Sorting methods, sorting systems and processors for recyclable materials

Abstract

This application discloses a sorting method, sorting system, and processor for recyclable materials. The sorting method includes: acquiring image information of multiple recyclable materials; identifying the category of each recyclable material in the image information; determining the material to be sorted among the multiple recyclable materials based on the category of each recyclable material; determining the position information of the material to be sorted and the corresponding jet width based on the image information; and controlling the jet valve to eject the material to be sorted based on the position information and the jet width, thereby completing the sorting of the material. By determining the jet width, this application allows the processor to control the jet valve to eject the material to be sorted according to the jet width, which can improve the sorting accuracy of recyclable materials.

Description

Technical Field

[0001] This application relates to the field of material handling technology, and specifically to a sorting method, sorting system and processor for recyclable materials. Background Technology

[0002] With the comprehensive advancement of waste sorting, the demand for replacing manual labor with machines, reducing the workload of sorting workers, and systematically constructing a waste management system encompassing sorting, collection, transportation, and disposal is becoming increasingly prominent, leading to a growing need for intelligent equipment in sorting centers. Traditional recyclable waste sorting centers and recyclable resource sorting centers primarily rely on manual sorting, which is characterized by high workload, harsh working environments, low efficiency, and unreliable sorting accuracy. To address these issues, existing technologies utilize image recognition methods for the identification, location, and sorting of recyclable materials; however, this method suffers from low accuracy. Summary of the Invention

[0003] The purpose of this application is to provide a sorting method, sorting system and processor for recyclable materials, in order to solve the problem of low accuracy in existing material sorting methods.

[0004] To achieve the above objectives, a first aspect of this application provides a method for sorting recyclable materials, comprising:

[0005] Acquire image information of multiple recyclable materials;

[0006] Identify the category to which each recyclable material in the image information belongs;

[0007] Identify the recyclable materials to be sorted from among multiple recyclable materials based on the category to which each recyclable material belongs;

[0008] The location information of the material to be sorted and the corresponding jet width of the material to be sorted are determined based on the image information.

[0009] Based on the location information of the materials to be sorted, the spray valve is controlled according to the spray width to spray out the materials to be sorted, so as to complete the sorting of the materials.

[0010] In this embodiment of the application, determining the jet width corresponding to the material to be sorted based on image information includes: generating a rectangular frame corresponding to the material to be sorted using a preset image processing algorithm; obtaining the length, width, and angle of the rectangular frame; and determining the jet width corresponding to the material to be sorted based on the length, width, and angle.

[0011] In this embodiment of the application, the jet width corresponding to the material to be sorted satisfies formula (1):

[0012]

[0013] Where P is the air jet width corresponding to the material to be sorted, H is the length of the rectangle, W is the width of the rectangle, and θ is the angle of the rectangle.

[0014] In this embodiment of the application, determining the location information of the material to be sorted based on the image information includes: determining the first coordinate information of the material to be sorted in the image plane coordinate system based on the image information; and determining the second coordinate information of the material to be sorted in the belt plane coordinate system based on the first coordinate information, based on the predetermined transformation relationship between the image plane coordinate system and the belt plane coordinate system, so as to obtain the location information.

[0015] In this embodiment, both the image plane coordinate system and the belt plane coordinate system are planar perpendicular coordinate systems, and the second coordinate information satisfies formula (2):

[0016]

[0017] Where X represents the second coordinate information in the first direction, Y represents the second coordinate information in the second direction, x represents the first coordinate information in the first direction, y represents the first coordinate information in the second direction, and α represents the horizontal angle between the image plane and the belt plane in the second direction.

[0018] In this embodiment of the application, identifying the category to which each recyclable material in the image information belongs includes: determining the material identification area in the image information; determining whether the bottle of each recyclable material is intact based on the material identification area; identifying the category to which the recyclable material with an intact bottle belongs; and filtering the recyclable material with an incomplete bottle.

