Parcel separation method and device for sorting line, electronic equipment and storage medium

Abstract

The invention provides a parcel separation method and device for a sorting line, electronic equipment and a storage medium. The sorting line is provided with a plurality of modules and further provided with a binocular vision camera and a separation baffle. The method comprises the steps that the position of a parcel on a sorting line is determined; when the parcel reaches a preset position, capturing an image of the parcel through a binocular vision camera, and determining an edge position of the parcel based on the image of the parcel; determining the size of the package based on the edge position of the package; the angle of the separation baffle is adjusted based on the size of the parcel to pass the parcel through the separation baffle. In the mode, a visual binocular camera and a separation baffle can be arranged on the sorting line, when the sorting line runs, the position and size of the parcel are tracked and calculated through the visual binocular camera and a visual algorithm, the angle of the separation baffle is dynamically adjusted according to the width of the parcel, and the parcels of different sizes can be filtered and separated; and therefore, rapid separation of the overlapped packages is achieved, and the achieving cost of package separation of the sorting line can be reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of inspection and sorting, and in particular to a package separation method, device, electronic equipment and storage medium for a sorting line. Background Art

[0002] At present, in the inspection and sorting system, parcels need to be scanned by the barcode scanning module to obtain parcel information before entering the sorting line, and then the parcels will be weighed, scanned by X-ray machines, etc. During the scanning process, the parcel information acquisition may fail or be wrong due to problems such as too fast scanning speed and overlapping parcels, thus affecting the accuracy of subsequent parcel weighing and X-ray scanning.

[0003] In the prior art, the overlapping parcels of the sorting line can be separated by a parcel separator, a parcel disperser and other equipment. However, it costs extra to set up a parcel separator and a parcel disperser in the sorting line, and the separation speed of the parcel separation is slow. Therefore, the method of separating parcels by a parcel separator, a parcel disperser and other equipment in the prior art has the problems of high cost and slow separation speed. Summary of the invention

[0004] In view of this, an object of the present invention is to provide a parcel separation method, device, electronic device and storage medium for a sorting line, so as to reduce the implementation cost of parcel separation of the sorting line and realize the rapid separation of overlapping parcels.

[0005] In a first aspect, an embodiment of the present invention provides a method for separating parcels on a sorting line, wherein the sorting line is provided with a plurality of modules, and the sorting line is also provided with a binocular vision camera and a separation baffle; the method comprises: determining the position of the parcel on the sorting line; when the parcel reaches a preset position, capturing an image of the parcel by a binocular vision camera, and determining an edge position of the parcel based on the image of the parcel; determining a size of the parcel based on the edge position of the parcel; and adjusting an angle of the separation baffle based on the size of the parcel so that the parcel passes through the separation baffle.

[0006] In an optional embodiment of the present application, the above-mentioned sorting line is also provided with a camera module; the step of determining the position of the package on the sorting line includes: taking an image of the sorting line by the camera module; identifying the package in the image of the sorting line, and determining the position of the package on the sorting line.

[0007] In an optional embodiment of the present application, the above-mentioned step of capturing an image of the package through a binocular vision camera and determining the edge position of the package based on the image of the package includes: capturing a left image and a right image of the package through a left lens and a right lens of the binocular vision camera respectively; calculating a disparity map of the left image and the right image, and determining a depth map based on the disparity map and an internal parameter of the binocular vision camera; and determining the edge position of the package based on the depth map.

[0008] In an optional embodiment of the present application, the step of determining the depth map based on the disparity map and the internal parameters of the binocular vision camera includes: calculating the depth value by the following formula: depth = (f×B) / disparity; wherein depth is the depth value, disparity is the disparity value, f is the focal length of the binocular vision camera, and B is the distance between the left lens and the right lens.

