A visual inspection method, device and system for cartons

Abstract

The present invention relates to the field of industrial vision, and in particular to a visual inspection method, device and system for cartons, wherein the method can collect the surface image of each loaded carton, and then determine its surface defects, and then simulate the stacking of cartons on a transport vehicle with the determined surface defects as the boundary conditions of the carton, so as to determine a stacking method that will not cause any loaded carton to become unstable under pressure, and send the stacking method to the palletizer to guide the palletizer to stack the loaded cartons in the method, so as to ensure the safety of the products in each loaded carton.

Description

Technical Field

[0001] The present invention relates to the field of industrial vision, and in particular to a visual inspection method, device and system for cartons. Background Art

[0002] A carton is a packaging container made of paper material, usually made of corrugated cardboard. It is light, strong and recyclable, and is widely used in the transportation and storage of goods.

[0003] After the product is produced, it is often necessary to pack the product in cartons and then transport it by truck. In order to save the loading space of the truck, the cartons often need to be stacked. The existing stacking method is often that the staff directly stacks the cartons manually, and it is difficult to consider the strength and force of each carton. It is difficult to avoid that some cartons with defects such as creases will become unstable under pressure, causing the products in the box to be squeezed and damaged. Summary of the invention

[0004] Based on this, it is necessary to provide a visual inspection method, device and system for cartons to address the above-mentioned problems.

[0005] The embodiment of the present invention is implemented by providing a visual inspection method for cartons, the method comprising:

[0006] S1: Obtain the compartment space dimensions of the transport vehicle;

[0007] S2: Determine the number of cartons to be loaded according to the compartment space size and carton size;

[0008] S3: Select the loading cartons corresponding to the loading quantity;

[0009] S4: For each loaded carton, a surface image of the loaded carton is collected by a visual device, and the weight of the loaded carton is obtained;

[0010] S5: determining the surface defects of the loaded carton according to the surface image;

[0011] S6: Determine the critical pressure value of the loaded carton in the case of the surface defect;

[0012] S7: performing simulated palletizing of each loaded carton according to the critical pressure value and the corresponding weight of each loaded carton, until obtaining a carton position arrangement in which the pressure on each loaded carton is not greater than the critical pressure value;

[0013] S8: Generate palletizing information including the position arrangement of the cartons, and send the palletizing information to a user terminal of a palletizer, so that the palletizer palletizes the loaded cartons according to the palletizing information.

[0014] In one embodiment, the present invention provides a visual inspection device for cartons, the device comprising:

[0015] An acquisition module, used to acquire the compartment space dimensions of the transport vehicle;

[0016] The first processing module is used to determine the number of cartons to be loaded according to the compartment space size and the carton size;

[0017] The second processing module is used to select loading cartons corresponding to the loading quantity;

[0018] The third processing module is used to collect a surface image of each loaded carton and obtain the weight of the loaded carton;

[0019] A fourth processing module is used to determine the surface defects of the loading carton according to the surface image;

[0020] A fifth processing module is used to determine a critical pressure value of the loaded carton in the case of the surface defect;

[0021] The sixth processing module is used to simulate the stacking of each loaded carton according to the pressure critical value and the corresponding weight of each loaded carton, until the carton position arrangement is obtained so that the pressure on each loaded carton is not greater than the pressure critical value;

[0022] The feedback module is used to generate the palletizing information including the position arrangement of the cartons, and send the palletizing information to the terminal of the palletizer, so that the palletizer can palletize the loaded cartons according to the palletizing information.

[0023] In one embodiment, the present invention provides a visual inspection system for cartons, the system comprising:

[0024] A visual device for collecting surface images of cartons being loaded onto a truck;

[0025] User terminal, used for receiving palletizing information;

[0026] The computer equipment communicates with the visual device and the user terminal, and is used to execute the visual inspection method for cartons.

