted height, the spreader on the container door crane is raised until there are no obstructions in the container's rotation area.

[0055] In one possible implementation, the scanning module is also used for:

[0056] The rotating area of ​​the container is scanned using a single-line laser scanner and a 3D laser scanner to obtain point cloud data of the rotating area.

[0057] Data analysis is performed on the point cloud data to obtain the scanning results.

[0058] In one possible implementation, the scanning module is also used for:

[0059] Density calculation and contour detection are performed on point cloud data to identify suspected obstacles in the point cloud data;

[0060] Based on statistical filtering and radius filtering methods, determine whether a suspected obstacle is a real obstacle;

[0061] If yes, the scan result indicates the presence of an obstacle; otherwise, the scan result indicates the absence of an obstacle.

[0062] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0063] The memory stores computer-executed instructions;

[0064] 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.

[0065] 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.

[0066] 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.

[0067] The container rotation method, apparatus, equipment, and medium applied to container door cranes provided in this application, upon receiving a container rotation request from the user, first drives the container door crane spreader connected to the container to rise upwards. When the spreader reaches a height sufficient to safely execute the rotation action, the rotation area through which the container will rotate is defined, and a scanning instrument is immediately invoked to perform real-time detection of this area to obtain the scan results. If the scan results show that there are obstacles in the rotation area, the spreader is instructed to continue rising until the rotation area is completely free of obstacles; conversely, if the scan confirms that there are no obstacles in the area, the container rotation operation is immediately executed. By organically combining spreader raising, rotation area definition, real-time scanning, and safety decision-making, a dynamic, closed-loop safety control mechanism is constructed, which can intelligently identify and proactively avoid potential collision risks during rotation, while saving the container door crane's operating time. Attached Figure Description

[0068] 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.

[0069] Figure 1 The flowchart of the container rotation method applied to the container door crane provided in this application is shown below. Figure 1 ;

[0070] Figure 2 The flowchart of the container rotation method applied to the container door crane provided in this application is shown below. Figure 2 ;

[0071] Figure 3 A schematic diagram of the rotating area of ​​a container used in a container door crane, as provided in this application;

[0072] Figure 4 A schematic diagram showing that there are no obstacles in the rotating area of ​​the container used in the container door crane provided in this application;

[0073] Figure 5 A schematic diagram showing the presence of obstacles in the rotating area of ​​a container used in a container door crane, as provided in this application;

[0074] Figure 6 A schematic diagram of the container rotating device applied to a container door crane provided in this application;

[0075] Figure 7 This is a hardware schematic diagram of a container rotating device applied to a container door crane, as provided in this application.

[0076] 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

[0077] 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 methods and approaches consistent with some aspects of this application as detailed in the appended claims.

[0078] Container door cranes typically rely on a "fixed height lifting + mechanical rotation" mode for container door operation. The specific process is as follows: The container door crane lifts the container to a preset safe height to ensure that it will not collide with the truck or surrounding obstacles when rotating the door; with the container in a high position, the door is adjusted to the target orientation using the rotating mechanism of the spreader; after rotation, the container door crane needs to lower the container back into the truck's cargo box. If the lowering height is not properly controlled, it may cause equipment damage or operation interruption due to collision with the truck's front bumper or hydraulic rod.

[0079] As described above, existing technologies consume significant time during the fixed-height lifting and lowering processes, and cannot dynamically adjust for safety hazards based on the actual working environment. The lowering phase is prone to collisions due to height errors or undetected obstacles. Furthermore, relying on preset rules and a fixed safety height prevents dynamic obstacle detection using existing sensors, leading to resource waste.

[0080] The container rotation method, apparatus, equipment, and medium provided in this application, applied to a container door crane, responds to a container rotation request from a user. First, it drives the container door crane spreader connected to the container to rise. Once the spreader is raised to a level suitable for safe rotation, it clearly defines the rotation area traversed by the container and then activates a scanning device to perform real-time detection of that area to obtain scan results. If the scan indicates the presence of an obstacle within the rotation area, it instructs the container door crane spreader to continue rising until the rotation area is completely free from the obstacle's influence. If the scan confirms there are no obstacles within the area, the container rotation is immediately executed.

