Method, device and equipment for identifying high and low containers in container truck

Abstract

The embodiment of the invention provides a method, a device and equipment for identifying high and low containers in a container truck. The method comprises the following steps: in response to a double-container packaging operation request, acquiring a top surface image data set obtained by performing image acquisition on the top surface of a to-be-grabbed target container by cameras deployed at at least two different positions, the double-container packaging operation request is used for grabbing a first container and a second container close to the first container on a container truck by the lifting appliance, and the height of the first container is larger than that of the second container; performing feature analysis on the top surface image data set, and identifying whether the target container has a high container identifier; if the target container has the high container identifier, determining that the target container to be grabbed by the lifting appliance is a first container; and if the target container does not have the high container identifier, determining that the target container to be grabbed by the lifting appliance is a second container. The method is used for achieving the effect of improving the accuracy and efficiency of identifying the high and low containers in the container truck.

Description

Technical Field

[0001] This application relates to the field of container technology, and in particular to a method, apparatus and equipment for identifying high and low containers in container trucks. Background Technology

[0002] With the increasing automation of ports, the demand for intelligent container handling operations is becoming increasingly urgent. In port yards, container trucks often need to stack two 20-foot containers on the same lane side, i.e., loading and unloading two 20-foot containers simultaneously. Since there are two types of containers, namely standard containers (also known as low-cube containers or flat containers) and high-cube containers, if the height difference between containers during operation is not accurately identified, the spreader may collide with the low-cube container during lifting, causing damage to electronic equipment such as cameras and sensors, and even leading to equipment downtime, safety accidents, and economic losses.

[0003] In existing technologies, container type identification is mainly achieved through manual identification, laser scanners, or camera identification. However, existing methods have limitations such as low efficiency, high cost, and poor reliability, resulting in low accuracy and low efficiency in identifying high and low containers in container trucks.

[0004] Therefore, there is an urgent need for a solution that can improve the accuracy and efficiency of identifying high and low containers in container trucks. Summary of the Invention

[0005] The high-low container identification method, apparatus, and equipment provided in this application are used to improve the accuracy and efficiency of identifying high-low containers in container trucks.

[0006] In a first aspect, embodiments of this application provide a method for identifying high and low containers in a container truck, including:

[0007] In response to a dual container loading operation request, the top surface of the target container to be grabbed by the spreader is captured by cameras deployed at at least two different locations. The resulting top surface image dataset is used for the spreader to grab the first container on the container truck and the second container that is close to the first container. The height of the first container is greater than the height of the second container.

[0008] Feature analysis is performed on the top surface image dataset to identify whether the target container has a high-cube marking.

[0009] If the target container has a high cube container marking, then the target container to be grabbed by the spreader is determined to be the first container;

[0010] If the target container does not have a high cube container marking, then the target container to be grabbed by the spreader is determined to be the second container.

[0011] In an optional example, the method also includes:

[0012] If the target container to be grabbed by the spreader is the second container, and the first container on the container truck has not been grabbed, the spreader should be controlled to stop the grabbing action and issue a warning.

[0013] In an optional example, the method also includes:

[0014] At least one camera is deployed at at least one location on the short side, long side, or at at least one of the four corners of the spreader; wherein the spreader is used to grab and move containers.

[0015] In an optional example, the method also includes:

[0016] At least one camera shall be deployed above the lane for container trucks; where above the lane refers to the area above the lane in which the container trucks travel.

[0017] In an optional example, the method also includes:

[0018] At least one camera shall be deployed on the outriggers or saddles of the gantry crane. The outriggers or saddles refer to the supporting structures of the gantry crane traveling mechanism of the yard crane or quay crane in the container yard.

[0019] In an optional example, feature analysis is performed on the top surface image dataset to identify whether the target container has a high-cube marking, including:

[0020] Obtain a marker recognition model, which is trained based on the image training set of the first container and / or the image training set of the second container;

[0021] Based on the marker recognition model, feature analysis is performed on each top surface image in the top surface image dataset to determine whether there is a target top surface image, which includes high box marker information;

[0022] If a top view image of the target exists, it is determined that the target container has a high-cube marking.