[0009] In an optional embodiment of the present application, the step of adjusting the angle of the separation baffle based on the size of the package includes: determining the angle of the separation baffle by the following formula: sinx = (lw-pw) / (2×bw); wherein x is the angle of the separation baffle, lw is the width of the sorting line, pw is the width of the package, and bw is the length of the separation baffle.

[0010] In an optional embodiment of the present application, after the above step of adjusting the angle of the separation baffle based on the size of the package, the method further includes: after the package passes through the separation baffle, adjusting the angle of the separation baffle to a preset angle.

[0011] In an optional embodiment of the present application, the above-mentioned sorting line is sequentially provided with a code scanning module, a weighing module, an X-ray machine module and a transplanting module; and a separation baffle is arranged between the code scanning module and the weighing module.

[0012] In a second aspect, an embodiment of the present invention further provides a parcel separation device for a sorting line, wherein the sorting line is provided with a plurality of modules, and the sorting line is also provided with a binocular vision camera and a separation baffle; the device comprises: a parcel position determination module, for determining the position of the parcel on the sorting line; a parcel edge position determination module, for capturing an image of the parcel by a binocular vision camera when the parcel arrives at a preset position, and determining the edge position of the parcel based on the image of the parcel; a parcel size determination module, for determining the size of the parcel based on the edge position of the parcel; and a separation baffle angle adjustment module, for adjusting the angle of the separation baffle based on the size of the parcel so that the parcel passes through the separation baffle.

[0013] In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising a processor and a memory, the memory storing computer executable instructions that can be executed by the processor, and the processor executing the computer executable instructions to implement the above-mentioned package separation method of the sorting line.

[0014] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the above-mentioned package separation method for the sorting line.

[0015] The embodiments of the present invention bring the following beneficial effects:

[0016] The embodiments of the present invention provide a method, device, electronic device and storage medium for separating packages on a sorting line, which determine the position of a package on the sorting line; when the package reaches a preset position, the image of the package is captured by a binocular vision camera, and the edge position of the package is determined based on the image of the package; the size of the package is determined based on the edge position of the package; and the angle of the separation baffle is adjusted based on the size of the package to allow the package to pass through the separation baffle. In this method, a visual binocular camera and a separation baffle can be set on the sorting line, and when the sorting line is running, the position and size of the package can be tracked and measured by the visual binocular camera and the visual algorithm, and the angle of the separation baffle can be dynamically adjusted according to the width of the package, so that packages of different sizes can be filtered and separated, thereby achieving rapid separation of overlapping packages, and can also reduce the cost of implementing package separation on the sorting line.

[0017] Other features and advantages of the present disclosure will be set forth in the following description, or some features and advantages may be inferred or unambiguously determined from the description, or may be learned by implementing the above-mentioned technology of the present disclosure.

[0018] In order to make the above-mentioned objectives, features and advantages of the present disclosure more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 A flow chart of a parcel separation method for a sorting line provided by an embodiment of the present invention;

[0021] Figure 2 A schematic diagram of a sorting line provided by an embodiment of the present invention;

[0022] Figure 3 A flow chart of another package separation method for a sorting line provided by an embodiment of the present invention;

[0023] Figure 4 A schematic diagram of calculating the angle of a separation baffle provided by an embodiment of the present invention;

[0024] Figure 5 A schematic structural diagram of a parcel separation device for a sorting line provided by an embodiment of the present invention;

[0025] Figure 6 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] At present, in the inspection and sorting system, the parcel needs to enter the sorting line after the parcel is scanned by the barcode scanning module to obtain the parcel information, and then the parcel will be weighed, scanned by an X-ray machine, and other operations. For example, after the parcel is weighed by the weighing module to obtain the weight information, the inspection and sorting system needs to automatically associate the weight information with the corresponding parcel. The parcel then enters the X-ray machine. When the X-ray machine scans and generates an X-ray image, the inspection and sorting system needs to automatically associate the X-ray image with the corresponding parcel and perform an intelligent review of the X-ray image. If the intelligent review finds that the parcel contains prohibited items, the inspection and sorting system will automatically move the parcel to the inspection area.

