Palletizing container optimization methods, devices, and sensors

Abstract

This application provides a method, apparatus, and sensor for optimizing palletizing containers. The method includes: acquiring the length, width, and height of each pallet at a first location to form a virtual container corresponding to each pallet; grouping the pallets according to the height of the virtual containers; acquiring a two-dimensional projection image of the virtual containers in a group of pallets; performing a morphological closing operation on the two-dimensional projection image and acquiring at least one connected region of the two-dimensional projection image; and determining the position and number of optimized containers at a second location based on the acquired at least one connected region. This improves the stability, efficiency, and space utilization of the palletizing system, and allows it to adapt to complex and irregular arrangements.

Description

Technical Field

[0001] This application relates to the field of palletizing container optimization, and more particularly to a palletizing container optimization method, apparatus, and sensor. Background Technology

[0002] With the rapid development of the manufacturing and logistics industries, especially the rise of automated palletizing equipment, the demand for pallet stacking has increased dramatically. Traditional manual arrangement methods are inefficient and have low space utilization, which can easily lead to the collapse or damage of goods during transportation, thus creating a demand for systematic optimization algorithms.

[0003] Early palletizing optimization mainly relied on fixed rules and layered arrangement methods, such as bottom-priority placement and staggered layouts. These methods originated from the study of classic loading problems and were suitable for single-product, high-volume production scenarios. However, in mixed-product environments, traditional methods struggle to cope with the complex requirements of diverse box sizes, weight distribution, support area, and center of gravity control, resulting in limited optimization effectiveness.

[0004] In recent years, with the improvement of computing power, more advanced computing technologies have begun to be applied to palletizing optimization, which has significantly improved the solution quality and practicality. Furthermore, with the advancement of artificial intelligence and Industry 4.0, the optimization has been driven from rigid palletizing to flexible intelligent palletizing.

[0005] It should be noted that the above introduction to the technical background is only for the purpose of providing a clear and complete explanation of the technical solutions of this application and facilitating understanding by those skilled in the art. It should not be assumed that these technical solutions are known to those skilled in the art simply because they have been described in the background section of this application. Summary of the Invention

[0006] The inventors discovered that in existing 3D palletizing systems, after the bottom pallet is placed, a virtual container needs to be generated for the placement of the upper pallet. However, the virtual containers generated by existing technologies suffer from severe fragmentation, difficulty in handling gaps, low space utilization, and difficulty in handling complex scenarios with irregular arrangements. Therefore, how to improve space utilization and palletizing stability in complex scenarios is a problem that needs to be solved.

[0007] To address at least one of the aforementioned technical problems or other similar issues, embodiments of this application provide a method, apparatus, and sensor for optimizing palletizing containers.

[0008] According to a first aspect of the embodiments of this application, a method for optimizing palletizing containers is provided. The method includes: obtaining the length, width, and height of each pallet at a first position to form a virtual container corresponding to each pallet; grouping the pallets according to the height of the virtual containers; obtaining a two-dimensional projection image of the virtual containers of a group of pallets; performing a morphological closing operation on the two-dimensional projection image and obtaining at least one connected region of the two-dimensional projection image; and determining the position and number of optimized containers at a second position according to the obtained at least one connected region.

[0009] In some embodiments, grouping the pallets according to the height of the virtual containers includes: sorting the absolute height of the virtual containers corresponding to each pallet; and grouping pallets whose height difference between the virtual containers is less than a height threshold into a group according to the sorting.

[0010] In some embodiments, the morphological closing operation includes performing dilation and / or erosion operations on the regions corresponding to each virtual container in the two-dimensional projection image.

[0011] In some embodiments, obtaining at least one connected region of the two-dimensional projected image includes: identifying and connecting regions corresponding to each of the virtual containers that have undergone the dilation operation and / or the erosion operation, to form at least one connected region.

[0012] In some embodiments, determining the position and number of optimized containers at the second location based on the at least one connected region includes: for each connected region, iteratively extracting the maximum inscribed rectangle using a dynamic programming algorithm, and obtaining a list of maximum inscribed rectangles; obtaining a size threshold for the optimized containers; and determining the position and number of optimized containers at the second location based on the size threshold and the list of maximum inscribed rectangles.