[0027] The present invention provides a visual inspection method, device and system for cartons, wherein the method comprises obtaining the space dimensions of a compartment of a transport vehicle; determining the number of cartons to be loaded according to the space dimensions of the compartment and the size of the cartons; selecting loaded cartons corresponding to the number of loaded cartons; for each loaded carton, collecting the surface image of the loaded carton through a visual device and obtaining the weight of the loaded carton; determining the surface defects of the loaded carton according to the surface image; determining the critical pressure value of the loaded carton in the case of the surface defects; performing simulated palletizing on each loaded carton according to the critical pressure value and the corresponding weight of each loaded carton until the pressure on each loaded carton is not too large. The present invention relates to an embodiment of the present invention which provides a method for arranging carton positions at a critical pressure value; generating palletizing information including the carton position arrangement, and sending the palletizing information to the user terminal of the palletizer, so that the palletizer can palletize the loaded cartons according to the palletizing information; in the present application, the surface image of each loaded carton can be collected to determine its surface defects, and then the palletizing of the cartons on the transport vehicle can be simulated with the determined surface defects as the boundary conditions of the carton, so as to determine a palletizing method that will not cause any loaded carton to become unstable under pressure, and send the palletizing method to the palletizer, so as to guide the palletizer to palletize the loaded cartons according to the method, so as to ensure the safety of the products in each loaded carton. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 It is a flow chart of a visual inspection method for cartons provided in one embodiment;

[0029] Figure 2 A schematic diagram of pressure simulation of a visual inspection method for cartons provided in one embodiment;

[0030] Figure 3 A schematic diagram of a standard stack of a visual inspection method for cartons provided in one embodiment;

[0031] Figure 4 A module flow chart of a visual inspection device for cartons provided in one embodiment;

[0032] Figure 5 A schematic diagram of the composition of a visual inspection system for cartons provided in one embodiment;

[0033] Figure 6 FIG. 4 is a block diagram of the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0035] It is understood that the terms "first", "second", etc. used in the present invention may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script without departing from the scope of the present invention.

[0036] like Figure 1 As shown, in one embodiment, a visual inspection method for cartons is proposed, the method comprising:

[0037] S1: Obtain the compartment space dimensions of the transport vehicle;

[0038] S2: Determine the number of cartons to be loaded according to the compartment space size and carton size;

[0039] S3: Select the loading cartons corresponding to the loading quantity;

[0040] S4: For each loaded carton, a surface image of the loaded carton is collected by a visual device, and the weight of the loaded carton is obtained;

[0041] S5: determining the surface defects of the loaded carton according to the surface image;

[0042] S6: Determine the critical pressure value of the loaded carton in the case of the surface defect;

[0043] S7: performing simulated palletizing of each loaded carton according to the critical pressure value and the corresponding weight of each loaded carton, until obtaining a carton position arrangement in which the pressure on each loaded carton is not greater than the critical pressure value;

[0044] S8: Generate palletizing information including the position arrangement of the cartons, and send the palletizing information to a user terminal of a palletizer, so that the palletizer palletizes the loaded cartons according to the palletizing information.

[0045] In this embodiment, the method is executed in a computer device, which can be an independent physical server or terminal, or a server cluster composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud servers, cloud databases, cloud storage and CDN; a visual device communicates with the computer device, and the visual device can be a high-definition industrial camera. The visual device can be set on a product production line. After the product is packed, it will be transported to a designated location by a conveyor belt for loading. The visual device can be installed on the conveyor belt, and multiple visual devices can be set to fully capture images of each surface of the carton; a user terminal communicates with the computer device, and can be a smart phone, tablet computer, laptop computer, desktop computer, smart watch, etc., but is not limited to this.

[0046] In this embodiment, on the production line, the cartons corresponding to the loading quantity are selected, that is, the cartons corresponding to the loading quantity that are most recently conveyed by the conveyor belt are selected; a number is marked on the surface of each carton, and after the visual device captures the carton image, the computer device can recognize the number of the corresponding carton through the carton image; the carton position arrangement finally generated includes the position of each numbered carton in the stack, so that the staff can find the carton with the corresponding number according to the position for palletizing;

[0047] In this embodiment, the computer device stores parameter information of various types of transport vehicles (including the size of the carriage used for loading goods). After receiving the model of the transport vehicle for this transportation, the volume of the carriage can be determined, and then according to the volume of the cartons, the maximum number of cartons that can be loaded can be determined. In order to ensure that all cartons can be loaded on the vehicle and local position adjustment can be performed, the maximum number can be divided by a coefficient greater than 1 (such as 1.2) to obtain the final loading quantity;

[0048] In this embodiment, a filtering algorithm (such as Gaussian filtering and median filtering) is applied to the collected image to remove image noise, a histogram equalization method and other methods are used to improve the image contrast, a Canny edge detection algorithm is used to extract edge information, and a grayscale co-occurrence matrix method and other methods are used to extract texture features. The image is segmented into defect areas and normal areas according to a set threshold, and compared with a standard defect image to identify and mark surface defects.