[0028] However, during the scanning process, the package information may fail to be obtained or may be incorrect due to problems such as scanning too fast or overlapping packages, which may affect the accuracy of subsequent package weighing and X-ray scanning.

[0029] In the prior art, the overlapping parcels of the sorting line can be separated by a parcel separator, a parcel disperser and other equipment. However, it costs extra to set up a parcel separator and a parcel disperser in the sorting line, and the separation speed of the parcel separation is slow. Therefore, the method of separating parcels by a parcel separator, a parcel disperser and other equipment in the prior art has the problems of high cost and slow separation speed.

[0030] Based on this, an embodiment of the present invention provides a parcel separation method, device, electronic device and storage medium for a sorting line. A visual binocular camera and a separation baffle can be set on the sorting line. When the sorting line is running, the position and size of the parcel can be tracked and measured by the visual binocular camera and the visual algorithm. The angle of the separation baffle is dynamically adjusted according to the width of the parcel. Parcels of different sizes can be filtered and separated, thereby achieving rapid separation of overlapping parcels and reducing the implementation cost of parcel separation on the sorting line.

[0031] To facilitate understanding of this embodiment, a parcel separation method for a sorting line disclosed in an embodiment of the present invention is first introduced in detail.

[0032] Embodiment 1:

[0033] The embodiment of the present invention provides a method for separating packages in a sorting line, wherein the sorting line is provided with a plurality of modules, and the sorting line is also provided with a binocular vision camera and a separation baffle. Figure 1 The flowchart of a parcel separation method of a sorting line is shown, and the parcel separation method of the sorting line comprises the following steps:

[0034] Step S102, determining the location of the package on the sorting line.

[0035] In some embodiments, the sorting line is further provided with a camera module; an image of the sorting line can be captured by the camera module; the package in the image of the sorting line can be identified to determine the position of the package on the sorting line.

[0036] The sorting line in this embodiment may be provided with one or more camera modules, through which the image of the sorting line may be captured. By identifying the parcel in the image of the sorting line, the position of the parcel on the sorting line may be further determined.

[0037] For example, if the sorting line is provided with a camera module, the camera module can capture the overall image of the sorting line. This embodiment can identify the packages in the overall image and determine the location of the packages in the sorting line.

[0038] For another example, a sorting line is provided with multiple camera modules, each of which can capture images of different areas of the sorting line. This embodiment can identify the packages in the images of the multiple camera modules and determine the location of the packages on the sorting line. The areas of the sorting line captured by each camera module can be completely different, or they can be the same or overlapped, which is not limited in this embodiment.

[0039] Preferably, in this embodiment, the Co-DETR (Collaborative Hybrid Assignments Training for DETR) model can be used to detect the package and determine the location of the package. The Co-DETR model is an improved DETR (Detection Transformer) model, which aims to solve the problem of insufficient positive sample allocation caused by one-to-one set matching in the DETR model, thereby improving the training efficiency and performance of the model.

[0040] The Co-DETR model enhances the training effect of the DETR model by introducing multiple label assignment methods. Specifically, the Co-DET model R uses multiple parallel auxiliary heads during training, which use a one-to-many label assignment method to increase the number of positive samples. These auxiliary heads share weights with the decoder of the main head during training, but are discarded during inference, without introducing additional parameters and computational costs.

[0041] The main advantages of the Co-DETR model include: 1. Improved training efficiency: Through a variety of label assignment methods, the Co-DETR model can provide richer supervision information, thereby accelerating the convergence of the model. 2. Enhanced feature learning: The use of auxiliary heads enhances the feature learning ability of the encoder and improves the discrimination ability of the model. 3. Reduced computational cost: During the inference process, the auxiliary heads are discarded and do not add additional computational burden.

