Container heap head type identification method, device and equipment and field bridge

Abstract

The invention provides a container heap head type identification method, apparatus and device, and a yard bridge. The method comprises the steps of obtaining container data under a top view angle of a container yard; determining a continuous container width according to the container data; and if the continuous container width is greater than the preset single container width, determining that the container heap head type is a dense heap type. By means of the mode, the system can automatically and accurately recognize the type of the heap head of the container, the automation degree of storage yard operation is improved, and the operation failure rate is reduced. By accurately judging the type of the pile head, the automation equipment can adjust the operation strategy according to the characteristics of the pile head, and the grabbing and releasing accuracy is improved.

Description

Technical Field

[0001] The present application relates to the technical field of container loading and unloading, and in particular to a method, device, equipment and yard crane for identifying the type of container stack. Background Art

[0002] The automatic container pick-and-place system is an important part of port automation. The automatic pick-and-place system can greatly improve the efficiency, accuracy and safety of port operations. On the one hand, it saves labor costs, and on the other hand, it reduces the risk of damage to containers during transportation.

[0003] Stack head recognition refers to analyzing and classifying the stacking structure of containers in the yard to determine the type of stack head at each stacking position, thereby providing important information for automatic grabbing and placing equipment. There may be multiple stacking methods in the container site. The existing technology uses the same grabbing and placing method for various stacking methods, generally without considering the stack head type of the container, which will cause the position of the gripper to deviate, reduce the automation process, and affect the safety of grabbing and placing.

[0004] Therefore, how to identify the type of container stack in the yard is an urgent problem to be solved. Summary of the invention

[0005] The method, device, equipment and yard crane for identifying the type of container stack provided in the present application are used to quickly identify the type of container stack in the yard, thereby guiding the grabbing and placing of the containers and improving the accuracy of the grabbing and placing.

[0006] In a first aspect, the present application provides a method for identifying a container stack type, the method comprising:

[0007] Obtain container data from the top perspective of the container yard;

[0008] determining a continuous container width based on the container data;

[0009] If the width of the continuous containers is greater than the preset width of a single container, the container stack type is determined to be a dense stack.

[0010] Optionally, the method further includes:

[0011] If the width of the continuous containers is less than or equal to the preset width of a single container, the container stack type is determined to be a general stack.

[0012] Optionally, if it is determined that the container stack type is a dense stack, the method further includes:

[0013] Determine the number of segments of continuous container width in the container width direction according to the container data;

[0014] If the number of segments is equal to 1, the pile head type is determined to be a single pile head in a dense pile;

[0015] If the number of segments is equal to 2, the pile head type is determined to be a double pile head in a dense pile;

[0016] If the number of segments is greater than 2, the pile head type is determined to be a multiple pile head in a dense pile.

[0017] Optionally, determining the continuous container width according to the container data includes:

[0018] Determine the outline of each container based on the container data;

[0019] If the width interval between any two container outlines is smaller than a preset value, it is determined that the any two container outlines are continuous container outlines;

[0020] The continuous container width is determined according to the continuous container profile.

[0021] Optionally, the container data is point cloud data, and determining the continuous container width according to the container data includes:

[0022] According to the point cloud data of the container, a continuous point cloud projection length in a preset direction is determined as the continuous container width.

[0023] Optionally, if it is determined that the container stack type is a dense stack, and the container data is point cloud data, the method further includes:

[0024] Constructing a coordinate system according to the point cloud data;

[0025] Determine the coordinate information of each container;

[0026] If the coordinate information of all containers conforms to the preset single stack arrangement mode, it is determined that the stack arrangement mode is a single stack in a dense stack.

[0027] Optionally, the method further includes:

[0028] Determine the grab and place control method corresponding to the stack type, wherein the grab and place control methods corresponding to different stack types have different container grab and place points;

[0029] Execute the grab and place control method.

[0030] In a second aspect, the present application provides a device for identifying a container stack type, the device comprising:

[0031] An acquisition module is used to acquire container data from the top perspective of the container yard;

[0032] A first determination module, configured to determine a continuous container width according to the container data;

[0033] The second determination module is used to determine that the container stack type is a dense stack if the width of the continuous containers is greater than the preset width of a single container.

