Sorting method and device, electronic equipment and storage medium

Abstract

The invention provides a sorting method and device, electronic equipment and a storage medium, and relates to the technical field of automation control, and the method comprises the following steps: determining a first image of at least one to-be-sorted object at the current moment; based on the first image, determining a target detection frame of each to-be-sorted object; based on the target detection frame of each to-be-sorted object, determining an opened air valve and the blowing time of the air valve; and sorting the to-be-sorted objects based on the opened air valves and the blowing time of the air valves. Through accurate identification of the target detection frame of the to-be-sorted object, accurate determination of the opened air valve and the air blowing time of the air valve is achieved, then effective sorting of the to-be-sorted object is achieved, and the sorting efficiency is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automation control, and in particular to a sorting method and device, electronic equipment and a storage medium. BACKGROUND

[0002] In the intelligent light sorting task of renewable resources (such as bottles), using various methods to identify and sort targets has become a key technology that is important and common, which can help the sorting device (i.e. air sorting device) to better determine the sorting time, thereby improving the sorting accuracy.

[0003] However, the use rate of line scan cameras in the intelligent light sorting task of renewable resources is not high, and even those renewable resource light sorting equipment that have tried to use line scan cameras have not fully played the advantages and benefits of line scan cameras, resulting in that even if the visual recognition module successfully identifies the target, the sorting device still has low sorting accuracy due to time errors and insufficient power provided. SUMMARY

[0004] The present application provides a sorting method, device, electronic equipment and storage medium to solve the problem of low sorting accuracy.

[0005] The present application provides a sorting method, comprising: determining a first image of at least one object to be sorted at the current time; determining a target detection frame of each of the objects to be sorted based on the first image; determining an open air valve and air blowing time of the air valve based on the target detection frame of each of the objects to be sorted; sorting each of the objects to be sorted based on the open air valve and the air blowing time of the air valve.

[0006] According to the sorting method provided by the present application, the target detection frame of each of the objects to be sorted is determined based on the first image, comprising: splitting the first image to obtain a plurality of split images; each of the split images has an overlap between them; for each of the split images, identifying the split image to obtain an identification result; the identification result includes a detection frame and a category probability of each of the objects to be sorted; mapping the split image based on the detection frame of each of the objects to be sorted to obtain a mapped image; the mapped image includes the detection frame of each of the objects to be sorted; determining the target detection frame of each of the objects to be sorted based on the category probability of each of the objects to be sorted and the mapped image.

[0007] According to the sorting method provided by the application, the target detection frame of each object to be sorted is determined based on the category probability of each object to be sorted and the mapped image, and the method comprises the following steps: The filtered detection frame of each object to be sorted is obtained by filtering the mapped image based on the category probability of each object to be sorted. The target detection frame of each object to be sorted is determined based on the filtered detection frame and the detection frame of each object to be sorted at the previous moment.

[0008] According to the sorting method provided by the application, the target detection frame of each object to be sorted is determined based on the category probability of each object to be sorted and the mapped image, and the method comprises the following steps: The distance from each object to be sorted to the edge of the conveying belt, the length of each object to be sorted and the width of each object to be sorted are determined based on the target detection frame of each object to be sorted. The open air valve and the blowing time of the air valve are determined based on the distance from each object to be sorted to the edge of the conveying belt, the length of each object to be sorted and the width of each object to be sorted.

[0009] According to the sorting method provided by the application, the target detection frame of each object to be sorted is determined based on the category probability of each object to be sorted and the mapped image, and the method comprises the following steps: The width of each object to be sorted passing through the air sorting device is determined based on the length of each object to be sorted and the width of each object to be sorted. The open air valve and the blowing time of the air valve are determined based on the distance from each object to be sorted to the edge of the conveying belt, the width of each object to be sorted passing through the air sorting device, the distance between each air valve, the distance between the air valve and the edge of the conveying belt and the opening time of the air valve.

[0010] According to the sorting method provided by the application, the target detection frame of each object to be sorted is determined based on the category probability of each object to be sorted and the mapped image, and the method comprises the following steps: The open air valve is determined based on the distance from each object to be sorted to the edge of the conveying belt, the width of each object to be sorted passing through the air sorting device, the distance between each air valve and the distance between the air valve and the edge of the conveying belt. The blowing time of the air valve is determined based on the length of each of the objects to be sorted, the width of each of the objects to be sorted, the opening time of the air valve, the width of each of the objects to be sorted passing through the air sorting device, and the distance between each air valve.