[0042] Therefore, the Co-DETR model is suitable for the package detection task in this embodiment, especially for target detection in complex scenes, such as target detection under extremely low light conditions. By training on images under dark conditions and enhanced images, the Co-DETRR model can accurately detect targets under low light conditions.

[0043] Step S104, when the package arrives at a preset position, an image of the package is captured by a binocular vision camera, and an edge position of the package is determined based on the image of the package.

[0044] See also Figure 2 A schematic diagram of a sorting line is shown in FIG. Figure 2 As shown, the sorting line is provided with a code scanning module, a weighing module, an X-ray machine module and a transplanting module in sequence; a separation baffle is provided between the code scanning module and the weighing module.

[0045] The parcel needs to enter the sorting line after scanning the barcode through the barcode scanning module to obtain the parcel information. After the parcel is weighed by the weighing module to obtain the weight information, the inspection and sorting system needs to automatically associate the weight information with the corresponding parcel. The parcel then enters the X-ray machine module. When the X-ray machine scans and generates an X-ray image, the inspection and sorting system needs to automatically associate the X-ray image with the corresponding parcel and perform an intelligent review of the X-ray image in the transfer module. If the intelligent review finds that the parcel contains prohibited items, the inspection and sorting system will automatically transfer the parcel to the inspection area.

[0046] When the package reaches a specified position (which may be referred to as a depth strategy trigger line), this embodiment may trigger depth measurement. Figure 2 As shown, the package in this embodiment can be scanned by the code scanning module and then trigger the depth measurement, that is, the depth strategy trigger line can be set after the code scanning module.

[0047] In this embodiment, the image of the package can be captured by a binocular vision camera, and the edge position of the package can be determined based on the image of the package. The binocular vision camera can measure the distance of the object based on the parallax principle by simultaneously shooting the same scene with two cameras and calculating the pixel difference of the same object in the field of view of the two cameras.

[0048] 1. Parallax calculation: When the same object appears in both left and right images, its position in the two images will be offset due to the baseline distance between the cameras. This offset is called parallax. The parallax can be obtained by calculating the distance difference between the corresponding pixels in the two images.

[0049] 2. Triangulation principle: Use parallax, baseline distance and focal length to calculate the three-dimensional coordinates of an object. The distance calculation formula is: distance = (baseline distance × focal length) / parallax. Among them, baseline distance and focal length are fixed parameters of the camera, and parallax is calculated from image pixels.

[0050] 3. Image correction and matching: First, calibrate the binocular camera to obtain the internal and external parameters and homography matrix of the two cameras. Then, correct the original image according to the calibration results so that the two corrected images are located in the same plane and parallel to each other. Then, perform pixel matching and calculate the depth of each pixel according to the matching results to obtain a depth map.

[0051] Step S106, determining the size of the package based on the edge position of the package.

[0052] After determining the edge position of the package, the present embodiment may also determine the size of the package, wherein the size of the package may include: the length, height and width of the package.

[0053] Step S108, adjusting the angle of the separation baffle based on the size of the package to allow the package to pass through the separation baffle.

[0054] After determining the size of the package, the present embodiment can also adjust the angle of the separation baffle based on the size of the package, so that the package can pass through the separation baffle smoothly, and other packages overlapping with the package do not pass through the separation baffle, thereby achieving rapid separation of overlapping packages, and there is no need to set up additional equipment such as package separators and package dispersers, and the cost of implementing package separation on the sorting line can also be reduced.

[0055] The embodiment of the present invention provides a method for separating parcels on a sorting line, which determines the position of a parcel on the sorting line; when the parcel reaches a preset position, the image of the parcel is captured by a binocular vision camera, and the edge position of the parcel is determined based on the image of the parcel; the size of the parcel is determined based on the edge position of the parcel; and the angle of the separation baffle is adjusted based on the size of the parcel to allow the parcel to pass through the separation baffle. In this method, a visual binocular camera and a separation baffle can be set on the sorting line, and when the sorting line is running, the position and size of the parcel can be tracked and measured by the visual binocular camera and the visual algorithm, and the angle of the separation baffle can be dynamically adjusted according to the width of the parcel, so that parcels of different sizes can be filtered and separated, thereby achieving rapid separation of overlapping parcels, and can also reduce the cost of implementing parcel separation on the sorting line.