[0034] In a third aspect, the present application provides an electronic device, including: a memory, a processor;

[0035] The memory stores computer-executable instructions;

[0036] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.

[0037] In a fourth aspect, the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the above first aspect and / or various possible implementations of the first aspect.

[0038] In a fifth aspect, the present application provides a field bridge, comprising a controller, wherein the controller is used to execute the above first aspect and / or various possible implementations of the first aspect.

[0039] In a sixth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above first aspect and / or various possible implementations of the first aspect.

[0040] The present application provides a method, device, equipment and yard crane for identifying the type of container pile head. The method includes: obtaining container data from the top perspective of the container yard; determining the continuous container width based on the container data; if the continuous container width is greater than the preset single container width, determining the container pile head type as a dense pile. In this way, the system can automatically and accurately identify the type of container pile head, improve the automation level of yard operations, and reduce the operational failure rate. By accurately judging the pile head type, the automation equipment can adjust the operation strategy according to the characteristics of the pile head and improve the accuracy of grabbing and releasing. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] 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.

[0042] Figure 1 A schematic diagram of a general pile provided for this application;

[0043] Figure 2 A schematic diagram of a double pile head in a dense pile provided by this application;

[0044] Figure 3A schematic diagram of the flow of the method for identifying the container stack type provided in this application;

[0045] Figure 4 A schematic diagram of a catch and release provided for this application;

[0046] Figure 5 Schematic diagram of the type of pile head provided for this application;

[0047] Figure 6 A schematic diagram of the process of identifying the type of pile head provided for this application;

[0048] Figure 7 A schematic diagram of the point cloud of a general pile provided for this application;

[0049] Figure 8 A schematic diagram of the point cloud of multiple pile heads provided for this application;

[0050] Fig. 9 A schematic diagram of the structure of a device for identifying container stack types provided in this application;

[0051] Fig.10 A schematic diagram of the structure of the electronic device provided in this application.

[0052] 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

[0053] 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, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. 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.

[0054] First, the terms involved in this application are explained:

[0055] Standard stacking: It is usually a regular stacking method of containers with fixed spacing between containers, suitable for standard pick-and-place equipment operation. The automation system can perform pick-and-place tasks based on the simple stacking form of standard stacking, using fixed pick-and-place procedures and paths.

[0056] Single pile head: refers to the stacking of containers in a certain position and placing them together continuously. The automation system needs to identify such individually stacked containers and adopt different grabbing and releasing strategies to avoid grabbing and releasing failures or equipment damage.

[0057] Double stack: refers to the stacking area where there are two groups of containers stacked, each group of containers is stacked on top of each other, and the two groups of containers are not connected.

[0058] Under these different types of stacking heads, the automatic equipment's grasping and placing methods, grasping and placing forces, working angles, etc. will all be different. Without accurate stacking head type identification, the grasping and placing device may not be able to determine the structure of the stacking location, resulting in grasping and placing failures, improper operation, or equipment collisions.

[0059] In view of the above problems, the present application provides a method for identifying container stack types, which identifies the stack types of containers in the yard before grabbing and releasing the containers, distinguishes different stacks, and then controls the grabbing and releasing equipment to perform container grabbing and releasing operations.

[0060] 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.

[0061] Figure 1 The schematic diagram of the general pile provided for this application is as follows Figure 1 As shown, in the normal stacking mode, there is a gap between each container and the adjacent container. Each container position may have one or more containers stacked.

[0062] Figure 2 The schematic diagram of the double pile head in the dense pile provided by this application is Figure 2 In the stack, there are continuous containers stacked on the left and right sides. On each side, there is no gap between containers, and this type of stack is called a double stack. When the left and right sides are connected together and there is no gap between all containers, the stack type is a single stack. If the container is divided into three parts, it is a triple stack, or a multi-stack.

[0063] Figure 3 A flow chart of the method for identifying the type of container stack provided in this application is as follows: Figure 3 As shown, the following steps are included:

[0064] S101. Obtain container data from the top perspective of the container yard.

[0065] Sensors are installed on the spreader or trolley platform to obtain container data from the perspective below. Figure 4 A schematic diagram of a catch and place provided for this application, in Figure 4 In the example of a single pile head in a dense stack, a sensor is installed on the trolley frame to scan the container below and obtain the container data.