[0081] The method provided in this application aims to shorten the overall operation cycle by reducing the safety height required for the door rotation and reducing the lifting and lowering time of the lifting device. While reducing the rotation height, obstacles on the rotation path are dynamically detected to avoid equipment damage or safety accidents caused by collisions. By dynamically adjusting the door adjustment strategy, the adaptability of the door machine to non-standard operation scenarios is improved.

[0082] 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 be described below with reference to the accompanying drawings.

[0083] Figure 1 The flowchart of the container rotation method applied to the container door crane provided in this application is shown below. Figure 1 ,like Figure 1 As shown, the method includes:

[0084] S101. In response to the container rotation request from the user, the spreader on the container door operator is raised.

[0085] In this embodiment, when the terminal operator issues a container rotation command via a remote control terminal or the operating interface in the driver's cab, the container door crane's control system immediately receives and parses the request. It then drives the lifting mechanism, causing the spreader, tightly connected to the container via a twist lock, to begin vertical ascent. The container door is used to control the spreader. The spreader grabs the container and lifts it to a safe height. The spreader then rotates the container 180 degrees, precisely placing the container, with the door aligned, back onto the truck, aligning the door with the cargo compartment and preparing for loading and unloading operations.

[0086] S102. If it is determined that the height of the spreader on the container door operator meets the rotation conditions, then the rotation area of ​​the container is determined.

[0087] In this embodiment, by monitoring the absolute height or height change relative to the initial position of the spreader in real time, once the increase reaches a preset minimum safety threshold that ensures the container does not interfere with fixed objects such as the vehicle body when rotating at its lowest point, the rotation condition is determined to be met. Based on the container's dimensions and the current attitude of the spreader, a three-dimensional dynamic spatial range is calculated in real time using a preset algorithm. This range is the maximum volume envelope swept by the container as it rotates around the spreader's rotation center. This step achieves a precise definition of the "rotation area," transforming the assessment of rotation safety from a coarse-grained approach relying on fixed height thresholds to a refined and personalized prediction based on the specific object's motion trajectory. This lays a precise target range for subsequent targeted area safety scanning.

[0088] S103. Using a scanning instrument, scan the rotating area of ​​the container to obtain the scan results.

[0089] In this embodiment, a scanning instrument is used to quickly and comprehensively scan the rotation area calculated in step S102, acquiring point cloud data or depth information of all objects within the area in real time. The scanning result is ultimately processed into a clear binary state: either "an obstacle exists" or "no obstacle exists" within the area. This step completely changes the traditional operation method that relies on operator visual observation and experience judgment, greatly improving the objectivity, accuracy, and reliability of safety detection, and is a core technical link in avoiding collision accidents.

[0090] S104. If the scan results show that there is an obstacle, the spreader on the container door operator will be raised according to the scan results until there is no obstacle in the rotation area of ​​the container; if the scan results show that there is no obstacle, the container will be rotated.

[0091] In this embodiment, if the scan results identify obstacles within the rotation area (such as forklifts that have not been completely removed, vehicles that are too tall, or stacked materials), the spreader will not rotate immediately. Instead, it will calculate a new, higher safe height based on the obstacle's height information and instruct the spreader to continue lifting. During this process, a second scan will be performed to confirm until the rotation area is confirmed to be completely cleared. Once the scan results confirm the area is safe, the rotation motor will be triggered without delay, driving the spreader and container to rotate smoothly and efficiently to the target angle. This step achieves dynamic and adaptive safety strategies, allowing the container door crane to flexibly adjust its actions according to the actual environment, rather than mechanically executing a fixed process. This not only intelligently eliminates the potential collision risk of each rotation operation, ensuring absolute operational safety, but also optimizes the action path by avoiding unnecessary excessive lifting, ultimately significantly improving the efficiency of a single rotation operation of the container door crane while ensuring safety.