[0013] According to a second aspect of the embodiments of this application, a palletizing container optimization apparatus is provided, the apparatus comprising: An acquisition unit acquires the length, width, and height of each pallet at a first position to form a virtual container corresponding to each pallet, and groups the pallets according to the height of the virtual containers; the acquisition unit also acquires a two-dimensional projection image of the virtual containers of a group of pallets; a calculation unit performs a morphological closing operation on the two-dimensional projection image and acquires at least one connected region of the two-dimensional projection image; and a determination unit determines the position and number of optimized containers at a second position based on the acquired at least one connected region.

[0014] In some embodiments, grouping the pallets according to the height of the virtual containers includes: sorting the absolute height of the virtual containers corresponding to each pallet; and grouping pallets whose height difference between the virtual containers is less than a height threshold into a group according to the sorting.

[0015] In some embodiments, the morphological closing operation includes performing dilation and / or erosion operations on the regions corresponding to each virtual container in the two-dimensional projection image.

[0016] In some embodiments, the computing unit identifies and connects regions corresponding to each of the adjacent virtual containers that have undergone the expansion operation and / or the erosion operation to form at least one connected region.

[0017] In some embodiments, the determining unit: for each connected region, iteratively extracts the maximum inscribed rectangle using a dynamic programming algorithm, and obtains a list of maximum inscribed rectangles; obtains a size threshold for the optimized container; and determines the position and number of optimized containers at the second location based on the size threshold and the list of maximum inscribed rectangles.

[0018] According to a third aspect of the embodiments of this application, a palletizing container optimization sensor is provided, the palletizing container optimization sensor including at least a processor, the processor performing the palletizing container optimization method described in any of the preceding claims.

[0019] According to a fourth aspect of the embodiments of this application, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program, which, when executed by a processor, implements the palletizing container optimization method described in any of the preceding claims.

[0020] One of the beneficial effects of this application's embodiments is that by processing the three-dimensional palletizing virtual containers whose heights belong to a group, the "empty" problem can be avoided, and the stability of palletizing stacking can be improved; and by using morphological closing operations, small gaps in two-dimensional projection images can be automatically processed without the need for precise alignment of the palletizing virtual containers, thereby improving efficiency and space utilization; furthermore, by determining the optimized position and number of containers through the obtained connected regions, space utilization can be improved and the system can adapt to complex and irregular arrangement scenarios.

[0021] Referring to the following description and accompanying drawings, specific implementation methods of the embodiments of this application are disclosed in detail, indicating how the principles of the embodiments of this application can be adopted. It should be understood that the implementation methods of this application are not limited in scope. Within the spirit and scope of the appended claims, the implementation methods of this application include many changes, modifications, and equivalents. Attached Figure Description

[0022] The elements and features described in one drawing or embodiment of this application may be combined with elements and features shown in one or more other drawings or embodiments. Furthermore, in the drawings, similar reference numerals denote corresponding parts in several drawings and can be used to indicate corresponding parts used in more than one embodiment.

[0023] The accompanying drawings, which form part of the specification, are used to provide a further understanding of the embodiments of this application and illustrate the implementation methods of this application, together with the textual description, to explain the principles of this application. Obviously, the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other implementation methods based on these drawings without creative effort. In the drawings: Figure 1 This is a schematic diagram of the generated virtual container; Figure 2 This is a schematic diagram of a palletizing container optimization method according to an embodiment of this application; Figure 3 This is a schematic diagram of a method for determining the optimal location and quantity of containers according to an embodiment of this application; Figure 4 This is a schematic diagram illustrating the generation of a set of virtual containers according to an embodiment of this application; Figure 5 This is a schematic diagram of a set of two-dimensional projection images of virtual containers according to an embodiment of this application; Figure 6 This is a schematic diagram of at least one connected region for obtaining a two-dimensional projection image according to an embodiment of this application; Figure 7 This is a schematic diagram of an optimized container according to an embodiment of this application; Figure 8 This is a schematic diagram of a palletizing container optimization device according to an embodiment of this application; Figure 9 This is a schematic diagram of a palletizing container optimization sensor according to an embodiment of this application. Detailed Implementation

[0024] Referring to the accompanying drawings, the foregoing and other features of the embodiments of this application will become apparent from the following description. Specific embodiments of this application are specifically disclosed in the description and drawings, illustrating partial implementations in which the principles of the embodiments of this application can be adopted. It should be understood that this application is not limited to the described embodiments; rather, the embodiments of this application include all modifications, variations, and equivalents falling within the scope of the appended claims.

