Method and equipment for identifying collision of lifting appliance, field bridge and storage medium
By analyzing point cloud data to identify the external contours of the container and the spreader, we can determine whether the distance between the spreader and the container is less than the preset threshold, and solve the safety and efficiency problems caused by relying on human judgment in the prior art, and achieve a more efficient and safe lifting operation.
Patent Information
- Application Number
- CN202411931921.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-25
- Publication Date
- 2025-04-18
AI Technical Summary
The prior art relies on the attention and judgment of operators during container lifting, and is susceptible to human factors, resulting in errors in judgment or untimely responses, affecting the safety and efficiency of lifting.
By obtaining the target point cloud data of the target area and the point cloud data of the spreader, the external contour of the container and the spreader is determined. If the distance between the two is less than the preset distance threshold, it is determined that there is a risk of collision of the spreader.
Effectively identify and prevent collisions between spreaders and containers, improve the safety and efficiency of lifting and unloading operations, and reduce the impact of human errors.
Smart Images
Figure CN119850662A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of container loading and unloading, and in particular to a method, device, field crane and storage medium for identifying spreader collision. Background Art
[0002] In modern logistics and port operations, ensuring safe lifting and handling of containers is a key factor affecting the efficiency of the transport chain. Through safe operation, the risk of cargo damage can be effectively reduced, and economic losses and transportation delays caused by damage can be avoided. In addition, safe and efficient operation can also reduce the wear of the spreader, extend its service life, reduce the frequency of maintenance and replacement, and thus reduce operating costs.
[0003] In the related art, in order to prevent the spreader from colliding with the container during operation, the operator usually monitors the lifting and unloading environment through cameras installed around the spreader to ensure safety. This method relies on the operator's attention and judgment ability, which is easily affected by human factors and may lead to misjudgment or untimely response, thus affecting the safety and efficiency of lifting and unloading. Summary of the invention
[0004] The present application provides a method, device, field bridge and storage medium for identifying spreader collision, so as to improve the safety and efficiency of the spreader during the container lifting and unloading process.
[0005] In a first aspect, the present application provides a method for identifying a spreader collision, comprising:
[0006] Acquire target point cloud data of a target area and spreader point cloud data of a spreader, wherein the target area includes the spreader, a target container, a lifting and unloading area of the target container, and a container area adjacent to the lifting and unloading area, and the target container is a container to be unloaded or a container to be lifted and loaded;
[0007] Determining, based on the target point cloud data, an outer contour of a container placed in a container area adjacent to the lifting and unloading area;
[0008] Determining the outer contour of the spreader according to the spreader point cloud data;
[0009] If the distance between the outer contour of the container and the outer contour of the spreader is less than a preset distance threshold, it is determined that there is a collision risk with the spreader.
[0010] In a possible implementation, the acquiring target point cloud data of the target area and the spreader point cloud data of the spreader includes:
[0011] The target point cloud data is obtained according to a plurality of laser radars pre-installed under the field bridge trolley;
[0012] The target point cloud data is intercepted at a height according to a reference height to obtain the spreader point cloud data, wherein the reference height is determined by adding a safety distance margin on the basis of the height between the upper surface of the target container and the ground.
[0013] In a possible implementation, the target point cloud data is obtained according to a plurality of laser radars pre-arranged under the field bridge trolley, including:
[0014] The point cloud data acquired by each laser radar pre-installed under the field bridge trolley are spliced to obtain initial point cloud data;
[0015] The target point cloud data is extracted from the initial point cloud data according to the plane size of the target container, the center of the spreader, and a preset magnification ratio, wherein the plane size includes the longitudinal size and the transverse size of the target container on a horizontal plane.
[0016] In a possible implementation, extracting the target point cloud data from the initial point cloud data according to the plane size of the target container, the center of the spreader, and a preset magnification ratio includes:
[0017] Determining the longitudinal size and the transverse size of the target container according to the plane size of the target container;
[0018] Enlarging the longitudinal size and the transverse size according to the preset enlargement ratio to obtain a target longitudinal size and a target transverse size;
[0019] The target point cloud data is extracted from the initial point cloud data by taking the center of the spreader as the center of symmetry and combining the target longitudinal dimension and the target transverse dimension.
[0020] In a possible implementation, determining, based on the target point cloud data, an outer contour of a container placed in a container area adjacent to the lifting and unloading area includes:
[0021] Performing projection processing on the target point cloud data in the vertical direction to obtain a binary image of the target area;
[0022] According to the plane size of the target container, the binary image of the target area is divided into adjacent areas, wherein the adjacent areas include adjacent container areas and / or adjacent row container areas;
[0023] Perform edge detection on the container in the adjacent area to obtain the outer contour of the container.
[0024] In a possible implementation manner, determining the outer contour of the spreader according to the spreader point cloud data includes:
[0025] Performing projection processing on the spreader point cloud data in the vertical direction to obtain a binary image of the spreader;
[0026] Edge detection is performed on the binary image of the spreader to obtain the outer contour of the spreader.
[0027] In a possible implementation manner, before acquiring the target point cloud data of the target area and the spreader point cloud data of the spreader, the method further includes:
[0028] Performing time synchronization processing on the multiple laser radars;
[0029] Based on the coordinate system of the sling, the coordinate system of each laser radar is spatially synchronized.