[0092] The container rotation method for container gate cranes provided in this application responds to a container rotation request from a user by raising the spreader on the container gate crane. If the height of the spreader on the container gate crane meets the rotation conditions, the rotation area of ​​the container is determined. The rotation area of ​​the container is scanned using a scanning instrument to obtain the scan result. If the scan result shows the presence of an obstacle, the spreader on the container gate crane is raised according to the scan result until there is no obstacle in the rotation area of ​​the container. If the scan result shows no obstacle, the container is rotated. This method eliminates the previous operation mode of setting a fixed height based solely on experience or manual visual inspection, enabling the container gate crane to autonomously adjust the lifting amplitude and timing according to changes in the site environment. This not only enhances the safety and reliability of the operation process but also improves the overall operation efficiency by reducing ineffective lifting and waiting links. Thus, it provides a technical support with both perception intelligence and response speed for container gate cranes to achieve safe and efficient container rotation in complex terminal operation environments, making container gate operation closer to the requirements of automated and precise modern port operations.

[0093] Figure 2 The flowchart of the container rotation method applied to the container door crane provided in this application is shown below. Figure 2 ,like Figure 2 As shown, in this embodiment... Figure 1 Based on the embodiments, a container rotation method applied to a container door crane is described in detail, wherein the rotation area of ​​the container is obtained through steps S201 to S203; and the rotation control of the container is realized through steps S204 to S206; the method includes:

[0094] S201. In response to the container rotation request from the user, the spreader on the container door operator is raised.

[0095] S202. Raise the spreader on the container door operator until the height of the container is higher than the height of the truck bed; obtain the container's size information, and obtain the container's rotation radius based on the size information; obtain the coordinates of the container's rotation center point based on the container's surface; obtain the container's position information, and obtain the container's position range based on the container's position information.

[0096] In this embodiment, the container information management system on the vehicle or remote terminal retrieves the size information of the currently operating container (e.g., length, width, and height, commonly the outer dimensions of a 20-foot or 40-foot standard container). Based on the connection status and current posture of the spreader and the container, and combined with the container's orientation (e.g., the end face where the door is located), the coordinates of the container's rotation center point are calculated. This center point is usually located at the geometric center of the spreader's slewing bearing and is mapped to the global coordinate system to uniformly describe the position of the rotation axis. By combining the spreader positioning and the container placement position, the container's position information and corresponding position range (i.e., the rectangular boundary of its projection on the ground) are obtained.

[0097] For example, if the current spreader is located at a known coordinate above the lane, the container is a 40-foot container, and the door is on the shorter side, then the three-dimensional coordinates of the rotation center at the spreader's rotation center can be calculated, and the projection range of the four corners of the container's bottom on the ground can be determined. This information is collected and stored in the cache in stage S201 so that the rotation radius and area can be directly calculated in S202. This implementation method makes the spreader's lifting not only a physical action but also the starting point for information collection. Its technical effect is to lock the spatial attributes and position of the container in advance, eliminate the time lag and uncertainty of subsequent calculations, and ensure that a precise geometric basis can be provided for the delineation of the dynamic collision avoidance zone during the lifting process. This improves the continuity and intelligence of the overall operation process while ensuring safety.

[0098] S203. Determine the first rotation area based on the rotation radius of the container and the coordinates of the rotation center point of the container; expand the preset area based on the first rotation area to obtain the second rotation area; obtain the container occupied area based on the location range of the container; subtract the container occupied area from the second rotation area to obtain the container's rotation area.