[0025] In the embodiments of this application, the terms "first," "second," etc., are used to distinguish different elements by name, but do not indicate the spatial arrangement or chronological order of these elements, and these elements should not be limited by these terms. The term "and / or" includes any one or more of the terms listed in association and all combinations thereof. The terms "comprising," "including," "having," etc., refer to the presence of the stated features, elements, components, or assemblies, but do not exclude the presence or addition of one or more other features, elements, components, or assemblies.

[0026] In the embodiments of this application, the singular forms "a," "the," etc., including the plural forms, should be broadly understood as "a kind" or "a class" rather than limited to the meaning of "an." Furthermore, the term "the" should be understood to include both the singular and plural forms, unless the context explicitly indicates otherwise. Additionally, the term "according to" should be understood as "at least partially based on…," and the term "based on" should be understood as "at least partially based on…," unless the context explicitly indicates otherwise.

[0027] Features described and / or illustrated for one embodiment may be used in the same or similar manner in one or more other embodiments, combined with features in other embodiments, or substituted for features in other embodiments. The term "comprising / including" as used herein means the presence of a feature, integral, step, or component, but does not exclude the presence or addition of one or more other features, integrals, steps, or components.

[0028] In existing 3D palletizing systems, after the bottom layer (e.g., corresponding to the "first position" in the following description of this application) is placed, palletizing needs to be placed on the upper layer (e.g., corresponding to the "second position" in the following description of this application). The placement of the upper layer palletizing is usually limited by the support surface of the bottom layer palletizing. Therefore, to optimize the position and number of upper layer palletizing, the support surface of the bottom layer palletizing is abstracted as a virtual container.

[0029] Figure 1 This is a schematic diagram of the generated virtual container; Figure 1 A two-dimensional projection image of a palletized virtual container generated according to existing technology is shown.

[0030] The inventors have discovered that the prior art has at least the following problems: Difficulties in handling gaps: such as Figure 1 As shown in scenario 1, in the prior art, precise matching and alignment of pallet sizes are required to merge the virtual containers of adjacent pallets; while for Figure 1 In cases 2 and 3, there are small gaps between the virtual containers in the palletizing, and the existing technology cannot handle these gaps, which prevents adjacent virtual containers from merging and wastes space. Severe fragmentation: Existing technologies require the generation of a virtual container for each bottom palletizing layer and the determination of the position of the upper palletizing layer based on the generated virtual containers. As a result, the upper palletizing containers are numerous, small in size, and severely fragmented, making it difficult to select containers when packing upper palletizing boxes and resulting in low space utilization. Difficulty in handling complex shapes: Existing technologies struggle to handle situations where the bottom stacking arrangement is irregular, forming complex support surfaces. Poor stability: The virtual containers generated by the existing technology do not take into account the height of the underlying palletizing layer. Therefore, when stacking the upper palletizing layer, it will cause the upper palletizing layer to "leap" and make the palletizing system less stable.

[0031] Therefore, in view of at least one of the above-mentioned technical problems or other similar problems, this application provides a method, apparatus and sensor for optimizing palletizing containers.

[0032] The following provides a further description of the palletizing container optimization method according to embodiments of this application.

[0033] Figure 2 This is a schematic diagram of a palletizing container optimization method according to an embodiment of this application, as shown below. Figure 2 As shown, the method includes: 201. Obtain the length, width, and height of each pallet at the first position to form a virtual container corresponding to each pallet; 202. Group the pallet according to the height of the virtual container; 203. Obtain a set of two-dimensional projection images of the stacked virtual containers; 204. Perform morphological closing operation on the two-dimensional projected image and obtain at least one connected region of the two-dimensional projected image; 205. Based on the obtained at least one connected region, determine the position and number of optimized containers at the second position.

[0034] It is worth noting that the above appendix Figure 2 The embodiments of this application have only been illustrated schematically, and the application is not limited thereto. For example, some of the above steps can be performed simultaneously or in a specific order, and the execution order between the various operations can be appropriately adjusted. Furthermore, other operations can be added or some operations can be removed. Those skilled in the art can make appropriate modifications based on the above description, and are not limited to the above-described embodiments. Figure 2 The records.

[0035] In some embodiments of this application, the first position is, for example, the position of the top layer of the currently stacked pallet, and the second position is, for example, the position of the layer above the top layer of the currently stacked pallet. For example, referring to the foregoing description of this application, relatively speaking, the first position can correspond to the position of the bottom layer of the pallet, and the second position can correspond to the position of the upper layer of the pallet to be stacked, etc. For example, in the subsequent embodiments of this application, "bottom layer" corresponds to the first position and "upper layer" corresponds to the second position, but this application does not limit this.