[0066] In one implementation, the sensor is a laser radar, and the laser radar can be a single-line laser radar or a multi-line laser radar. There can be multiple laser radars, so the acquired container data is point cloud data collected by the laser radar.

[0067] In one implementation, the sensor is a camera, and the camera may be a depth camera. Therefore, the acquired container data is image data.

[0068] S102: Determine the continuous container width according to the container data.

[0069] In this step, the outline of the container can be determined based on the container data, so the gap width between each container and the adjacent container in the container stacking direction can be determined. If the width is less than a preset value, the container is determined to be continuous. The continuous partial containers are taken as a whole to determine the continuous container width. The preset value can be set to 20cm, 30cm, 40cm, etc.

[0070] S103: If the width of the continuous containers is greater than the preset width of a single container, determine that the container stack type is a dense stack.

[0071] In this step, if the width of the continuous containers is greater than the preset width of a single container, it can be determined that the containers are stacked together and the stack type is a dense stack. Otherwise, it means that the containers are dispersedly arranged, and there is a gap between each container and each other, and it can be determined that it is a general stack.

[0072] The standard width of a container is 2.438 m. In actual applications, the width of a single container may be set to other values ​​in consideration of error factors.

[0073] If the container stack type is determined to be dense stacking, it can be determined whether it is a single stack, double stack or multiple stacks according to the number of continuous container segments. That is, one continuous container segment is determined as a single stack, two continuous containers are determined as double stacks, and three or more continuous containers are determined as multiple stacks.

[0074] The method for identifying the type of container stack provided in this embodiment includes: obtaining container data from the top perspective of the container yard; determining the continuous container width according to the container data; if the continuous container width is greater than the preset single container width, determining the container stack type as a dense stack. In this way, the system can automatically and accurately identify the type of container stack, improve the automation of yard operations, and reduce the operation failure rate.

[0075] By accurately determining the type of pile head, automated equipment (such as automatic stackers, automatic carts, etc.) can adjust the operation strategy according to the characteristics of the pile head (such as the type of dense pile). For example, dense pile areas require higher pick-and-place accuracy or a preset pick-and-place method that is different from general piles. Automated equipment can adjust the pick-and-place method according to the type of pile head to avoid misoperation and improve operation efficiency.

[0076] In densely stacked areas, containers are stacked closely together. If the identification is wrong (dense stacks are identified as ordinary stacks), the automated equipment may perform operations incorrectly, which may lead to failure of pick-and-place, and may also cause equipment collision or container damage. This solution can effectively distinguish between dense stacks and ordinary stacks, ensure that the pick-and-place equipment adopts appropriate strategies for operation, and reduce the risk of equipment damage and container damage caused by misoperation.

[0077] The following uses the point cloud data of the LiDAR and the images taken by the camera as examples to introduce how to identify the type of container stack.

[0078] Example 1

[0079] Figure 5 The schematic diagram of the stack type provided for this application shows different stack modes. In the heavy container mode, the containers are arranged in a general stack.

[0080] Figure 6 The schematic diagram of the process of pile head type identification provided for this application is as follows: Figure 6 The steps shown include:

[0081] S201, the vehicle approaches the target position.

[0082] At this time, the LiDAR scans and collects point cloud information of the containers in the yard. The point cloud data contains information such as the spatial distribution, location, size, and height of the containers.

[0083] S202, scanning the container contour information.

[0084] By processing the point cloud data scanned by the LiDAR, the point cloud information on the ground is first filtered out to ensure that the point cloud on the ground does not affect subsequent analysis. At the same time, the point cloud data outside the yard is filtered out to ensure that only the container data inside the yard is processed.

[0085] S203: Determine whether the pile head type is a dense pile according to the projection length of the point cloud.

[0086] The acquired container point cloud is projected onto a two-dimensional plane, which may be a plane perpendicular to the ground and along the width of the container. Then, the projected point cloud data is segmented, and the basis for segmentation is usually the interval between containers.

[0087] According to the point cloud data, the continuous point cloud projection length in the horizontal direction of the two-dimensional plane is determined and used as the continuous container width. Then, it is determined whether the continuous point cloud projection length is greater than the preset single container width. If so, it is determined to be a dense pile, otherwise it is a general pile.