[0030] In a second aspect, the present application provides a device for identifying a spreader collision, comprising:
[0031] an acquisition module, configured to acquire target point cloud data of a target area and spreader point cloud data of a spreader, wherein the target area includes the spreader, a target container, a lifting and unloading area of the target container, and a container area adjacent to the lifting and unloading area, and the target container is a container to be unloaded or a container to be lifted and loaded;
[0032] A first processing module is used to determine the outer contour of the container placed in the container area adjacent to the lifting and unloading area according to the target point cloud data;
[0033] A second processing module, for determining an outer contour of the spreader according to the spreader point cloud data;
[0034] The determination module is configured to determine that there is a collision risk with the spreader if the distance between the outer contour of the container and the outer contour of the spreader is less than a preset distance threshold.
[0035] In a possible implementation manner, the acquisition module is specifically configured to:
[0036] The target point cloud data is obtained according to a plurality of laser radars pre-installed under the field bridge trolley;
[0037] The target point cloud data is intercepted at a height according to a reference height to obtain the spreader point cloud data, wherein the reference height is determined by adding a safety distance margin on the basis of the height between the upper surface of the target container and the ground.
[0038] In a possible implementation manner, the acquisition module is specifically configured to:
[0039] The point cloud data acquired by each laser radar pre-installed under the field bridge trolley are spliced to obtain initial point cloud data;
[0040] The target point cloud data is extracted from the initial point cloud data according to the plane size of the target container, the center of the spreader, and a preset magnification ratio, wherein the plane size includes the longitudinal size and the transverse size of the target container on a horizontal plane.
[0041] In a possible implementation manner, the acquisition module is specifically configured to:
[0042] Determining the longitudinal size and the transverse size of the target container according to the plane size of the target container;
[0043] Enlarging the longitudinal size and the transverse size according to the preset enlargement ratio to obtain a target longitudinal size and a target transverse size;
[0044] The target point cloud data is extracted from the initial point cloud data by taking the center of the spreader as the center of symmetry and combining the target longitudinal dimension and the target transverse dimension.
[0045] In a possible implementation manner, the first processing module is specifically configured to:
[0046] Performing projection processing on the target point cloud data in the vertical direction to obtain a binary image of the target area;
[0047] According to the plane size of the target container, the binary image of the target area is divided into adjacent areas, wherein the adjacent areas include adjacent container areas and / or adjacent row container areas;
[0048] Perform edge detection on the container in the adjacent area to obtain the outer contour of the container.
[0049] In a possible implementation manner, the second processing module is specifically configured to:
[0050] Performing projection processing on the spreader point cloud data in the vertical direction to obtain a binary image of the spreader;
[0051] Edge detection is performed on the binary image of the spreader to obtain the outer contour of the spreader.
[0052] In a possible implementation manner, the device for identifying a spreader collision further includes:
[0053] A third processing module is used to perform time synchronization processing on the multiple laser radars;
[0054] The third processing module is further used to perform spatial synchronization processing on the coordinate system of each laser radar based on the coordinate system of the sling.
[0055] In a third aspect, the present application provides an electronic device, including: a memory, a processor;
[0056] The memory stores computer-executable instructions;
[0057] The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method for identifying a spreader collision as described in any one of the first aspects.
[0058] In a fourth aspect, the present application provides a field crane, including a hoist, a field crane trolley, a laser radar and the electronic equipment described in the third aspect.
[0059] In a fifth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method for identifying a sling collision as described in any one of the first aspects.
[0060] In a sixth aspect, the present application provides a computer program product, the computer program product comprising a computer program, and the computer program, when executed by a processor, is used to implement the method for identifying a sling collision as described in any one of the first aspects.
[0061] The method, device, crane and storage medium for identifying spreader collision provided by the present application determine the outer contour of the container in the adjacent container area and the outer contour of the spreader by acquiring the target point cloud data of the target area and the spreader point cloud data of the spreader. The spreader is determined to be at risk of collision based on the distance between the outer contour of the container and the outer contour of the spreader being less than a preset distance threshold. The method effectively identifies the risk of spreader collision, thereby improving the safety and efficiency of the spreader during container lifting and unloading. BRIEF DESCRIPTION OF THE DRAWINGS
[0062] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0063] Figure 1 A schematic diagram of an application scenario provided by an embodiment of the present application;
[0064] Figure 2 A flow chart of a method for identifying a spreader collision provided in the present application;
[0065] Figure 3 A schematic diagram of the installation position of the laser radar provided in the embodiment of the present application;
[0066] Figure 4 A schematic diagram of the division of adjacent areas provided in an embodiment of the present application;
[0067] Figure 5 A schematic diagram of a first embodiment of the relative position of the external contour of the spreader and the external contour of the container provided in the present application;
[0068] Figure 6 A schematic diagram of a flow chart of a second embodiment of a method for identifying a spreader collision provided by the present application;
[0069] Figure 7 A schematic diagram of a container falling into a designated adjacent area provided in an embodiment of the present application;
[0070] Figure 8 A schematic diagram of a second embodiment of the relative position of the outer contour of the spreader and the outer contour of the container provided in the present application;
[0071] Fig. 9 A schematic diagram of a third embodiment of the relative position of the external contour of the spreader and the external contour of the container provided in the present application;
[0072] Fig.10 A schematic diagram of a fourth embodiment of the relative position of the outer contour of the spreader and the outer contour of the container provided in the present application;
[0073] Fig.11 A schematic diagram of a flow chart of a third embodiment of a method for identifying a spreader collision provided by the present application;
[0074] Fig.12 A schematic flow chart of a fourth embodiment of the method for identifying a spreader collision provided by the present application;
[0075] Fig.13 A schematic diagram of the structure of a first embodiment of a device for identifying a spreader collision provided by the present application;
[0076] Fig.14 A schematic diagram of the structure of a second embodiment of a device for identifying a spreader collision provided by the present application;
[0077] Fig.15 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.
[0078] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION
[0079] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.