[0036] In some embodiments of this application, the term "palletizing" may also be replaced with "box", "box", "object", "material", etc., but this application does not limit it in this way.

[0037] In this embodiment, the length, width, and height of each pallet at a first location are obtained, and the three-dimensional palletizing virtual containers belonging to a group are projected onto a two-dimensional projection image. Morphological closing operations are then used to obtain the connected regions of the two-dimensional projection image, and the position and number of optimized containers at a second location are determined based on these connected regions. Therefore, by processing the three-dimensional palletizing virtual containers whose heights belong to a group, the "empty" problem can be avoided, improving the stability of pallet stacking; and the use of morphological closing operations can automatically handle small gaps in the two-dimensional projection image, eliminating the need for precise alignment of the palletizing virtual containers, thus improving efficiency and space utilization; furthermore, determining the position and number of optimized containers through the obtained connected regions can improve space utilization and adapt to complex and irregular arrangements.

[0038] The following provides a detailed explanation of each of the above steps: For step "201", the length, width, and height of each pallet at the first position are obtained to form a virtual container corresponding to each pallet: For example, the term "virtual container" can also be referred to as "basic container," etc., and this application does not impose any restrictions on this. For example, a perfectly fitted virtual container is generated for each bottom-layer box, where the position and size of each virtual container correspond to the stacking. When obtaining the virtual container, gap compensation can be considered. For example, the "effective size" of the box can be expanded: actual placement size = nominal size + gaps on both sides (for example, if the actual width of the box is 300 mm and the gap is 10 mm, then the effective width of the virtual container corresponding to the box is 320 mm). This ensures that there is buffer space during actual stacking. The above is only an example, and other gap compensation methods can also be used. This application does not limit these methods.

[0039] For example, in step "201", a list of virtual containers is also output. This list may include at least one of the following: the number of virtual containers (equal to the number of pallets), the number of each virtual container, and the length, width, and height of each virtual container. For example, the length, width, and height of each virtual container may correspond to the "three-dimensional data" of the virtual container; or, the coordinates of each virtual container and other related information. The above is only an example. The list of virtual containers may also include other information, and this application does not limit this.

[0040] In this embodiment of the application, after obtaining the length, width, and height of each pallet at the first position in step "201", the bottom pallets are grouped according to the height of the virtual container corresponding to each pallet in step "202": In some embodiments, the absolute height of the virtual container corresponding to each pallet is sorted; and according to the sorting, pallets whose height difference of the virtual container is less than a height threshold are grouped together.

[0041] Therefore, optimizing virtual containers belonging to the same group in subsequent steps can ensure that virtual containers in the same group can be safely merged, and can ensure that the upper box is placed on the real support surface, thus ensuring the stability of the palletizing system.

[0042] In some embodiments, the height threshold may be set by the operator based on experience, or preset at the factory, or determined by other means, and this application is not limited thereto.

[0043] For example, taking a height threshold of 2 centimeters (cm) as an example, the absolute height of the virtual containers is sorted, and virtual containers with similar heights are grouped together. For example, virtual containers with a height difference of less than 2cm are grouped into one group. For example, in step "202", a height grouping list may also be output, which may include at least one of the following: the grouping result; or, information such as the average height of each group of virtual containers; the above is only an example, and the height grouping list may also include other information, which is not limited in this application.

[0044] In some embodiments, in step “203”, a two-dimensional projection image of a set of stacked virtual containers is obtained.

[0045] In this embodiment, virtual containers in the same group are projected onto a two-dimensional grid to generate a two-dimensional projected image (resolution 1mm / pixel).

[0046] For example, a method for obtaining a two-dimensional projected image can start with three-dimensional data, projecting the three-dimensional representation of the virtual container onto a two-dimensional plane (such as the top-view XOY plane) to generate a two-dimensional projected image. For example, it includes at least one of the following steps: acquiring three-dimensional data of a virtual container, for example, the three-dimensional data of the virtual container may correspond to the length, width, and height of the aforementioned virtual container; projecting the three-dimensional data of the virtual container onto a two-dimensional plane: for example, projecting each three-dimensional point (x, y, z) into a two-dimensional point (x', y'), typically projecting along the Z-axis (x' = x, y' = y, or using a projection matrix); and then generating a two-dimensional projected image: mapping the projected points onto an image grid to form at least one of a density map, a binary image, or a scatter plot.