[0019] In this embodiment of the application, determining the material identification area in the image information includes: acquiring the shooting field width of the image acquisition device, the image acquisition time interval, the length of the recyclable material, and the maximum operating speed of the belt conveyor; and determining the material identification area in the image information based on the shooting field width, the image acquisition time interval, the length of the recyclable material, and the maximum operating speed.

[0020] In this embodiment of the application, determining whether the bottle of each recyclable material is intact based on the material identification area includes: identifying recyclable materials whose bottles are located in at least part of the material identification area as recyclable materials with intact bottles; and identifying recyclable materials whose bottles are not located in the material identification area as recyclable materials with incomplete bottles.

[0021] A second aspect of this application provides a processor configured to perform the above-described sorting method for recyclable materials.

[0022] A third aspect of this application provides a sorting system for recyclable materials, including: an image acquisition device; and a processor.

[0023] The above technical solution acquires image information of multiple recyclable materials and identifies the category of each recyclable material in the image information. Based on the category of each recyclable material, it determines the materials to be sorted from the multiple recyclable materials. The processor then determines the location information of the materials to be sorted and the corresponding jet width based on the image information. Finally, based on the location information of the materials to be sorted, the spray valve is controlled according to the jet width to spray the materials to be sorted, thereby completing the sorting of the materials. This application, by determining the jet width, allows the processor to control the spray valve to spray the materials to be sorted according to the jet width, thereby achieving the sorting of the materials and improving the sorting accuracy of recyclable materials.

[0024] Other features and advantages of the embodiments of this application will be described in detail in the following detailed description section. Attached Figure Description

[0025] The accompanying drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the following detailed description to explain the embodiments of this application, but do not constitute a limitation on the embodiments of this application. In the drawings:

[0026] Figure 1 A flowchart illustrating a sorting method for recyclable materials according to an embodiment of this application is shown schematically.

[0027] Figure 2 A schematic diagram of a material identification area according to an embodiment of this application is shown;

[0028] Figure 3 A schematic diagram illustrating an air jet width according to an embodiment of this application is shown;

[0029] Figure 4 The flowchart illustrating a sorting method for recyclable materials according to a specific embodiment of this application is shown schematically.

[0030] Figure 5 The diagram illustrates the structure of a sorting system for recyclable materials according to an embodiment of this application.

[0031] Explanation of reference numerals in the attached figures

[0032] 1 Image acquisition device 2 Processor

[0033] 3. Light source 4. Display device Detailed Implementation

[0034] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for illustration and explanation of the embodiments of this application and are not intended to limit the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0035] It should be noted that if the embodiments of this application involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of the components in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0036] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0037] Figure 1 A flowchart illustrating a sorting method for recyclable materials according to an embodiment of this application is shown schematically. Figure 1 As shown in the illustration, this application provides a sorting method for recyclable materials. Taking the application of this sorting method to a processor as an example, the sorting method may include the following steps:

[0038] Step S101: Obtain image information of multiple recyclable materials.

[0039] Step S102: Identify the category to which each recyclable material in the image information belongs.

[0040] Step S103: Determine the materials to be sorted from multiple recyclable materials according to the category to which each recyclable material belongs.

[0041] Step S104: Determine the location information of the material to be sorted and the corresponding jet width of the material to be sorted based on the image information.

[0042] Step S105: Based on the location information of the material to be sorted, the spray valve is controlled according to the spray width to spray out the material to be sorted, so as to complete the sorting of the material.

[0043] In this embodiment, the processor can acquire image information of multiple recyclable materials in real time from the field of view of the sorting system mounted on a belt conveyor via an image acquisition device. Recyclable materials include, but are not limited to, polyethylene terephthalate bottles, polyethylene bottles, and aluminum cans. Using image processing algorithms, such as the YOLOv5_OBB algorithm, the processor can perform deep learning on various features of the recyclable materials, such as shape, texture, and color. Thus, after acquiring image information, the processor can identify the material and color of multiple recyclable materials based on the image information, thereby determining the category of each recyclable material. The category of recyclable materials can be divided based on material and color. Further, based on the category of each recyclable material and the category of recyclable materials currently to be sorted, the processor can determine the materials to be sorted among the multiple recyclable materials. The materials to be sorted can be one or multiple. In one example, if polyethylene bottles need to be sorted, after determining the category of each recyclable material in the image information, the processor can identify the recyclable material identified as a polyethylene bottle as the material to be sorted.