[0099] In this embodiment, as Figure 3 As shown, according to step S202, the rotation radius R0 of the container (the maximum sweep distance calculated from the dimensions) and the coordinates of the rotation center point (the center of rotation of the spreader, i.e., Figure 3Based on the centroid (R0) and the centroid, a first rotational region is determined that closely follows the rotational envelope of the container. This is a theoretical circle or sector-shaped space with the rotation center as the center and the rotation radius as the radius, representing the minimum range of motion required for the container body to rotate, which is the red area in the figure. However, considering only the theoretical range is not enough. In actual operation, a safety margin needs to be reserved to cope with sensor errors, mechanical sway, or sudden interference. Therefore, the area is expanded by a preset amount based on the first rotational region, that is, R1 is added to the first rotational region to form a second rotational region, which is equivalent to adding a "safety buffer" to the motion trajectory, which is the blue area in the figure. Further, based on the container's position information, its position range on the ground (i.e., the projected rectangle) is obtained, which is the white area in the figure. This position range is subtracted from the second rotational region to eliminate the space occupied by the container itself, finally obtaining the rotational region that actually needs to be monitored, which is the external space that the container will "sweep" through during rotation but does not occupy by the container itself. That is, the red area plus the blue area and the white area minus the white area in the figure, resulting in the red and blue areas shown in the figure, which is the rotational region.

[0100] In practical implementation, an example can be given: Assuming the container is a 40-foot standard container, the measured radius of the rotation range is 5 meters, and the coordinates of the rotation center point are (X0, Y0, Z0), then the first rotation area is a circular space with a radius of 5 meters centered at this point. After a preset expansion of 0.5 meters, the radius of the second rotation area becomes 5.5 meters; at the same time, the projection range of the container on the ground is a rectangle [(X1, Y1) to (X2, Y2)]. Through geometric Boolean operations, subtracting the point set of the rectangular area from the circular point set of the second rotation area yields an annular or arc-shaped area with a gap, which is the rotation area that the scanning instrument needs to focus on detecting. This process is usually completed in real time by the system's spatial geometry calculation module and combined with the spreader height information to form a three-dimensional safety detection body.

[0101] This step balances safety and detection accuracy. Expanding the area ensures that even minor positioning deviations can cover potential risks, while excluding the container itself prevents the system from misjudging its own structure as an obstacle. This refined area definition method allows the container door crane to quickly identify real threats in complex terminal environments while avoiding ineffective lifting or operational interruptions caused by false alarms. Ultimately, it optimizes the response speed and smoothness of rotation operations while ensuring safety, making it an indispensable key element for achieving intelligent and efficient container door operation.

[0102] S204. Using a single-line laser scanner and a three-dimensional laser scanner, the rotating area of ​​the container is scanned to obtain point cloud data of the rotating area.

[0103] In this embodiment, unlike existing technologies that often perform large-area, indiscriminate scanning at fixed locations, this application fully utilizes the structural characteristics of the container door crane itself and the spatial distribution of the operating scene. The scanning task is decomposed into two complementary, locally high-precision detection methods: two single-line laser scanners on the short side of the spreader are installed on both sides near the center of the spreader's rotation. During operation, they scan vertically downwards along the short side of the container. Their advantage lies in their ability to capture narrow areas near the spreader and the lower part of the container in the rotating area at close range and high resolution, especially the low-level space between the spreader and the truck bed where interference is likely to occur. Simultaneously, a three-dimensional laser scanner is positioned high to the side of the truck lane, scanning the entire truck lane area laterally. This covers a wide three-dimensional space from the ground to a certain height, compensating for the shortcomings of single-line scanners in terms of horizontal breadth and high-level field of view. This dual-instrument, regionalized, three-dimensional, and cross-functional layout combines "precise detection of key areas" with "macro-level monitoring of the entire area," ensuring that there are no blind spots in the rotating area from low to high positions and from the near field of the spreader to the far field of the lane.