[0047] In some embodiments, after obtaining the two-dimensional projection image in step "203", a morphological closing operation is performed on the two-dimensional projection image in step "204" and at least one connected region of the two-dimensional projection image is obtained.

[0048] In some embodiments, the morphological closing operation includes performing dilation and / or erosion operations on the region corresponding to each virtual container in the two-dimensional projected image.

[0049] For example, dilation involves pattern matching for each point in the input image. If a match is successful (e.g., all surrounding pixels have the same color as the pixel), the pixel is retained; if a match fails (e.g., not all surrounding pixels have the same color), the pixel is removed. Erosion, on the other hand, processes the image as the output of dilation. Erosion fills all surrounding pixels with the same color as the original pixel, resulting in the final output image.

[0050] In some embodiments, obtaining at least one connected region of the two-dimensional projected image includes: identifying and connecting regions corresponding to each of the virtual containers that have undergone the dilation operation and / or the erosion operation, to form at least one connected region.

[0051] For example, using morphological closing operations to automatically fill small gaps allows the corresponding regions of adjacent virtual containers to be automatically connected into at least one connected region. For example, step "204" can also output a list of connected components, which may include information such as the number of connected components and their size. The above is only an example, and the list of connected components may also include other information, which is not limited in this application.

[0052] Therefore, morphological closing operations can automatically fill small gaps (such as gaps smaller than the tolerance) between virtual containers, automatically identify and merge adjacent containers, reduce the number of containers, and improve the merging rate.

[0053] After obtaining at least one connected component, in step "205", the position and number of optimized containers at the second location are determined based on the obtained at least one connected component: Figure 3 This is a schematic diagram of a method for determining the optimal position and number of containers according to an embodiment of this application; as shown Figure 3 As shown, for example, it includes the following steps: 2051. For each connected region, use a dynamic programming algorithm to iteratively extract the maximum inscribed rectangle and obtain a list of maximum inscribed rectangles. 2052, obtain the size threshold for optimizing the container. 2053, determine the position and number of optimized containers at the second location based on the size threshold and the list of maximum inscribed rectangles.

[0054] Specifically, step "2051" for obtaining the list of maximum inscribed rectangles includes, for example: Extract the submatrix of each connected region: For example, use the connected component labeling algorithm to obtain the mask and bounding box of all connected regions; for each connected region, crop out its minimum bounding rectangle subimage, and keep only the pixels in the region (e.g., the foreground is empty 0, and the other parts are set to occupied 1 or ignored), forming an independent binary submatrix (e.g., the empty region is 1, which is convenient for subsequent calculation of the maximum all-1 rectangle). Iteratively apply dynamic programming algorithm to extract the maximum inscribed rectangle on the submatrix: for example, construct the height matrix row by row from top to bottom: each column records the number of consecutive empty (1) rows from the current position upwards. Calculate the area of ​​the maximum rectangle in the histogram using a monotonic stack for the height array of each row, and record the rectangle coordinates (e.g., top row, bottom row, left column, right column); find the global maximum inscribed rectangle in the current submatrix; add the information of the maximum rectangle (e.g., area, coordinates) to the candidate list; mark the rectangle region as occupied (set to 0) in the submatrix to prevent overlap; repeat the above process until the area of ​​the extracted rectangle is less than the preset minimum threshold (e.g., the size threshold of the subsequent optimized container) or there are no valid rectangles. Get the list of the largest inscribed rectangles of the connected region: This results in a list sorted in descending order of area. For example, this list of the largest inscribed rectangles represents the preferred candidate locations for placing boxes within the connected region (the larger the area, the higher the priority). Repeat this process for all connected regions to obtain a list of the largest inscribed rectangles for each connected region.

[0055] Then, in step "2052": An optimized container size threshold is obtained to remove excessively small containers; for example, the optimized container size threshold can be a one-dimensional threshold, such as filtering out containers whose length or width is smaller than the one-dimensional threshold (e.g., 80mm), or the optimized container size threshold can be a two-dimensional threshold, such as filtering out containers with an area smaller than the two-dimensional threshold (e.g., 100mm). Containers smaller than 100mm will be filtered out. Alternatively, the optimized container size threshold could be a three-dimensional threshold; for example, containers with a volume smaller than this three-dimensional threshold (e.g., 100mm) would be filtered out. 100mm Containers with a diameter of 100mm or less will be filtered out. The above is only an example. The size threshold of the optimized container can be set by the operator based on experience, or preset at the factory, or determined by other means. This application is not limited to this.