[0044] A row of spray valves is evenly distributed at the end of the belt. The valves simultaneously spray air to eject the material to be sorted. Each recyclable material enters the belt in a different posture, and the number of spray valves required to perform the action is determined by the spray width. The spray width is the length perpendicular to the belt's direction of movement, passing through the material's coordinate center point. After processing the image information using an image processing algorithm, the processor can determine the position information of the material to be sorted and the corresponding spray width, and then determine the number of spray valves based on the spray width. After locating the material to be sorted based on its position information, the processor can control the corresponding spray valves according to the number of spray valves to eject the material, thus completing the sorting process. Furthermore, during the sorting process, based on the category and position information of each recyclable material in two consecutive image frames, the processor can remove duplicate recyclable material information. Specifically, if any recyclable material in two consecutive image frames has the same category and position information or is within a preset error range, the processor can determine that any recyclable material in the two consecutive image frames is the same recyclable material, and thus remove the duplicate recyclable material information.

[0045] In addition, the sorting system also includes a display device. The display device can be a screen or a host computer. During the sorting process, the recognition results and the location information of the materials to be sorted can be displayed on the display device in real time through video streaming. The display device can also display information such as the processor's operating status, memory and graphics processor usage, the image acquisition interval of the image acquisition device, and the category of recyclable materials that need to be sorted in real time.

[0046] The above technical solution acquires image information of multiple recyclable materials and identifies the category of each recyclable material in the image information. Based on the category of each recyclable material, it determines the materials to be sorted from the multiple recyclable materials. The processor then determines the location information of the materials to be sorted and the corresponding jet width based on the image information. Finally, based on the location information of the materials to be sorted, the spray valve is controlled according to the jet width to spray the materials to be sorted, thereby completing the sorting of the materials. This application, by determining the jet width, allows the processor to control the spray valve to spray the materials to be sorted according to the jet width, thereby achieving the sorting of the materials and improving the sorting accuracy of recyclable materials.

[0047] Figure 2 A schematic diagram of a material identification area according to an embodiment of this application is shown. Figure 2 As shown in the embodiments of this application, identifying the category to which each recyclable material in the image information belongs may include: determining the material identification area in the image information; determining whether the bottle of each recyclable material is intact based on the material identification area; identifying the category to which the recyclable material with an intact bottle belongs; and filtering the recyclable material with an incomplete bottle.

[0048] In this embodiment, the processor can set a material recognition area. Recyclable materials are placed on the conveyor belt and move with it. To ensure that each recyclable material can be captured with at least one frame of image information, the processor can obtain the field of view width of the image acquisition device and the length of the recyclable material, and subtract the length of the recyclable material from the field of view width to determine the maximum material recognition area in the image information. Simultaneously, the processor can obtain the maximum operating speed of the conveyor belt and the image acquisition time interval of the image acquisition device, and multiply the maximum operating speed by the image acquisition time interval to determine the minimum material recognition area. The material recognition area can be set between the maximum and minimum material recognition areas, and its specific value can be determined according to actual conditions. By setting a material recognition area within the field of view of the image acquisition device, the processor can filter out recyclable materials with incomplete bottle bodies captured by the image acquisition device, and perform image processing on the recyclable materials captured completely, i.e., identify the category to which the recyclable materials with complete bottle bodies belong. This reduces the possibility of malfunction of the spray valve.

[0049] In this embodiment of the application, determining the material identification area in the image information may include: acquiring the shooting field width of the image acquisition device, the image acquisition time interval, the length of the recyclable material, and the maximum operating speed of the belt conveyor; and determining the material identification area in the image information based on the shooting field width, the image acquisition time interval, the length of the recyclable material, and the maximum operating speed.