[0104] Specifically, when the container is lifted and enters the rotation preparation state, two single-line laser scanners will be activated immediately. Their laser beams will form a fan-shaped thin line scanning surface vertically downward along the short side of the spreader, closely following the lower edge of the container's rotation trajectory, to quickly detect low-level obstacles that may protrude (such as ground equipment, bulk materials, or personnel). At the same time, the 3D laser scanner next to the lane will cover the entire width and height range of the lane in a lateral sweeping manner, generating a 3D point cloud of the lane space to capture obstacles that may appear at a high position in the container's rotation path (such as suspended pipelines, machinery that protrudes above the truck bed, or vehicles in adjacent lanes). Because the two instruments have a clear division of labor and complementary fields of view, they can jointly generate complete 3D point cloud data of the rotating area in a very short time. This layout has significant advantages over the existing technology of deploying a wide-area scanner at a single high position or fixed location: the existing technology's large-area scanning often has uneven resolution, low-level details are easily ignored, and there is a lot of data redundancy and long processing time. This application ensures low-level accuracy through close-range single-line scanning, while high-level and wide-area detection are handled by the 3D scanner. This not only improves the resolution and reliability of key areas, but also avoids the flood of invalid data, making subsequent point cloud analysis and obstacle recognition faster and more accurate.

[0105] S205. Perform density calculation and contour detection on the point cloud data to obtain suspected obstacles in the point cloud data; determine whether the suspected obstacles are actual obstacles based on statistical filtering and radius filtering methods; if so, the scan result is that there are obstacles; if not, the scan result is that there are no obstacles.

[0106] In this embodiment, point cloud data is essentially a large collection of discrete coordinate points in space. Direct analysis is inefficient and easily affected by interference. Therefore, feature extraction is required first: the point cloud is rasterized or spatially divided into blocks, and the point density in each small region is calculated. When the density of a certain region is significantly higher than the average density of the surrounding environment, it is marked as a suspected obstacle region. Subsequently, contour detection is performed on these high-density regions, and edge extraction or convex hull algorithms are used to delineate their shape boundaries, forming several independent spatial contours of suspected obstacles. For example, a point cloud cluster may delineate the shape of a vehicle, equipment, or human figure. These contours become candidate objects for the next step of discrimination.

[0107] For example, the point cloud of the rotating region is divided into cubic grids with a side length of 0.1 meters. The number of points in each grid is calculated. If the density of a grid exceeds twice the overall mean, it is marked as a high-density unit. The clustering algorithm merges these adjacent high-density units into connected regions, and the convex hull algorithm is used to generate the outer contour of the region, thus obtaining a list of suspected obstacles with well-defined shapes. Next, the filtering and discrimination stage begins: First, statistical filtering is applied to calculate the average distance and standard deviation from the point cloud of each suspected obstacle to its neighboring points. If the distance deviates significantly from the statistical distribution of the overall point cloud, it is identified as an outlier and removed. Then, radius filtering is performed, using each point as the center and setting a radius to perform a sphere query. If the number of points in the sphere is less than a set threshold, the point is considered isolated noise and deleted. After these two types of filtering, sparse and irregular point clusters formed by laser reflection ghosts, flying dust, or occasional stray light points from a distance are removed. Only the remaining dense and structurally stable point cloud clusters are identified as solid obstacles, and their spatial location and approximate size are given.

[0108] This step-by-step discrimination mechanism significantly improves the accuracy and robustness of obstacle recognition. Density calculation and contour detection first identify potential threat targets based on morphology and clustering, avoiding blind analysis of the entire point cloud. Statistical filtering utilizes the overall distribution pattern of the point cloud data to eliminate outliers, while radius filtering further cleans up sparse noise. The combination of these two methods effectively distinguishes between real obstacles and temporary interference, making the scanning results more reliable. Compared to existing technologies that directly use the raw point cloud for threshold judgment, which is prone to misclassifying noise as obstacles or missing low-contrast targets, this solution uses multi-level screening with more scientific judgment criteria and stronger fault tolerance. This reduces invalid lifting caused by false alarms and avoids collision risks caused by missed alarms, increasing the ability to perceive the environment and providing a solid data foundation for subsequent intelligent lifting based on obstacle type and height.