[0023] If no top view image of the target is available, it is determined that the target container does not have a high-cube marking.

[0024] In an optional example, based on a marker recognition model, feature analysis is performed on each top-surface image in the top-surface image dataset to determine whether a target top-surface image exists, including:

[0025] Based on the marker recognition model, detect whether each top surface image contains at least one of the edge features, texture features, and color features of the high box marker;

[0026] If the top surface image contains at least one of edge features, texture features, and color features, then the top surface image is determined to be the target top surface image.

[0027] In an optional example, the method also includes:

[0028] The spreader is controlled to grab the first container before grabbing the second container from the container truck.

[0029] Secondly, embodiments of this application provide a container truck high / low container identification device, comprising:

[0030] The response module is used to respond to a dual container loading operation request by acquiring images of the top surface of the target container to be grabbed by the spreader from cameras deployed at at least two different locations. The resulting top surface image dataset is used for the spreader to grab the first container on the container truck and the second container that is close to the first container. The height of the first container is greater than the height of the second container.

[0031] The recognition module is used to perform feature analysis on the top surface image dataset to identify whether the target container has a high-cube marking.

[0032] The first processing module is used to determine the target container to be grabbed by the spreader as the first container if the target container has a high-cube mark.

[0033] The second processing module is used to determine that the target container to be grabbed by the spreader is the second container if the target container does not have a high cube container marking.

[0034] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0035] The memory stores instructions that the computer executes;

[0036] The processor executes computer execution instructions stored in memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0037] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0038] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0039] The method, apparatus, and equipment for identifying high and low containers in container trucks provided in this application, in response to a dual-container loading operation request, acquire images of the top surface of the target container to be grabbed by the spreader from cameras deployed at at least two different locations, obtaining a top surface image dataset. Further, feature analysis is performed on the top surface image dataset to identify whether the target container has a high container marking. If the target container has a high container marking, the target container to be grabbed by the spreader is determined to be the first container; if the target container does not have a high container marking, the target container to be grabbed by the spreader is determined to be the second container. The dual-container loading operation request is used for the spreader to grab the first container on the container truck and the second container adjacent to the first container, where the height of the first container is greater than the height of the second container. This method, by deploying cameras at multiple different locations, achieves multi-angle acquisition of images of the container top surface, thereby comprehensively covering the characteristic areas of the target container, ensuring the integrity and accuracy of the image data. By performing feature analysis on the acquired image data, high container markings can be quickly and accurately identified, effectively improving the accuracy and efficiency of identifying high and low containers in container trucks. This method improves the accuracy and efficiency of identifying high and low containers in container trucks. Attached Figure Description

[0040] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0041] Figure 1 A schematic diagram illustrating the container loading and unloading operation scenario provided in this application;

[0042] Figure 2 Flowchart of the method for identifying high and low containers in container trucks provided in this application Figure 1 ;

[0043] Figure 3 Flowchart of the method for identifying high and low containers in container trucks provided in this application Figure 2 ;

[0044] Figure 4 Schematic diagram of the camera deployment scenario provided in this application Figure 1 ;

[0045] Figure 5 Schematic diagram of the camera deployment scenario provided in this application Figure 2 ;

[0046] Figure 6 A schematic diagram of the high and low container identification device for container trucks provided in this application;

[0047] Figure 7 A schematic diagram of the structure of the electronic device provided in this application.

[0048] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0049] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0050] First, let me explain the terms used in this application:

[0051] Containers are large cargo containers with certain strength, rigidity, and specifications. Containers typically have standardized dimensions and structures, facilitating rapid loading, unloading, and transshipment between different modes of transport. For example, container types include standard containers (also known as low-cube containers) and high cube containers.

[0052] Double 20-foot container: refers to two 20-foot standard-length containers involved in the same operation, but with different heights.

[0053] Container trucks: These are heavy-duty trucks specifically designed for transporting containers.