[0080] First, the terms involved in this application are explained:
[0081] GPS clock: refers to the high-precision clock used in the Global Positioning System (GPS) to provide accurate time synchronization information.
[0082] Binary image: refers to an image in which each pixel is either black or white.
[0083] Edge detection: refers to the identification and location of areas in an image where brightness or color changes significantly in image processing. These areas usually correspond to the boundaries or outlines of objects.
[0084] Figure 1 This is a schematic diagram of an application scenario provided by an embodiment of the present application. Figure 1 , including a large vehicle 100, a bridge trolley 101, and a container 102. A lifting device 103 for lifting and unloading the container 102 is arranged under the bridge trolley 101. The driver can accurately position the lifting device 103 by manipulating the bridge trolley 101 to ensure that it is accurately aligned with the container 102, thereby achieving safe and efficient lifting and unloading operations.
[0085] Among them, the trolley 100 refers to the entire crane structure, which moves along the track, usually parallel to the direction of the dock or cargo area. The movement of the trolley allows the crane to cover a larger area to load and unload containers from ships or move containers in the yard; the yard crane trolley 101 is a movable component installed on the trolley, usually moving along the crossbeam of the trolley. The main function of the yard crane trolley 101 is to accurately position the spreader in order to grab, lift, move and place containers. The movement of the yard crane trolley 101 is usually perpendicular to the direction of movement of the trolley.
[0086] In the related art, in order to prevent the spreader from colliding with the container during operation, the operator usually monitors the lifting and unloading environment through cameras installed around the spreader to ensure safety. This method relies on the operator's attention and judgment, which is easily affected by human factors and may lead to misjudgment or untimely response, thus affecting the safety and efficiency of the lifting and unloading operation.
[0087] In response to the above problems, the inventors consider that by acquiring point cloud data of the spreader and the containers adjacent to the lifting and unloading area, the relative position between the spreader and the surrounding containers can be identified, thereby effectively reducing the risk of collision. Specifically, the target point cloud data of the target area and the point cloud data of the spreader can be acquired. By analyzing the target point cloud data, the outer contour of the container placed near the lifting and unloading area can be determined; by analyzing the spreader point cloud data, the outer contour of the spreader can be determined. If the distance between the outer contour of the container and the outer contour of the spreader is less than a preset distance threshold, it can be determined that the spreader is at risk of collision, thereby effectively reducing the risk of misjudgment or untimely response due to human operation. Based on this, the present application proposes a method for identifying spreader collisions, which aims to improve the safety and efficiency of lifting and unloading operations by accurately analyzing point cloud data.
[0088] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.
[0089] Figure 2 This is a flow chart of the first embodiment of the method for identifying a sling collision provided by the present application. Figure 2 , the method comprising:
[0090] S201, acquiring target point cloud data of a target area and spreader point cloud data of a spreader.
[0091] The execution subject of the embodiment of the present application may be an electronic device, or a device for identifying a spreader collision provided in the electronic device. The device for identifying a spreader collision may be implemented by software, or by a combination of software and hardware. The device for identifying a spreader collision may be a processor in the electronic device. For ease of understanding, the following description will be made by taking the execution subject as an electronic device as an example.
[0092] In this step, the electronic device can obtain the target point cloud data of the target area and the spreader point cloud data of the spreader. The target area includes the spreader, the target container, the lifting and unloading area of the target container, and the container area adjacent to the lifting and unloading area. The target container is a container to be unloaded or a container to be lifted.
[0093] The target container loading and unloading area refers to an area specifically used for loading and unloading the target container.
[0094] In a specific implementation, a laser radar may be installed below the field crane trolley to obtain target point cloud data and spreader point cloud data through the laser radar.
[0095] Figure 3 This is a schematic diagram of the laser radar installation location provided in the embodiment of the present application. Figure 3 , multiple LiDAR devices can be installed under the field bridge trolley, including LiDAR A, LiDAR B, LiDAR C, and LiDAR D. Each LiDAR is strategically arranged to cover different monitoring areas, providing comprehensive environmental perception capabilities. For example, LiDAR A is used to monitor the front of the field bridge trolley, LiDAR B is used to monitor the rear of the field bridge trolley, LiDAR C is used to monitor the right side of the field bridge trolley, and LiDAR D is used to monitor the left side of the field bridge trolley.
[0096] Optionally, target point cloud data can be acquired based on multiple laser radars pre-installed under the field bridge, wherein the field bridge trolley can be used to hang the sling.
[0097] Furthermore, the target point cloud data can be intercepted at a height according to a reference height to obtain the spreader point cloud data, wherein the reference height is determined by adding a safety distance margin based on the height between the upper surface of the target container and the ground.
[0098] S202: Determine the outer contour of the container placed in the container area adjacent to the lifting and unloading area according to the target point cloud data.
[0099] In this step, the acquired target point cloud data may be projected in the vertical direction to obtain a binary image of the target area, and the outer contour of the container placed in the container area adjacent to the lifting and unloading area may be determined based on the binary image of the target area.
[0100] Specifically, after obtaining a binary image of the target area based on the target point cloud data, the binary image of the target area can be divided into adjacent areas according to the plane size of the target container, and the adjacent areas include adjacent container areas and / or adjacent row container areas; then edge detection is performed on the containers in the adjacent areas to obtain the external contour of the containers.