[0109] S206. If the scan result indicates the presence of an obstacle, then acquire an image of the obstacle using a high-definition camera; input the obstacle image and the scan result into a pre-trained prediction model to obtain the predicted type of the obstacle; determine the predicted height corresponding to the predicted type of the obstacle based on the mapping relationship; raise the spreader on the container door crane according to the predicted height until there are no obstacles in the rotation area of ​​the container; if the scan result shows that there are no obstacles, then rotate the container.

[0110] In this embodiment, a combination of visual recognition and a prediction model is used to intelligently determine the type and height of obstacles, thereby providing an accurate height reference for the safe lifting of the lifting equipment. After confirming the presence of a physical obstacle within the rotation area in the preceding step S205, a high-definition camera mounted on the lifting equipment is activated to capture high-definition images of the obstacle from multiple angles, obtaining visual information such as its appearance, texture, and contour. This image data, along with the point cloud coordinates and dimensions obtained from laser scanning, are input into a pre-trained deep learning prediction model. This prediction model is typically a classification or regression model based on a convolutional neural network (CNN). It can identify obstacles in the image and output their predicted types (e.g., "truck cab," "forklift," "personnel," "tool vehicle," etc.). Through an internally preset mapping table of "obstacle type - typical height," the typical height or maximum possible height (i.e., "predicted height") of the object can be quickly retrieved based on the predicted obstacle type.

[0111] Optionally, the training process of the prediction model is a data-driven supervised learning process. First, a large-scale dataset needs to be constructed, containing multi-angle high-resolution images of various obstacles (such as trucks, forklifts, containers, and personnel) collected in the port environment. Each image is precisely labeled manually, marking the bounding box of the obstacle and its specific type label. Simultaneously, for each obstacle in the image, its true height value needs to be obtained through LiDAR measurement or other precise measurement methods, serving as a supervision signal during training. After the data preparation is complete, a suitable deep convolutional neural network architecture (such as ResNet, YOLO, or Faster R-CNN) is selected as the base model. The image, its corresponding type label, and height value are used as input for end-to-end training. The training objective is to enable the model to accurately predict both the type and height value of obstacles in the image simultaneously. By continuously adjusting the network parameters, the classification error between the predicted type and the true type, as well as the regression error between the predicted height and the true height, are minimized. The resulting prediction model then possesses the ability to infer the most critical height dimension of the obstacle in three-dimensional space based on one or more two-dimensional images.

[0112] like Figure 4 and Figure 5 As shown, if the container's rotation area shows no obstacles, rotation can be performed directly. If obstacles are present, the required lifting height is predicted based on the obstacle image from step S206. After raising the container to the required height, rotation is then performed. The implementation of step S206 significantly improves the intelligence and decision-making efficiency of the container door operator in handling sudden obstacles in complex operating environments. Traditional safety strategies may tend to adopt a "one-size-fits-all" approach with large-scale lifting, while this step uses image recognition to predict the height, achieving on-demand and precise obstacle-avoidance lifting. This ensures absolute safety (the lifting height is sufficient to overcome the obstacle) while avoiding the waste of time and energy caused by excessive lifting. Integrating the predictive model into the control loop means that the control of the spreader no longer relies solely on real-time, potentially incomplete geometric data, but can utilize accumulated prior knowledge (typical heights of various obstacles) for reasoning and judgment, enhancing robustness in cases of missing information. Furthermore, this vision-based recognition method can effectively handle obstacle types that are difficult to distinguish from point clouds (e.g., distinguishing between open shelves and solid equipment), thereby making more reasonable obstacle avoidance decisions.