[0056] Embodiment 2:

[0057] This embodiment provides another method for separating packages in a sorting line. This method is implemented on the basis of the above embodiment, and focuses on the specific steps of determining the edge position of the package and adjusting the angle of the separation baffle. Figure 3 The flowchart of another method for separating parcels of a sorting line is shown, and the method for separating parcels of a sorting line comprises the following steps:

[0058] Step S302, determining the location of the package on the sorting line;

[0059] Step S304, when the package arrives at the preset position, the left image and the right image of the package are captured by the left lens and the right lens of the binocular vision camera respectively; the disparity map of the left image and the right image is calculated, and the depth map is determined based on the disparity map and the internal parameters of the binocular vision camera; the edge position of the package is determined based on the depth map.

[0060] This embodiment can simultaneously capture the left image and the right image from the left lens and the right lens of the binocular vision camera, use the stereo matching algorithm StereoSGBM (Semi-Global Block Matching) to calculate the disparity map of the left image and the right image, and generate a depth map according to the disparity map and the internal parameters of the binocular vision camera.

[0061] Among them, StereoSGBM is an algorithm for stereo vision, which is mainly used to calculate the disparity map of the image to generate the depth map. The StereoSGBM algorithm combines the characteristics of local matching and global optimization, and can provide more accurate disparity results while maintaining computational efficiency.

[0062] The main steps of the StereoSGBM algorithm include:

[0063] 1. Preprocessing: Perform edge detection and gradient calculation on the input left and right images to generate a gradient image.

[0064] 2. Matching cost calculation: For each pixel, calculate its matching cost under different disparities, usually using absolute difference or square difference as the cost function.

[0065] 3. Minimize the energy function: Define an energy function, including data terms and smoothing terms. The data term represents the matching cost, and the smoothing term represents the disparity continuity of adjacent pixels. Use the dynamic programming method to calculate the cumulative cost along multiple directions and find the minimum value as the final cost.

[0066] 4. Disparity map generation: Select the best disparity based on the final cost and generate the disparity map.

[0067] 5. Post-processing: Optimize the generated disparity map and process outliers or holes, usually using methods such as median filtering or WLS (weighted least squares) filtering.

[0068] In this embodiment, the depth value can be calculated by the following formula: depth = (f×B) / disparity; wherein depth is the distance (depth) from the target point to the camera, disparity is the disparity value, that is, the horizontal position difference (in pixels) of the same point in the same scene in two images, f is the focal length of the binocular vision camera, and B is the distance between the left lens and the right lens.

[0069] Step S306, determining the size of the package based on the edge position of the package.

[0070] Step S308, adjusting the angle of the separation baffle based on the size of the package to allow the package to pass through the separation baffle.

[0071] Among them, see Figure 4 A schematic diagram of calculating the angle of the separation baffle is shown. The angle of the separation baffle can be determined by the following formula: sinx=(lw-pw) / (2×bw); wherein x is the angle of the separation baffle, lw is the width of the sorting line, pw is the width of the package, and bw is the length of the separation baffle.

[0072] In summary, the existing method of separating packages by using a package separator, a package disperser and other equipment has the problems of high cost and slow separation speed.

[0073] The above method provided by the embodiment of the present invention can set a visual binocular camera and a separation baffle on the sorting line. When the sorting line is running, the position and size of the package are tracked and measured by the visual binocular camera and the visual algorithm, and the angle of the separation baffle is dynamically adjusted according to the width of the package. Parcels of different sizes can be filtered and separated, thereby realizing rapid separation of overlapping packages; and there is no need to additionally set up equipment such as package separators and package dispersers, and the cost of implementing package separation on the sorting line can also be reduced, which has the advantages of low cost and simple installation.

