Express separation method, device, equipment, storage medium and product
By obtaining the 3D point cloud information of the objects to be separated, screening and performing secondary separation, the problem of low accuracy of separation of mechanical equipment is solved, and the accuracy and efficiency of express separation are improved.
Patent Information
- Application Number
- CN202410628844.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-21
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-05-21
AI Technical Summary
In the prior art, mechanical equipment has a single function when used for express separation, resulting in low accuracy in express separation, especially when the express volume is large, stacking is prone to occur, affecting the separation efficiency.
By obtaining the image information of the object to be separated, especially the 3D point cloud, the object feature extraction and posture determination are performed, overlapping objects are selected and secondary separation is performed until the separation of all objects is achieved.
It improves the accuracy and efficiency of express separation, and ensures the integrity and correct classification of objects.
Smart Images

Figure CN118212392B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of artificial intelligence technology, and in particular to express separation methods, devices, equipment, storage media and products. Background Art
[0002] At present, with the trend of economic globalization and the accelerated development of e-commerce, the logistics industry is changing from traditional logistics to modern logistics. The essential characteristics of modern logistics are to strengthen resources and optimize the entire logistics process, so the logistics industry has become an indispensable basic support in a network-developed society. Among them, in the process of logistics express delivery, the separation of express items is an important node. At present, most of the separation of express items is done by manual sorting, but with the increase in the workload of express sorting, manual sorting has the problems of low efficiency and high cost.
[0003] The related art proposes to use mechanical equipment to sort express items to replace manual sorting. However, the mechanical equipment in this method has a single sorting function. When the express volume is large, express items are easily piled up, resulting in low accuracy in express separation.
[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention
[0005] The main purpose of this application is to provide a method for express separation, aiming to solve the technical problem of low accuracy of express separation.
[0006] To achieve the above objectives, the present application proposes a method for separating express delivery, which comprises:
[0007] Get the object to be separated;
[0008] Separating the object to be separated once to obtain separated objects after the separation and image information of the separated objects after the separation;
[0009] Based on the image information, overlapping objects are screened out from the separated objects after the primary separation, and the overlapping objects are subjected to secondary separation to obtain separated target objects.
[0010] In one embodiment, the image information includes a 3D point cloud, and the step of selecting overlapping objects from the separated objects after the first separation based on the image information includes:
[0011] Based on the 3D point cloud, feature extraction is performed through a preset object segmentation model to obtain an object feature map;
[0012] Determining object posture information based on the object feature map and the 3D point cloud;
[0013] Based on the object posture information, overlapping objects are obtained by screening out the separated objects after the first separation.
[0014] In one embodiment, the step of determining the object posture information based on the object feature map and the 3D point cloud includes:
[0015] Determining a semantic mask and a center offset of the object feature map;
[0016] Combining the 3D point cloud with the center offset to obtain a combined graph;
[0017] Based on the semantic mask, clustering calculation is performed on the combination graph to obtain object posture information.
[0018] In one embodiment, the step of selecting overlapping objects from the separated objects after the first separation based on the object posture information includes:
[0019] Based on the object posture information, determining the outer contour information of the separated object after the first separation;
[0020] Deleting the outer contour information of each separated object after the first separation to obtain remaining outer contour information;
[0021] Comparing the remaining outer contour information with the outer contour information to obtain a comparison result;
[0022] If the comparison result is that the number of contours in the remaining peripheral contour information is less than the number of contours in the peripheral contour information, then the separated object is a non-overlapping object;
[0023] If the number of contours in the remaining outer contour information is equal to or greater than the number of contours in the outer contour information, the separated object is an overlapping object.
[0024] In one embodiment, after the step of determining that the separated objects are overlapping objects if the number of contours in the remaining outer contour information is equal to or greater than the number of contours in the outer contour information, the method includes:
[0025] Determining area information of the separated object after the first separation based on the object posture information;
[0026] Based on the area information, classification information of each of the overlapping objects is determined, wherein the classification information includes a full overlap category and an intersection category.
[0027] In one embodiment, the step of determining classification information of each of the overlapping objects based on the area information includes:
[0028] Adding the area information of each overlapping object and its adjacent object to obtain an addition result;
[0029] Comparing the sum of the overlapping objects with their area information to obtain a comparison result;
[0030] If the comparison result is that the addition result is equal to its area information, then the classification information of the separated object is a full overlap category;
[0031] If the comparison result is that the addition result is not equal to its area information, the classification information of the separated object is an intersection category.