[0054] With the increasing automation of ports, the demand for intelligent container handling operations is becoming increasingly urgent. In port yards, container trucks often need to stack two 20-foot containers on the same lane side, i.e., loading and unloading two 20-foot containers simultaneously. Since there are two types of containers, namely standard containers (also known as low-cube containers or flat containers) and high-cube containers, if the height difference between containers during operation is not accurately identified, the spreader may collide with the low-cube container during lifting, causing damage to electronic equipment such as cameras and sensors, and even leading to equipment downtime, safety accidents, and economic losses.

[0055] For ease of understanding, Figure 1 This application provides a schematic diagram of a container loading and unloading operation scenario, such as... Figure 1 As shown, this scenario includes: container trucks, high-cube containers, standard containers (also known as low-cube containers), and spreaders.

[0056] Specifically, the container truck is loaded with two containers (high-cube and low-cube) and waits for loading and unloading operations on the side of the lane. To achieve automated operation, cameras are installed on the spreader for remote identification and monitoring, so that the spreader can grab the container from the truck and stack or load and unload it.

[0057] Since two containers are usually placed side-by-side with a small gap between them, if the spreader prioritizes grabbing the shorter, standard container, it can easily touch the taller container, causing damage. Simultaneously, it can also cause the spreader to collide with the shorter container, damaging related equipment and potentially leading to a safety accident. Specifically, when the spreader operates on the shorter container first, components such as cameras located below the spreader are prone to hitting the adjacent taller container, or colliding due to improper height control during the operation, resulting in damage to these components.

[0058] Therefore, it is necessary to accurately identify high-profile and low-profile containers in container trucks, so as to grab the high-profile containers first and then the regular containers, thereby ensuring operational safety.

[0059] Based on the above scenarios, it can be seen that in the existing technology, the identification of container types is mainly achieved through manual identification, laser scanners or camera identification, etc. However, the existing technology has limitations such as low efficiency, high cost and poor reliability, resulting in low accuracy and low efficiency in identifying high and low containers in container trucks.

[0060] Specifically, in existing technologies, driver's eye recognition of the height adjustment box is easily affected by factors such as fatigue, lighting, and obstructed vision, leading to recognition errors. Installing a laser scanner on the lane side for detection requires high precision and multi-line laser scanners due to the relatively narrow space available on the lane side, resulting in high costs. Installing a camera on the main beam on the lane side to recognize standard codes (ISO codes) also has limitations due to the narrow space available on the lane side, requiring a suitable installation angle, and ISO codes can be obstructed or damaged, making them unrecognizable.

[0061] Therefore, there is an urgent need for a solution that can improve the accuracy and efficiency of identifying high and low containers in container trucks.

[0062] The method of this application achieves multi-angle image acquisition of the top surface of the container by deploying cameras at multiple different locations, thereby comprehensively covering the characteristic areas of the target container and ensuring the integrity and accuracy of the image data. By performing feature analysis on the acquired image data, it can quickly and accurately identify high-top container markings, effectively improving the accuracy and efficiency of identifying high-top and low-top containers in container trucks. The method of this application improves the accuracy and efficiency of identifying high-top and low-top containers in container trucks.

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

[0064] Figure 2 Flowchart of the method for identifying high and low containers in container trucks provided in this application Figure 1 ,like Figure 2 As shown, the method includes:

[0065] S201. In response to a dual container loading operation request, acquire images of the top surface of the target container to be grabbed by the spreader from cameras deployed at at least two different locations, and obtain a top surface image dataset. The dual container loading operation request is used for the spreader to grab the first container on the container truck and the second container that is close to the first container. The height of the first container is greater than the height of the second container.

[0066] S202. Perform feature analysis on the top surface image dataset to identify whether the target container has a high-cube marking.

[0067] S203. If the target container has a high-cube marking, then the target container to be grabbed by the spreader is determined to be the first container.

[0068] S204. If the target container does not have a high cube container marking, then the target container to be grabbed by the spreader is determined to be the second container.