[0074] Embodiment three:

[0075] Corresponding to the above method embodiment, the embodiment of the present invention provides a parcel separation device for a sorting line, wherein the sorting line is provided with a plurality of modules, and the sorting line is also provided with a binocular vision camera and a separation baffle. Figure 5 The schematic diagram of the structure of a parcel separation device of a sorting line is shown, and the parcel separation device of the sorting line comprises:

[0076] A parcel location determination module 51, used to determine the location of the parcel on the sorting line;

[0077] A package edge position determination module 52, used for capturing an image of the package through a binocular vision camera when the package arrives at a preset position, and determining an edge position of the package based on the image of the package;

[0078] A package size determination module 53, for determining the size of the package based on the edge position of the package;

[0079] The separation baffle angle adjustment module 54 is used to adjust the angle of the separation baffle based on the size of the package so that the package passes through the separation baffle.

[0080] The embodiment of the present invention provides a parcel separation device for a sorting line, which determines the position of a parcel on the sorting line; when the parcel reaches a preset position, the image of the parcel is captured by a binocular vision camera, and the edge position of the parcel is determined based on the image of the parcel; the size of the parcel is determined based on the edge position of the parcel; and the angle of the separation baffle is adjusted based on the size of the parcel to allow the parcel to pass through the separation baffle. In this method, a visual binocular camera and a separation baffle can be set on the sorting line, and when the sorting line is running, the position and size of the parcel can be tracked and measured by the visual binocular camera and the visual algorithm, and the angle of the separation baffle can be dynamically adjusted according to the width of the parcel, so that parcels of different sizes can be filtered and separated, thereby realizing the rapid separation of overlapping parcels, and can also reduce the cost of implementing parcel separation on the sorting line.

[0081] The sorting line is also provided with a camera module; the package position determination module is used to capture an image of the sorting line through the camera module; identify the package in the image of the sorting line, and determine the position of the package on the sorting line.

[0082] The above-mentioned package edge position determination module is used to capture the left image and the right image of the package through the left lens and the right lens of the binocular vision camera respectively; calculate the disparity map of the left image and the right image, and determine the depth map based on the disparity map and the internal parameters of the binocular vision camera; determine the edge position of the package based on the depth map.

[0083] The above-mentioned package edge position determination module is used to calculate the depth value through the following formula: depth = (f×B) / disparity; wherein depth is the depth value, disparity is the disparity value, f is the focal length of the binocular vision camera, and B is the distance between the left lens and the right lens.

[0084] The separation baffle angle adjustment module is used to determine the angle of the separation baffle by the following formula: sinx=(lw-pw) / (2×bw); wherein x is the angle of the separation baffle, lw is the width of the sorting line, pw is the width of the package, and bw is the length of the separation baffle.

[0085] The above-mentioned device also includes: a separation baffle angle recovery module, which is used to adjust the angle of the separation baffle to a preset angle after the package passes through the separation baffle.

[0086] The sorting line is provided with a code scanning module, a weighing module, an X-ray machine module and a transplanting module in sequence; and a separation baffle is provided between the code scanning module and the weighing module.

[0087] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the parcel separation device of the sorting line described above can refer to the corresponding process in the embodiment of the parcel separation method of the sorting line mentioned above, and will not be repeated here.

[0088] Embodiment 4:

[0089] The embodiment of the present invention also provides an electronic device for running the parcel separation method of the above-mentioned sorting line; see Figure 6 A structural schematic diagram of an electronic device is shown, the electronic device includes a memory 100 and a processor 101, wherein the memory 100 is used to store one or more computer instructions, and the one or more computer instructions are executed by the processor 101 to implement the package separation method of the above-mentioned sorting line.

[0090] Further, Figure 6 The electronic device shown further includes a bus 102 and a communication interface 103 , and the processor 101 , the communication interface 103 and the memory 100 are connected via the bus 102 .