[0032] In addition, to achieve the above-mentioned purpose, the present application also proposes a courier separation device, the courier separation device comprising:
[0033] An acquisition module, used for acquiring objects to be separated;
[0034] A separation module, used for performing a separation on the object to be separated, and obtaining separated objects after the separation and image information of the separated objects after the separation;
[0035] The screening module is used to screen the separated objects after the primary separation to obtain overlapping objects based on the image information, and perform secondary separation on the overlapping objects to obtain separated target objects.
[0036] In addition, to achieve the above-mentioned purpose, the present application also proposes an express separation device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the express separation method described above.
[0037] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the express separation method described above are implemented.
[0038] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the express separation method described above.
[0039] One or more technical solutions proposed in this application have at least the following technical effects:
[0040] The present application improves the accuracy of express delivery separation by, after separating the objects to be separated once, determining the overlapping objects based on the image information of the separated objects after the first separation, and then performing a second separation on the overlapping objects until all the objects are separated. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0043] Figure 1 A schematic diagram of a flow chart provided for the first embodiment of the express separation method of the present application;
[0044] Figure 2 This is a schematic diagram of the structure of the primary separation device of the express separation method of this application;
[0045] Figure 3 This is a schematic diagram of the structure of the secondary separation device of the express separation method of this application;
[0046] Figure 4 This is a schematic diagram of the module structure of the express delivery separation device according to an embodiment of the present application;
[0047] Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the express separation method in the embodiment of the present application.
[0048] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0049] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.
[0050] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.
[0051] The main solution of the embodiment of the present application is: obtaining objects to be separated; performing a separation on the objects to be separated to obtain separated objects after the first separation and image information of the separated objects after the first separation; based on the image information, screening out overlapping objects from the separated objects after the first separation, and performing a second separation on the overlapping objects to obtain separated target objects.
[0052] In this embodiment, for ease of description, the express separation device is used as the execution body for explanation below.
[0053] The related art proposes to use mechanical equipment to sort express items to replace manual sorting. However, the mechanical equipment in this method has a single sorting function. When the express volume is large, express items are easily piled up, resulting in low accuracy in express separation.
[0054] The present application provides a solution to achieve express delivery separation, thereby improving the security of express delivery separation.
[0055] It can be seen from the above embodiments that the present application improves the accuracy of express delivery separation by separating the objects to be separated once, judging the overlapping objects based on the image information of the separated objects after the first separation, and then performing a second separation on the overlapping objects until all the objects are separated.
[0056] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a terminal system, etc. The following takes the bastion host as an example to illustrate this embodiment and the following embodiments.
[0057] Based on this, the embodiment of the present application provides a method for separating express delivery. Figure 1 , Figure 1 This is a flow chart of the first embodiment of the express separation method of the present application.
[0058] In this embodiment, the express separation method includes steps S100 to S300:
[0059] Step S100, obtaining objects to be separated;
[0060] In a specific implementation, the objects to be separated refer to express objects to be separated individually, wherein the express objects can be documents or parcels, wherein the parcels can be small parcels with small volume or large parcels with large volume.
[0061] In a specific implementation, the device may obtain the objects to be separated by receiving the express items placed by the courier based on a preset express conveyor belt in the express system, thereby obtaining the objects to be separated, and subsequently separating the objects to be separated to achieve single-item separation of multiple express deliveries.
[0062] Step S200, performing a separation on the object to be separated, and obtaining a separated object after the separation and image information of the separated object after the separation;
[0063] In the specific implementation, refer to Figure 2The device is provided with a plurality of primary separation devices. The primary separation devices initially separate the objects on the conveyor belt through a wavy conveyor belt with a certain amplitude. The overlapping objects are separated by the principle that the falling speeds of the overlapping objects are the same but the contact areas with the conveyor belt are different during the falling process, thereby obtaining the separated objects after the primary separation.
