Garbage sorting method, device and equipment and storage medium

Abstract

The invention relates to the field of garbage sorting, and discloses a garbage sorting method, device and equipment and a storage medium. The method provided by the embodiment of the invention comprises the following steps: acquiring preset segmentation time; based on the preset segmentation time, the garbage on the conveying belt is segmented into a plurality of garbage clusters, and each garbage cluster is garbage passing through the conveying belt within the preset segmentation time; performing image recognition on each garbage cluster, and detecting each garbage cluster through one or more of ultrasonic detection, thermal imaging detection and electromagnetic detection to generate a classification range of each garbage cluster; and whether the classification range of each garbage cluster meets a confirmation condition or not is judged, if the confirmation condition is met, the garbage clusters are conveyed into the material areas corresponding to the classification ranges, and if the confirmation condition is not met, the garbage clusters are conveyed into the transfer area. According to the method provided by the embodiment of the invention, the sorting efficiency is high, and meanwhile, the garbage which is wrongly sorted can be uniformly treated.

Description

Technical Field

[0001] The present invention relates to the field of garbage sorting, and in particular to a garbage sorting method, device, equipment and storage medium. Background Art

[0002] With the acceleration of urbanization, garbage classification has become an important part of urban management. However, traditional garbage classification management methods often rely on manual inspections and on-site supervision, which is not only inefficient but also has regulatory blind spots.

[0003] There are some sensor-based garbage classification and delivery management systems in the prior art. However, these systems can often only perform simple classification and delivery, and it is difficult to accurately classify the garbage. In addition, the garbage classification and delivery management systems in the prior art will issue alarms when garbage delivery errors occur, reminding relevant staff to intervene and handle the problem.

[0004] However, in actual garbage sorting, the amount of incorrectly placed garbage only accounts for a small part of the total amount of garbage. However, the system in the prior art will issue an alarm every time a garbage sorting error occurs. Such frequent alarms are not only inefficient, but also increase a lot of unnecessary manpower costs. Summary of the invention

[0005] The embodiments of the present invention provide a garbage sorting method, device, equipment and storage medium to solve the above problems.

[0006] In a first aspect, an embodiment of the present invention provides a garbage sorting method for sorting garbage on a conveyor belt into different material areas according to the type of garbage material on the conveyor belt, the garbage sorting method comprising: obtaining a preset segmentation time; based on the preset segmentation time, dividing the garbage on the conveyor belt into multiple garbage clusters, each garbage cluster being garbage that passes through the conveyor belt within the preset segmentation time; performing image recognition on each garbage cluster, and detecting each garbage cluster through one or more of ultrasonic detection, thermal imaging detection, or electromagnetic detection to generate a classification range for each garbage cluster; determining whether the classification range of each garbage cluster meets a confirmation condition, if the confirmation condition is met, transporting the garbage cluster to the material area corresponding to the classification range, if the confirmation condition is not met, transporting the garbage cluster to a transfer area.

[0007] The garbage sorting method provided by the embodiment of the present invention divides the garbage on the conveyor belt into multiple garbage clusters according to preset segment time, performs image recognition on each garbage cluster, and performs one or more of ultrasonic detection, thermal imaging detection, or electromagnetic detection on each garbage cluster, thereby confirming the classification range of each garbage cluster, and finally transporting the garbage clusters that meet the confirmation conditions to the corresponding material area, and transporting the garbage clusters that do not meet the confirmation conditions to the transfer area. While improving the sorting efficiency, it can also achieve accurate sorting through different types of detection, and at the same time, it can also uniformly transport the incorrectly sorted garbage to the transfer area for subsequent unified sorting, thereby avoiding unnecessary multiple warnings.

[0008] Optionally, image recognition is performed on each garbage cluster, and each garbage cluster is detected by one or more of ultrasonic detection, thermal imaging detection, or electromagnetic detection, and the step of generating a classification range for each garbage cluster includes: performing image recognition on each garbage cluster to obtain image information of each garbage cluster; generating an initial classification range for each garbage cluster based on the image information; and detecting each garbage cluster by one or more of ultrasonic detection, thermal imaging detection, or electromagnetic detection to generate a final classification range for each garbage cluster.

[0009] Optionally, each garbage cluster is detected by one or more of ultrasonic detection, thermal imaging detection, or electromagnetic detection, and the step of generating a final classification range for each garbage cluster includes: performing ultrasonic detection on each garbage cluster to obtain density information of each garbage cluster; based on the density information, generating a first material range for each garbage cluster; performing thermal imaging detection on each garbage cluster to obtain temperature information of each garbage cluster; based on the temperature information and the first material range, generating a second material range for each garbage cluster; performing electromagnetic detection on each garbage cluster to obtain magnetic field information of each garbage cluster; based on the magnetic field information and the second material range, generating a final classification range for the garbage cluster; the number of material types included in the first material range, the second material range, and the final classification range decreases in sequence.

[0010] Optionally, each garbage cluster is detected by one or more of ultrasonic detection, thermal imaging detection, or electromagnetic detection, and the step of generating the final classification range of each garbage cluster includes: generating a classification range for each information based on image information, density information, temperature information, and magnetic field information; obtaining a referee module; inputting the classification range of each image information, density information, temperature information, and magnetic field information into the referee module to generate an evaluation result for each classification range; obtaining the number of votes for the evaluation results of each image information, density information, temperature information, and magnetic field information; inputting each evaluation result and the number of votes corresponding to each evaluation result into the referee module, calculating the evaluation result with the largest number of votes, and taking the classification range corresponding to the evaluation result with the largest number of votes as the final classification range of the garbage cluster.

[0011] Optionally, after the step of obtaining the final classification range of the garbage cluster, the method also includes: detecting whether the initial classification range of each garbage cluster has any overlapping part with the corresponding final classification range; if the initial classification range and the final classification range have overlapping part, the confirmation condition is met; if the initial classification range and the final classification range have no overlapping part, the confirmation condition is not met.