[0011] According to the sorting method provided by the application, before the opening air valve and the blowing time of the air valve are determined based on the target detection frame of each of the objects to be sorted, the method further comprises: The translation amount of each of the objects to be sorted is determined based on the target detection frame of each of the objects to be sorted and the i-th row image corresponding to the next moment. Whether to discard the target detection frame of each of the objects to be sorted is determined based on the translation amount.

[0012] The application further provides a sorting device, comprising: A first determination module is configured to determine a first image of at least one object to be sorted at a current moment. A second determination module is configured to determine a target detection frame of each of the objects to be sorted based on the first image. A third determination module is configured to determine an opening air valve and a blowing time of the air valve based on the target detection frame of each of the objects to be sorted. A sorting module is configured to sort each of the objects to be sorted based on the opening air valve and the blowing time of the air valve.

[0013] The application further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the sorting method of any of the above when executing the computer program.

[0014] The application further provides a non-transitory computer readable storage medium, which stores a computer program executable by a processor to implement the sorting method of any of the above.

[0015] The application further provides a computer program product, comprising a computer program executable by a processor to implement the sorting method of any of the above.

[0016] The sorting method, device, electronic equipment and storage medium provided by the application determine a first image of at least one object to be sorted at the current time; determine a target detection frame of each object to be sorted based on the first image; determine an open air valve and air blowing time of the air valve based on the target detection frame of each object to be sorted; and sort each object to be sorted based on the open air valve and air blowing time of the air valve. Through accurate identification of the target detection frame of the object to be sorted, the open air valve and the air blowing time of the air valve are accurately determined, and the effective sorting of the object to be sorted is realized, thereby improving the sorting efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0018] Figure 1 is one of the flowcharts of the sorting method provided by the application.

[0019] Figure 2 is another flowchart of the sorting method provided by the application.

[0020] Figure 3 is a structural schematic diagram of the sorting device provided by the application.

[0021] Figure 4 is a structural schematic diagram of the electronic equipment provided by the application. DETAILED DESCRIPTION

[0022] In order to make the objects, technical solutions and advantages of the application clearer, the technical solutions in the application will be described clearly and completely in combination with the drawings in the application. Obviously, the described embodiments are some embodiments of the application, not all embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the application.

[0023] The sorting method of the application will be described below in combination with Figures 1-2

[0024] Figure 1 is one of the flowcharts of the sorting method provided by the application, as Figure 1 shown, the method comprises the following steps 101-104.

[0025] Step 101, determining a first image of at least one object to be sorted at the current time.​

[0026] It should be noted that the sorting method provided by the present application can be applied to the scenario of sorting objects to be sorted by an optical sorter based on a line scan camera, for example, sorting bottle objects; the execution subject of the method can be a sorting device, such as an electronic device, or a control module in the sorting device for executing the sorting method.

[0027] Specifically, the objects to be sorted can be bottle objects, such as beverage bottles. The first image includes at least one object to be sorted. The first image of at least one object to be sorted at the current time can be determined by the line scan camera.

[0028] First, a matrix is constructed I The size of the matrix I can be set according to the related parameters of the components of the intelligent optical sorter, for example, the size of the matrix I is , wherein w represents the image width sampled by the line scan camera, represents the actual width of the line scan camera, i.e., the width of the conveying belt; w and are fixed values for a specific line scan camera device; represents the forward distance of the conveying belt, corresponds to the length of the image to be retained, can be set to times of (n is an integer), and is greater than the distance from the line scan camera to the sorting device (such as an air sorting device) in the horizontal direction . For example, the image width sampled by the line scan camera is 2048, the actual width of the line scan camera (i.e., the width of the conveying belt) is 1.4 m, the forward distance of the conveying belt is 2.8 m, and the size of the matrix I is set to .