[0069] The subject of this application may be an equipment control system (ECS) or other related equipment.

[0070] In step S201, the dual container handling request can refer to a task instruction issued by the Terminal Operating System (TOS) or other related equipment, which instructs the spreader to handle two adjacent containers simultaneously, one of which is a high cube container and the other is a standard container (low cube container). For example, the request includes parameters such as the operation type and the operation objective.

[0071] For example, when the executing entity of this application receives a request for a double container loading operation, it automatically triggers a camera acquisition process to acquire images of the top surface of the target container to be grabbed by the spreader from cameras deployed at least two different locations, resulting in a top surface image dataset.

[0072] Cameras are deployed in at least two locations, which may include, but are not limited to, the short side, long side, or four corners of the spreader, as well as above the driveway or on the outriggers / saddles of the trolley. It is understood that the choice of camera deployment locations aims to ensure comprehensive coverage of the top surface of the target container from different angles, thereby obtaining more complete and accurate image data. For example, a camera on the spreader can capture close-up details of the container's top surface, while a camera above the driveway can provide a more macroscopic perspective, facilitating the identification of the container's overall features.

[0073] A top-view image dataset can refer to a collection of image data acquired by cameras at multiple different locations for subsequent feature analysis.

[0074] The first container can refer to the taller container in a pair of containers, and the second container can refer to the shorter container in a pair of containers. That is, the height of the first container is greater than that of the second container, and at the same time, the first container and the second container are similar in length and width.

[0075] For example, a double container is a double 20-foot container, both of which are 20 feet in length. Specifically, the two containers in a double 20-foot container are both about 6.06 meters long and about 2.44 meters wide, but their heights differ.

[0076] For example, the first container may refer to a high cube container with a height of 9 feet 6 inches (about 2.9 meters), while the second container may refer to a standard container (or low cube container) with a height of 8 feet 6 inches (about 2.59 meters).

[0077] It should be noted that the 20-inch length of the double container is just an example. The length and width of the double container can also be other sizes. There are no restrictions on the length and width of the double container, as long as the first and second containers in the double container are consistent in length and width.

[0078] In step S202, feature analysis is performed on the top surface image dataset. This can be achieved by using image processing algorithms or artificial intelligence (AI) vision technology to analyze the collected image data in order to identify whether the target container has a high-cube marking.

[0079] High cube container markings refer to specific markings or features placed on the top surface of a container to distinguish it from a low cube container. High cube container markings can be color-coded, shape-coded, etc. Color-coded markings can indicate that the top surface of the high cube container is painted with stripes or areas of a specific color; shape-coded markings can indicate that the top surface of the high cube container may have a unique geometric shape.

[0080] In one possible implementation, feature analysis can be performed as follows: First, the images in the acquired top-side image dataset are preprocessed (e.g., noise is removed by Gaussian filtering, and image contrast is enhanced by histogram equalization). Then, key information such as color markers and shape markers are extracted from the preprocessed images. For color markers, a pre-defined color segmentation algorithm can be used to identify regions of specific colors, and for shape markers, an edge detection algorithm can be used to identify the contours of specific geometric shapes. Finally, a pre-trained marker recognition model is used to analyze the key information to determine whether there are high-top container markers in the image. This model can be based on deep learning algorithms, such as Convolutional Neural Networks (CNNs), and trained on a large amount of labeled container image data to improve the accuracy and robustness of recognition.

[0081] It should be noted that the specific form of high-cube container markings can be designed and adjusted according to the actual application scenario. For example, in some ports, high-cube container markings may be a specific bar label; in other scenarios, high-cube container markings may be a special reflective material area. No specific limitations are placed on the specific form of high-cube container markings here.

[0082] In step S203, if the target container has a high-cube marking, then the target container to be grabbed by the spreader is determined to be the first container, which is the high-cube among the two containers on the container truck.

[0083] In step S204, if the target container does not have a high-cube designation, then the target container to be grabbed by the spreader is determined to be the second container, which is the low-cube of the two containers on the container truck.