[0012] Optionally, the step of determining whether the classification range of each garbage cluster meets the confirmation condition includes: obtaining a probability verification model; using image information, density information, temperature information, and magnetic field information as input parameters of the probability verification model to calculate the confidence of the final classification range; if the confidence reaches an output threshold, the confirmation condition is met; if the confidence is lower than the output threshold, the confirmation condition is not met.

[0013] Optionally, the image information includes color information, shape information, and texture information of the garbage on the conveyor belt.

[0014] Optionally, image recognition is performed on each garbage cluster, and each garbage cluster is detected by one or more of ultrasonic detection, thermal imaging detection, or electromagnetic detection, and the step of generating a classification range for each garbage cluster includes: performing image recognition, ultrasonic detection, thermal imaging detection, and electromagnetic detection on each garbage cluster to obtain image information, density information, temperature information, and magnetic field information of each garbage cluster; based on one or more of the image information, density information, temperature information, and magnetic field information, the garbage cluster is divided into multiple material parts, and the multiple material parts include a high metal content part, a high organic content part, and a mixed material part.

[0015] Optionally, the method also includes: in the garbage cluster, based on density information and image information, generating correlation analysis results of high metal content parts, high organic content parts, and mixed material parts; based on the correlation analysis results, screening garbage individuals in each material part.

[0016] Optionally, a plurality of sensors are provided on the conveyor belt for acquiring image information, density information, temperature information, and magnetic field information of the garbage cluster multiple times. The method further comprises: acquiring at least one of the image information, density information, temperature information, and magnetic field information of each garbage cluster at any one time; acquiring the initial classification area of ​​each garbage individual based on the material position of each garbage individual in the garbage cluster and at least one of the image information, density information, temperature information, and magnetic field information; after acquiring the initial classification area of ​​each garbage individual, acquiring at least one of the image information, density information, temperature information, and magnetic field information of each garbage individual in the garbage cluster at least once again, and determining whether the initial classification area of ​​each garbage individual in the garbage cluster has changed; if the number of times the initial classification area has changed exceeds a review threshold, the confirmation condition is not met, and the corresponding garbage individual in the garbage cluster is transported to the transfer area; if the number of times the initial classification area has changed does not exceed the review threshold, the confirmation condition is met, and the corresponding garbage individual in the garbage cluster is transported to the corresponding material area.

[0017] In a second aspect, an embodiment of the present invention provides a garbage sorting device, which is used to sort the garbage on the conveyor belt into different material areas according to the type of garbage material on the conveyor belt. The garbage sorting device includes: a segmentation module, which is used to segment the garbage on the conveyor belt into multiple garbage clusters based on a preset segmentation time, and each garbage cluster is garbage that passes through the conveyor belt within the preset segmentation time; a sensor module, which is used to perform image recognition, ultrasonic detection, thermal imaging detection, and electromagnetic detection on each garbage cluster to generate corresponding image information, density information, temperature information, and magnetic field information; a processing module, which is connected to the segmentation module The block and the sensor module are communicatively connected, the processing module is used for performing image recognition on each garbage cluster, and detecting each garbage cluster by one or more of ultrasonic detection, thermal imaging detection, or electromagnetic detection, generating a classification range of each garbage cluster, and judging whether the classification range of each garbage cluster satisfies a confirmation condition; if the confirmation condition is satisfied, the garbage cluster is transported to a material area corresponding to the classification range; if the confirmation condition is not satisfied, the garbage cluster is transported to a transfer area; a sorting component, the sorting component is electrically connected to the processing module, and the sorting component is used for sorting garbage individuals in a garbage cluster into corresponding material areas or transfer areas.

[0018] The garbage sorting device provided in the embodiment of the present invention can divide the garbage on the conveyor belt into multiple garbage clusters according to preset segment time, and perform image recognition on each garbage cluster, as well as perform one or more of ultrasonic detection, thermal imaging detection, or electromagnetic detection on each garbage cluster, so as to confirm the classification range of each garbage cluster, and finally transport the garbage clusters that meet the confirmation conditions to the corresponding material area, and transport the garbage clusters that do not meet the confirmation conditions to the transfer area. While improving the sorting efficiency, it can also achieve accurate sorting through different types of detection. At the same time, it can also uniformly transport the incorrectly sorted garbage to the transfer area for subsequent unified sorting, thereby avoiding unnecessary multiple warnings.

[0019] In a third aspect, an embodiment of the present invention provides a garbage sorting device, comprising: a processor and a memory, wherein instructions are stored in the memory; the processor calls the instructions in the memory so that the processor executes the garbage sorting method of any of the aforementioned embodiments of the first aspect of the present invention.

[0020] The processor of the garbage sorting equipment provided by the embodiment of the present invention executes the garbage sorting method of any of the aforementioned embodiments of the first aspect of the present invention by calling the instructions in the memory, so as to divide the garbage on the conveyor belt into multiple garbage clusters according to the preset segment time, and perform image recognition on each garbage cluster, and perform one or more of ultrasonic detection, thermal imaging detection, or electromagnetic detection on each garbage cluster, so as to confirm the classification range of each garbage cluster, and finally transport the garbage clusters that meet the confirmation conditions to the corresponding material area, and transport the garbage clusters that do not meet the confirmation conditions to the transfer area. While improving the sorting efficiency, it can also achieve accurate sorting through different types of detection, and at the same time, it can also uniformly transport the incorrectly sorted garbage to the transfer area for subsequent unified sorting, thereby avoiding unnecessary multiple warnings.

[0021] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, in which instructions are stored. When the instructions are executed by a processor, the garbage sorting method of any of the aforementioned embodiments of the first aspect of the present invention is implemented.

[0022] The instructions stored in the computer-readable storage medium provided in the embodiment of the present invention can be called by the processor and execute the garbage sorting method of any of the aforementioned embodiments of the first aspect of the present invention, and can divide the garbage on the conveyor belt into multiple garbage clusters according to the preset segment time, and perform image recognition on each garbage cluster, and perform one or more of ultrasonic detection, thermal imaging detection, or electromagnetic detection on each garbage cluster, so as to confirm the classification range of each garbage cluster, and finally transport the garbage clusters that meet the confirmation conditions to the corresponding material area, and transport the garbage clusters that do not meet the confirmation conditions to the transfer area. While improving the sorting efficiency, it can also achieve accurate sorting through different types of detection, and at the same time, it can also uniformly transport the incorrectly sorted garbage to the transfer area for subsequent unified sorting, thereby avoiding unnecessary multiple warnings. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.