[0101] Figure 4 This is a schematic diagram of the division of adjacent areas provided in the embodiment of the present application. Figure 4 , the container lifting task is a lifting task, that is, using a sling to lift the target container from the lifting area; the size of the target container is 6 meters (m) × 2.5m × 2.6m, which is approximately equal to 20 feet. Among them, the plane size of the target container is 6m × 2.5m. According to the plane size of the target container, the binary map of the target area is divided into adjacent areas, and adjacent area 1, adjacent area 2, adjacent area 3, and adjacent area 4 can be obtained. Adjacent area 1 and adjacent area 3 are adjacent containers, and adjacent area 2 and adjacent area 4 are adjacent row container areas.
[0102] It should be noted that when dividing adjacent areas, it is necessary to consider increasing the safe activity space for personnel based on the plane size of the target container. For example, if the preset personnel passage space is 1m, the plane size of the lifting and unloading area and each adjacent area can be 7m×3.5m.
[0103] Optionally, edge detection can be performed on containers in adjacent areas using an edge detection algorithm to obtain the outer contour of the container. For example, edge detection can be performed on containers in adjacent areas using a Canny edge detection algorithm and a longitude and latitude scanning method to obtain the outer contour of the container.
[0104] S203: Determine the outer contour of the spreader according to the spreader point cloud data.
[0105] In this step, the acquired spreader point cloud data may be projected in the vertical direction to obtain a binary image of the spreader, and edge detection may be performed on the binary image of the spreader to obtain an external contour of the spreader.
[0106] For example, the acquired spreader point cloud data may be projected in the vertical direction to obtain a binary image of the spreader, and the edge detection of the binary image of the spreader may be performed using a Canny edge detection algorithm to obtain an external contour of the spreader.
[0107] S204: If the distance between the outer contour of the container and the outer contour of the spreader is less than a preset distance threshold, it is determined that there is a collision risk with the spreader.
[0108] In this step, the electronic device may determine that there is a potential collision risk with the spreader based on the distance between the outer contour of the container and the outer contour of the spreader being less than a preset distance threshold.
[0109] For the preset distance threshold, the preset distance threshold can be ensured to meet relevant safety requirements according to industry standards and safety regulations. For example, the preset distance threshold can be 0.1m.
[0110] Figure 5 This is a schematic diagram of the relative position of the outer contour of the spreader and the outer contour of the container provided in this application. Figure 5 , it can be determined that there is no collision risk between the spreader and the container based on the distance between the outer contour of the spreader and the outer contour of the container being greater than a preset distance threshold.
[0111] Exemplarily, eight distances can be determined based on the outer contour of the spreader and the outer contour of the container, namely distance d1, distance d2, ..., and distance d8. Since the values of distances d1 to d8 are all greater than the preset distance threshold of 0.1m, it is determined that there is no risk of collision between the spreader and the container.
[0112] In an embodiment of the present application, target point cloud data of a target area and point cloud data of a spreader can be obtained. Based on the target point cloud data, the outer contour of a container placed in a container area adjacent to the lifting and unloading area is identified. Using the spreader point cloud data, the outer contour of the spreader is identified. If it is detected that the distance between the outer contour of the container and the outer contour of the spreader is less than a preset distance threshold, it is determined that there is a potential collision risk for the spreader. In the above process, by acquiring and analyzing the point cloud data of the target area and the spreader, the distance between the container and the spreader can be identified and monitored in real time, thereby effectively improving the safety and efficiency of the lifting and unloading operations.
[0113] exist Figure 2 Based on the embodiment shown below, combined with Figure 6 , the above method for identifying spreader collision is further described in detail.
[0114] Figure 6 This is a flow chart of the second embodiment of the method for identifying the collision of the lifting equipment provided by this application. Figure 6 , the method may include:
[0115] S601. Obtain target point cloud data based on multiple laser radars pre-installed under the field bridge trolley.
[0116] In this step, a target area consisting of a spreader, a target container, a lifting and unloading area of the target container, and a container area adjacent to the lifting and unloading area can be obtained based on multiple laser radars pre-installed under the yard crane trolley. Among them, the target container is a container to be unloaded or a container to be lifted.
[0117] For containers to be unloaded, the spreader may be lifting a target container and preparing to unload it to a lifting and unloading area; for containers to be loaded, the spreader may be preparing to load the target container from the lifting and unloading area.
[0118] In an optional implementation, the point cloud data obtained by each laser radar pre-installed under the yard crane trolley can be spliced to obtain initial point cloud data; according to the plane size of the target container, the center of the spreader, and the preset magnification ratio, the target point cloud data is extracted from the initial point cloud data. The plane size includes the longitudinal size and the transverse size of the target container on the horizontal plane, and the preset magnification ratio can be preset according to actual needs.
[0119] For example, if laser radar A is used to monitor the front of the field bridge trolley, laser radar B is used to monitor the rear of the field bridge trolley, laser radar C is used to monitor the right side of the field bridge trolley, and laser radar D is used to monitor the left side of the field bridge trolley; the point cloud data obtained by the four laser radars can be spliced to obtain the initial point cloud data.
[0120] Furthermore, if the magnification ratio is preset to 1.3, for the task of lifting a 20-foot target container, with the center of the spreader as the symmetry center, the direction of the trolley can be set to -3.85m to +3.85m, and the direction of the trolley can be set to -1.6m to +1.6m, and the target point cloud data can be extracted from the initial point cloud data. Among them, the plane size of the target container is 6 meters × 2.5 meters.
[0121] S602: intercept the target point cloud data at a height according to a reference height to obtain the spreader point cloud data.
[0122] In this step, the reference height determined by the safety distance margin can be increased based on the height between the upper surface of the target container and the ground, and the target point cloud data can be intercepted at the height to obtain the spreader point cloud data.
[0123] The safety distance margin refers to the additional height added to the height between the upper surface of the container and the ground to ensure safe operation during lifting tasks.