[0064] Secondly, the device also acquires images of the separated objects after the first separation, including: (1) the image of the separated objects after the current first separation can be taken by a camera; (2) it can also be irradiated by an X-ray source so that the X-rays pass through the object to be measured and then generate an X-ray image in the device; (2) it can also be photographed by a preset grasping device. Secondly, the device uses the left and right infrared cameras and the camera internal parameters to use the triangulation method to achieve depth measurement, and then obtains the depth map of the photographed object, and generates a 3D point cloud by reversely projecting the depth map of the object through the internal parameters of the grasping device, that is, the image information of the separated object after the first separation is a 3D point cloud.
[0065] Step S300 , based on the image information, overlapping objects are screened from the separated objects after the primary separation, and the overlapping objects are secondary separated to obtain separated target objects.
[0066] In a specific implementation, since there are still a certain number of overlapping objects among the separated objects after the first separation, the present application proposes to screen out overlapping objects from the separated objects after the first separation based on the image information, and then perform a second separation on the overlapping objects to obtain the separated target objects.
[0067] In the specific implementation, refer to Figure 3 , for the determined overlapping objects, Figure 3 The secondary separation equipment is used to separate overlapping objects, specifically through a cone barrel with a certain amplitude, so that large and small objects are separated during the descent of overlapping objects. Compared with the primary separation equipment, the secondary separation equipment has a larger falling amplitude, making it easier to fall and separate.
[0068] Furthermore, after the device screens out overlapping objects from the separated objects after the primary separation based on the image information and performs secondary separation on the overlapping objects to obtain separated target objects, the device further includes the following steps:
[0069] The device obtains the image information of the separated target object, and then screens the image information of the separated target object for the next cycle to obtain the overlapping objects of the next cycle, and then performs secondary separation on the overlapping objects to obtain the separated target object. That is, the overlapping object detection is performed iteratively on the objects until there are no overlapping objects in the objects before stopping the separation.
[0070] In a specific implementation, the step of selecting overlapping objects from the separated objects after the first separation based on the image information includes:
[0071] The device extracts features based on the 3D point cloud through a preset object segmentation model to obtain an object feature map; determines object posture information based on the object feature map and the 3D point cloud; and screens overlapping objects from the separated objects after the first separation based on the object posture information.
[0072] It should be noted that the preset object segmentation model refers to a model that uses U-Net as the network architecture and extracts the features of the object through a Taylor neural network; the present application proposes to use a high-order Taylor function for feature extraction, wherein a high-order Taylor function refers to a Taylor function expansion of the second order or higher; feature information extraction refers to feature extraction of high-order information that is conducive to boundary segmentation; and an object feature map refers to a feature map after extracting high-order information. The preset object segmentation model is a model that exists in a computer device with a camera function, and the 3D point cloud is processed by the object segmentation model in the computer device to obtain a processed feature map.
[0073] In the specific implementation, the present application first examines the relationship between the fully connected neural network and the Taylor expansion. The convolutional neural network is then redesigned into a Taylor neural network using the Taylor expansion. For objects placed in a disorderly manner, the segmentation of boundaries affects the segmentation of objects of different instances. When using neural networks for image segmentation, the high-frequency features of objects may be beneficial for segmenting the boundaries of different objects. To this end, the present application proposes high-order modeling of the main high-frequency information in the image. For a network with several stacked convolutional layers, different layers can further extract high-frequency features from their respective inputs, such as textures and edges.
[0074] It is understood that the object posture information refers to an instance mask for segmenting the boundary of a single object, wherein the instance mask refers to information for segmenting a single object. The object feature map and the 3D point cloud are processed to obtain the object posture information. The device processes the object feature map and the 3D point cloud through a program in a computer device to obtain an instance mask for segmenting the boundary of a single object.
[0075] In a specific implementation, the step of determining the object posture information based on the object feature map and the 3D point cloud includes:
[0076] The device determines the semantic mask and center offset of the object feature map; combines the 3D point cloud with the center offset to obtain a combined map; and performs clustering calculation on the combined map based on the semantic mask to obtain object posture information.
[0077] It should be noted that the semantic mask refers to three semantic categories including background, desktop and desktop objects; the combined image refers to an image of the predicted object center of each pixel obtained by adding the 3D point cloud and the object offset. The device combines the 3D point cloud with the center offset to obtain a combined image; based on the semantic mask, the device performs mean shift clustering calculation on the combined image to obtain object posture information. The device sends the object feature map to the convolution layer to obtain the semantic mask and center offset, and visualizes the center offset using the optical flow method. The device processes the object feature map through the preset instance segmentation model in the computer device to obtain the semantic mask and center offset. The preset instance segmentation model adds the 3D point cloud and the center offset to obtain the center drift, and calculates the center drift to obtain the object posture information.