[0024] Figure 1 A flowchart of an embodiment of the garbage sorting method of the present invention;

[0025] Figure 2 This is a flow chart of step S130 in the first embodiment of the garbage sorting method of the present invention;

[0026] Figure 3 This is a flow chart of step S140 in the first embodiment of the garbage sorting method of the present invention;

[0027] Figure 4 This is a flow chart of step S133 in the first embodiment of the garbage sorting method of the present invention;

[0028] Figure 5 This is a flow chart of step S230 in the second embodiment of the garbage sorting method of the present invention;

[0029] Figure 6 This is a flow chart of step S233 in the second embodiment of the garbage sorting method of the present invention;

[0030] Figure 7 is a flow chart of step S330 in the third embodiment of the garbage sorting method of the present invention;

[0031] Figure 8 is a flow chart of step S340 in the third embodiment of the garbage sorting method of the present invention;

[0032] Fig. 9 It is a structural block diagram of an embodiment of the garbage sorting device of the present invention;

[0033] Fig.10 The figure is a structural block diagram of an embodiment of the garbage sorting equipment of the present invention.

[0034] Description of Figure Numbers:

[0035] 201-segmentation module; 202-sensor module; 203-processing module; 204-sorting component;

[0036] 301 - processor; 302 - memory; 303 - communication interface; 304 - bus. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] It should be noted that all directional indications such as up, down, left, right, front, back, etc. in the embodiments of the present invention are only used to explain the relative position relationship, movement status, etc. between the components in a certain specific posture as shown in the accompanying drawings. If the specific posture changes, the directional indication will also change accordingly.

[0039] In addition, the descriptions of "first", "second", etc. in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0040] For ease of understanding, the garbage sorting method of the embodiment of the present invention is described below. Figure 1 As shown, the garbage sorting method is used to sort the garbage on the conveyor belt into different material areas according to the type of garbage material on the conveyor belt. The garbage sorting method in the embodiment of the present invention includes steps S110 to S140.

[0041] In step S110, a preset segment time is obtained.

[0042] In this embodiment, the preset segment time can be 2 minutes, 3 minutes, 5 minutes, 10 minutes or any other time length. The preset segment time can be pre-set and is not limited in this application.

[0043] In step S120, based on a preset segmentation time, the garbage on the conveyor belt is divided into a plurality of garbage clusters, each of which is garbage that passes through the conveyor belt within the preset segmentation time.

[0044] In this embodiment, when the garbage moves on the conveyor belt, every time a preset segment time passes, the garbage pile passing through the conveyor belt within the preset segment time is divided into multiple garbage clusters according to the preset segment time, so as to facilitate sorting of each garbage cluster and improve sorting efficiency.

[0045] In step S130, image recognition is performed on each garbage cluster, and each garbage cluster is detected by one or more of ultrasonic detection, thermal imaging detection, or electromagnetic detection to generate a classification range for each garbage cluster. The image information includes color information, shape information, and texture information of the garbage on the conveyor belt, the color information is the color of the garbage, the shape information is the shape of the garbage, and the texture information is the texture of the garbage surface.

[0046] like Figure 2 As shown, in some optional embodiments, step S130 includes steps S131 to S133.

[0047] In step S131 , image recognition is performed on each garbage cluster to obtain image information of each garbage cluster.

[0048] In step S132 , an initial classification range of each garbage cluster is generated based on the image information.

[0049] In this embodiment, the image information can be processed according to a deep learning model, such as a convolutional neural network, to extract the color information, shape information, and texture information of the garbage, and the color information, shape information, and texture information of the garbage can be sorted and preliminarily classified to obtain the initial classification range of each garbage cluster.

[0050] In step S133, each garbage cluster is detected by one or more of ultrasonic detection, thermal imaging detection, or electromagnetic detection to generate a final classification range for each garbage cluster.

[0051] In this embodiment, after performing image recognition on the garbage cluster, the initial classification range of the garbage cluster is generated according to the obtained image information, and then one or more of ultrasonic detection, thermal imaging detection, or electromagnetic detection is performed on the garbage cluster to generate the final classification range of the garbage cluster. Through multiple detections, the recognition accuracy of the garbage cluster is improved and the occurrence of sorting errors is reduced.

[0052] like Figure 4 As shown, further, step S133 includes steps S1331 to S1336.

[0053] In step S1331, ultrasonic detection is performed on each garbage cluster to obtain density information of each garbage cluster.

[0054] In step S1332 , a first material range of each garbage cluster is generated based on the density information.

[0055] In step S1333, thermal imaging detection is performed on each garbage cluster to obtain temperature information of each garbage cluster.

[0056] In step S1334 , a second material range of each garbage cluster is generated based on the temperature information and the first material range.

[0057] In step S1335, electromagnetic detection is performed on each garbage cluster to obtain magnetic field information of each garbage cluster.

[0058] In step S1336, a final classification range of the garbage cluster is generated based on the magnetic field information and the second material range.

[0059] Among them, the number of material types included in the first material range, the second material range, and the final classification range decreases in sequence.

[0060] In this embodiment, when ultrasonic detection is performed on a garbage cluster, the density information and thickness information of the garbage in the garbage cluster can be obtained. By comparing with a pre-built complex material physical property mapping library, the material range that meets the detected density information and thickness information can be screened out.

[0061] When performing thermal imaging detection on garbage clusters, thermal imaging images of the garbage in the garbage clusters, i.e., temperature information, can be obtained. Based on the temperature information, density information, and thickness information, the material range of the garbage can be further narrowed down by comparing it with the complex material physical property mapping library to obtain a second material range.

[0062] Finally, electromagnetic detection is performed on each garbage cluster to obtain the magnetic field information of each garbage cluster. The corresponding material range that meets the magnetic field information is screened within the second material range to obtain the final classification range of the garbage cluster and realize accurate sorting of garbage.