[0049] In the present application, the surface image of each loaded carton can be collected to determine its surface defects, and then the stacking of the cartons on the transport vehicle can be simulated with the determined surface defects as the boundary conditions of the cartons, so as to determine the stacking method that will not cause any loaded carton to become unstable under pressure, and send the stacking method to the palletizer to guide the palletizer to stack the loaded cartons in this way, thereby ensuring the safety of the products in each loaded carton.

[0050] As a preferred embodiment, the collected surface image includes an upper surface image and a side surface image, and between step S5 and step S6, the following steps are further included:

[0051] Identify the size of each surface of the loading carton according to each surface image, and then determine the size of the loading carton;

[0052] Generate a three-dimensional model of the carton according to the determined size of the loading carton;

[0053] For each model surface of the carton three-dimensional model except the bottom surface, determining a surface image corresponding to the model surface;

[0054] It is determined whether there is a surface defect on the determined surface image. If so, the size and position of the surface defect are identified, and a corresponding simulated defect is generated on the model surface according to the identified size and position.

[0055] In this embodiment, the surface range in the surface image can be detected by a target recognition algorithm (such as the YOLO algorithm), and the size of the surface range can be further identified; the three-dimensional model of the carton is a finite element model established by finite element software (such as Abaqus software), and the material strength of the carton is pre-stored in the computer device. The finite element model is established with this material strength parameter as the strength boundary adjustment, so that the model has a load-bearing capacity consistent with the actual carton. In addition, according to the identified surface defects, the units at the corresponding positions on the corresponding model surface are adjusted by boundary adjustments such as shape and strength to obtain the final three-dimensional model of the carton.

[0056] As a preferred embodiment, determining the critical pressure value of the loading carton in the case of the surface defect includes:

[0057] S61: take n=0;

[0058] S62: performing a pressure simulation on the three-dimensional carton model corresponding to the loaded carton with n sides restricted, so as to determine a critical pressure value of the loaded carton when the n sides are restricted;

[0059] S63: Take n=n+1, and execute steps S62 to S63 until n is greater than 4.

[0060] The axial compression simulation of the carton three-dimensional model corresponding to the loaded carton with n sides restricted includes:

[0061] S621: Determine the three-dimensional model of the carton A combination of restricted sides;

[0062] S622: Select a restricted side combination, and mark the side corresponding to the restricted side combination on the three-dimensional model of the carton;

[0063] S623: applying a simulated limiting plane on the side of the mark;

[0064] S624: applying a basic pressure to the top surface of the three-dimensional carton model, and gradually increasing the pressure until the three-dimensional carton model becomes unstable, and taking the pressure corresponding to the instability as the instability pressure corresponding to the restricted side combination;

[0065] S625: Repeat steps S622 to S625 until the instability pressure corresponding to each combination of restricted sides is obtained, and the lowest instability pressure is used as the critical pressure value of the carton three-dimensional model when n sides are restricted.

[0066] In this embodiment, n is the number of restricted sides. The restriction of the sides will affect the compressive capacity of the carton. In the stack, there may be 0 to 4 restricted sides. For any value of n, For example, for n=2, two adjacent sides can form a restricted side combination, and one side and its opposite side can also form a restricted side combination, that is, any two sides can be selected from the four sides of the carton to form a restricted side combination, for a total of =6 combinations; e.g. Figure 2 As shown, since the cartons are in surface contact with each other, the basic pressure (the basic pressure is a preset smaller pressure, such as the pressure corresponding to one tenth of the weight of the loaded cartons) is a uniformly distributed pressure applied on the top surface of the carton three-dimensional model. The critical pressure value takes the lowest instability pressure, which can ensure that the carton will not become unstable when the pressure is lower than the critical pressure value. Therefore, the critical pressure value can characterize the overall pressure bearing capacity of the carton.

[0067] As a preferred embodiment, the weight of each loaded carton is the sum of the standard weight of the loaded goods and the standard weight of the loaded carton; and the simulated palletizing of each loaded carton according to the pressure critical value and the corresponding weight of each loaded carton includes:

[0068] Determine the standard stack according to the shape of the compartment space and the shape of the carton, and identify each stacking position of the standard stack;

[0069] When n takes any value among 0, 1, 2, 3 and 4, determine the critical pressure value of the three-dimensional carton model corresponding to each loaded carton when n sides are restricted, and arrange the critical pressure values ​​in descending order to obtain the carton ranking when n sides are restricted;

[0070] For each stacking position of the standard stack, the number of restricted surfaces of the stacking position is determined according to the number of adjacent stacking positions on the side of the stacking position, and the stacking positions with the same number of restricted surfaces are grouped into one group;