[0050] In this embodiment, the processor can set a material recognition area. Recyclable materials are placed on the conveyor belt and move with it. To ensure that at least one frame of image information is captured for each piece of recyclable material, the processor can obtain the field of view width of the image acquisition device and the length of the recyclable material, and subtract the length of the recyclable material from the field of view width to determine the maximum material recognition area in the image information. Simultaneously, the processor can obtain the maximum operating speed of the conveyor belt and the image acquisition time interval of the image acquisition device, and multiply the maximum operating speed by the image acquisition time interval to determine the minimum material recognition area. The value of the material recognition area can be set between the maximum and minimum material recognition areas, and the specific value can be determined according to actual conditions. In this way, the processor can reduce the possibility of malfunctioning spray valves by setting the material recognition area.

[0051] In this embodiment of the application, determining whether the bottle of each recyclable material is intact based on the material identification area includes: identifying recyclable materials whose bottles are located in at least part of the material identification area as recyclable materials with intact bottles; and identifying recyclable materials whose bottles are not located in the material identification area as recyclable materials with incomplete bottles.

[0052] In this embodiment, after determining the material identification area, the processor can determine whether the bottle of each recyclable material is intact based on the material identification area. Specifically, the processor can identify recyclable materials with at least a portion of their bottle body located within the material identification area as recyclable materials with intact bottle bodies, and identify recyclable materials with no bottle body located within the material identification area as recyclable materials with incomplete bottle bodies. This reduces the possibility of errors in the jet width corresponding to the recyclable material to be sorted due to the image acquisition device not capturing the complete bottle body of the material to be sorted after it has been determined that the recyclable material is to be sorted.

[0053] In this embodiment of the application, determining the location information of the material to be sorted based on the image information may include: determining the first coordinate information of the material to be sorted in the image plane coordinate system based on the image information; and determining the second coordinate information of the material to be sorted in the belt plane coordinate system based on the first coordinate information, based on the predetermined transformation relationship between the image plane coordinate system and the belt plane coordinate system, so as to obtain the location information.

[0054] In this embodiment, the processor can determine the location information of the material to be sorted based on image information. The origins of the image plane coordinate system and the belt plane coordinate system can be the same. Both the image plane coordinate system and the belt plane coordinate system include a first direction and a second direction, where the first direction is perpendicular to the second direction and points to the left, and the second direction is the direction of belt movement. After processing the image information using an image processing algorithm, the processor can determine the first coordinate information of the material to be sorted in the image plane coordinate system. The image processing algorithm used here is determined according to actual needs; a preset image processing algorithm or other image processing algorithms can be used. Subsequently, based on the pre-determined transformation relationship between the image plane coordinate system and the belt plane coordinate system, the processor can convert the first coordinate information of the material to be sorted into the second coordinate information, i.e., the location information, in the belt plane coordinate system. Thus, the processor can determine the location information of the material to be sorted.

[0055] In this embodiment, both the image plane coordinate system and the belt plane coordinate system are planar perpendicular coordinate systems, and the second coordinate information can satisfy formula (2):

[0056]

[0057] Where X represents the second coordinate information in the first direction, Y represents the second coordinate information in the second direction, x represents the first coordinate information in the first direction, y represents the first coordinate information in the second direction, and α represents the horizontal angle between the image plane and the belt plane in the second direction.

[0058] In this embodiment, the first direction is a direction perpendicular to the second direction and pointing to the left, and the second direction is the direction of belt movement. Both the image plane coordinate system and the belt plane coordinate system are planar vertical coordinate systems. Using the above formula, the processor can convert the first coordinate information of the material to be sorted into the second coordinate information, i.e., position information, in the belt plane coordinate system. In this way, the processor can perform calibration conversion between the first coordinate information of the material to be sorted in the image plane coordinate system and the second coordinate information of the material to be sorted in the belt plane coordinate system.

[0059] Figure 3 A schematic diagram illustrating one jet width according to an embodiment of this application is shown. Figure 3 As shown in this embodiment, determining the jet width corresponding to the material to be sorted based on image information may include: generating a rectangular frame corresponding to the material to be sorted using a preset image processing algorithm; obtaining the length, width, and angle of the rectangular frame; and determining the jet width corresponding to the material to be sorted based on the length, width, and angle.