[0063] In step S140, it is determined whether the classification range of each garbage cluster meets the confirmation conditions. If the confirmation conditions are met, the garbage cluster is transported to the material area corresponding to the classification range. If the confirmation conditions are not met, the garbage cluster is transported to the transfer area.

[0064] In some optional embodiments, after the step of obtaining the final classification range of the garbage cluster, the step of determining whether the classification range of each garbage cluster meets the confirmation condition includes: detecting whether the initial classification range of each garbage cluster has any overlapping parts with the corresponding final classification range; if the initial classification range and the final classification range have overlapping parts, the confirmation condition is met; if the initial classification range and the final classification range have no overlapping parts, the confirmation condition is not met.

[0065] In this embodiment, the initial classification range of the garbage cluster obtained according to the image information is compared with the final classification range of the garbage cluster. If the initial classification range and the final classification range have overlapping material types, the garbage cluster is transported to the material area corresponding to the classification range. If the initial classification range and the final classification range do not have overlapping material types, the garbage cluster is transported to the transfer area for subsequent unified sorting. By uniformly transporting the incorrectly sorted garbage to the transfer area, the unified sorting of the incorrectly sorted garbage is achieved, avoiding the situation where a prompt is given every time the incorrectly sorted garbage is detected, thereby reducing the sorting cost.

[0066] like Figure 3 As shown, in some optional embodiments, the step of determining whether the classification range of each garbage cluster meets the confirmation condition further includes steps S141 to S143.

[0067] In step S141, a probability verification model is obtained.

[0068] In step S142, the image information, density information, temperature information, and magnetic field information are used as input parameters of the probability verification model to calculate the confidence of the final classification range.

[0069] In step S143, if the confidence reaches the output threshold, the confirmation condition is met; if the confidence is lower than the output threshold, the confirmation condition is not met.

[0070] In this embodiment, the obtained image information, density information, temperature information, and magnetic field information are stored in a temporary classification area to be confirmed. After the final classification range of the garbage cluster is obtained, the image information, density information, temperature information, and magnetic field information of the corresponding garbage cluster are input into the probability verification model as input parameters of the probability verification model to calculate the confidence of the final classification range. If the confidence reaches the output threshold, the confirmation condition is met, and the garbage cluster is sorted into the corresponding material area. If the confidence is lower than the output threshold, the confirmation condition is not met, and the garbage cluster is transported to the transfer area. The garbage in the transfer area can be sorted again in a unified manner, or manually sorted.

[0071] The output threshold is a preset value, for example, the output threshold may be 90%, 94%, 95% or other values.

[0072] The garbage sorting method provided by the present invention also includes a second embodiment. Some steps of the second embodiment are the same as those of the first embodiment. The differences between the two will be described below, and the similarities will not be described in detail.

[0073] In the second embodiment of the present invention, the garbage sorting method includes steps S210 to S240, wherein steps S210 to S220 and step S240 are the same as the garbage sorting method in the first embodiment of the present invention, and will not be repeated here.

[0074] In step S210, a preset segment time is obtained.

[0075] In step S220, based on a preset segmentation time, the garbage on the conveyor belt is divided into a plurality of garbage clusters, each of which is garbage that passes through the conveyor belt within the preset segmentation time.

[0076] In step S230, image recognition is performed on each garbage cluster, and each garbage cluster is detected by one or more of ultrasonic detection, thermal imaging detection, or electromagnetic detection to generate a classification range for each garbage cluster. The image information includes color information, shape information, and texture information of the garbage on the conveyor belt.

[0077] like Figure 5 As shown, step S230 includes steps S231 to S233.

[0078] In step S231, image recognition is performed on each garbage cluster to obtain image information of each garbage cluster.

[0079] In step S232, an initial classification range of each garbage cluster is generated based on the image information.

[0080] In step S233, each garbage cluster is detected by one or more of ultrasonic detection, thermal imaging detection, or electromagnetic detection to generate a final classification range for each garbage cluster.

[0081] Further, step S233 includes step S2331 to step S2335.

[0082] like Figure 6 As shown, in step S2331, a classification range for each type of information is generated based on image information, density information, temperature information, and magnetic field information.

[0083] In step S2332, obtain the referee module.

[0084] In step S2333, the classification ranges of the image information, density information, temperature information, and magnetic field information are respectively input into the judging module to generate an evaluation result for each classification range.

[0085] In step S2334, the number of votes for the evaluation results of each of the image information, density information, temperature information, and magnetic field information is obtained.

[0086] In step S2335, each evaluation result and the number of votes corresponding to each evaluation result are input into the judging module, the evaluation result with the largest number of votes is calculated, and the classification range corresponding to the evaluation result with the largest number of votes is used as the final classification range of the garbage cluster.

[0087] In this embodiment, the image information, density information, temperature information, and magnetic field information of the garbage cluster are detected by corresponding visual sensors, ultrasonic sensors, thermal imaging sensors, and electromagnetic sensors. A plurality of nodes are arranged on the conveyor belt, and each node may be provided with at least one of the visual sensors, ultrasonic sensors, thermal imaging sensors, and electromagnetic sensors to detect the garbage cluster on the conveyor belt.

[0088] For garbage clusters whose initial classification range and final classification range are inconsistent, the "intelligent debate" link will be initiated. According to the detection results of sensors at different nodes, evidence will be provided to support the classification range determined by each sensor. Finally, the final classification result will be determined by the "referee" system. In this referee system, each node is equipped with a decision-making module and communicates with the sensor at the node. The decision-making module can vote for the results of the classification range determined by itself. Finally, according to the number of votes for the evaluation results of image information, density information, temperature information, and magnetic field information, the evaluation result with the most votes is calculated, and the classification range corresponding to the evaluation result with the most votes is used as the final classification range of the garbage cluster.

[0089] In step S240, it is determined whether the classification range of each garbage cluster meets the confirmation conditions. If the confirmation conditions are met, the garbage cluster is transported to the material area corresponding to the classification range. If the confirmation conditions are not met, the garbage cluster is transported to the transfer area.