[0124] For example, if the container lifting task is a lifting task, and the height between the upper surface of the 20-foot target container and the ground is 2.6m, a safety distance margin of 0.2m can be added. Therefore, the reference height will become 2.8m. The reference height of 2.8m can be used to intercept the target point cloud data, thereby obtaining the spreader point cloud data.
[0125] For another example, if the container lifting and unloading task is an unloading task, and the height between the upper surface of the 20-foot target container and the ground is 5m, a safety distance margin of 0.2m can be added. Therefore, the reference height will become 5.2m. The reference height of 5.2m can be used to intercept the target point cloud data, thereby obtaining the spreader point cloud data.
[0126] S603: Perform vertical projection processing on the target point cloud data to obtain a binary image of the target area.
[0127] In this step, the target point cloud data may be projected in the vertical direction to generate a binary image of the target area.
[0128] For example, projecting the target point cloud data containing a container vertically can produce a top view, in which the outline of the container is presented in the form of black and white pixels on a two-dimensional plane. Black pixels can represent the area where the container is located, while white pixels represent blank areas or backgrounds.
[0129] S604: Divide the binary image of the target area into adjacent areas according to the plane size of the target container.
[0130] In this step, the binary image of the target area can be divided into adjacent areas according to the plane size of the target container, so as to more accurately identify and process different areas. The adjacent areas include adjacent container areas and / or adjacent row container areas.
[0131] For example, the plane size of a 20-foot target container is 6m×2.5m. The binary image can be divided into multiple adjacent regions, each of which is 7m×3.5m in size, so as to identify the specific location of the container and the open space or other objects adjacent to it. The size of each adjacent region is obtained by dividing the binary image of the target area after adding the safe activity space for personnel on the basis of the plane size of the target container.
[0132] S605: Perform edge detection on containers in adjacent areas to obtain external contours of the containers.
[0133] In this step, edge detection may be performed on the container located in the adjacent area to extract the outer contour of the container.
[0134] In a specific implementation, whether the container is located in the designated adjacent area can be determined by determining whether the projection of the center of mass of the container in the vertical direction falls into the adjacent area.
[0135] Figure 7 A schematic diagram of a container falling into a designated adjacent area provided in an embodiment of the present application. Figure 7 , including adjacent area 1, adjacent area 2, adjacent area 3, and adjacent area 4. There is container 1 in adjacent area 1, and the projection of its center of mass falls into adjacent area 1; there is container 2 in adjacent area 2, and the projection of its center of mass falls into adjacent area 2; there is container 3 in adjacent area 3, and the projection of its center of mass falls into adjacent area 3; there is container 4 in adjacent area 4, and the projection of its center of mass falls into adjacent area 4.
[0136] For example, the Canny edge detection algorithm can be used to perform edge detection on container 1, container 2, container 3, and container 4 to obtain the outer contours of the containers, including outer contour 1, outer contour 2, outer contour 3, and outer contour 4.
[0137] Optionally, if the binary image of the target area is divided into adjacent areas according to the plane size of the target container, and it is detected that there is no container in the adjacent area, it means that there is no collision risk for the spreader.
[0138] S606: Perform vertical projection processing on the spreader point cloud data to obtain a binary image of the spreader.
[0139] For example, projecting the spreader point cloud data vertically can produce a top view, where the spreader's outline is presented in the form of black and white pixels on a two-dimensional plane. Black pixels can represent the area where the spreader is located, while white pixels represent blank areas or backgrounds.
[0140] S607: Perform edge detection on the binary image of the spreader to obtain the outer contour of the spreader.
[0141] For example, the Canny edge detection algorithm may be used to perform edge detection on the spreader to obtain the outer contour A of the spreader.
[0142] S608: If the distance between the outer contour of the container and the outer contour of the spreader is less than a preset distance threshold, it is determined that there is a collision risk with the spreader.
[0143] In this step, if the distance between the outer contour of the container and the outer contour of the spreader is less than a preset distance threshold, it can be determined that there is a risk of collision with the spreader.
[0144] Figure 8 This is a schematic diagram of the relative position of the outer contour of the spreader and the outer contour of the container provided in this application. Figure 8 , including the outer contour A of the spreader, the outer contour 1, outer contour 2, outer contour 3, and outer contour 4 of the container. If the preset distance threshold is 0, it can be determined that there is no collision risk for the spreader based on the distance between the outer contour A and the outer contour 1, outer contour 2, outer contour 3, and outer contour 4 being greater than the preset distance threshold 0.
[0145] Exemplarily, the distance d1 and the distance d2 can be determined based on the external contour A and the external contour 1; the distance d7 and the distance d8 can be determined based on the external contour A and the external contour 2; the distance d6 and the distance d5 can be determined based on the external contour A and the external contour 3; the distance d4 and the distance d3 can be determined based on the external contour A and the external contour 4; and based on the values of d1 to d8 being greater than the preset distance threshold 0, it is determined that there is no risk of collision between the sling and the container.
[0146] Fig. 9 This is a schematic diagram of the relative position of the outer contour of the spreader and the outer contour of the container provided in this application. Fig. 9 , including the outer contour A of the spreader, the outer contour 1, the outer contour 2, the outer contour 3, and the outer contour 4 of the container. If the preset distance threshold is 0, it can be determined that the spreader has a collision risk based on the distance between the outer contour A and the outer contour 2 being less than the preset distance threshold 0.
[0147] Exemplarily, the distance d1 and the distance d2 can be determined based on the external contour A and the external contour 1; the distance d7 and the distance d8 can be determined based on the external contour A and the external contour 2; the distance d6 and the distance d5 can be determined based on the external contour A and the external contour 3; the distance d4 and the distance d3 can be determined based on the external contour A and the external contour 4; and based on the value of the distance d7 being less than the preset distance threshold 0, it is determined that there is a risk of collision between the sling and the container 2.