[0071] For each stacking position in each group, multiply the number of stacking positions above the stacking position by the weight of the loaded cartons to obtain the load-bearing weight of the stacking position, and sort the stacking positions in the group in descending order of load-bearing weight to obtain the stacking position sorting corresponding to the group;

[0072] According to the order of each stacking position and each carton order, the three-dimensional carton models are stacked into a stack having a shape consistent with the shape of the standard stack;

[0073] For each stacking position in the stacked pile, determine whether the pressure on the three-dimensional carton model in the stacking position reaches the corresponding instability pressure. If so, adjust the position of the three-dimensional carton model in the stacking position so that the pressure on the three-dimensional carton model in the stacking position is below the corresponding instability pressure. When the pressure on the three-dimensional carton model on each stacking position is below the corresponding instability pressure, the target stack is obtained;

[0074] The position of each carton three-dimensional model on the target stack is identified, thereby obtaining the carton position arrangement.

[0075] In this embodiment, if Figure 3 As shown, the standard stack is determined by first determining the shape and size of the bottom of the transport vehicle compartment, using a carton model to simulate filling the bottom of the vehicle, so that the bottom surface of the carton model completely covers the bottom surface of the compartment, that is, forming the first layer of the standard stack, and then stacking up layer by layer (each layer has the same area and shape) until the selected carton models are stacked. The stack formed is the standard stack, outlining the edges of each model of the standard stack, hiding all the models, leaving a three-dimensional grid, and the range of each grid represents a stacking position of the standard stack (the stacking position is the position of a certain row and column of a certain layer in the stack for stacking cartons), and its shape and size are consistent with the carton model; the standard stack is not the final stacking method, but only represents the overall shape of the stack formed at the end. Therefore, after obtaining the three-dimensional grid, the standard stack is broken up (or a copy model is generated for each model, and the copy model is subsequently stacked according to the standard stack) for subsequent stacking, and the subsequent stacking can use the three-dimensional grid as a reference;

[0076] In this embodiment, the standard weight of the loaded goods and the standard weight of the loaded cartons are weighed in advance by the staff and input into the computer device; when n takes each value of 0, 1, 2, 3 and 4, the critical pressure value of the three-dimensional carton model corresponding to each loaded carton is determined when n sides are restricted, that is, when n=0, the critical pressure value of each carton is determined when 0 sides are restricted, when n=1, the critical pressure value of each carton is determined when 1 side is restricted, and so on;

[0077] In this embodiment, each three-dimensional carton model is firstly stacked as a whole according to the sorting of each stacking position, the sorting of each carton and the standard stack; each carton three-dimensional model is stacked into a stack having the same shape as the standard stack, that is, after the stacked stack overlaps with the standard stack, each stacking position of the stack overlaps with a stacking position of the standard stack; after the stacking is completed, for each three-dimensional carton model, a corresponding carton weight is assigned to it so that each model is subjected to a corresponding pressure, and the stress condition of each three-dimensional carton model is monitored. If the corresponding instability pressure has been reached, it is locally adjusted until all the three-dimensional carton models do not reach the instability pressure; the obtained carton position arrangement includes the arrangement position of each numbered carton in each layer of the generated stack.

[0078] As a preferred embodiment, stacking the three-dimensional carton models into a stack having a shape consistent with the shape of a standard stack according to the order of each stacking position and the order of each carton includes:

[0079] Take the stacking position sequence of the group with the number of restricted faces being 0, place the three-dimensional carton models in the carton sequence corresponding to n=0 in the respective stacking positions in the stacking position sequence in order, and delete the already placed three-dimensional carton models in other carton sequences;

[0080] Take the stacking position sequence of the group with the number of restricted faces being 1, place the three-dimensional carton models in the carton sequence corresponding to n=1 in the order of precedence at each stacking position in the stacking position sequence, and delete the already placed three-dimensional carton models in other carton sequences;

[0081] Take the stacking position sequence of the group with the number of restricted faces being 2, place the three-dimensional carton models in the carton sequence corresponding to n=2 in the order of precedence at each stacking position in the stacking position sequence, and delete the already placed three-dimensional carton models in other carton sequences;

[0082] Take the stacking position sequence of the group with a restricted number of faces of 3, place the three-dimensional carton models in the carton sequence corresponding to n=3 in the order of precedence at each stacking position in the stacking position sequence, and delete the already placed three-dimensional carton models in other carton sequences;

[0083] Take the stacking position sorting of the group with the number of restricted faces being 4, place the three-dimensional carton models in the carton sorting corresponding to n=4 in the order of precedence at each stacking position in the stacking position sorting, and delete the already placed three-dimensional carton models in other carton sortings.