[0090] The garbage sorting method provided by the present invention also includes a third embodiment. Some steps of the third embodiment are the same as those of the first embodiment. The differences between the two will be described below, and the similarities will not be described in detail.

[0091] In the third embodiment of the present invention, the garbage sorting method includes steps S310 to S340, wherein steps S310 to S320 are the same as those in the first embodiment of the present invention, and will not be repeated here.

[0092] In step S310, a preset segment time is obtained.

[0093] In step S320, based on a preset segmentation time, the garbage on the conveyor belt is divided into a plurality of garbage clusters, each of which is garbage that passes through the conveyor belt within the preset segmentation time.

[0094] In step S330, image recognition is performed on each garbage cluster, and each garbage cluster is detected by one or more of ultrasonic detection, thermal imaging detection, or electromagnetic detection to generate a classification range for each garbage cluster. The image information includes color information, shape information, and texture information of the garbage on the conveyor belt.

[0095] Among them, Figure 7 As shown, step S330 includes step S331 to step S332.

[0096] In step S331, image recognition, ultrasonic detection, thermal imaging detection, and electromagnetic detection are performed on each garbage cluster to obtain image information, density information, temperature information, and magnetic field information of each garbage cluster.

[0097] In step S332, based on one or more of the image information, density information, temperature information, and magnetic field information, the garbage cluster is divided into multiple material parts, including a high metal content part, a high organic content part, and a mixed material part.

[0098] In this embodiment, the garbage cluster is divided into multiple material parts according to one or more of the image information, density information, temperature information, and magnetic field information of the garbage cluster. For example, the garbage cluster can be divided into a high metal content part with a higher metal content, a high organic content part with a higher organic content, and a mixed material part where various materials are mixed, thereby realizing macroscopic partitioning of the garbage cluster to facilitate further precise sorting of each material part.

[0099] Further, after step S332, the method of the embodiment of the present application also includes steps S333 to S334.

[0100] In step S333, in the garbage cluster, based on the density information and the image information, the correlation analysis results of the high metal content parts, the high organic matter content parts, and the mixed material parts are generated.

[0101] In step S334, based on the association analysis results, the garbage individuals in each material part are screened.

[0102] In this embodiment, the correlation between garbage individuals in each material part is analyzed. For example, in the part with high metal content, by performing image recognition and ultrasonic detection on the garbage individuals therein, interconnected or nested garbage individuals are screened out, and it is determined whether these interconnected or nested garbage individuals are different parts of the same garbage individual or a combination of different types of metal products.

[0103] For garbage individuals that are related to each other, they are considered as related individuals. Based on one or more of the density information, temperature information, and magnetic field information of each garbage individual in the related individual and the connection relationship between each garbage individual in the related individual, for example, the density information and thickness information obtained by ultrasonic detection are used to judge the internal structure continuity of each garbage individual in the related individual, and a related model is constructed through a graph theory algorithm, and the common source of each garbage individual in the related individual is further simulated and calculated to achieve accurate screening of garbage individuals in each material part.

[0104] In step S340, it is determined whether the classification range of each garbage cluster meets the confirmation conditions. If the confirmation conditions are met, the garbage cluster is transported to the material area corresponding to the classification range. If the confirmation conditions are not met, the garbage cluster is transported to the transfer area.

[0105] In this embodiment, a plurality of sensors are arranged on the conveyor belt for acquiring image information, density information, temperature information, and magnetic field information of the garbage cluster multiple times.

[0106] Specifically, for example, there are multiple silver block objects in the area with high metal content. The texture information obtained through image recognition found that the surfaces of these block objects have similar textures, and some objects have connected parts. The thickness information and density information obtained through ultrasonic testing can be obtained that the internal structural echoes of these block objects are similar, and in certain specific locations, their echoes show continuity, proving that these objects are physically connected to each other, that is, they are different parts of a garbage individual.

[0107] Through the magnetic field information and density information, we can further analyze and find that the shapes and sizes of these block objects are consistent with some characteristics of the computer case shell. By comparing with the complex material physical property mapping library, it is judged that the garbage individuals may be different parts of a large computer case after disassembly, and its material is aluminum alloy.

[0108] Furthermore, thermal imaging can be used to detect the heating elements in each material part or the garbage individuals in the parts with high organic content, and ultrasonic detection of the gaps and reflection frequencies between the garbage individuals can be used to achieve comprehensive analysis and judgment. Finally, by comparing with the complex material physical property mapping library, it can be determined that these garbage are components of the electronic equipment heat dissipation module, including heat sinks and heat pipes, and they are divided into an associated group. Through the analysis of thermal properties and material characteristics, it is speculated that the material may be a mixture of metals with good thermal conductivity such as copper or aluminum and some polymer heat dissipation materials.

[0109] In the mixed material area, there are generally a lot of colored plastic shells, fine metal wires, glass fibers and other types of garbage. Through image recognition, the color, shape and texture information of plastic shells and metal wires can be obtained. Through ultrasonic detection, the density and thickness information of individual garbage can be obtained, and through electromagnetic detection, the magnetic field information of individual garbage can be obtained.

[0110] Based on a comprehensive judgment of image information, temperature information, density information and / or thickness information and magnetic field information, and by comparing with the complex material physical property mapping library, it is judged that this part of the garbage topic may come from the internal structure of different electronic devices, and the related plastic casings, metal wires and other objects are divided into an associated group for transportation to the corresponding material area.

[0111] like Figure 8 As shown, step S340 includes steps S341 to S343.

[0112] In step S341 , at least one of image information, density information, temperature information, and magnetic field information of each garbage cluster is obtained at any one time.

[0113] In step S342, the initial classification area of ​​each garbage individual is obtained based on the material position of each garbage individual in the garbage cluster, and at least one of the image information, density information, temperature information, and magnetic field information.