[0060] In this embodiment, the processor can determine the jet width corresponding to the material to be sorted. The preset image processing algorithm can be an improved YOLOv5_OBB algorithm, or other object detection algorithms from the FastCRT-CNN, SSD, and YOLO series. When using the YOLOv5_OBB algorithm, based on the posture of the recyclable material, the processor can output a rotated bounding box that more tightly surrounds the recyclable material, making the detection results more accurate. To achieve rapid generation of the bounding box and rapid output of parameters, the YOLOv5 network model with the shallowest depth and narrowest feature map width can be used as the training algorithm and accelerated by TensorRT. Thus, through the preset image processing algorithm, the processor can generate a bounding box corresponding to the material to be sorted based on the size of the material in the image information, and then obtain the length, width, and angle of the bounding box. The angle refers to the angle between the long side of the bounding box and the negative direction of the first direction, output after converting the quadrant coordinates (-90°, 90°) to (0, 180°). In this way, the processor can determine the jet width corresponding to the material to be sorted based on the length, width, and angle of the bounding box.

[0061] In this embodiment of the application, the jet width corresponding to the material to be sorted can satisfy formula (1):

[0062]

[0063] Where P is the air jet width corresponding to the material to be sorted, H is the length of the rectangle, W is the width of the rectangle, and θ is the angle of the rectangle.

[0064] In this embodiment, based on the range of the angle of the rectangle, combined with the length, width, and angle of the rectangle, the processor can determine the jet width corresponding to the material to be sorted. The jet width satisfies formula (1).

[0065] Figure 4 A flowchart illustrating a sorting method for recyclable materials according to a specific embodiment of this application is shown schematically. Figure 4 As shown in a specific embodiment of this application, the sorting method for recyclable materials may include:

[0066] S1: Obtain image information.

[0067] S2: Image processing algorithm processes image information.

[0068] S3: Output image parameters.

[0069] S4: Set the material identification area.

[0070] S5: Calibration conversion.

[0071] S6: Output the location information of the materials to be sorted.

[0072] S7: Obtain the image information for the next frame.

[0073] S8: Remove duplicates.

[0074] S9: Sorting.

[0075] In one specific embodiment of this application, the image acquisition device is triggered by the processor to take pictures at regular intervals, with the picture interval set to 200ms to 300ms. The field of view of the image acquisition device covers the entire width of the conveyor belt. By taking pictures at regular intervals, the image acquisition device captures images of recyclable materials on the conveyor belt within its field of view and transmits the image information to the processor via a network cable for processing. The processor can process the image information transmitted from the image acquisition device using image processing algorithms to identify the category and color of the recyclable materials and output parameters such as the category, pixel coordinates, angle, and jet width of all recyclable materials in its field of view. The processor can set a material recognition area to filter out incomplete recyclable materials in the field of view along the direction of conveyor belt movement, retaining only complete recyclable materials.

[0076] After identifying the recyclable materials to be sorted from among multiple recyclable materials, the processor calibrates and transforms the first coordinate information of the materials to be sorted in the image plane coordinate system to obtain the second coordinate information of the materials to be sorted in the belt plane coordinate system, i.e., the position information of the materials to be sorted. The processor then acquires the next frame of image information, similarly performs the aforementioned steps, and outputs the position information and category of each material to be sorted. The processor can acquire the position information and category of each material to be sorted frame by frame, perform deduplication and target localization, thereby realizing the sorting of the materials. Furthermore, the processor can display the recognition and localization results in real time on a display device via video streaming, while simultaneously displaying the status information of the sorting system.

[0077] In summary, compared with the prior art, the advantages of the technical solution provided in this application are as follows:

[0078] 1) The sorting system operates at a high speed and can be adapted to belt speeds of up to 3.8 m / s.

[0079] 2) The sorting system outputs the geometric center of the materials to be sorted, which improves the positioning accuracy compared with existing technologies.