[0084] In this embodiment, the steps of placing the three-dimensional carton models in the carton sort in the order of precedence in each stacking position in the stacking position sort are as follows: take the first stacking position in the stacking position sort, and stack the first three-dimensional carton model in the carton sort on the stacking position, take the second stacking position in the stacking position sort, and stack the second three-dimensional carton model in the carton sort on the stacking position, and so on, until the stacking positions in the stacking position sort are filled.

[0085] In this embodiment, the carton is more likely to become unstable when the number of restriction surfaces is smaller. Therefore, the stacking positions of the group with fewer restriction surfaces are stacked first, so that the cartons with higher load-bearing capacity are stacked on these stacking positions first. Furthermore, the models at the front of the carton sorting are stacked on the front of the stacking position sorting, which can make the models with higher load-bearing capacity be subjected to greater pressure. This stacking method can prevent the models with low load-bearing capacity from being subjected to excessive pressure and becoming unstable.

[0086] As a preferred embodiment, determining whether the pressure on the three-dimensional carton model in the stacking position reaches the corresponding instability pressure, and if so, adjusting the position of the three-dimensional carton model in the stacking position includes:

[0087] Identify the restricted side combination of the three-dimensional carton model in the stacking position, and determine whether the pressure on the three-dimensional carton model reaches the instability pressure of the three-dimensional carton model under the restricted side combination;

[0088] If yes, the carton three-dimensional model is rotated around the vertical axis to change the combination of restricted sides of the carton three-dimensional model until the pressure on the carton three-dimensional model is lower than the instability pressure of the carton three-dimensional model under the corresponding combination of restricted sides;

[0089] If the pressure on the carton 3D model is still not lower than the corresponding instability pressure when the carton 3D model completes one rotation, the carton 3D model will be swapped with other carton 3D models one by one until the pressure on the two swapped carton 3D models is lower than the corresponding instability pressure.

[0090] In this embodiment, after the two cartons are swapped, if the pressure still exceeds the instability pressure, the two models can be rotated on the corresponding new stacking positions to adjust the corresponding restricted side combinations. If both models can be adjusted to a situation where the pressure does not exceed the instability pressure, the adjustment is completed. Otherwise, the two models are reset and the positions of the original model and other models are swapped again. In this embodiment, if a model cannot make the pressure less than the instability pressure under all optional adjustment methods, the computer device generates a prompt message to prompt the stacking personnel to replace the corresponding carton (take out the products in the carton, put them in a new carton, and then re-simulate through this method).

[0091] like Figure 4 As shown, in one embodiment, a visual inspection device for a carton is provided, the device comprising:

[0092] An acquisition module, used to acquire the compartment space dimensions of the transport vehicle;

[0093] The first processing module is used to determine the number of cartons to be loaded according to the compartment space size and the carton size;

[0094] The second processing module is used to select loading cartons corresponding to the loading quantity;

[0095] The third processing module is used to collect a surface image of each loaded carton and obtain the weight of the loaded carton;

[0096] A fourth processing module is used to determine the surface defects of the loading carton according to the surface image;

[0097] A fifth processing module is used to determine a critical pressure value of the loaded carton in the case of the surface defect, wherein the critical pressure value is a maximum pressure value at which the carton does not become unstable;

[0098] The sixth processing module is used to simulate the stacking of each loaded carton according to the pressure critical value and the corresponding weight of each loaded carton, until the carton position arrangement is obtained so that the pressure on each loaded carton is not greater than the pressure critical value;

[0099] The feedback module is used to generate the palletizing information including the position arrangement of the cartons, and send the palletizing information to the terminal of the palletizer, so that the palletizer can palletize the loaded cartons according to the palletizing information.

[0100] The process of each module in the visual inspection device for cartons provided in the embodiment of the present application realizing its respective function can be specifically referred to the aforementioned Figure 1 The description of the illustrated embodiment will not be repeated here.

[0101] like Figure 5 As shown, in one embodiment, a visual inspection system for cartons is provided, the system comprising:

[0102] A visual device for collecting surface images of cartons being loaded onto a truck;

[0103] User terminal, used for receiving palletizing information;

[0104] The computer equipment communicates with the visual device and the user terminal, and is used to execute the visual inspection method for cartons.