[0114] In step S343, after obtaining the initial classification area of ​​each garbage individual, at least one of the image information, density information, temperature information, and magnetic field information of each garbage individual in the garbage cluster is obtained again at least once to determine whether the initial classification area of ​​each garbage individual in the garbage cluster has changed. If the number of times the initial classification area has changed exceeds the review threshold, the confirmation condition is not met, and the corresponding garbage individual in the garbage cluster is transported to the transfer area. If the number of times the initial classification area has changed does not exceed the review threshold, the confirmation condition is met, and the corresponding garbage individual in the garbage cluster is transported to the corresponding material area.

[0115] In this embodiment, the image information, density information, temperature information, and magnetic field information of the garbage cluster are detected by corresponding visual sensors, ultrasonic sensors, thermal imaging sensors, and electromagnetic sensors. A plurality of nodes are arranged on the conveyor belt, and each node may be provided with at least one of the visual sensors, ultrasonic sensors, thermal imaging sensors, and electromagnetic sensors to detect the garbage cluster on the conveyor belt.

[0116] A garbage cluster is detected by a sensor in a node to obtain an initial classification area of ​​each garbage individual in the garbage cluster. After that, each garbage individual in the garbage cluster passes through a subsequent node again, and each garbage individual in the garbage cluster is detected again to obtain at least one of image information, density information, temperature information, and magnetic field information. The classification area of ​​each garbage individual in the garbage cluster is obtained based on the detection result obtained again, and it is determined whether the initial classification area of ​​each garbage individual in the garbage cluster has changed. If the classification area obtained again is different from the initial classification area, the initial classification area has changed once.

[0117] In this embodiment, the review threshold can be 2 times, 3 times, 4 times or other integer values. For example, if the initial classification area of ​​a garbage cluster or a garbage individual changes more than 3 times, it proves that the classification area result of the garbage cluster or the garbage individual is unstable, and the garbage cluster or the garbage individual has a sorting error and does not meet the confirmation condition, so the corresponding garbage individual in the garbage cluster is transported to the transfer area.

[0118] If the number of times the initial classification area changes does not exceed 3 times, the confirmation condition is met, and the material area to be transported for the garbage cluster or the garbage individual is the correct sorting area, so the corresponding garbage individual in the garbage cluster is transported to the material area.

[0119] The garbage sorting method provided by the embodiment of the present invention includes: obtaining a preset segmentation time; based on the preset segmentation time, dividing the garbage on the conveyor belt into multiple garbage clusters, each garbage cluster is the garbage passing through the conveyor belt within the preset segmentation time; performing image recognition on each garbage cluster, and detecting each garbage cluster through one or more of ultrasonic detection, thermal imaging detection, or electromagnetic detection to generate a classification range for each garbage cluster; judging whether the classification range of each garbage cluster meets the confirmation condition, if the confirmation condition is met, transporting the garbage cluster to the material area corresponding to the classification range, if the confirmation condition is not met, transporting the garbage cluster to the transfer area.

[0120] The method provided by the embodiment of the present invention can divide the garbage on the conveyor belt into multiple garbage clusters according to preset segment time, and perform image recognition on each garbage cluster, as well as perform one or more of ultrasonic detection, thermal imaging detection, or electromagnetic detection on each garbage cluster, so as to confirm the classification range of each garbage cluster, and finally transport the garbage clusters that meet the confirmation conditions to the corresponding material area, and transport the garbage clusters that do not meet the confirmation conditions to the transfer area. While improving the sorting efficiency, it can also achieve accurate sorting through different types of detection, and at the same time, the incorrectly sorted garbage can be uniformly transported to the transfer area for subsequent unified sorting, thereby avoiding unnecessary multiple warnings.

[0121] For the above method embodiment, the embodiment of the present invention also provides Fig. 9 The garbage sorting device shown is used to sort the garbage on the conveyor belt into different material areas according to the type of garbage material on the conveyor belt. The garbage sorting device includes: a segmentation module 201, a sensor module 202, a processing module 203 and a sorting component 204.

[0122] The segmentation module 201 is used to segment the garbage on the conveyor belt into a plurality of garbage clusters based on a preset segmentation time, each garbage cluster being garbage that passes through the conveyor belt within the preset segmentation time.

[0123] The sensor module 202 is used to perform image recognition, ultrasonic detection, thermal imaging detection, and electromagnetic detection on each garbage cluster to generate corresponding image information, density information, temperature information, and magnetic field information.

[0124] The processing module 203 is communicatively connected with the segmentation module 201 and the sensor module 202. The processing module 203 is used to perform image recognition on each garbage cluster, and detect each garbage cluster through one or more of ultrasonic detection, thermal imaging detection, or electromagnetic detection, generate a classification range for each garbage cluster, and determine whether the classification range of each garbage cluster meets the confirmation conditions. If the confirmation conditions are met, the garbage cluster is transported to the material area corresponding to the classification range. If the confirmation conditions are not met, the garbage cluster is transported to the transfer area.

[0125] The sorting component 204 is electrically connected to the processing module 203, and is used to sort individual garbage items in a garbage cluster into corresponding material areas or transfer areas.

[0126] In this embodiment, the sensor module 202 includes a timer, a visual sensor, an ultrasonic sensor, a thermal imaging sensor and an electromagnetic sensor. The transmission belt is provided with multiple detection nodes, and at least one of the visual sensor, ultrasonic sensor, thermal imaging sensor and electromagnetic sensor is provided on each detection node.

[0127] When the garbage is transported to the conveyor belt, the garbage on the conveyor belt is divided into multiple garbage clusters by a timer, and the processing module 203 performs image recognition on the garbage clusters through a visual sensor, and performs preliminary identification and screening of the garbage clusters. Then, the processing module 203 repeatedly detects the garbage clusters through at least one of an acoustic sensor, a thermal imaging sensor, and an electromagnetic sensor, and finally combines multiple detection results to determine the type of garbage individuals in the garbage clusters and transport them to the corresponding material area.

[0128] Among them, the sorting component 204 includes a transmission member and a driving member, the transmission member is connected to the conveyor belt, and the processing module 203 can drive the transmission member to move through the driving member to change the conveying direction of the conveyor belt and transport the corresponding garbage clusters or garbage individuals to the corresponding material area.