[0029] Let the first I row and the first row of the matrix be the position of the matrix I to which the image collected by the line scan camera needs to be stored (wherein and i is a positive integer), i.e., when the line scan camera collects a row of images, the images are stored in the first row and the first row of ; reduce by 1 and set i = i-1, and then store the row of images collected by the line scan camera in the first row and the first row, and sequentially circulates. It should be noted that if the reduced is equal to , then is added to becomes At this time, the image data of the row to the row of the is a complete conveyor image from the position corresponding to the current acquisition time to the advancing distance of the conveyor. For example, and i is a positive integer, and at this time to row data is a conveyor image with an image size of and an actual space size of .

[0030] Since the image size of the input of the oriented bounding box (OBB) task is , whenever the last OBB task is completed, the corresponding to the row after reading image data from the image data collected by the line scan camera and stored in the matrix I at the current time t, a first image Image with an image size of is obtained.

[0031] Step 102, determining the target detection frame of each of the objects to be sorted based on the first image.

[0032] Specifically, based on the first image, the target detection frame of each object to be sorted in the first image can be further determined, wherein the target detection frame is the complete detection frame of the object to be sorted.

[0033] Step 103, determining the opened air valve and the blowing time of the air valve based on the target detection frame of each of the objects to be sorted.

[0034] Specifically, based on the target detection frame of each object to be sorted, the opened air valve and the blowing time of the air valve can be determined.

[0035] Step 104, sorting each of the objects to be sorted based on the opened air valve and the blowing time of the air valve.

[0036] Specifically, based on the opened air valve and the blowing time of the air valve, each object to be sorted is sorted using a sorting device.

[0037] The sorting method provided by this invention involves: determining a first image of at least one object to be sorted at the current moment; determining a target detection box for each object based on the first image; determining the open air valve and the air blowing time based on the target detection boxes of each object; and sorting each object based on the open air valve and the air blowing time. By accurately identifying the target detection boxes of the objects to be sorted, the accurate determination of the open air valve and the air blowing time is achieved, thereby enabling effective sorting of the objects and improving sorting efficiency.

[0038] Optionally, the specific implementation of step 102 above includes: The first image is split into multiple split images; there is overlap between the split images; for each split image, recognition is performed to obtain a recognition result; the recognition result includes the detection box and category probability of each object to be sorted; based on the detection box of each object to be sorted, the split images are mapped to obtain a mapped image; the mapped image includes the detection box of each object to be sorted; based on the category probability of each object to be sorted and the mapped image, the target detection box of each object to be sorted is determined.

[0039] Specifically, the first image is split along the width direction corresponding to w, resulting in multiple split images with overlap between them. For example, along the width direction corresponding to w, the first image is split into pairs of images that overlap by half every 1024 / 2 = 512 pixels. open The image is divided into length and width sections. For each section, recognition is performed to obtain the recognition results; the recognition results include the bounding boxes and class probabilities for each object to be sorted; for example, ... open Composition of length and width of split image The target matrix is ​​input into the OBB model to obtain the output of the OBB model. k is the number of detection boxes obtained by the OBB model for at least one object to be sorted in a single split image, and each detection box has the following format: , The coordinates of the center point of the detection box along the direction corresponding to 1024 (the conveyor belt's forward distance) in the first image Image are: The center point of the detection box is along the first image Image. Coordinates in the corresponding direction The height of the detection frame, The width of the detection frame. The tilt angle of the detection frame.

[0040] For each split image, based on the detection box of each object to be sorted, the split image is mapped, and a mapped image can be obtained; for example, for the first image Image, the detection box of each object to be sorted is mapped to the first image Image, and the detection box of each object to be sorted in the first image Image is obtained.

[0041] Based on the category probability of each object to be sorted and the mapped image, the target detection box of each object to be sorted is further determined.

[0042] Optionally, the target detection box of each object to be sorted is determined based on the category probability of each object to be sorted and the mapped image, including: Based on the category probability of each object to be sorted, the detection box of each object to be sorted in the mapped image is filtered to obtain the filtered detection box of each object to be sorted; and based on the filtered detection box and the detection box of each object to be sorted at the last moment, the target detection box of each object to be sorted is determined.