[0084] The high-low container identification method for container trucks provided in this application achieves multi-angle image acquisition of the container top surface by deploying cameras at multiple different locations, thereby comprehensively covering the feature areas of the target container and ensuring the integrity and accuracy of the image data. By performing feature analysis on the acquired image data, it can quickly and accurately identify high-low container markings, effectively improving the accuracy and efficiency of identifying high-low containers in container trucks. The method of this application improves the accuracy and efficiency of identifying high-low containers in container trucks.

[0085] Figure 3 Flowchart of the method for identifying high and low containers in container trucks provided in this application Figure 2 ,like Figure 3 As shown, this embodiment, based on the aforementioned embodiments, provides a detailed description of the method for identifying high and low containers in container trucks. The method includes:

[0086] S301. In response to a dual container loading operation request, acquire images of the top surface of the target container to be grabbed by the spreader from cameras deployed at at least two different locations, and obtain a top surface image dataset. The dual container loading operation request is used for the spreader to grab the first container on the container truck and the second container that is close to the first container. The height of the first container is greater than the height of the second container.

[0087] In one alternative implementation, the deployment (or installation) of the camera may include:

[0088] At least one camera is deployed at at least one location on the short side, long side, or at at least one of the four corners of the spreader; wherein the spreader is used to grab and move containers.

[0089] Deploying cameras along the short side of the spreader allows for close-up capture of details on the container's top surface, effectively monitoring the top features of the target container, especially during spreader movement. Deploying cameras along the long side provides a wider field of view, covering a larger area of ​​the container's top surface, which helps identify the container's overall characteristics. Deploying cameras at the four corners of the spreader enables omnidirectional image acquisition, ensuring image data is obtained from multiple angles, thereby improving the accuracy and reliability of high-cube container identification.

[0090] It is understandable that, since the position and angle of the container under the spreader may change, the advantage of deploying at least one camera at at least one of the short side, long side, or four corners of the spreader is that it can ensure full coverage of the top surface of the target container from multiple angles, thereby obtaining more complete and accurate image data.

[0091] In one alternative implementation, based on the deployment of the cameras, it may further include:

[0092] At least one camera shall be deployed above the lane for container trucks; where above the lane refers to the area above the lane in which the container trucks travel.

[0093] Among them, the cameras above the lane can provide a macro view, covering the entire lane area, making it easier to identify the type and location of containers in advance.

[0094] For example, cameras can be deployed on beams or brackets above the lane to ensure that their field of vision covers the entire lane, including container trucks that are about to enter the work area.

[0095] It is understandable that container trucks may have positional deviations when entering the work area. By deploying at least one camera above the container truck lane, the beneficial effect of this setup is that the type and location of the container can be identified in advance, providing support for the precise grabbing of the spreader.

[0096] In one alternative implementation, based on the deployment of the cameras, it may further include:

[0097] At least one camera shall be deployed on the outriggers or saddles of the gantry crane. The outriggers or saddles refer to the supporting structures of the gantry crane traveling mechanism of the yard crane or quay crane in the container yard.

[0098] Among them, the cameras at the outriggers or saddles of the truck can provide a side view, making it easier to identify differences in container height.

[0099] It is understandable that, given the height difference between high-profile and low-profile containers, deploying at least one camera on the outriggers or saddle beams of the trolley has the advantage of accurately identifying the height difference of the containers from the side. At the same time, it can compensate for the blind spots of the spreader cameras, ensure the visibility of the markings on the top of the containers, and further improve the accuracy and reliability of identification.

[0100] For example, to facilitate understanding of camera deployment, Figure 4 Schematic diagram of the camera deployment scenario provided in this application Figure 1 , Figure 5 Schematic diagram of the camera deployment scenario provided in this application Figure 2 .

[0101] like Figure 4 As shown, taking a rubber-tyred container gantry crane (RTG) as an example, the camera can be installed on the spreader (specifically on the short side, long side, or four corners of the spreader), above the truck lane, or near the outriggers or saddle beam of the trolley.