[0056] Furthermore, for example in step "2053", the final list of optimized containers is created: For a connected region, iterate through the list of the largest inscribed rectangles of the connected region (e.g., sorted in descending order of area). For the largest inscribed rectangle, check if it meets the size thresholds for the optimized container: for example, both the rectangle's width and length are ≥ a one-dimensional threshold (e.g., 80mm); or, for another example, the rectangle's area is ≥ a two-dimensional threshold (e.g., 100mm). In the case of 100mm, the maximum inscribed rectangle satisfies the size threshold of the optimized container; The final optimized container list is then generated: for example, the position and number of optimized containers at the second position are output.

[0057] Therefore, space utilization can be maximized by applying a list of maximum inscribed rectangles; and the merging rate can be further improved by setting a size threshold for optimized containers to exclude the positions and numbers of containers that do not meet the size requirements.

[0058] The following examples, in conjunction with the accompanying drawings, illustrate the optimized palletizing container method of this application: Figure 4 This is a schematic diagram illustrating the generation of a set of virtual containers according to an embodiment of this application, such as... Figure 4 As shown, the dashed lines indicate the length and width of the four generated virtual containers in the X and Y axes, corresponding to the four pallets respectively.

[0059] For example, in step "201", the following list of virtual containers is output: Total number of virtual containers: 4; Virtual container 1: 636mm wide, 467mm long, 468mm high; Virtual container 2: 328mm wide, 539mm long, 469mm high; Virtual container 3: 652mm wide, 472mm long, 458mm high; Virtual container 4: 442mm wide, 633mm long, and 469mm high.

[0060] For example, in step "202", the absolute values ​​of the heights of all virtual containers are sorted. Since the height difference between virtual containers 1 and virtual containers 4 is within 2cm, virtual containers 1 to virtual containers 4 are divided into 1 group.

[0061] Figure 5 This is a schematic diagram of a set of two-dimensional projection images of virtual containers according to an embodiment of this application.

[0062] Furthermore, such as Figure 5 As shown, for Figure 4 The set of virtual containers shown is used to obtain two-dimensional projection images of virtual container 1 to virtual container 4 according to the method in step "203" above; Figure 6 This is a schematic diagram of obtaining at least one connected region of a two-dimensional projected image according to an embodiment of this application.

[0063] like Figure 6 As shown, for Figure 5 The two-dimensional projection graphics of a set of virtual containers shown are subjected to dilation and erosion operations to obtain a connected region (601) of the two-dimensional projection image; then the connected region (601) is processed by step "2051" to obtain a list of maximum inscribed rectangles, for example, the list of maximum inscribed rectangles includes maximum inscribed rectangle 1, maximum inscribed rectangle 2, and maximum inscribed rectangle 3; then steps "2052" and "2053" are executed to create a final list of optimized containers, including the position and number of optimized containers.

[0064] Figure 7 This is a schematic diagram of an optimized container according to an embodiment of this application; Figure 7 It shows that, according to the foregoing Figures 4 to 6 The number and location of the generated optimized containers.

[0065] Figure 7 The generated optimized container 1, optimized container 2, optimized container 3, and their corresponding positions are shown; and, as... Figures 3 to 7 As shown, the number of virtual containers in this application is 4, and the number of optimized containers is 3. Therefore, through the implementation method of this application, the merging rate is as high as 75%; and, as Figure 7 As shown, the space utilization of the optimized container is significantly improved, and the generated optimized container can adapt to complex and irregular arrangement scenarios. In addition, this application optimizes virtual containers with height belonging to a group, which improves the stability of the palletizing system.

[0066] It is worth noting that the above appendix Figure 4 To be continued Figure 7 The embodiments of this application have only been illustrated schematically, and the application is not limited thereto. For example, some of the above steps can be performed simultaneously or in a specific order, and the execution order between the various operations can be appropriately adjusted. Furthermore, other operations can be added or some operations can be removed. Those skilled in the art can make appropriate modifications based on the above description, and are not limited to the above-described embodiments. Figure 4 To be continued Figure 7 The records.

[0067] The above illustrative description illustrates the palletizing container optimization method of this application embodiment. The following illustrative description illustrates the palletizing container optimization device of this application embodiment, omitting the description of the same content as the foregoing embodiments.