[0105] In the present application, computer equipment cooperates with visual terminals and user equipment to execute a visual inspection method for cartons, which can collect surface images of each loaded carton and then determine its surface defects. The stacking of cartons on transport vehicles is simulated with the determined surface defects as boundary conditions of the cartons, thereby determining a stacking method that will not cause any loaded carton to become unstable under pressure, and sending the stacking method to the palletizer to guide the palletizer to stack the loaded cartons in this way, thereby ensuring the safety of the products in each loaded carton.

[0106] Figure 6 FIG. 2 shows an internal structure diagram of a computer device in one embodiment. Figure 6 As shown, the computer device includes a processor, a memory, a network interface, an input device and a display screen connected through a system bus. Among them, the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program. When the computer program is executed by the processor, the processor can implement the visual inspection method for cartons provided in the embodiment of the present invention. The internal memory may also store a computer program. When the computer program is executed by the processor, the processor can execute the visual inspection method for cartons provided in the embodiment of the present invention. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0107] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0108] In one embodiment, the visual inspection device for cartons provided by the embodiment of the present invention can be implemented in the form of a computer program. The computer program can be used in Figure 6 The computer device shown in the figure is run on the computer device. The memory of the computer device can store various program modules that constitute the visual inspection device for cartons, such as: Figure 4 The acquisition module, the first processing module, the second processing module, the third processing module, the fourth processing module, the fifth processing module, the sixth processing module and the feedback module shown in the figure. The computer program composed of each program module enables the processor to execute the steps of the visual inspection method for cartons in each embodiment of the present invention described in this specification.

[0109] For example, Figure 6 The computer device shown can be Figure 4 The acquisition module in the visual inspection device for cartons shown executes step S1; the computer device may execute step S2 through the first processing module; the computer device may execute step S3 through the second processing module; the computer device may execute step S4 through the third processing module; the computer device may execute step S5 through the fourth processing module; the computer device may execute step S6 through the fifth processing module; the computer device may execute step S7 through the sixth processing module; the computer device may execute step S8 through the seventh processing module.

[0110] In one embodiment, a computer device is provided, the computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the following steps are implemented:

[0111] S1: Obtain the compartment space dimensions of the transport vehicle;

[0112] S2: Determine the number of cartons to be loaded according to the compartment space size and carton size;

[0113] S3: Select the loading cartons corresponding to the loading quantity;

[0114] S4: For each loaded carton, a surface image of the loaded carton is collected by a visual device, and the weight of the loaded carton is obtained;

[0115] S5: determining the surface defects of the loaded carton according to the surface image;

[0116] S6: Determine the critical pressure value of the loaded carton in the case of the surface defect;

[0117] S7: performing simulated palletizing of each loaded carton according to the critical pressure value and the corresponding weight of each loaded carton, until obtaining a carton position arrangement in which the pressure on each loaded carton is not greater than the critical pressure value;

[0118] S8: Generate palletizing information including the position arrangement of the cartons, and send the palletizing information to a user terminal of a palletizer, so that the palletizer palletizes the loaded cartons according to the palletizing information.

[0119] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the processor performs the following steps:

[0120] S1: Obtain the compartment space dimensions of the transport vehicle;

[0121] S2: Determine the number of cartons to be loaded according to the compartment space size and carton size;

[0122] S3: Select the loading cartons corresponding to the loading quantity;

[0123] S4: For each loaded carton, a surface image of the loaded carton is collected by a visual device, and the weight of the loaded carton is obtained;

[0124] S5: determining the surface defects of the loaded carton according to the surface image;

[0125] S6: Determine the critical pressure value of the loaded carton in the case of the surface defect;

[0126] S7: performing simulated palletizing of each loaded carton according to the critical pressure value and the corresponding weight of each loaded carton, until obtaining a carton position arrangement in which the pressure on each loaded carton is not greater than the critical pressure value;

[0127] S8: Generate palletizing information including the position arrangement of the cartons, and send the palletizing information to a user terminal of a palletizer, so that the palletizer palletizes the loaded cartons according to the palletizing information.