[0043] Specifically, based on the category probability of each object to be sorted, the category probability and a preset threshold are compared, in a case where the category probability is less than the preset threshold, the detection box of the object to be sorted in the mapped image is removed; and in a case where the category probability is not less than the preset threshold, the detection box of the object to be sorted in the mapped image is retained. For example, 1000 detection boxes with higher possibility are obtained. Then, based on the filtered detection box and the detection box of each object to be sorted at the last moment, the Non-Maximum Suppression (NMS) is used to determine the target detection box of each object to be sorted, that is, only one complete detection box of each object to be sorted in the mapped image corresponding to the first row to the m-th row in the matrix

[0044] ​​​​​​​​​​​​​​​​​​Optionally, before determining the opened air valve and the blowing time of the air valve based on the target detection frame of each of the objects to be sorted, the method further comprises: determining the translation amount of each of the objects to be sorted based on the target detection frame of each of the objects to be sorted and the i-th row image corresponding to the next moment; and determining whether to discard the target detection frame of each of the objects to be sorted based on the translation amount.

[0045] Specifically, before entering the next OBB task, the translation amount is calculated based on the target detection frame of each of the objects to be sorted and the i-th row image corresponding to the next moment . If , the new translation amount is obtained by adding to ; if the new translation amount , the step of determining the opened air valve and the blowing time of the air valve based on the target detection frame of each of the objects to be sorted is performed so that the air sorting device sorts each of the objects to be sorted; if the new translation amount , the target detection frame of each of the objects to be sorted is discarded, otherwise the target detection frame of each of the objects to be sorted is not discarded.

[0046] Optionally, the specific implementation of the above step 103 comprises: determining the distance from each of the objects to be sorted to the edge of the conveying belt, the length of each of the objects to be sorted and the width of each of the objects to be sorted based on the target detection frame of each of the objects to be sorted; and determining the opened air valve and the blowing time of the air valve based on the distance from each of the objects to be sorted to the edge of the conveying belt, the length of each of the objects to be sorted and the width of each of the objects to be sorted.

[0047] Specifically, based on the target detection frame of each of the objects to be sorted , the distance from each of the objects to be sorted to the edge of the conveying belt , the length of each of the objects to be sorted and the width of each of the objects to be sorted are obtained by multiplying , respectively. Then, the opened air valve and the blowing time of the air valve are further determined based on the distance from each of the objects to be sorted to the edge of the conveying belt, the length of each of the objects to be sorted and the width of each of the objects to be sorted.

[0048] Optionally, the determination of the opened air valve and the blowing time of the air valve based on the distance from each of the objects to be sorted to the edge of the conveying belt, the length of each of the objects to be sorted and the width of each of the objects to be sorted comprises:​​​​ determining the width of each of the objects to be sorted passing through the air sorting device based on the length of each of the objects to be sorted and the width of each of the objects to be sorted; and determining the opened air valves and the blowing time of the air valves based on the distance of each of the objects to be sorted to the side edge of the conveying belt, the width of each of the objects to be sorted passing through the air sorting device, the distance between each of the air valves, the distance between the air valves and the side edge of the conveying belt, and the opening time of the air valves.

[0049] Specifically, the width of each of the objects to be sorted passing through the air sorting device is determined based on the length of each of the objects to be sorted and the width of each of the objects to be sorted. Then, the opened air valves and the blowing time of the air valves are determined based on the distance of each of the objects to be sorted to the side edge of the conveying belt, the width of each of the objects to be sorted passing through the air sorting device, the distance between each of the air valves, the distance between the air valves and the side edge of the conveying belt, and the opening time of the air valves.

[0050] Optionally, the determining the opened air valves and the blowing time of the air valves based on the distance of each of the objects to be sorted to the side edge of the conveying belt, the width of each of the objects to be sorted passing through the air sorting device, the distance between each of the air valves, the distance between the air valves and the side edge of the conveying belt, and the opening time of the air valves comprises: determining the opened air valves based on the distance of each of the objects to be sorted to the side edge of the conveying belt, the width of each of the objects to be sorted passing through the air sorting device, the distance between each of the air valves, and the distance between the air valves and the side edge of the conveying belt; and determining the blowing time of the air valves based on the length of each of the objects to be sorted, the width of each of the objects to be sorted, the opening time of the air valves, the width of each of the objects to be sorted passing through the air sorting device, and the distance between each of the air valves.