[0068] Figure 8 This is a schematic diagram of a palletizing container optimization device according to an embodiment of this application, as shown below. Figure 8 As shown, the palletizing container optimization device 800 includes an acquisition unit 801, a calculation unit 802, and a determination unit 803.

[0069] The acquisition unit 801 acquires the length, width, and height of each pallet at the first position to form a virtual container corresponding to each pallet, and groups the pallets according to the height of the virtual containers; the acquisition unit 801 also acquires a two-dimensional projection image of the virtual containers of a group of pallets. The computing unit 802 performs morphological closing operations on the two-dimensional projection image and obtains at least one connected region of the two-dimensional projection image; The determining unit 803 determines the position and number of optimized containers at the second position based on the acquired at least one connected region.

[0070] Therefore, the length, width, and height of each pallet at the first position are obtained, and the 3D palletizing virtual containers belonging to the same group are projected onto a 2D projection image. Morphological closing operations are then used to obtain the connected regions of the 2D projection image, and the position and number of optimized containers at the second position are determined based on these connected regions. By processing the 3D palletizing virtual containers whose heights belong to the same group, the "empty" problem can be avoided, improving the stability of pallet stacking. Furthermore, morphological closing operations can automatically handle small gaps in the 2D projection image, eliminating the need for precise alignment of the palletizing virtual containers, thus improving efficiency and space utilization. Additionally, determining the position and number of optimized containers through the obtained connected regions can further improve space utilization and adapt to complex and irregular arrangements.

[0071] For detailed descriptions of each unit of the palletizing container optimization device 800, please refer to the documentation. Figure 2The steps of the medium-sized palletizing container optimization method will not be repeated here.

[0072] This application also provides an optimized sensor for palletizing containers. Figure 9 This is a schematic diagram of a palletizing container optimization sensor according to an embodiment of this application.

[0073] like Figure 9 As shown, the palletizing container optimization sensor 900 may include: a memory 901 and a processor (e.g., a central processing unit CPU) 902; the memory 901 is coupled to the central processing unit 902.

[0074] The memory 901 can store various data and information processing programs, which are executed under the control of the processor 902. It is worth noting that the palletizing container optimization sensor 900 is not necessarily included. Figure 9 All components shown; in addition, the palletizing container optimization sensor 900 may also include Figure 9 Components not shown in the document.

[0075] In some embodiments, the processor 902 is configured to execute the aforementioned palletizing container optimization method for the color sensor (e.g., Figure 2 (As shown). For example, processor 902 is configured to perform the following operations: acquire the length, width, and height of each pallet at a first location to form a virtual container corresponding to each pallet; group the pallets according to the height of the virtual containers; acquire a two-dimensional projection image of the virtual containers of a group of pallets; perform a morphological closing operation on the two-dimensional projection image and acquire at least one connected region of the two-dimensional projection image; and determine the position and number of optimized containers at a second location based on the acquired at least one connected region.

[0076] The above embodiments are merely illustrative examples of embodiments of this application, but this application is not limited thereto, and appropriate modifications can be made based on the above embodiments. For example, the above embodiments can be used alone, or one or more of the above embodiments can be combined.

[0077] It is worth noting that the above description only covers the components or modules relevant to this application, but this application is not limited thereto. The menu navigation device in the embodiments of this application may also include other components or modules, and for details regarding these components or modules, please refer to related technologies.

[0078] For simplicity, the figures above only illustrate the connection relationships or signal flows between the various components or modules. However, those skilled in the art should understand that various related technologies, such as bus connections, can be used. The various components or modules described above can be implemented using hardware facilities such as processors and memory; the embodiments of this application do not limit this.

[0079] This application also provides a storage medium storing a computer-readable program, wherein the computer-readable program causes a computer in an electronic device to execute the palletizing container optimization method as described in the preceding embodiments.

[0080] The apparatus and methods described above in this application can be implemented in hardware or in combination with software. This application relates to a computer-readable program that, when executed by a logic component, enables the logic component to implement the apparatus or components described above, or to implement the various methods or steps described above. This application also relates to storage media for storing the above programs, such as hard disks, magnetic disks, optical disks, DVDs, flash memory, etc.

[0081] The methods / apparatus described in conjunction with the embodiments of this application can be directly embodied in hardware, software modules executed by a processor, or a combination of both. For example, one or more and / or combinations of one or more functional block diagrams shown in the figures can correspond to various software modules in a computer program flow, or to various hardware modules. These software modules can correspond to the various steps shown in the figures, respectively. These hardware modules can be implemented, for example, using a field-programmable gate array (FPGA) to embed these software modules.