[0148] In an optional implementation, the outer contour in the binary image of the target area can be indexed back to the point cloud data to determine the maximum value of the adjacent container, and the outer contour in the binary image of the spreader can be indexed back to the point cloud data to determine the maximum value of the spreader. The distance between the outer contour of the container and the outer contour of the spreader can be calculated based on the maximum value of the adjacent container and the maximum value of the spreader.
[0149] Fig.10 This is a schematic diagram of the relative position of the outer contour of the spreader and the outer contour of the container provided in this application. Fig.10 , it can be determined that there is a collision risk between the spreader and the container based on the distance between the outer contour of the spreader and the outer contour of the container being less than a preset distance threshold.
[0150] Exemplarily, eight distances can be determined based on the outer contour of the spreader and the outer contour of the container, namely distance d1, distance d2, ..., and distance d8. Since the value of distance d7 is less than the preset distance threshold 0, it is determined that there is a risk of collision between the spreader and the container.
[0151] Specifically, the distances of the eight spreaders relative to the edge of the container can be determined based on the maximum values of the adjacent containers and the maximum values of the spreaders, which are distance d1, distance d2, ..., and distance d8. For example, for d7, the point cloud data can be indexed back based on the external contour 2 of container 2 to determine the maximum value Y1 of container 2 in the longitudinal direction, and the point cloud data can be indexed back based on the external contour A of the spreader to determine the maximum value Y2 of the spreader in the longitudinal direction. d7 is determined based on the difference between Y1 and Y2. Since the difference between Y1 and Y2 is less than 0, it can be determined that the value of d7 is less than the preset distance threshold 0, so it can be determined that there is a risk of collision between the spreader and container 2.
[0152] It should be noted that in the positive direction of the coordinate axis (including the X-axis and the Y-axis), the distance between the container and the outer contour of the spreader can be calculated by subtracting the maximum value of the spreader from the maximum value of the container, that is, (d=Y1-Y2) or (d=X1-X2); in the negative direction, it is calculated by subtracting the maximum value of the container from the maximum value of the spreader, that is, (d=Y2-Y1) or (d=X2-X1). If the result is a negative value, it means that the spreader has exceeded the boundary of the container.
[0153] In an embodiment of the present application, target point cloud data can be acquired through multiple laser radars under the yard bridge trolley, and the spreader point cloud data can be obtained by intercepting according to the reference height. The target point cloud data is vertically projected to generate a binary map of the target area, and the adjacent areas are divided according to the plane size of the container. Edge detection is performed on the containers in the adjacent areas to obtain the external contour, and the spreader point cloud data is projected and edge detected to obtain the external contour of the spreader. If the distance between the external contour of the container and the spreader is less than a preset threshold, it is determined that there is a collision risk. In the above process, by acquiring and processing the target point cloud data and the spreader point cloud data, the relative position between the spreader and the container can be quickly detected, the potential collision risk can be identified in time, and the safety and efficiency of the operation can be improved.
[0154] Fig.11 This is a flow chart of the third embodiment of the method for identifying the collision of the lifting equipment provided by this application. Fig.11 On the basis of the above-mentioned second embodiment, the target point cloud data is obtained according to multiple laser radars pre-set under the field bridge trolley in step 601, and the specific implementation also includes the following steps:
[0155] S1101. The point cloud data acquired by each laser radar pre-installed under the field bridge trolley are spliced to obtain initial point cloud data.
[0156] S1102: extracting target point cloud data from the initial point cloud data according to the plane size of the target container, the center of the spreader, and a preset magnification ratio.
[0157] In this step, target point cloud data may be selected from the initial point cloud data according to the plane size of the target container, the center position of the spreader, and a preset magnification ratio.
[0158] In a specific implementation, the longitudinal and transverse dimensions of the target container can be determined according to the plane dimensions of the target container; the longitudinal and transverse dimensions are enlarged according to a preset enlargement ratio to obtain the target longitudinal and transverse dimensions; the center of the spreader is used as the symmetry center, and the target longitudinal and transverse dimensions are combined to extract the target point cloud data from the initial point cloud data.
[0159] Optionally, the preset magnification ratio can be adjusted according to actual needs, and the same or different magnification ratios can be set for the longitudinal and transverse dimensions. For example, the same magnification ratio can be set for both the longitudinal and transverse dimensions, such as 1.3; or different magnification ratios can be set for the longitudinal and transverse dimensions, for example, the magnification ratio of the longitudinal dimension is 1.3, and the magnification ratio of the transverse dimension is 1.2.
[0160] Through the preset magnification ratio, part of the adjacent containers (including adjacent containers and / or adjacent rows of containers) can be included in the target point cloud data range, thereby reducing unnecessary data processing; by selecting the center of the spreader as the symmetry center for magnification processing, the detection range can be evenly expanded and the consistency in all directions can be maintained to accommodate containers of different sizes.
[0161] For example, if the lifting and unloading task is to lift a 20-foot container, the longitudinal dimension of the target container can be determined to be 6m and the transverse dimension to be 2.5m. Then, the longitudinal dimension of 6m and the transverse dimension of 2.5m can be enlarged according to the preset enlargement ratio of 1.3 to obtain the target longitudinal dimension of 7.8m and the target transverse dimension of 3.2m. Then, the center of the spreader is used as the symmetry center, combined with the target longitudinal dimension of 7.8m and the target transverse dimension of 3.2m, the target point cloud data is extracted from the initial point cloud data. Among them, the target longitudinal dimension of 7.8 meters can be set to -3.85m to +3.85m in the direction of the large vehicle, and the target transverse dimension of 3.2 meters can be set to -1.6m to +1.6m in the direction of the yard bridge trolley.