[0091] The memory 100 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 103 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used. The bus 102 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0092] The processor 101 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 101. The above processor 101 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present invention can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module may be located in a storage medium mature in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 100, and the processor 101 reads the information in the memory 100 and completes the steps of the method of the above embodiment in combination with its hardware.

[0093] An embodiment of the present invention further provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the package separation method for the above-mentioned sorting line. The specific implementation can be found in the method embodiment, which will not be repeated here.

[0094] The computer program product of the package separation method, device, electronic device and storage medium for the sorting line provided in the embodiments of the present invention includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the method in the previous method embodiment. The specific implementation can be found in the method embodiment, which will not be repeated here.

[0095] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and / or device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0096] In addition, in the description of the embodiments of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0097] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0098] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0099] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for separating packages on a sorting line, characterized in that: The sorting line is provided with a plurality of modules, and the sorting line is also provided with a binocular vision camera and a separation baffle; the method comprises: determining the location of the parcel in the sorting line; When the package arrives at a preset position, the binocular vision camera captures an image of the package, and determines an edge position of the package based on the image of the package; determining a size of the package based on edge locations of the package; The angle of the separation baffle is adjusted based on the size of the package to allow the package to pass through the separation baffle.

2. The method according to claim 1, characterized in that The sorting line is also provided with a camera module; the step of determining the position of the package on the sorting line comprises: Taking an image of the sorting line by using the camera module; A package is identified in the image of the sorting line, and a position of the package on the sorting line is determined.

3. The method according to claim 1, characterized in that The step of capturing an image of the package by the binocular vision camera and determining the edge position of the package based on the image of the package comprises: Capturing a left image and a right image of the package through a left lens and a right lens of the binocular vision camera respectively; Calculating a disparity map of the left image and the right image, and determining a depth map based on the disparity map and an internal parameter of the binocular vision camera; The edge position of the package is determined based on the depth map.

4. The method according to claim 3, characterized in that The step of determining a depth map based on the disparity map and the internal parameters of the binocular vision camera comprises: The depth value is calculated by the following formula: depth = (f×B) / disparity; wherein depth is the depth value, disparity is the disparity value, f is the focal length of the binocular vision camera, and B is the distance between the left lens and the right lens.

5. The method according to claim 1, characterized in that The step of adjusting the angle of the separation baffle based on the size of the package comprises: The angle of the separation baffle is determined by the following formula: sinx=(lw-pw) / (2×bw); wherein x is the angle of the separation baffle, lw is the width of the sorting line, pw is the width of the package, and bw is the length of the separation baffle.

6. The method according to any one of claims 1 to 5, characterized in that: After the step of adjusting the angle of the separation baffle based on the size of the package, the method further includes: After the package passes through the separation baffle, the angle of the separation baffle is adjusted to a preset angle.

7. The method according to any one of claims 1 to 5, characterized in that: The sorting line is provided with a code scanning module, a weighing module, an X-ray machine module and a transplanting module in sequence; the separation baffle is provided between the code scanning module and the weighing module.

8. A parcel separation device for a sorting line, characterized in that: The sorting line is provided with a plurality of modules, and the sorting line is also provided with a binocular vision camera and a separation baffle; the device comprises: A parcel location determination module, used to determine the location of the parcel on the sorting line; A package edge position determination module, used for capturing an image of the package through the binocular vision camera when the package arrives at a preset position, and determining an edge position of the package based on the image of the package; A package size determination module, configured to determine the size of the package based on the edge position of the package; The separation baffle angle adjustment module is used to adjust the angle of the separation baffle based on the size of the package so that the package passes through the separation baffle.

9. An electronic device, characterized in that: The electronic device includes a processor and a memory, wherein the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement the package separation method of the sorting line according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are called and executed by the processor, the computer-executable instructions prompt the processor to implement the parcel separation method for the sorting line according to any one of claims 1 to 7.

Images