[0113] Figure 6 The structural schematic diagram of the container rotating device applied to the container door crane provided in this application is as follows: Figure 6 As shown, the container rotating device 60 applied to the container door crane provided in this embodiment includes:

[0114] The control module 601 is used to raise the spreader on the container door operator in response to a container rotation request from the user terminal; wherein the spreader on the container door operator is connected to the container;

[0115] The acquisition module 602 is used to determine the rotation area of ​​the container if it is determined that the height of the spreader on the container door crane meets the rotation conditions.

[0116] The scanning module 603 is used to scan the rotating area of ​​the container using a scanning instrument to obtain the scanning results;

[0117] The processing module 604 is used to raise the spreader on the container door operator according to the scanning result if the scanning result shows that there is an obstacle, until there is no obstacle in the rotation area of ​​the container; if the scanning result shows that there is no obstacle, the container is rotated.

[0118] In one possible implementation, the acquisition module 602 is further configured to:

[0119] Raise the spreader on the container door operator until the height of the container is higher than the height of the truck bed;

[0120] Obtain the container's dimensions and determine the container's rotation radius based on those dimensions.

[0121] Based on the container's surface, obtain the coordinates of the container's rotation center point;

[0122] Obtain the location information of the container, and determine the location range of the container based on the location information;

[0123] The rotation area of ​​the container is obtained based on the radius of its rotation range, the coordinates of its rotation center point, and its position range.

[0124] In one possible implementation, the acquisition module 602 is further configured to:

[0125] The first rotation area is determined based on the rotation radius of the container and the coordinates of the rotation center point of the container; wherein, the first rotation area is used to characterize the rotation area with respect to the rotation radius of the container.

[0126] Based on the first rotation region, the area is expanded by a preset amount to obtain the second rotation region;

[0127] Based on the location range of the container, the container-occupied area is obtained; the container-occupied area is used to characterize the area occupied by the container in the second rotation area before rotation.

[0128] Subtract the container's occupied area from the second rotation area to obtain the container's rotation area.

[0129] In one possible implementation, the processing module 604 is further configured to:

[0130] Images of obstacles are obtained using a high-definition camera;

[0131] Input the image and scan results of the obstacle into a pre-trained prediction model to obtain the predicted type of the obstacle;

[0132] Based on the mapping relationship, the predicted height corresponding to the predicted type of obstacle is determined; where the mapping relationship is the correspondence between the predicted type and the predicted height.

[0133] Based on the predicted height, the spreader on the container door crane is raised until there are no obstructions in the container's rotation area.

[0134] In one possible implementation, the scanning module 603 is further configured to:

[0135] The rotating area of ​​the container is scanned using a single-line laser scanner and a 3D laser scanner to obtain point cloud data of the rotating area.

[0136] Data analysis is performed on the point cloud data to obtain the scanning results.

[0137] In one possible implementation, the scanning module 603 is further configured to:

[0138] Density calculation and contour detection are performed on point cloud data to identify suspected obstacles in the point cloud data;

[0139] Based on statistical filtering and radius filtering methods, determine whether a suspected obstacle is a real obstacle;

[0140] If yes, the scan result indicates the presence of an obstacle; otherwise, the scan result indicates the absence of an obstacle.

[0141] Figure 7 This is a hardware schematic diagram of a container rotating device applied to a container door crane, as provided in this application. Figure 7 As shown, the electronic device 70 provided in this embodiment includes at least one processor 701 and a memory 702. Optionally, the device 70 further includes a communication component 703. The processor 701, memory 702, and communication component 703 are connected via a bus 704.

[0142] In a specific implementation, at least one processor 701 executes computer execution instructions stored in memory 702, causing at least one processor 701 to perform the above-described method.

[0143] The specific implementation process of processor 701 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0144] 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.

[0145] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0146] 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.

[0147] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0148] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0149] 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.

[0150] 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.