[0162] In the embodiment of the present application, the point cloud data obtained by each laser radar pre-set under the yard crane trolley can be spliced to obtain initial point cloud data. Then, according to the plane size of the target container, the center position of the spreader, and the preset magnification ratio, the target point cloud data is extracted from the initial point cloud data. In the above process, by extracting the target point cloud data, unnecessary data processing can be reduced, thereby optimizing the use of computing resources and improving efficiency.
[0163] Furthermore, the method for identifying spreader collision provided in the embodiment of the present application can extract target point cloud data according to the size of the target container, the spreader center and the magnification ratio, so that it can flexibly adapt to containers of different sizes and shapes, thereby improving operational flexibility.
[0164] Fig.12 This is a flow chart of the fourth embodiment of the method for identifying the collision of the lifting equipment provided by this application. Fig.12 Based on the above-mentioned embodiment 2 or embodiment 3, before acquiring the target point cloud data according to the multiple laser radars pre-set under the yard bridge trolley in step 601, the method for identifying the spreader collision also includes:
[0165] S1201. Perform time synchronization processing on multiple laser radars.
[0166] In this step, time synchronization processing can be performed on multiple laser radars pre-installed under the field bridge trolley to ensure that the multiple laser radars can work together and provide consistent point cloud data.
[0167] In a specific implementation, the clock sources of multiple laser radars can be synchronized to a GPS clock. The GPS clock timing can provide a high-precision time signal, so that each laser radar can operate under the same time reference.
[0168] Optionally, the data collection interval of the lidar can be controlled within a preset time range, such as 10 milliseconds, to ensure the synchronization and consistency of the data.
[0169] S1202. Based on the coordinate system of the sling, perform spatial synchronization processing on the coordinate system of each laser radar.
[0170] In this step, in order to improve the accuracy and consistency of point cloud data fusion, the coordinate system of each lidar can be aligned with the coordinate system of the spreader to achieve spatial synchronization.
[0171] In an optional embodiment, each laser radar can be calibrated with external parameters to determine the rotation and translation relationship of its coordinate system relative to the coordinate system of the sling. The external parameter calibration process can be performed by placing a calibration plate in the field of view of the laser radar. First, the point cloud data of the calibration plate is collected and the feature points on it are identified. Then, these feature points are used to calculate the rotation and translation matrix of the laser radar coordinate system relative to the sling coordinate system, thereby realizing the coordinate system conversion and alignment of the two.
[0172] For example, the coordinate system of the laser radar can be converted to the coordinate system of the sling by the following formula.
[0173]
[0174] in, is the rotation and translation matrix, is the laser radar coordinate system, is the coordinate system of the spreader. Optionally, the center of the spreader can be selected as the origin of the coordinate system of the spreader.
[0175] In an embodiment of the present application, by performing time and space synchronization processing on multiple lidars, the consistency and accuracy of point cloud data collection can be guaranteed, and the fusion effect of multi-sensor data can be enhanced, which helps to generate more accurate environmental information, thereby further improving the safety and efficiency of lifting and unloading operations.
[0176] Fig.13 For a structural diagram of the first embodiment of the device for identifying a sling collision provided by this application, see Fig.13 The device 10 for identifying a spreader collision provided in this embodiment includes:
[0177] An acquisition module 11 is used to acquire target point cloud data of a target area and spreader point cloud data of a spreader, wherein the target area includes the spreader, a target container, a lifting and unloading area of the target container, and a container area adjacent to the lifting and unloading area, and the target container is a container to be unloaded or a container to be lifted and loaded;
[0178] A first processing module 12 is used to determine the outer contour of the container placed in the container area adjacent to the lifting and unloading area according to the target point cloud data;
[0179] A second processing module 13 is used to determine the outer contour of the spreader according to the spreader point cloud data;
[0180] The determination module 14 is configured to determine that there is a collision risk with the spreader if the distance between the outer contour of the container and the outer contour of the spreader is less than a preset distance threshold.
[0181] The device for identifying sling collision provided in the embodiment of the present application can execute the technical solution shown in the above method embodiment, and its implementation principle and beneficial effects are similar, which will not be repeated here.
[0182] In a possible implementation manner, the acquisition module 11 is specifically configured to:
[0183] The target point cloud data is obtained according to a plurality of laser radars pre-installed under the field bridge trolley;
[0184] The target point cloud data is intercepted at a height according to a reference height to obtain the spreader point cloud data, wherein the reference height is determined by adding a safety distance margin on the basis of the height between the upper surface of the target container and the ground.
[0185] In a possible implementation manner, the acquisition module 11 is specifically configured to:
[0186] The point cloud data acquired by each laser radar pre-installed under the field bridge trolley are spliced to obtain initial point cloud data;
[0187] The target point cloud data is extracted from the initial point cloud data according to the plane size of the target container, the center of the spreader, and a preset magnification ratio, wherein the plane size includes the longitudinal size and the transverse size of the target container on a horizontal plane.
[0188] In a possible implementation manner, the acquisition module 11 is specifically configured to:
[0189] Determining the longitudinal size and the transverse size of the target container according to the plane size of the target container;
[0190] Enlarging the longitudinal size and the transverse size according to the preset enlargement ratio to obtain a target longitudinal size and a target transverse size;
[0191] The target point cloud data is extracted from the initial point cloud data by taking the center of the spreader as the center of symmetry and combining the target longitudinal dimension and the target transverse dimension.