[0078] In a specific implementation, the device performs mean shift clustering calculation on the combined graph to obtain the object posture information;
[0079] It is understandable that in order to generate the object posture information, the device uses mean shift clustering for center voting. Mean shift clustering is a non-parametric, iterative pattern search algorithm that does not require a priori knowledge of the number of clusters and does not restrict the shape of the clusters. Mean shift clustering is used to find distribution patterns approximated by kernel density estimation (KDE). The present application uses Gaussian mean shift, and after clustering by center voting, each pixel is assigned to the nearest cluster center. The computer device calculates the combined graph to obtain the object posture information.
[0080] In a specific implementation, the step of selecting overlapping objects from the separated objects after the first separation based on the object posture information includes:
[0081] The device determines the outer contour information of the separated objects after the first separation based on the object posture information; deletes the outer contour information of each separated object after the first separation to obtain remaining outer contour information; compares the remaining outer contour information with the outer contour information to obtain a comparison result; if the comparison result is that the number of contours in the remaining outer contour information is less than the number of contours in the outer contour information, then the separated object is a non-overlapping object; if the number of contours in the remaining outer contour information is equal to or greater than the number of contours in the outer contour information, then the separated object is an overlapping object.
[0082] In a specific implementation, the object posture information includes the outer contour information of all separated objects after one separation. As for whether each separated object is an overlapping object, the device specifically deletes the outer contour of the separated object that needs to be judged, and retains the outer contours of all other objects, that is, the remaining outer contour information. If after deleting the outer contour of the separated object that needs to be judged, the remaining outer contour information is compared with the outer contour information, and the number of contours in the remaining outer contour information is less than the number of contours in the outer contour information, then the separated object is a non-overlapping object; if the number of contours in the remaining outer contour information is equal to or greater than the number of contours in the outer contour information, then the separated object is an overlapping object. In this way, the overlapping judgment of the object is made through its 3D point cloud, which is more accurate than image judgment.
[0083] In a specific implementation, after the step of determining that if the number of contours in the remaining peripheral contour information is equal to or greater than the number of contours in the peripheral contour information, the separated objects are overlapping objects, the method includes:
[0084] The device determines the area information of the separated objects after the first separation based on the object posture information; and determines the classification information of each of the overlapping objects based on the area information, wherein the classification information includes a full overlap category and an intersection category.
[0085] It should be noted that overlapping objects also include objects in the full overlapping category and objects in the intersecting category, wherein the full overlapping category objects refer to two or more objects that completely overlap, and the intersecting category objects refer to two or more objects that only partially overlap.
[0086] In a specific implementation, the present application proposes to classify overlapping objects and perform different separation treatments on overlapping objects of different categories to improve the object separation effect. For example, objects in the fully overlapping category are more difficult to separate than objects in the intersecting category. Therefore, objects in the fully overlapping category require object separation parameters with higher vibration frequencies to better separate the objects.
[0087] In a specific implementation, the step of determining the classification information of each of the overlapping objects based on the area information includes:
[0088] The device respectively adds the area information of each overlapping object and its adjacent object to obtain an addition result; compares the addition result of each overlapping object with its area information to obtain a comparison result; if the comparison result is that the addition result is equal to its area information, then the classification information of the separated object is a full overlap category; if the comparison result is that the addition result is not equal to its area information, then the classification information of the separated object is an intersection category.
[0089] In a specific implementation, the present application proposes to classify overlapping objects by the area information of their adjacent objects, add the area information of each overlapping object and its adjacent objects to obtain an addition result; compare the addition result of each overlapping object with its area information to obtain a comparison result; if the comparison result is that the addition result is equal to its area information, then the classification information of the separated object is a full overlapping category; if the comparison result is that the addition result is not equal to its area information, then the classification information of the separated object is an intersection category.
[0090] In a specific implementation, the present application also proposes to perform corresponding separation processing according to the classification information of the separated objects. Specifically, the device determines a separation processing scheme based on the classification information of the separated objects, and transports the objects to corresponding secondary separation equipment based on the separation processing scheme, wherein the secondary separation equipment includes equipment with different separation parameters. The present application proposes to classify overlapping objects and perform different separation processing on overlapping objects of different categories, thereby improving the separation effect of the objects.