[0151] 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, methods, or units, and may be electrical, mechanical, or other forms.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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 container rotation method applied to a container door crane, characterized in that, include: In response to a container rotation request from the user, the spreader on the container door operator is raised; wherein the spreader on the container door operator is connected to the container; If it is determined that the height to which the spreader on the container door operator rises meets the rotation conditions, then the rotation area of ​​the container is determined. The rotating area of ​​the container is scanned using a scanning instrument to obtain the scanning results; If the scan results show that there is an obstacle, the spreader on the container door operator is raised according to the scan results until there is no obstacle in the rotation area of ​​the container; if the scan results show that there is no obstacle, the container is rotated.

2. The method according to claim 1, characterized in that, If it is determined that the lifting height of the spreader on the container door operator meets the rotation conditions, then the rotation area of ​​the container is determined, including: Raise the spreader on the container door operator until the height of the container is higher than the height of the truck bed; Obtain the size information of the container, and calculate the radius of rotation range of the container based on the size information; Based on the container's surface, the coordinates of the container's rotation center point are obtained; Obtain the location information of the container, and determine the location range of the container based on the location information; The rotation area of ​​the container is obtained based on the rotation radius of the container, the coordinates of the rotation center point of the container, and the position range of the container.

3. The method according to claim 2, characterized in that, The step of obtaining the rotation area of ​​the container based on the rotation radius of the container, the coordinates of the rotation center point of the container, and the position range of the container includes: A first rotation area is determined based on the rotation radius of the container and the coordinates of the rotation center point of the container; wherein, the first rotation area is used to characterize the rotation area with the rotation radius of the container; Based on the first rotating region, the area is expanded by a preset amount to obtain the second rotating region; Based on the location range of the container, the container-occupied area is obtained; the container-occupied area is used to characterize the area occupied by the container in the second rotation area before rotation; The rotation area of ​​the container is obtained by subtracting the container-occupied area from the second rotation area.

4. The method according to claim 1, wherein a high-definition camera is installed on the hanger of the door machine, characterized in that, After the scan results indicate the presence of an obstacle, the process includes: The image of the obstacle is acquired using the high-definition camera; The image and scan results of the obstacle are input into a pre-trained prediction model to obtain the predicted type of the obstacle. Based on the mapping relationship, the predicted height corresponding to the predicted type of the obstacle is determined; wherein, the mapping relationship is the correspondence between the predicted type and the predicted height; Based on the predicted height, the spreader on the container door operator is raised until there are no obstructions in the rotation area of ​​the container.

5. The method according to any one of claims 1-4, wherein two single-line laser scanners are provided on the hanger of the gate machine, and a three-dimensional laser scanner is provided beside the lane where the gate machine is located, characterized in that, include: The rotating area of ​​the container is scanned using a single-line laser scanner and the three-dimensional laser scanner to obtain point cloud data of the rotating area; The point cloud data is analyzed to obtain the scanning results.

6. The method according to claim 5, characterized in that, The step of performing data analysis on the point cloud data to obtain the scanning results includes: Density calculation and contour detection are performed on the point cloud data to obtain suspected obstacles in the point cloud data; Based on statistical filtering and radius filtering methods, determine whether the suspected obstacle is a physical obstacle; If yes, the scan result indicates the presence of an obstacle; if no, the scan result indicates the absence of an obstacle.

7. A container rotating device applied to a container door crane, characterized in that, include: A control module is used to raise the spreader on the container door operator in response to a container rotation request from the user terminal; wherein the spreader on the container door operator is connected to the container; The acquisition module is used to determine the rotation area of ​​the container if it is determined that the height of the spreader on the container door operator meets the rotation conditions. The scanning module is used to scan the rotating area of ​​the container using a scanning instrument to obtain the scanning results; The processing module is configured to, if the scan result indicates the presence of an obstacle, raise the spreader on the container door operator until there is no obstacle in the rotation area of ​​the container; if the scan result indicates the absence of an obstacle, rotate the container.

8. 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 1-6.

9. 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 1-6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-6.

Images