[0192] In a possible implementation manner, the first processing module 12 is specifically configured to:
[0193] Performing projection processing on the target point cloud data in the vertical direction to obtain a binary image of the target area;
[0194] According to the plane size of the target container, the binary image of the target area is divided into adjacent areas, wherein the adjacent areas include adjacent container areas and / or adjacent row container areas;
[0195] Perform edge detection on the container in the adjacent area to obtain the outer contour of the container.
[0196] In a possible implementation manner, the second processing module 13 is specifically configured to:
[0197] Performing projection processing on the spreader point cloud data in the vertical direction to obtain a binary image of the spreader;
[0198] Edge detection is performed on the binary image of the spreader to obtain the outer contour of the spreader.
[0199] Fig.14 This is a schematic diagram of the structure of the second embodiment of the device for identifying the collision of the sling provided in this application. Fig.13 Based on the examples shown, see Fig.14 The device 10 for identifying a spreader collision provided in this embodiment further includes:
[0200] A third processing module 15 is used to perform time synchronization processing on the multiple laser radars;
[0201] The third processing module 15 is further used to perform spatial synchronization processing on the coordinate system of each laser radar based on the coordinate system of the sling.
[0202] The device for identifying sling collision provided in the embodiment of the present application can execute the technical solution shown in the above method embodiment, and its implementation principle and beneficial effects are similar, which will not be repeated here.
[0203] Fig.15 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Fig.15The electronic device 20 provided in the embodiment of the present application includes: at least one processor 21 and a memory 22. Optionally, the device 20 also includes a communication component 23. The processor 21, the memory 22 and the communication component 23 are connected via a bus 24.
[0204] In a specific implementation process, at least one processor 21 executes the computer-executable instructions stored in the memory 22, so that at least one processor 21 executes the above method.
[0205] The specific implementation process of the processor 21 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.
[0206] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.
[0207] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.
[0208] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.
[0209] The present application also provides a field bridge, including a hoist, a field bridge trolley, a laser radar and Fig.15 The electronic device shown is used to implement the method for identifying the collision of the spreader in the above embodiment.
[0210] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.
[0211] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.
[0212] The above-mentioned 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 memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.
[0213] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium 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 be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.
[0214] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.
[0215] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0216] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0217] If the function is implemented in the form of 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 the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.
[0218] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.
[0219] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.
Claims
1. A method for identifying a spreader collision, characterized in that: include: Acquire target point cloud data of a target area and spreader point cloud data of a spreader, wherein the target area includes the spreader, a target container, a lifting and unloading area of the target container, and a container area adjacent to the lifting and unloading area, and the target container is a container to be unloaded or a container to be lifted and loaded; Determining, based on the target point cloud data, an outer contour of a container placed in a container area adjacent to the lifting and unloading area; Determining the outer contour of the spreader according to the spreader point cloud data; If the distance between the outer contour of the container and the outer contour of the spreader is less than a preset distance threshold, it is determined that there is a collision risk with the spreader.
2. The method according to claim 1, characterized in that The step of acquiring target point cloud data of the target area and spreader point cloud data of the spreader includes: The target point cloud data is obtained according to a plurality of laser radars pre-installed under the field bridge trolley; The target point cloud data is intercepted at a height according to a reference height to obtain the spreader point cloud data, wherein the reference height is determined by adding a safety distance margin on the basis of the height between the upper surface of the target container and the ground.
3. The method according to claim 2, characterized in that The target point cloud data is obtained according to a plurality of laser radars pre-arranged under the field bridge trolley, including: The point cloud data acquired by each laser radar pre-installed under the field bridge trolley are spliced to obtain initial point cloud data; The target point cloud data is extracted from the initial point cloud data according to the plane size of the target container, the center of the spreader, and a preset magnification ratio, wherein the plane size includes the longitudinal size and the transverse size of the target container on a horizontal plane.
4. The method according to claim 3, characterized in that The step of extracting the target point cloud data from the initial point cloud data according to the plane size of the target container, the center of the spreader, and a preset magnification ratio includes: Determining the longitudinal size and the transverse size of the target container according to the plane size of the target container; Enlarging the longitudinal size and the transverse size according to the preset enlargement ratio to obtain a target longitudinal size and a target transverse size; The target point cloud data is extracted from the initial point cloud data by taking the center of the spreader as the center of symmetry and combining the target longitudinal dimension and the target transverse dimension.
5. The method according to any one of claims 1 to 4, characterized in that: The step of determining the outer contour of a container placed in a container area adjacent to the lifting and unloading area according to the target point cloud data includes: Performing projection processing on the target point cloud data in the vertical direction to obtain a binary image of the target area; According to the plane size of the target container, the binary image of the target area is divided into adjacent areas, wherein the adjacent areas include adjacent container areas and / or adjacent row container areas; Perform edge detection on the container in the adjacent area to obtain the outer contour of the container.
6. The method according to any one of claims 1 to 4, characterized in that: Determining the outer contour of the spreader according to the spreader point cloud data includes: Performing projection processing on the spreader point cloud data in the vertical direction to obtain a binary image of the spreader; Edge detection is performed on the binary image of the spreader to obtain the outer contour of the spreader.
7. The method according to any one of claims 2 to 4, characterized in that: Before acquiring the target point cloud data of the target area and the spreader point cloud data of the spreader, the method further includes: Performing time synchronization processing on the multiple laser radars; Based on the coordinate system of the sling, the coordinate system of each laser radar is spatially synchronized.
8. An electronic device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 7.
9. A field bridge, characterized in that: It comprises a hoist, a field bridge trolley, a laser radar and the electronic equipment described in claim 8.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.