[0091] The present application improves the accuracy of express delivery separation by, after separating the objects to be separated once, determining the overlapping objects based on the image information of the separated objects after the first separation, and then performing a second separation on the overlapping objects until all the objects are separated.
[0092] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the express separation method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.
[0093] This application also provides a courier separation device, please refer to Figure 4 , the express separation device comprises:
[0094] An acquisition module 10 is used to acquire objects to be separated;
[0095] A separation module 20, configured to perform a separation on the object to be separated, and obtain separated objects after the separation and image information of the separated objects after the separation;
[0096] The screening module 30 is used to screen the separated objects after the primary separation to obtain overlapping objects based on the image information, and perform secondary separation on the overlapping objects to obtain separated target objects.
[0097] Optionally, the screening module 30 includes:
[0098] A feature extraction module, used to extract features based on the 3D point cloud through a preset object segmentation model to obtain an object feature map;
[0099] A determination module, used to determine the object posture information based on the object feature map and the 3D point cloud;
[0100] The overlapping object screening module is used to screen the overlapping objects from the separated objects after the first separation based on the object posture information.
[0101] Optionally, the determining module includes:
[0102] A feature map information determination module, used to determine the semantic mask and center offset of the object feature map;
[0103] A combining module, used for combining the 3D point cloud with the center offset to obtain a combined graph;
[0104] A clustering module is used to perform clustering calculation on the combination graph based on the semantic mask to obtain object posture information.
[0105] Optionally, the overlapping object screening module includes:
[0106] An outer contour information determination module, used to determine the outer contour information of the separated object after the first separation based on the object posture information;
[0107] A deleting module, used for deleting the outer contour information of each separated object after the first separation, to obtain the remaining outer contour information;
[0108] A comparison module, used for comparing the remaining outer contour information with the outer contour information to obtain a comparison result;
[0109] a non-overlapping object determination module, configured to determine that the separated object is a non-overlapping object if the comparison result is that the number of contours in the remaining peripheral contour information is less than the number of contours in the peripheral contour information;
[0110] The overlapping object determining module is used for determining that the separated object is an overlapping object if the number of contours in the remaining peripheral contour information is equal to or greater than the number of contours in the peripheral contour information.
[0111] Optionally, the express separation device further comprises:
[0112] An area information determination module, used to determine the area information of the separated object after the first separation based on the object posture information;
[0113] The classification information determination module is used to determine the classification information of each of the overlapping objects based on the area information, wherein the classification information includes a full overlap category and an intersection category.
[0114] Optionally, the classification information determination module includes:
[0115] An area calculation module, used to add the area information of each overlapping object and its adjacent objects to obtain an addition result;
[0116] A comparison module, used for comparing the addition result of each overlapping object with its area information to obtain a comparison result;
[0117] A full overlap category determination module, used for determining that if the comparison result is that the addition result is equal to its area information, the classification information of the separated object is a full overlap category;
[0118] The intersection category determination module is used for determining that if the comparison result is that the addition result is not equal to its area information, the classification information of the separated object is an intersection category.
[0119] The express separation device provided by the present application adopts the express separation method in the above embodiment, which can solve the technical problem of express separation. Compared with the prior art, the beneficial effects of the express separation device provided by the present application are the same as the beneficial effects of the express separation method provided by the above embodiment, and the other technical features in the express separation device are the same as the features disclosed in the above embodiment method, which will not be repeated here.
[0120] The present application provides an express separation device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the express separation method in the above-mentioned embodiment one.
[0121] Reference below Figure 5 , which shows a schematic diagram of the structure of a courier separation device suitable for implementing the embodiment of the present application. The courier separation device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The express separation device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0122] like Figure 5As shown, the express separation device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the express separation device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the express separation device to communicate with other devices wirelessly or by wire to exchange data. Although the express separation device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.
[0123] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.
[0124] The express separation device provided by the present application adopts the express separation method in the above embodiment, which can solve the technical problem of express separation. Compared with the prior art, the beneficial effects of the express separation device provided by the present application are the same as the beneficial effects of the express separation method provided by the above embodiment, and the other technical features in the express separation device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.
[0125] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.
[0126] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
[0127] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the express separation method in the above-mentioned embodiment.
[0128] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.