[0051] Specifically, the opened air valves are determined based on the distance of each of the objects to be sorted to the side edge of the conveying belt, the width of each of the objects to be sorted passing through the air sorting device, the distance between each of the air valves, and the distance between the air valves and the side edge of the conveying belt. to When the area of the target detection frame is 1m 2 , the opening time of the corresponding opened air valves is Q, then for the obtained target detection frame, the blowing time of the air valves is determined based on the length of each of the objects to be sorted, the width of each of the objects to be sorted, the opening time of the air valves, the width of each of the objects to be sorted passing through the air sorting device, and the distance between each of the air valves. .

[0052] Figure 2 is the second flowchart of the sorting method provided by the present application, asFigure 2 As shown, the method comprises steps 201-213.

[0053] Step 201, determining a first image of at least one object to be sorted at a current time.

[0054] Step 202, splitting the first image to obtain a plurality of split images; there is an overlap between each split image.

[0055] Step 203, for each split image, identifying the split image to obtain an identification result; the identification result comprises a detection box and a category probability of each object to be sorted.

[0056] Step 204, based on the detection box of each object to be sorted, mapping the split image to obtain a mapped image; the mapped image comprises the detection box of each object to be sorted.

[0057] Step 205, based on the category probability of each object to be sorted, filtering the mapped image to obtain a filtered detection box of each object to be sorted.

[0058] Step 206, based on the filtered detection box and the detection box of each object to be sorted at the previous time, determining a target detection box of each object to be sorted.

[0059] Step 207, based on the target detection box of each object to be sorted and the i-th row image corresponding to the next time, determining a translation amount of each object to be sorted.

[0060] Step 208, based on the translation amount, determining whether to discard the target detection box of each object to be sorted.

[0061] Step 209, based on the target detection box of each object to be sorted, determining a distance from each object to be sorted to an edge of one side of the conveyor belt, a length of each object to be sorted, and a width of each object to be sorted.

[0062] Step 210, based on the length of each object to be sorted and the width of each object to be sorted, determining a width of each object to be sorted through the air sorting device.

[0063] Step 211, based on the distance from each object to be sorted to the edge of one side of the conveyor belt, the width of each object to be sorted through the air sorting device, a distance between each air valve, and a distance between the air valve and the edge of one side of the conveyor belt, determining an open air valve.

[0064] Step 212, based on the length of each object to be sorted, the width of each object to be sorted, an opening time of the air valve, the width of each object to be sorted through the air sorting device, and the distance between each air valve, determining a blowing time of the air valve.

[0065] Step 213, sorting each object to be sorted based on the opened air valve and the blowing time of the air valve.

[0066] The sorting method provided by the application can accurately determine and identify the relative position of the object to be sorted and the sorting device (such as the air sorting device) by using the binding relationship between the line scanning camera (encoder hard trigger) line sampling and the conveying belt advancing distance, and sorting is performed, which greatly improves the sorting accuracy and eliminates the influence of the conveying belt speed on the false artifact and object tracking matching problem. At the same time, based on the detection frame obtained by the OBB task, the volume of the object to be sorted can be obtained to a certain extent, especially for single-layer objects such as plastic bottles, and the size of the detection frame is positively correlated with the mass of the object to be sorted. The size of the detection frame can be used to better provide different degrees of influence on objects to be sorted of different weights, thereby avoiding the influence of the sorting failure caused by the fact that the visual detection model correctly identifies but the sorting module is insufficient, thereby improving the sorting efficiency.

[0067] The sorting device provided by the application is described below, and the sorting device described below can be correspondingly referred to the sorting method described above.

[0068] Figure 3 The sorting device provided by the application is described below, and the sorting device described below can be correspondingly referred to the sorting method described above. Figure 3 As shown in FIG. 3, the sorting device 300 comprises a first determination module 301, a second determination module 302, a third determination module 303 and a sorting module 304; wherein, The first determination module 301 is configured to determine a first image of at least one object to be sorted at the current time. The second determination module 302 is configured to determine a target detection frame of each object to be sorted based on the first image. The third determination module 303 is configured to determine an opened air valve and a blowing time of the air valve based on the target detection frame of each object to be sorted. The sorting module 304 is configured to sort each object to be sorted based on the opened air valve and the blowing time of the air valve.