[0082] The software module can reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art. A storage medium can be coupled to the processor, enabling the processor to read information from and write information to the storage medium; or the storage medium can be an integral part of the processor. The processor and storage medium can reside in an ASIC. The software module can be stored in the memory of a mobile terminal or in a memory card that can be inserted into the mobile terminal. For example, if the device (such as a mobile terminal) uses a high-capacity MEGA-SIM card or a high-capacity flash memory device, the software module can be stored in the MEGA-SIM card or the high-capacity flash memory device.

[0083] One or more and / or one or more combinations of functional blocks described in the accompanying drawings can be implemented as a general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, or any suitable combination thereof for performing the functions described herein. One or more and / or one or more combinations of functional blocks described in the accompanying drawings can also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in communication with a DSP, or any other such configuration.

[0084] The present application has been described above with reference to specific embodiments. However, those skilled in the art should understand that these descriptions are exemplary and not intended to limit the scope of protection of the present application. Those skilled in the art can make various modifications and variations to the present application based on the principles thereof, and these modifications and variations are also within the scope of the present application.

Claims

1. A method for optimizing palletizing containers, characterized in that, The method includes: Obtain the length, width, and height of each pallet at the first position to form a virtual container corresponding to each pallet; The palletizing is grouped according to the height of the virtual container; Obtain a two-dimensional projection image of a set of stacked virtual containers; Perform morphological closing operations on the two-dimensional projected image and obtain at least one connected region of the two-dimensional projected image; and Based on the at least one connected region obtained, determine the position and number of optimized containers at the second location.

2. The method according to claim 1, characterized in that, Grouping the palletizing according to the height of the virtual container includes: Sort the absolute height of the virtual container corresponding to each pallet; Based on the sorting, stacks with a height difference of less than a height threshold are grouped together.

3. The method according to claim 1, characterized in that, The morphological closing operation includes: Dilation and / or erosion operations are performed on the regions corresponding to each virtual container in the two-dimensional projection image.

4. The method according to claim 3, characterized in that, Obtaining at least one connected region of the two-dimensional projected image includes: Identify and connect the regions corresponding to each of the virtual containers that have undergone the expansion operation and / or the erosion operation, forming at least one connected region.

5. The method according to claim 4, characterized in that, Based on the acquired at least one connected region, determining the position and number of optimized containers at the second location includes: For each of the connected regions, a dynamic programming algorithm is used to iteratively extract the maximum inscribed rectangle and obtain a list of maximum inscribed rectangles; Obtain the size threshold for the optimized container; The position and number of optimized containers at the second location are determined based on the size threshold and the list of maximum inscribed rectangles.

6. A palletizing container optimization device, characterized in that, The device includes: The acquisition unit acquires the length, width, and height of each pallet at a first position to form a virtual container corresponding to each pallet, and groups the pallets according to the height of the virtual containers; The acquisition unit also acquires a set of two-dimensional projection images of the stacked virtual containers; A computing unit performs morphological closing operations on the two-dimensional projected image and obtains at least one connected region of the two-dimensional projected image; and The determining unit determines the position and number of optimized containers at the second location based on the acquired at least one connected region.

7. The apparatus according to claim 6, characterized in that, Grouping the palletizing according to the height of the virtual container includes: Sort the absolute height of the virtual container corresponding to each pallet; Based on the sorting, stacks with a height difference of less than a height threshold are grouped together.

8. The apparatus according to claim 6, characterized in that, The morphological closing operation includes: Dilation and / or erosion operations are performed on the regions corresponding to each virtual container in the two-dimensional projection image.

9. The apparatus according to claim 8, characterized in that, The computing unit identifies and connects the regions corresponding to each virtual container that has undergone the expansion operation and / or the erosion operation, forming at least one connected region; as well as The determining unit: for each connected region, iteratively extracts the maximum inscribed rectangle using a dynamic programming algorithm, and obtains a list of maximum inscribed rectangles; obtains the size threshold of the optimized container; The position and number of optimized containers at the second location are determined based on the size threshold and the list of maximum inscribed rectangles.

10. A palletizing container optimization sensor, characterized in that, The palletizing container optimization sensor includes at least a processor that executes the palletizing container optimization method according to any one of claims 1 to 5.

Images