[0129] The computer-readable storage medium may be included in the express separation device; or it may exist independently without being assembled into the express separation device.
[0130] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the express separation device, the express separation device performs: express separation.
[0131] Computer program code for performing the operations of the present application may be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0132] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0133] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.
[0134] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned express separation method, and can solve the technical problem of express separation. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the express separation method provided in the above-mentioned embodiment, and will not be repeated here.
[0135] The present application also provides a computer program product, including a computer program, which implements the steps of the express separation method as described above when executed by a processor.
[0136] The computer program product provided in this application can solve the technical problem of express separation. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the express separation method provided in the above embodiment, which will not be repeated here.
[0137] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.
Claims
1. A method for separating express delivery, characterized in that: The express separation method comprises: Get the object to be separated; Separating the object to be separated once to obtain the separated object after the separation and image information of the separated object after the separation, wherein the image information includes a 3D point cloud; Based on the image information, overlapping objects are screened out from the separated objects after the primary separation, and the overlapping objects are secondary separated to obtain separated target objects; The step of screening out overlapping objects from the separated objects after the first separation based on the image information comprises: Based on the 3D point cloud, feature extraction is performed through a preset object segmentation model to obtain an object feature map; Determining object posture information based on the object feature map and the 3D point cloud; Based on the object posture information, filtering out overlapping objects from the separated objects after the first separation; The step of determining the object posture information based on the object feature map and the 3D point cloud comprises: Determining a semantic mask and a center offset of the object feature map; Combining the 3D point cloud with the center offset to obtain a combined graph; Based on the semantic mask, clustering calculation is performed on the combination graph to obtain object posture information.
2. The express separation method according to claim 1, characterized in that: The step of selecting overlapping objects from the separated objects after the first separation based on the object posture information comprises: Based on the object posture information, determining the outer contour information of the separated object after the first separation; Deleting the outer contour information of each separated object after the first separation to obtain remaining outer contour information; Comparing the remaining outer contour information with the outer contour information to obtain a comparison result; If the comparison result is that the number of contours in the remaining peripheral contour information is less than the number of contours in the peripheral contour information, then the separated object is a non-overlapping object; If the number of contours in the remaining outer contour information is equal to or greater than the number of contours in the outer contour information, the separated object is an overlapping object.
3. The express delivery separation method according to claim 2, characterized in that: After the step of determining that if the number of contours in the remaining outer contour information is equal to or greater than the number of contours in the outer contour information, the separated objects are overlapping objects, the method comprises: Determining area information of the separated object after the first separation based on the object posture information; Based on the area information, classification information of each of the overlapping objects is determined, wherein the classification information includes a full overlap category and an intersection category.
4. The express delivery separation method according to claim 3, characterized in that: The step of determining classification information of each of the overlapping objects based on the area information comprises: Adding the area information of each overlapping object and its adjacent object to obtain an addition result; Comparing the sum of the overlapping objects with their area information to obtain a comparison result; If the comparison result is that the addition result is equal to its area information, then the classification information of the separated object is a full overlap category; If the comparison result is that the addition result is not equal to its area information, the classification information of the separated object is an intersection category.
5. A courier separation device, characterized in that: The device comprises: An acquisition module, used for acquiring objects to be separated; A separation module, used for performing a separation on the object to be separated, and obtaining a separated object after the separation and image information of the separated object after the separation, wherein the image information includes a 3D point cloud; A screening module, configured to screen the separated objects after the primary separation to obtain overlapping objects based on the image information, and perform secondary separation on the overlapping objects to obtain separated target objects; The screening module comprises: A feature extraction module, used to extract features based on the 3D point cloud through a preset object segmentation model to obtain an object feature map; A determination module, used to determine the object posture information based on the object feature map and the 3D point cloud; An overlapping object screening module, configured to screen the overlapping objects from the separated objects after the first separation based on the object posture information; The determining module comprises: A feature map information determination module, used to determine the semantic mask and center offset of the object feature map; A combining module, used for combining the 3D point cloud with the center offset to obtain a combined graph; A clustering module is used to perform clustering calculation on the combination graph based on the semantic mask to obtain object posture information.
6. A courier separation device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the express separation method according to any one of claims 1 to 4.
7. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the express separation method according to any one of claims 1 to 4 are implemented.
8. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the express separation method according to any one of claims 1 to 4 are implemented.