[0128] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0129] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0130] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0131] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A visual inspection method for cartons, characterized in that: The method comprises: S1: Obtain the compartment space dimensions of the transport vehicle; S2: Determine the number of cartons to be loaded according to the compartment space size and carton size; S3: Select the loading cartons corresponding to the loading quantity; S4: For each loaded carton, a surface image of the loaded carton is collected by a visual device, and the weight of the loaded carton is obtained; S5: determining the surface defects of the loaded carton according to the surface image; S6: Determine the critical pressure value of the loaded carton in the case of the surface defect; S7: performing simulated palletizing of each loaded carton according to the critical pressure value and the corresponding weight of each loaded carton, until obtaining a carton position arrangement in which the pressure on each loaded carton is not greater than the critical pressure value; S8: Generate palletizing information including the position arrangement of the cartons, and send the palletizing information to a user terminal of a palletizer, so that the palletizer palletizes the loaded cartons according to the palletizing information; The collected surface images include an upper surface image and a side surface image, and between step S5 and step S6, the following is also included: Identify the size of each surface of the loading carton according to each surface image, and then determine the size of the loading carton; Generate a three-dimensional model of the carton according to the determined size of the loading carton; For each model surface of the carton three-dimensional model except the bottom surface, determining a surface image corresponding to the model surface; Determine whether there is a surface defect on the determined surface image, and if so, identify the size and position of the surface defect, and generate a corresponding simulated defect on the model surface according to the identified size and position; Determining the critical pressure value of the loaded carton under the condition of the surface defect includes: S61: take n=0; S62: performing a pressure simulation on the three-dimensional carton model corresponding to the loaded carton with n sides restricted, so as to determine a critical pressure value of the loaded carton when the n sides are restricted; S63: Take n=n+1, and execute steps S62 to S63 until n is greater than 4; The axial compression simulation of the carton three-dimensional model corresponding to the loaded carton with n sides restricted includes: S621: Determine the three-dimensional model of the carton A combination of restricted sides; S622: Select a restricted side combination, and mark the side corresponding to the restricted side combination on the three-dimensional model of the carton; S623: applying a simulated limiting plane on the side of the mark; S624: applying a basic pressure to the top surface of the three-dimensional carton model, and gradually increasing the pressure until the three-dimensional carton model becomes unstable, and taking the pressure corresponding to the instability as the instability pressure corresponding to the restricted side combination; S625: Repeat steps S622 to S625 until the instability pressure corresponding to each combination of restricted sides is obtained, and the lowest instability pressure is used as the critical pressure value of the carton three-dimensional model when n sides are restricted.

2. The method according to claim 1, characterized in that: The weight of each loaded carton is the sum of the standard weight of the loaded goods and the standard weight of the loaded carton; the simulated palletizing of each loaded carton according to the critical pressure value and the corresponding weight of each loaded carton includes: Determine the standard stack according to the shape of the compartment space and the shape of the carton, and identify each stacking position of the standard stack; When n takes any value among 0, 1, 2, 3 and 4, determine the critical pressure value of the three-dimensional carton model corresponding to each loaded carton when n sides are restricted, and arrange the critical pressure values ​​in descending order to obtain the carton ranking when n sides are restricted; For each stacking position of the standard stack, the number of restricted surfaces of the stacking position is determined according to the number of adjacent stacking positions on the side of the stacking position, and the stacking positions with the same number of restricted surfaces are grouped into one group; For each stacking position in each group, multiply the number of stacking positions above the stacking position by the weight of the loaded cartons to obtain the load-bearing weight of the stacking position, and sort the stacking positions in the group in descending order of load-bearing weight to obtain the stacking position sorting corresponding to the group; According to the order of each stacking position and each carton order, the three-dimensional carton models are stacked into a stack having a shape consistent with the shape of the standard stack; For each stacking position in the stacked pile, determine whether the pressure on the three-dimensional carton model in the stacking position reaches the corresponding instability pressure. If so, adjust the position of the three-dimensional carton model in the stacking position so that the pressure on the three-dimensional carton model in the stacking position is below the corresponding instability pressure. When the pressure on the three-dimensional carton model on each stacking position is below the corresponding instability pressure, the target stack is obtained; The position of each carton three-dimensional model on the target stack is identified, thereby obtaining the carton position arrangement.

3. The method according to claim 2, characterized in that According to the order of each stacking position and each carton order, the three-dimensional carton models are stacked into a stack with a shape consistent with the shape of the standard stack, including: Take the stacking position sequence of the group with the number of restricted faces being 0, place the three-dimensional carton models in the carton sequence corresponding to n=0 in the respective stacking positions in the stacking position sequence in order, and delete the already placed three-dimensional carton models in other carton sequences; Take the stacking position sequence of the group with the number of restricted faces being 1, place the three-dimensional carton models in the carton sequence corresponding to n=1 in the order of precedence at each stacking position in the stacking position sequence, and delete the already placed three-dimensional carton models in other carton sequences; Take the stacking position sequence of the group with the number of restricted faces being 2, place the three-dimensional carton models in the carton sequence corresponding to n=2 in the order of precedence at each stacking position in the stacking position sequence, and delete the already placed three-dimensional carton models in other carton sequences; Take the stacking position sequence of the group with a restricted number of faces of 3, place the three-dimensional carton models in the carton sequence corresponding to n=3 in the order of precedence at each stacking position in the stacking position sequence, and delete the already placed three-dimensional carton models in other carton sequences; Take the stacking position sorting of the group with the number of restricted faces being 4, place the three-dimensional carton models in the carton sorting corresponding to n=4 in the order of precedence at each stacking position in the stacking position sorting, and delete the already placed three-dimensional carton models in other carton sortings.