[0088] For example, Figure 7 The point cloud diagram of the general pile provided for this application is Figure 7 In the above example, a coordinate system with the collection point as the origin is constructed. The horizontal axis is the horizontal arrangement distance of the containers, and the vertical axis is the height from the collection point. Figure 7 The point cloud data in the image is analyzed. Each horizontal line represents a container, and the location point or outline of the container can be determined. In this way, the distance between the outlines can be determined. The continuous points at the bottom represent the point cloud data of the ground, and the ground data is not considered in the analysis. Figure 7 In the figure, the projection length of the point cloud at position 1 (i.e. the horizontal length of the point cloud) is not connected to the projection length of the point cloud at position 2 (i.e. the horizontal length of the point cloud). The distance between the two is greater than the preset value. And positions 3, 4, 5, and 6 are also not connected. Therefore, it can be determined that the type of pile head in the yard is a general pile.

[0089] For example, Figure 8 The point cloud diagram of the multi-stack head provided for this application is Figure 8 In, construct and Figure 7 Similar coordinate system, analysis method is also the same Figure 7 Same, in Figure 8 It can be seen that there is no gap between the projection lengths of the point clouds at 1, 2, and 3, which are continuous. The overall continuous projection length is greater than the width of a container, and there are containers on the left and right sides, so it can be determined that there are multiple piles. If there are only two groups of containers in the yard, and each group is continuous, then this is a double pile.

[0090] When determining the projection length of the point cloud, it can be determined by the coordinates of the point cloud. Furthermore, the interval between each two containers can also be determined by the coordinate information of each container. If the difference between any adjacent coordinates in the preset single stack arrangement is greater than the preset value, it can be determined whether it is a single stack according to the coordinate information.

[0091] S204: Determine whether the stacking mode is a single stacking mode according to the location information of the container.

[0092] For areas identified as densely packed, the coordinate information of the containers can be used to distinguish between single-stack and double-stack areas. Figure 7 and Figure 8 It has been introduced in , so I won’t repeat it here.

[0093] By processing and classifying the point cloud data, the pile type information of the target bay is output, including whether it is a dense pile and whether it is a single pile or a double pile.

[0094] S205: Determine the pick-and-place control method corresponding to the pile head type.

[0095] The grab and place control methods corresponding to different pile head types are stored in advance, and the container positions to be grabbed and placed are different in different grab and place control methods.

[0096] For the general pile pick and place control method, you can rely on the preset standard layout to perform pick and place. The control method is usually simpler because the distribution of containers is known. The pick and place equipment will locate the pick and place points according to the planned path, usually these points are located at the top center or four corners of the container. When performing pick and place, the equipment will directly move along the set path, accurately reach the pick and place points, and then pick and place and transport. Since the general pile container position is fixed, the equipment has less path planning and motion adjustment, the pick and place efficiency is high, and the operation is simple and stable.

[0097] In the single stacking method, there are other containers around a container to interfere. Therefore, in the control method of the single stacking method, it is first necessary to scan the position of the container in real time through a sensor or a visual system to ensure the accuracy of the position. Prevent slight offsets from increasing the difficulty of grabbing and placing. According to the scanning results, the grabbing and placing points are automatically adjusted, and the top center of the container or other suitable grabbing and placing points are selected. It is also necessary to consider anti-collision measures based on the surrounding containers to prevent the grabbing and placing equipment from colliding with surrounding obstacles. Compared with the general stacking method, the entire grabbing and placing process is relatively complicated, and the equipment needs to adjust the path and action based on real-time feedback to ensure safety and accuracy.

[0098] For multiple stacks, the pick and place operation is the same as for single stacks, but the pick and place order may be different from that for single stacks. Pick and place each stack of containers in turn, or adjust the pick and place mode of the equipment to complete the pick and place of two groups of containers in parallel. The equipment's path planning will be optimized according to the gaps between containers to ensure smooth and safe pick and place.

[0099] S206: Execute the determined catch-and-release control method.

[0100] This example provides a solution for identifying the type of stack head by scanning the container stacking position information at the bay by single-line or multi-line radar, which can improve the automation level of general stacking and dense stacking, improve the safety of automation and reduce the failure rate.