[0129] The garbage sorting device provided by the embodiment of the present invention can divide the garbage on the conveyor belt into multiple garbage clusters according to preset segment time by implementing the above method, and perform image recognition on each garbage cluster, as well as perform one or more of ultrasonic detection, thermal imaging detection, or electromagnetic detection on each garbage cluster, so as to confirm the classification range of each garbage cluster, and finally transport the garbage clusters that meet the confirmation conditions to the corresponding material area, and transport the garbage clusters that do not meet the confirmation conditions to the transfer area. While improving the sorting efficiency, it can also achieve accurate sorting through different types of detection. At the same time, it can also uniformly transport the incorrectly sorted garbage to the transfer area for subsequent unified sorting, thereby avoiding unnecessary multiple warnings.

[0130] For the above method embodiment, the embodiment of the present invention also provides Fig.10 A garbage sorting device shown includes: a processor 301 and a memory 302, wherein the memory 302 stores instructions; the processor 301 calls the instructions in the memory 302 so that the processor 301 executes the garbage sorting method of any of the aforementioned embodiments of the present invention.

[0131] The garbage sorting method provided by the aforementioned embodiment of the present invention includes: obtaining a preset segmentation time; based on the preset segmentation time, dividing the garbage on the conveyor belt into multiple garbage clusters, each garbage cluster being the garbage passing through the conveyor belt within the preset segmentation time; performing image recognition on each garbage cluster, and detecting each garbage cluster through one or more of ultrasonic detection, thermal imaging detection, or electromagnetic detection to generate a classification range for each garbage cluster; determining whether the classification range of each garbage cluster meets a confirmation condition, and if so, transporting the garbage cluster to a material area corresponding to the classification range; and if not, transporting the garbage cluster to a transfer area.

[0132] The garbage sorting equipment provided by the embodiment of the present invention implements the above method to divide the garbage on the conveyor belt into multiple garbage clusters according to preset segment time, and performs image recognition on each garbage cluster, as well as one or more of ultrasonic detection, thermal imaging detection, or electromagnetic detection on each garbage cluster, so as to confirm the classification range of each garbage cluster, and finally transport the garbage clusters that meet the confirmation conditions to the corresponding material area, and transport the garbage clusters that do not meet the confirmation conditions to the transfer area. While improving the sorting efficiency, it can also achieve accurate sorting through different types of detection. At the same time, it can also uniformly transport the incorrectly sorted garbage to the transfer area for subsequent unified sorting, thereby avoiding unnecessary multiple warnings.

[0133] Furthermore, the garbage sorting device provided by the embodiment of the present invention may further include a communication interface 303 and a bus 304 , and the processor 301 , the memory 302 and the communication interface 303 are electrically connected via the bus 304 .

[0134] The memory 302 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 303 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used. The bus 304 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.10 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0135] The processor 301 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 301. The above processor 301 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiment of the present invention can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module may be located in a storage medium mature in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 302, and the processor 301 reads the information in the memory 302 and completes the steps of the method of the above embodiment in combination with its hardware.

[0136] An embodiment of the present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of the above-mentioned garbage sorting method.

[0137] The computer-readable storage medium provided by the embodiment of the present invention stores data and computer executable instructions of the above-mentioned garbage sorting method, and the above-mentioned garbage sorting method includes: obtaining a preset segmentation time; based on the preset segmentation time, dividing the garbage on the conveyor belt into multiple garbage clusters, each garbage cluster is the garbage passing through the conveyor belt within the preset segmentation time; performing image recognition on each garbage cluster, and detecting each garbage cluster through one or more of ultrasonic detection, thermal imaging detection, or electromagnetic detection to generate a classification range for each garbage cluster; judging whether the classification range of each garbage cluster meets the confirmation condition, if the confirmation condition is met, then transporting the garbage cluster to the material area corresponding to the classification range, if the confirmation condition is not met, then transporting the garbage cluster to the transfer area.

[0138] The computer-readable storage medium provided by the embodiment of the present invention can implement the above method to divide the garbage on the conveyor belt into multiple garbage clusters according to preset segment time, perform image recognition on each garbage cluster, and perform one or more of ultrasonic detection, thermal imaging detection, or electromagnetic detection on each garbage cluster, so as to confirm the classification range of each garbage cluster, and finally transport the garbage clusters that meet the confirmation conditions to the corresponding material area, and transport the garbage clusters that do not meet the confirmation conditions to the transfer area. While improving the sorting efficiency, it can also achieve accurate sorting through different types of detection. At the same time, it can also uniformly transport the incorrectly sorted garbage to the transfer area for subsequent unified sorting, thereby avoiding unnecessary multiple warnings.

[0139] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0140] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program codes.

[0141] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A garbage sorting method, characterized in that: The method is used to sort garbage on the conveyor belt into different material areas according to the type of garbage material on the conveyor belt, and the method comprises: Get the preset segment time; Based on the preset segment time, the garbage on the conveyor belt is divided into a plurality of garbage clusters, each of which is garbage that passes through the conveyor belt within the preset segment time; Performing image recognition on each of the garbage clusters, and detecting each of the garbage clusters by one or more of ultrasonic detection, thermal imaging detection, or electromagnetic detection, to generate a classification range for each of the garbage clusters; Determine whether the classification range of each garbage cluster meets the confirmation conditions. If the confirmation conditions are met, the garbage cluster is transported to the material area corresponding to the classification range. If the confirmation conditions are not met, the garbage cluster is transported to the transfer area.

2. The garbage sorting method according to claim 1, characterized in that: The steps of performing image recognition on each garbage cluster, and detecting each garbage cluster by one or more of ultrasonic detection, thermal imaging detection, or electromagnetic detection to generate a classification range for each garbage cluster include: Performing image recognition on each of the garbage clusters to obtain image information of each of the garbage clusters; Based on the image information, generating an initial classification range for each of the garbage clusters; Each of the garbage clusters is detected by one or more of ultrasonic detection, thermal imaging detection, or electromagnetic detection to generate a final classification range of each of the garbage clusters.