[0080] 3) To improve the sorting efficiency at the end of the line, a strategy for adjusting the jet width is proposed, which can improve the sorting accuracy.

[0081] 4) By setting up a material identification area, erroneous actions during jetting can be reduced.

[0082] This application also provides a processor configured to perform the above-described sorting method for recyclable materials.

[0083] Specifically, in this embodiment of the application, the processor can be configured to: acquire image information of multiple recyclable materials; identify the category to which each recyclable material in the image information belongs; determine the material to be sorted among the multiple recyclable materials according to the category to which each recyclable material belongs; determine the location information of the material to be sorted and the jet width corresponding to the material to be sorted according to the image information; and control the spray valve to spray out the material to be sorted according to the jet width based on the location information of the material to be sorted, so as to complete the sorting of the material to be sorted.

[0084] In one embodiment, the processor is further configured to: generate a rectangular frame corresponding to the material to be sorted using a preset image processing algorithm; obtain the length, width, and angle of the rectangular frame; and determine the jet width corresponding to the material to be sorted based on the length, width, and angle.

[0085] In one embodiment, the jet width corresponding to the material to be sorted satisfies formula (1):

[0086]

[0087] Where P is the air jet width corresponding to the material to be sorted, H is the length of the rectangle, W is the width of the rectangle, and θ is the angle of the rectangle.

[0088] In one embodiment, the processor is further configured to: determine the first coordinate information of the material to be sorted in the image plane coordinate system based on the image information; and determine the second coordinate information of the material to be sorted in the belt plane coordinate system based on the first coordinate information, according to a predetermined transformation relationship between the image plane coordinate system and the belt plane coordinate system, to obtain position information.

[0089] In one embodiment, both the image plane coordinate system and the belt plane coordinate system are planar perpendicular coordinate systems, and the second coordinate information satisfies formula (2):

[0090]

[0091] Where X represents the second coordinate information in the first direction, Y represents the second coordinate information in the second direction, x represents the first coordinate information in the first direction, y represents the first coordinate information in the second direction, and α represents the horizontal angle between the image plane and the belt plane in the second direction.

[0092] In one embodiment, the processor is further configured to: determine a material identification area in the image information; determine whether the bottle of each recyclable material is intact based on the material identification area; identify the category to which the recyclable material with an intact bottle belongs; and filter recyclable materials with incomplete bottles.

[0093] In one embodiment, the processor is further configured to: acquire the field of view of the image acquisition device, the image acquisition time interval, the length of the recyclable material, and the maximum operating speed of the belt conveyor; and determine the material identification area in the image information based on the field of view, the image acquisition time interval, the length of the recyclable material, and the maximum operating speed.

[0094] In one embodiment, the processor is further configured to: identify recyclable material with at least a portion of the bottle body located in the material identification area as recyclable material with an intact bottle body; and identify recyclable material with the entire bottle body not located in the material identification area as recyclable material with an incomplete bottle body.

[0095] The above technical solution acquires image information of multiple recyclable materials and identifies the category of each recyclable material in the image information. Based on the category of each recyclable material, it determines the materials to be sorted from the multiple recyclable materials. The processor then determines the location information of the materials to be sorted and the corresponding jet width based on the image information. Finally, based on the location information of the materials to be sorted, the spray valve is controlled according to the jet width to spray the materials to be sorted, thereby completing the sorting of the materials. This application, by determining the jet width, allows the processor to control the spray valve to spray the materials to be sorted according to the jet width, thereby achieving the sorting of the materials and improving the sorting accuracy of recyclable materials.

[0096] Figure 5 This diagram schematically illustrates the structure of a sorting system for recyclable materials according to an embodiment of this application. Figure 5 As shown in the figure, this application embodiment also provides a sorting system for recyclable materials, which may include: an image acquisition device 1; and a processor 2.