[0102] like Figure 5 As shown, taking a rail-mounted gantry crane (RMG) as an example, the camera can be installed on the spreader (specifically on the short side, long side, or four corners of the spreader), above the truck lane, or near the outriggers or saddle beam of the trolley.

[0103] S302. Obtain the identification model, which is trained based on the image training set of the first container and / or the image training set of the second container.

[0104] The identification model can be a deep learning model, such as a convolutional neural network, which can automatically learn the high-top container identification in images of container top surfaces.

[0105] In one possible implementation, the training steps for the identifier recognition model can be:

[0106] Obtain the image training set of the first container and / or the image training set of the second container as the target training set; wherein, the image training set includes the top surface image of the container and the corresponding annotation information; input the target training set into the initial deep learning model for training and adjust the model parameters of the initial deep learning model; if the deep learning model after parameter adjustment meets the preset training completion conditions (e.g., loss function convergence), then the object recognition model is obtained.

[0107] It is understandable that training with a large number of labeled top surface images can improve the training efficiency and recognition accuracy of the model.

[0108] S303. Based on the marker recognition model, perform feature analysis on each top surface image in the top surface image dataset to determine whether there is a target top surface image, which includes high box marker information.

[0109] Feature analysis refers to using a trained sign recognition model to process the collected image data, extract feature information from the image, and determine whether there are high box signs.

[0110] It is understandable that feature analysis can extract key features of the high-box signage from the collected image data, providing a basis for subsequent identification and judgment steps.

[0111] In one alternative implementation, step S303 may include:

[0112] S3031. Based on the marker recognition model, detect whether each top surface image contains at least one of the edge features, texture features, and color features of the high box marker;

[0113] S3032. If the top surface image contains at least one of edge features, texture features, and color features, then the top surface image is determined to be the target top surface image.

[0114] Among them, edge features can refer to the outline or boundary of the high cube marking on the top of the container, such as the rectangle of the high cube marking.

[0115] Texture features can refer to the surface texture or pattern of the high cube markings on the top of a container, such as special patterns on the high cube markings.

[0116] Color features can refer to specific colors or color combinations used for high cube markings on the top of a container, such as the yellow and black color markings on a high cube marking.

[0117] It is understandable that if the top surface image contains at least one of edge features, texture features, and color features, then the top surface image can be determined to be the target top surface image; if these features are not present, then the top surface image can be determined not to be the target top surface image.

[0118] It is understandable that judging by extracting the edge, texture, or color features of high-cube markings has the following benefits: in scenarios where the container top surface is dirty, the marking recognition model avoids recognition failure due to missing ISO codes by enhancing the extraction of edge features; under low light conditions, the marking recognition model compensates for the weakening of edge features by enhancing the extraction of color features.

[0119] S304. If a top view image of the target exists, then it is determined that the target container has a high-cube marking.

[0120] It is understandable that after confirming the existence of a target top surface image containing a high-cube mark through feature analysis, the conclusion that the target container is a high-cube can be accurately drawn, thereby enabling corresponding operation scheduling and handling. This ensures that the spreader can correctly identify and prioritize the handling of high-cube containers, avoiding collisions or damage during stacking or handling.

[0121] It is understandable that the top surface image dataset includes multiple top surface images. As long as there is an image containing the high-top container label, it can be determined that the target container has the high-top container label. By deploying at least two cameras, the accuracy and efficiency of recognition can be improved.

[0122] S305. If no top view image of the target is available, then it is determined that the target container does not have a high-cube marking.

[0123] It is understandable that if no target top surface image is detected in any of the top surface images in the top surface image dataset, it can be determined that the target container does not have a high container identifier, and thus the target container is determined to be a low container.

[0124] It is understandable that by using a marker recognition model to perform feature analysis on each top surface image in the top surface image dataset, it is possible to determine whether a target top surface image exists, and thus determine whether the target container has a high cube marker. The beneficial effect of this setup is that it can automatically and accurately identify the type of container, thereby improving the efficiency and safety of port operations.