3. The garbage sorting method according to claim 2, characterized in that: The step of detecting each garbage cluster by one or more of ultrasonic detection, thermal imaging detection, or electromagnetic detection to generate a final classification range of each garbage cluster includes: Performing ultrasonic detection on each of the garbage clusters to obtain density information of each of the garbage clusters; Based on the density information, generating a first material range for each of the garbage clusters; Perform thermal imaging detection on each of the garbage clusters to obtain temperature information of each of the garbage clusters; generating a second material range for each of the garbage clusters based on the temperature information and the first material range; Performing electromagnetic detection on each of the garbage clusters to obtain magnetic field information of each of the garbage clusters; Based on the magnetic field information and the second material range, generating the final classification range of the garbage cluster; The number of material types included in the first material range, the second material range, and the final classification range decreases in sequence.

4. The garbage sorting method according to claim 3, characterized in that: The step of detecting each garbage cluster by one or more of ultrasonic detection, thermal imaging detection, or electromagnetic detection to generate a final classification range of each garbage cluster includes: Based on the image information, the density information, the temperature information, and the magnetic field information, generating a classification range for each type of information; Get the referee module; Inputting the classification ranges of the image information, the density information, the temperature information, and the magnetic field information into the judging module to generate an evaluation result for each classification range; Obtaining the number of votes of the evaluation results of each of the image information, the density information, the temperature information, and the magnetic field information; Each of the evaluation results and the number of votes corresponding to each of the evaluation results are input into the judging module, the evaluation result with the largest number of votes is calculated, and the classification range corresponding to the evaluation result with the largest number of votes is used as the final classification range of the garbage cluster.

5. The garbage sorting method according to claim 4, characterized in that: After the step of obtaining the final classification range of the garbage cluster, the method further includes: Check whether the initial classification range of each garbage cluster overlaps with the corresponding final classification range. If the initial classification range overlaps with the final classification range, the confirmation condition is met; if the initial classification range does not overlap with the final classification range, the confirmation condition is not met.

6. The garbage sorting method according to claim 3, characterized in that: The step of determining whether the classification range of each garbage cluster meets the confirmation condition includes: Obtain a probabilistic validation model; Using the image information, the density information, the temperature information, and the magnetic field information as input parameters of the probability verification model, and calculating the confidence of the final classification range; If the confidence reaches the output threshold, the confirmation condition is met; if the confidence is lower than the output threshold, the confirmation condition is not met.

7. The garbage sorting method according to claim 2, characterized in that: The image information includes color information, shape information, and texture information of the garbage on the conveyor belt.

8. The garbage sorting method according to claim 1, characterized in that: The steps of performing image recognition on each garbage cluster, and detecting each garbage cluster by one or more of ultrasonic detection, thermal imaging detection, or electromagnetic detection to generate a classification range for each garbage cluster include: Performing image recognition, ultrasonic detection, thermal imaging detection, and electromagnetic detection on each of the garbage clusters to obtain image information, density information, temperature information, and magnetic field information of each of the garbage clusters; Based on one or more of the image information, the density information, the temperature information, and the magnetic field information, the garbage cluster is divided into a plurality of material parts, the plurality of material parts including a high metal content part, a high organic matter content part, and a mixed material part.

9. The garbage sorting method according to claim 8, characterized in that: The method further comprises: In the garbage cluster, based on the density information and the image information, generating correlation analysis results of the high metal content part, the high organic matter content part, and the mixed material part; Based on the association analysis results, the garbage individuals in each of the material locations are screened.

10. The garbage sorting method according to claim 9, characterized in that: The conveyor belt is provided with a plurality of sensors for acquiring the image information, the density information, the temperature information, and the magnetic field information of the garbage cluster multiple times. The method further includes: Acquire at least one of the image information, the density information, the temperature information, and the magnetic field information of each garbage cluster at any one time; Based on the material position of each garbage individual in the garbage cluster, and at least one of the image information, the density information, the temperature information, and the magnetic field information, an initial classification area of ​​each garbage individual is obtained; After obtaining the initial classification area of ​​each of the garbage individuals, obtain at least one of the image information, the density information, the temperature information, and the magnetic field information of each of the garbage individuals in the garbage cluster at least once again to determine whether the initial classification area of ​​each garbage individual in the garbage cluster has changed. If the number of times the initial classification area has changed exceeds the review threshold, the confirmation condition is not met, and the corresponding garbage individuals in the garbage cluster are transported to the transfer area. If the number of times the initial classification area has changed does not exceed the review threshold, the confirmation condition is met, and the corresponding garbage individuals in the garbage cluster are transported to the corresponding material area.

11. A garbage sorting device, characterized in that: The device is used to sort the garbage on the conveyor belt into different material areas according to the type of garbage material on the conveyor belt, and the garbage sorting device includes: A segmentation module, the segmentation module is used to segment the garbage on the conveyor belt into a plurality of garbage clusters based on a preset segmentation time, each of the garbage clusters being garbage that passes through the conveyor belt within the preset segmentation time; A sensor module, the sensor module is used to perform image recognition, ultrasonic detection, thermal imaging detection, and electromagnetic detection on each of the garbage clusters to generate corresponding image information, density information, temperature information, and magnetic field information; a processing module, the processing module being communicatively connected with the segmentation module and the sensor module, the processing module being used to perform image recognition on each of the garbage clusters, and to detect each of the garbage clusters by one or more of ultrasonic detection, thermal imaging detection, or electromagnetic detection, to generate a classification range for each of the garbage clusters, and to determine whether the classification range of each of the garbage clusters meets a confirmation condition; if the confirmation condition is met, the garbage cluster is transported to the material area corresponding to the classification range; if the confirmation condition is not met, the garbage cluster is transported to a transfer area; A sorting component is electrically connected to the processing module, and is used for sorting individual garbage in a garbage cluster into the corresponding material area or the transfer area.

12. A garbage sorting device, characterized in that: The garbage sorting device comprises: a processor and a memory, wherein instructions are stored in the memory; The processor is capable of calling the instructions in the memory so as to enable the garbage sorting device to implement the garbage sorting method as described in any one of claims 1 to 10.

13. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the garbage sorting method as described in any one of claims 1 to 10 is implemented.

Images