[0101] The above example introduces the method of determining the type of pile head by point cloud data. The following introduces an image-based method to determine single pile, double pile and multiple piles.

[0102] First, obtain images or videos from the top perspective of the container through a camera or other image capture device (such as a laser scanner, stereo camera, depth camera, etc.).

[0103] The collected images are preprocessed, such as denoising, graying, contrast enhancement, etc. The purpose of preprocessing is to improve image quality and facilitate subsequent image analysis.

[0104] Pile head type feature extraction: extract the edges of stacked items through edge detection algorithms (such as Canny operator, Sobel operator, etc.). These edges can help identify the boundaries and contours of objects, thereby distinguishing different stacking areas.

[0105] In one approach, contours are extracted from the image, and the type of pile of stacked items is determined by analyzing the number, shape, and size of the contours. For example, if there is only one clear contour in the image, it may be a single pile; if there are two clear contours, it may be a double pile; if there are multiple contours or areas, it may be multiple piles.

[0106] In another approach, the color information is used to segment the image and determine the boundaries between different stacked objects. By converting the image to a color space (such as from RGB to HSV), the differences between different objects can be better distinguished.

[0107] Image segmentation algorithms (such as threshold-based segmentation, K-means clustering, region growing, etc.) are used to divide the stacking area. After segmentation, it is possible to determine whether it is a single pile, double pile, or multiple piles based on the shape and number of each area.

[0108] After dividing the image into different regions or contours, if only one obvious stacking region is detected in the image and there is no obvious segmentation or gap in the space, it can be determined as a single pile.

[0109] If two relatively independent stacking areas appear in the image, and there is an obvious interval or different stacking methods between the two areas, it can be determined as a double pile.

[0110] If multiple independent stacking areas are detected in the image, and the width of each of these areas is equal to the error range of a container width, it is determined to be a general stack; otherwise, it is determined to be a single stack.

[0111] Optionally, a CNN model can be used for object detection and classification. By training a deep learning model to recognize different types of piles in an image, the model can automatically learn the characteristics of single piles, double piles, and multiple piles and classify them.

[0112] Optionally, using an instance segmentation algorithm, each stacking area in the image can be accurately segmented and labeled, thereby more accurately identifying single piles, double piles and multiple piles.

[0113] By labeling the image data of different types of pile heads, we train the deep learning model so that the model can automatically identify and classify the pile head types. After the model training is completed, we need to use the test set to evaluate its accuracy and robustness.

[0114] Through the above-mentioned image processing method, the type of the pile head can also be identified, and then the corresponding pick-and-place control method of the pile head can be determined.

[0115] Fig. 9 A schematic diagram of the structure of the device for identifying the type of container stack provided in this application, such as Fig. 9 As shown, the container stack type identification device 90 provided in this embodiment includes:

[0116] An acquisition module 901 is used to acquire container data from the top perspective of the container yard;

[0117] A first determination module 902, configured to determine a continuous container width according to the container data;

[0118] The second determination module 903 is configured to determine that the container stack type is a dense stack if the width of the continuous containers is greater than the preset width of a single container.

[0119] Optionally, the second determining module 903 is used to:

[0120] If the width of the continuous containers is less than or equal to the preset width of a single container, the container stack type is determined to be a general stack.

[0121] Optionally, if it is determined that the container stack type is a dense stack, the second determining module 903 is further configured to:

[0122] Determine the number of segments of continuous container width in the container width direction according to the container data;

[0123] If the number of segments is equal to 1, the pile head type is determined to be a single pile head in a dense pile;

[0124] If the number of segments is equal to 2, the pile head type is determined to be a double pile head in a dense pile;

[0125] If the number of segments is greater than 2, the pile head type is determined to be a multiple pile head in a dense pile.

[0126] Optionally, the first determining module 902 is further configured to:

[0127] Determine the outline of each container based on the container data;

[0128] If the width interval between any two container outlines is smaller than a preset value, it is determined that the any two container outlines are continuous container outlines;

[0129] The continuous container width is determined according to the continuous container profile.

[0130] Optionally, the container data is point cloud data, and the first determining module 902 is further used to:

[0131] According to the point cloud data of the container, a continuous point cloud projection length in a preset direction is determined as the continuous container width.