[0069] The sorting device provided by the application determines a first image of at least one object to be sorted at the current time, determines a target detection frame of each object to be sorted based on the first image, determines an opened air valve and a blowing time of the air valve based on the target detection frame of each object to be sorted, and sorts each object to be sorted based on the opened air valve and the blowing time of the air valve. Through accurate identification of the target detection frame of the object to be sorted, accurate determination of the opened air valve and the blowing time of the air valve is realized, and effective sorting of the object to be sorted is realized, thereby improving the sorting efficiency.

[0070] Optionally, the second determining module 302 is specifically used for: splitting the first image to obtain a plurality of split images, wherein overlaps exist between the split images; for each split image, identifying the split image to obtain an identification result, wherein the identification result comprises a detection frame and a category probability of each object to be sorted; mapping the split image based on the detection frame of each object to be sorted to obtain a mapped image, wherein the mapped image comprises the detection frame of each object to be sorted; determining a target detection frame of each object to be sorted based on the category probability of each object to be sorted and the mapped image.

[0071] Optionally, the second determining module 302 is further used for: filtering the mapped image based on the category probability of each object to be sorted to obtain a filtered detection frame of each object to be sorted; determining a target detection frame of each object to be sorted based on the filtered detection frame and the detection frame of each object to be sorted at the previous moment.

[0072] Optionally, the third determining module 303 is specifically used for: determining a distance from each object to be sorted to an edge of a conveying belt, a length of each object to be sorted, and a width of each object to be sorted based on the target detection frame of each object to be sorted; determining the opened air valve and blowing time of the air valve based on the distance from each object to be sorted to the edge of the conveying belt, the length of each object to be sorted, and the width of each object to be sorted.

[0073] Optionally, the third determining module 303 is further used for: determining a width of each object to be sorted passing through the air sorting device based on the length of each object to be sorted and the width of each object to be sorted; determining the opened air valve and blowing time of the air valve based on the distance from each object to be sorted to the edge of the conveying belt, the width of each object to be sorted passing through the air sorting device, a distance between each air valve, a distance between the air valve and the edge of the conveying belt, and opening time of the air valve.

[0074] Optionally, the third determining module 303 is further used for: determining the opened air valve based on the distance from each object to be sorted to the edge of the conveying belt, the width of each object to be sorted passing through the air sorting device, the distance between each air valve, and the distance between the air valve and the edge of the conveying belt. The blowing time of the air valve is determined based on the length of each of the objects to be sorted, the width of each of the objects to be sorted, the opening time of the air valve, the width of each of the objects to be sorted passing through the air sorting device, and the distance between each air valve.

[0075] Optionally, the sorting device 300 further includes: A fourth determination module is configured to determine the translation amount of each of the objects to be sorted based on the target detection frame of each of the objects to be sorted and the i-th row image corresponding to the next moment. A fifth determination module is configured to determine whether to discard the target detection frame of each of the objects to be sorted based on the translation amount.

[0076] Figure 4 is a schematic diagram of an electronic device provided by the present application, as Figure 4 As shown in the figure, the electronic device 400 can include a processor 410, a communications interface 420, a memory 430, and a communications bus 440, wherein the processor 410, the communications interface 420, and the memory 430 complete mutual communication through the communications bus 440. The processor 410 can invoke the logical instructions in the memory 430 to execute a sorting method, which includes determining a first image of at least one object to be sorted at a current moment; determining a target detection frame of each of the objects to be sorted based on the first image; determining an open air valve and a blowing time of the air valve based on the target detection frame of each of the objects to be sorted; and sorting each of the objects to be sorted based on the open air valve and the blowing time of the air valve.

[0077] In addition, the logical instructions in the memory 430 described above can be implemented in the form of a software function unit and sold or used as an independent product, which can be stored in a computer-readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in the embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0078] In another aspect, the present application also provides a computer program product comprising a computer program, which can be stored on a non-transitory computer readable storage medium, and the computer program is executable by a processor to enable a computer to perform the sorting method provided by the above-mentioned methods, which comprises: determining a first image of at least one object to be sorted at a current time; determining a target detection frame of each of the objects to be sorted based on the first image; determining an open air valve and a blowing time of the air valve based on the target detection frame of each of the objects to be sorted; and sorting each of the objects to be sorted based on the open air valve and the blowing time of the air valve.