[0097] In this embodiment, the sorting system may include an image acquisition device 1, a processor 2, a light source 3, and a display device 4. The sorting system is built on a belt conveyor and can efficiently and accurately identify and sort various recyclable materials. The image acquisition device 1 communicates with the processor 2, and the processor 2 communicates with the display device 4. The image acquisition device 1 can be an industrial area scan camera. The image acquisition device 1 is installed at the top center of the sorting system architecture, and the light source 3 is evenly installed around the image acquisition device 1. The display device 4 can display the working status and recognition results of the sorting system in real time. By capturing images of the movement on the belt of the belt conveyor in real time using the image acquisition device 1, the processor 2 can acquire image information of multiple recyclable materials. After processing the image information using a deep learning algorithm, the processor 2 identifies the material and color of the recyclable materials, thereby determining the materials to be sorted. Through the transformation relationship between the image plane coordinate system and the belt plane coordinate system, the processor can determine the position information of the materials to be sorted, thereby realizing the identification and sorting of recyclable material types and colors.

[0098] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0099] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0100] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0101] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0102] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0103] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0104] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0105] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0106] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for sorting recyclable materials, characterized in that, include: Acquire image information of multiple recyclable materials; Identify the category to which each recyclable material in the image information belongs; The materials to be sorted among the plurality of recyclable materials are determined according to the category to which each recyclable material belongs; The location information of the material to be sorted and the corresponding jet width of the material to be sorted are determined based on the image information. Based on the location information of the material to be sorted, the spray valve is controlled according to the jet width to spray out the material to be sorted in order to complete the sorting of the material to be sorted. The step of determining the jet width corresponding to the material to be sorted based on the image information includes: generating a rectangular frame corresponding to the material to be sorted using a preset image processing algorithm; obtaining the length, width, and angle of the rectangular frame; and determining the jet width corresponding to the material to be sorted based on the length, width, and angle. Wherein, the jet width corresponding to the material to be sorted satisfies formula (1): ；（1） in, The jet width corresponding to the material to be sorted. The length of the rectangle is... The width of the rectangle is [value]. The angle of the rectangle is the angle between the long side of the rectangle and the negative direction of the first direction, and is output after converting the quadrant coordinates (-90°, 90°) to (0, 180°).

2. The sorting method according to claim 1, characterized in that, Determining the location information of the material to be sorted based on the image information includes: The first coordinate information of the material to be sorted in the image plane coordinate system is determined based on the image information. Based on the predetermined transformation relationship between the image plane coordinate system and the belt plane coordinate system, the second coordinate information of the material to be sorted in the belt plane coordinate system is determined according to the first coordinate information, so as to obtain the position information.

3. The sorting method according to claim 2, characterized in that, Both the image plane coordinate system and the belt plane coordinate system are plane perpendicular coordinate systems, and the second coordinate information satisfies formula (2): ；（2） in, The second coordinate information is in the first direction. This refers to the second coordinate information in the second direction. The first coordinate information in the first direction. The first coordinate information in the second direction. The angle between the image plane and the belt plane in the second direction is denoted as .

4. The sorting method according to claim 1, characterized in that, The identification of the category to which each recyclable material in the image information belongs includes: Determine the material identification area in the image information; Based on the material identification area, determine whether the bottle of each recyclable material is intact; Identify the category of recyclable material belonging to a complete bottle; and Recyclable materials in incomplete filter bottles.

5. The sorting method according to claim 4, characterized in that, Determining the material identification region in the image information includes: The image acquisition device used to acquire the image information is configured to obtain the field of view, image acquisition time interval, length of the recyclable material, and maximum operating speed of the belt conveyor. The material identification area in the image information is determined based on the shooting field width, the image acquisition time interval, the length of the recyclable material, and the maximum operating speed.

6. The sorting method according to claim 4, characterized in that, The step of determining whether the bottle of each recyclable material is intact based on the material identification area includes: Recyclable material with at least a portion of the bottle body located within the material identification area is identified as recyclable material with the bottle body intact; and Recyclable materials whose entire bottle body is not located in the material identification area are identified as recyclable materials with incomplete bottle bodies.

7. A processor, characterized in that, A sorting method configured to perform any one of claims 1 to 6 for recyclable materials.

8. A sorting system for recyclable materials, characterized in that, include: Image acquisition equipment; as well as The processor according to claim 7.

Images