[0132] Optionally, if it is determined that the container stack type is a dense stack, and the container data is point cloud data, the second determination module 903 is further used to:

[0133] Constructing a coordinate system according to the point cloud data;

[0134] Determine the coordinate information of each container;

[0135] If the coordinate information of all containers conforms to the preset single stack arrangement mode, it is determined that the stack arrangement mode is a single stack in a dense stack.

[0136] Optionally, the device further includes: an execution module 904, specifically configured to:

[0137] Determine the grab and place control method corresponding to the stack type, wherein the grab and place control methods corresponding to different stack types have different container grab and place points;

[0138] Execute the grab and place control method.

[0139] The device for identifying the type of container stack provided in this embodiment can execute the method provided in the above method embodiment, and its implementation principle and technical effect are similar, which will not be described in detail in this embodiment.

[0140] Fig.10 This is a schematic diagram of the structure of the electronic device provided in this application. The electronic device can be a controller of the field bridge or a controller attached to the field bridge. Fig.10 As shown, the electronic device 50 provided in this embodiment includes: at least one processor 501 and a memory 502. Optionally, the device 50 also includes a communication component 503. The processor 501, the memory 502 and the communication component 503 are connected via a bus 504.

[0141] In a specific implementation process, at least one processor 501 executes the computer-executable instructions stored in the memory 502, so that at least one processor 501 executes the above method.

[0142] The specific implementation process of the processor 501 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.

[0143] 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 (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the invention can be directly implemented as a hardware processor, or can be implemented by a combination of hardware and software modules in the processor.

[0144] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (NVM), such as at least one disk storage.

[0145] 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. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of this application is not limited to only one bus or one type of bus.

[0146] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0147] 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.

[0148] The present application also provides a yard crane, which includes a controller, a sensor, a lifting system, a driving system, etc. The sensor is used to collect container data from the top perspective of the container yard, and the controller is used to implement the method in the above embodiment.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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 container stack type, characterized in that: The method comprises: Obtain container data from the top perspective of the container yard; determining a continuous container width based on the container data; If the width of the continuous containers is greater than the preset width of a single container, the container stack type is determined to be a dense stack.

2. The method according to claim 1, characterized in that The method further comprises: If the width of the continuous containers is less than or equal to the preset width of a single container, the container stack type is determined to be a general stack.

3. The method according to claim 1, characterized in that: If it is determined that the container stack type is a dense stack, the method further includes: Determine the number of segments of continuous container width in the container width direction according to the container data; If the number of segments is equal to 1, the pile head type is determined to be a single pile head in a dense pile; If the number of segments is equal to 2, the pile head type is determined to be a double pile head in a dense pile; If the number of segments is greater than 2, the pile head type is determined to be a multiple pile head in a dense pile.

4. The method according to any one of claims 1 to 3, characterized in that: The determining of the continuous container width according to the container data comprises: Determine the outline of each container based on the container data; If the width interval between any two container outlines is smaller than a preset value, it is determined that the any two container outlines are continuous container outlines; The continuous container width is determined according to the continuous container profile.

5. The method according to claim 4, characterized in that The container data is point cloud data, and determining the continuous container width according to the container data includes: According to the point cloud data of the container, a continuous point cloud projection length in a preset direction is determined as the continuous container width.

6. The method according to claim 1, characterized in that If it is determined that the container stack type is a dense stack, and the container data is point cloud data, the method further includes: Constructing a coordinate system according to the point cloud data; Determine the coordinate information of each container; If the coordinate information of all containers conforms to the preset single stack arrangement mode, it is determined that the stack arrangement mode is a single stack in a dense stack.

7. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: Determine the grab and place control method corresponding to the stack type, wherein the grab and place control methods corresponding to different stack types have different container grab and place points; Execute the grab and place control method.

8. A device for identifying container stack type, characterized in that: The device comprises: An acquisition module is used to acquire container data from the top perspective of the container yard; A first determination module, configured to determine a continuous container width according to the container data; The second determination module is used to determine that the container stack type is a dense stack if the width of the continuous containers is greater than the preset width of a single container.

9. 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.

10. A field bridge, characterized in that: The method comprises a controller, wherein the controller is used to execute the method according to any one of claims 1 to 7.

Images