4. The method according to claim 3, characterized in that: Determine whether the pressure on the three-dimensional model of the carton in the stacking position reaches the corresponding instability pressure. If so, adjust the position of the three-dimensional model of the carton in the stacking position including: Identify the restricted side combination of the three-dimensional carton model in the stacking position, and determine whether the pressure on the three-dimensional carton model reaches the instability pressure of the three-dimensional carton model under the restricted side combination; If yes, the carton three-dimensional model is rotated around the vertical axis to change the combination of restricted sides of the carton three-dimensional model until the pressure on the carton three-dimensional model is lower than the instability pressure of the carton three-dimensional model under the corresponding combination of restricted sides; If the pressure on the carton 3D model is still not lower than the corresponding instability pressure when the carton 3D model completes one rotation, the carton 3D model will be swapped with other carton 3D models one by one until the pressure on the two swapped carton 3D models is lower than the corresponding instability pressure.

5. A visual inspection device for cartons, characterized in that: The device comprises: An acquisition module, used to acquire the compartment space dimensions of the transport vehicle; The first processing module is used to determine the number of cartons to be loaded according to the compartment space size and the carton size; The second processing module is used to select loading cartons corresponding to the loading quantity; The third processing module is used to collect a surface image of each loaded carton and obtain the weight of the loaded carton; A fourth processing module is used to determine the surface defects of the loading carton according to the surface image; A fifth processing module is used to determine a critical pressure value of the loaded carton in the case of the surface defect, wherein the critical pressure value is a maximum pressure value at which the carton does not become unstable; The sixth processing module is used to simulate the stacking of each loaded carton according to the pressure critical value and the corresponding weight of each loaded carton, until the carton position arrangement is obtained so that the pressure on each loaded carton is not greater than the pressure critical value; A feedback module is used to generate palletizing information including the position arrangement of the cartons, and send the palletizing information to the terminal of the palletizer, so that the palletizer can palletize the loaded cartons according to the palletizing information; The collected surface images include an upper surface image and a side surface image, and between step S5 and step S6, the following is also included: Identify the size of each surface of the loading carton according to each surface image, and then determine the size of the loading carton; Generate a three-dimensional model of the carton according to the determined size of the loading carton; For each model surface of the carton three-dimensional model except the bottom surface, determining a surface image corresponding to the model surface; Determine whether there is a surface defect on the determined surface image, and if so, identify the size and position of the surface defect, and generate a corresponding simulated defect on the model surface according to the identified size and position; Determining the critical pressure value of the loaded carton under the condition of the surface defect includes: S61: take n=0; S62: performing a pressure simulation on the three-dimensional carton model corresponding to the loaded carton with n sides restricted, so as to determine a critical pressure value of the loaded carton when the n sides are restricted; S63: Take n=n+1, and execute steps S62 to S63 until n is greater than 4; The axial compression simulation of the carton three-dimensional model corresponding to the loaded carton with n sides restricted includes: S621: Determine the three-dimensional model of the carton A combination of restricted sides; S622: Select a restricted side combination, and mark the side corresponding to the restricted side combination on the three-dimensional model of the carton; S623: applying a simulated limiting plane on the side of the mark; S624: applying a basic pressure to the top surface of the three-dimensional carton model, and gradually increasing the pressure until the three-dimensional carton model becomes unstable, and taking the pressure corresponding to the instability as the instability pressure corresponding to the restricted side combination; S625: Repeat steps S622 to S625 until the instability pressure corresponding to each combination of restricted sides is obtained, and the lowest instability pressure is used as the critical pressure value of the carton three-dimensional model when n sides are restricted.

6. A visual inspection system for cartons, characterized in that: The system comprises: A visual device for collecting surface images of cartons being loaded onto a truck; User terminal, used for receiving palletizing information; A computer device, communicating with a visual device and a user terminal, is used to execute a visual inspection method for cartons as described in any one of claims 1 to 4.

Images