[0125] S306. If the target container to be grabbed by the spreader is the second container, and the first container on the container truck has not been grabbed, control the spreader to stop the grabbing action and issue a warning.

[0126] For example, early warnings can be implemented through audible and visual alarms, console prompts, or automatically sending warning messages to the operator's mobile device. Meanwhile, controlling the spreader to stop its gripping action can be implemented using a programmable logic controller (PLC).

[0127] It is understandable that by automatically triggering an early warning and stop mechanism when a high box is detected not being grabbed while a low box is about to be grabbed, the beneficial effect of this setting is that it can significantly improve the safety of the operation, prevent equipment damage and potential safety accidents caused by operational errors, and at the same time help maintain the smoothness and efficiency of the operation process.

[0128] S307. Control the spreader to grab the first container before grabbing the second container on the container truck.

[0129] For example, the executing entity of this application can automatically adjust the grabbing order of the spreader according to the recognition result. First, the spreader is controlled to move to the high box position for grabbing, and then it is moved to the low box position for grabbing.

[0130] It is understandable that by prioritizing the grabbing of high containers before low containers, the beneficial effects of this design are that it optimizes the work process, reduces operational risks caused by differences in container height, and also improves the accuracy and efficiency of operations, ensuring the smooth progress of port loading and unloading operations.

[0131] The method described in this application improves the accuracy and efficiency of identifying high and low containers in container trucks.

[0132] Figure 6 This is a structural schematic diagram of the container truck high / low container identification device provided in this application, as shown below. Figure 6 As shown, the container truck high and low container identification device 60 provided in this embodiment includes: a response module 601, an identification module 602, a first processing module 603, and a second processing module 604.

[0133] The response module 601 is used to respond to a double container loading operation request by acquiring images of the top surface of the target container to be grabbed by the spreader from cameras deployed at at least two different locations, and obtaining a top surface image dataset. The double container loading operation request is used for the spreader to grab the first container on the container truck and the second container that is close to the first container. The height of the first container is greater than the height of the second container.

[0134] The identification module 602 is used to perform feature analysis on the top surface image dataset to identify whether the target container has a high-cube marking.

[0135] The first processing module 603 is used to determine the target container to be grabbed by the spreader as the first container if the target container has a high-cube mark.

[0136] The second processing module 604 is used to determine that the target container to be grabbed by the spreader is the second container if the target container does not have a high cube container marking.

[0137] In an optional example, the container truck high / low container identification device 60 also includes a control module for controlling the spreader to stop the grabbing action and issue a warning when the target container to be grabbed by the spreader is the second container and the first container on the container truck has not been grabbed.

[0138] In an optional example, the container truck high / low container identification device 60 also includes a deployment module for deploying at least one camera at at least one location on the short side, long side, or four corners of the spreader; wherein the spreader is used to grab and move containers.

[0139] In an optional example, the deployment module is also used to deploy at least one camera above the lane of the container truck; where above the lane refers to the area above the driving lane of the container truck.

[0140] In an optional example, the deployment module is also used to deploy at least one camera on the outriggers or saddles of the trolley, which refers to the support structure of the trolley traveling mechanism of the yard crane or quay crane in the container yard.

[0141] In an optional example, the recognition module 602 is further configured to obtain a marker recognition model, which is trained based on the image dataset of the first container and / or the image training set of the second container;

[0142] Based on the marker recognition model, feature analysis is performed on each top surface image in the top surface image dataset to determine whether there is a target top surface image, which includes high box marker information;

[0143] If a top view image of the target exists, it is determined that the target container has a high-cube marking.

[0144] If no top view image of the target is available, it is determined that the target container does not have a high-cube marking.

[0145] In an optional example, the recognition module 602 is also configured to detect, based on the marker recognition model, whether at least one of the edge features, texture features, and color features of the high box marker exists in each top surface image;

[0146] If the top surface image contains at least one of edge features, texture features, and color features, then the top surface image is determined to be the target top surface image.

[0147] In an optional example, the control module is also used to control the spreader to prioritize grabbing the first container before grabbing the second container on the container truck.