[0079] In yet another aspect, the present application also provides a non-transitory computer readable storage medium having a computer program stored thereon, which is executable by a processor to implement a sorting method provided by the above-mentioned methods, which comprises: determining a first image of at least one object to be sorted at a current time; determining a target detection frame of each of the objects to be sorted based on the first image; determining an open air valve and a blowing time of the air valve based on the target detection frame of each of the objects to be sorted; and sorting each of the objects to be sorted based on the open air valve and the blowing time of the air valve.

[0080] The device embodiments described above are merely illustrative, wherein the units illustrated as separate components can or can not be physically separate, and the components illustrated as units can or can not be physical units, i.e., can be located in one place, or can be distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiment scheme according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0081] From the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be realized by means of software plus necessary universal hardware platforms, and of course can also be realized by hardware. Based on such understanding, the above technical solutions, essentially or in other words, the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0082] It should be pointed out finally that the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit the same; and although the present application has been described in detail with reference to the foregoing embodiments, it should be appreciated by those skilled in the art that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features thereof can be replaced equivalently; and these modifications 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 application.

Claims

1. A method of sorting, characterized by, The method comprises the following steps: determining a first image of at least one object to be sorted at a current time; determining a target detection frame of each object to be sorted based on the first image; determining an open air valve and a blowing time of the air valve based on the target detection frame of each object to be sorted; sorting each object to be sorted based on the open air valve and the blowing time of the air valve.

2. The sorting method of claim 1, wherein, The method comprises the following steps: splitting the first image to obtain a plurality of split images; each split image overlaps with another split image; for each split image, identifying the split image to obtain an identification result; the identification result comprises a detection frame and a category probability of each object to be sorted; mapping the split image based on the detection frame of each object to be sorted to obtain a mapped image; the mapped image comprises the detection frame of each object to be sorted; determining a target detection frame of each object to be sorted based on the category probability of each object to be sorted and the mapped image.

3. The sorting method of claim 2, wherein, The method comprises the following steps: filtering the mapped image based on the category probability of each object to be sorted to obtain a filtered detection frame of each object to be sorted; determining a target detection frame of each object to be sorted based on the filtered detection frame and a detection frame of each object to be sorted at a previous time.

4. The sorting method of claim 1, wherein, The method comprises the following steps: determining a distance of each object to be sorted to an edge of a conveying belt, a length of each object to be sorted, and a width of each object to be sorted based on the target detection frame of each object to be sorted; determining the open air valve and the blowing time of the air valve based on the distance of each object to be sorted to the edge of the conveying belt, the length of each object to be sorted, and the width of each object to be sorted.

5. The sorting method of claim 4, wherein, The method comprises the following steps: determining a width of each object to be sorted passing through an air selection device based on the length of each object to be sorted and the width of each object to be sorted; determining the open air valve and the blowing time of the air valve based on the distance of each object to be sorted to the edge of the conveying belt, the width of each object to be sorted passing through the air selection device, a distance between each air valve, a distance between the air valve and the edge of the conveying belt, and an opening time of the air valve.

6. The sorting method of claim 5, wherein, The method comprises the following steps: determine the opened air valve based on the distance of each of the objects to be sorted to the edge of the conveying belt, the width of each of the objects to be sorted passing through the air sorting device, the distance between each air valve, and the distance between the air valve and the edge of the conveying belt; determine the blowing time of the air valve based on the length of each of the objects to be sorted, the width of each of the objects to be sorted, the opening time of the air valve, the width of each of the objects to be sorted passing through the air sorting device, and the distance between each air valve.

7. The sorting method of claim 1, wherein, Before the determining the opened air valve and the blowing time of the air valve based on the target bounding box of each of the objects to be sorted, the method further comprises: determine the translation of each of the objects to be sorted based on the target bounding box of each of the objects to be sorted and the i-th row of image corresponding to the next time; determine whether to discard the target bounding box of each of the objects to be sorted based on the translation.

8. A sorting device characterized by comprise: a first determining module configured to determine a first image of at least one object to be sorted at a current time; a second determining module configured to determine a target bounding box of each of the objects to be sorted based on the first image; a third determining module configured to determine an opened air valve and a blowing time of the air valve based on the target bounding box of each of the objects to be sorted; a sorting module configured to sort each of the objects to be sorted based on the opened air valve and the blowing time of the air valve.

9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to realize the sorting method of any one of claims 1 to 7. 10.A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the sorting method of any one of claims 1 to 7.

Images