[0148] The container truck high and low container identification device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0149] Figure 7 A schematic diagram of the structure of the electronic device provided in this application, such as... Figure 7 As shown, the electronic device 70 provided in this embodiment includes at least one processor 701 and a memory 702. Optionally, the electronic device 70 further includes a communication component 703. The processor 701, memory 702, and communication component 703 are connected via a bus 704.

[0150] In a specific implementation, at least one processor 701 executes computer execution instructions stored in memory 702, causing at least one processor 701 to perform the above-described method.

[0151] The specific implementation process of processor 701 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0152] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0153] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0154] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0155] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0156] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0157] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0158] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0159] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0160] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0161] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0162] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0163] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0164] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for identifying high and low containers in a container truck, characterized in that, include: In response to a dual container loading operation request, images of the top surface of the target container to be grabbed by the spreader are acquired by cameras deployed at at least two different locations. The resulting top surface image dataset is used for the spreader to grab a first container on a container truck and a second container that is close to the first container. The height of the first container is greater than the height of the second container. Feature analysis is performed on the top surface image dataset to identify whether the target container has a high-cube marking. If the target container has the high cube container marking, then the target container to be grabbed by the spreader is determined to be the first container; If the target container does not have the high cube container marking, then the target container to be grabbed by the spreader is determined to be the second container.

2. The method according to claim 1, characterized in that, The method further includes: If the target container to be grabbed by the spreader is the second container, and the first container on the container truck has not been grabbed, the spreader is controlled to stop the grabbing action and a warning is issued.

3. The method according to claim 1, characterized in that, The method further includes: At least one camera is deployed at at least one location on the short side, long side, or four corners of the spreader; wherein the spreader is used to grab and move containers.

4. The method according to claim 1 or 2, characterized in that, The method further includes: At least one camera is deployed above the lane of the container truck; wherein, "above the lane" refers to the area above the lane in which the container truck travels.

5. The method according to claim 1 or 2, characterized in that, The method further includes: At least one camera is deployed on the outriggers or saddles of the trolley, where the outriggers or saddles refer to the supporting structure of the trolley traveling mechanism of the yard crane or quay crane in the container yard.

6. The method according to claim 1, characterized in that, The step of performing feature analysis on the top surface image dataset to identify whether the target container has a high-cube marking includes: Obtain a marker recognition model, wherein the marker recognition model is trained based on the image training set of the first container and / or the image training set of the second container; Based on the marker recognition model, feature analysis is performed on each top surface image in the top surface image dataset to determine whether a target top surface image exists, wherein the target top surface image includes high box marker information; If the target top surface image exists, then it is determined that the target container has the high-cube identifier; If the target top surface image does not exist, it is determined that the target container does not have the high-cube identifier.

7. The method according to claim 6, characterized in that, The step of performing feature analysis on each top surface image in the top surface image dataset based on the marker recognition model to determine whether a target top surface image exists includes: Based on the marker recognition model, detect whether each top surface image contains at least one of the edge features, texture features, and color features of the tall box marker; If the top surface image contains at least one of the edge features, the texture features, and the color features, then the top surface image is determined to be the target top surface image.

8. The method according to claim 1, characterized in that, The method further includes: The spreader is controlled to grab the first container first, before grabbing the second container on the container truck.

9. A container truck high / low container identification device, characterized in that, include: The response module is used to respond to a dual container loading operation request by acquiring images of the top surface of the target container to be grabbed by the spreader from cameras deployed at at least two different locations, and obtaining a top surface image dataset. The dual container loading operation request is used for the spreader to grab a first container on a container truck and a second container close to the first container, wherein the height of the first container is greater than the height of the second container. The identification module is used to perform feature analysis on the top surface image dataset to identify whether the target container has a high-cube marking. The first processing module is used to determine that the target container to be grabbed by the spreader is the first container if the target container has the high-cube identifier; The second processing module is used to determine that the target container to be grabbed by the spreader is the second container if the target container does not have the high cube container identifier.

10. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-8.

Images