Garbage classification method, device and system

By combining the separation and identification module with Yolo V5 model to identify garbage types, and using conveyor belts and automatic packaging devices to deal with multiple garbage, the problem that existing smart garbage cans cannot efficiently handle multiple garbage, and efficient and accurate garbage classification and Storage reduces processing costs and is suitable for urban waste disposal needs.

CN119059128AInactive Publication Date: 2024-12-03PINGXIANG UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411185489.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-27
Publication Date
2024-12-03
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing smart trash cans can only place a single garbage in a single time, and cannot efficiently process multiple garbage, resulting in inefficient identification and classification, and cannot meet the needs of urban garbage disposal.

Method used

Use the separation module to separate multiple garbage into single garbage, and use the garbage classification model (based on Yolo V5 model) to analyze and identify garbage types. Combined with display, conveyor belt control, compression and automatic packaging devices, the automatic classification and storage of multiple garbage can be realized. .

Benefits of technology

It significantly improves the efficiency and accuracy of garbage classification, reduces processing costs, promotes resource recycling, and has good scalability and adaptability, and is suitable for needs in different scenarios.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119059128A_ABST
    Figure CN119059128A_ABST
Patent Text Reader

Abstract

The invention discloses a garbage classification method, device and system. The garbage classification method comprises the steps that S1, multiple pieces of garbage thrown at the same time are separated into single garbage; s2, performing feature analysis on the garbage image of the single garbage through a garbage classification model, and identifying garbage types; wherein the garbage classification model is obtained by training a Yolo V5 model according to various garbage images. And S3, the garbage types, the number, the result whether classification succeeds or not, the full load result and the packaging condition are displayed. By the adoption of the technical scheme, simultaneous throwing of multiple pieces of garbage is supported, the recognition and classification efficiency and accuracy are remarkably improved, and a new intelligent solution is provided for urban garbage treatment.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of garbage disposal, and in particular relates to a garbage classification method, device and system. Background Art

[0002] With the acceleration of urbanization and the continuous expansion of population, the amount of urban garbage has increased dramatically, bringing great pressure to the environment. At present, ordinary trash cans need to automatically put different types of garbage according to classification standards, and the existing smart trash cans only support the single placement of a single piece of garbage. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a garbage classification method, device and system, which support the simultaneous delivery of multiple garbage, significantly improve the efficiency and accuracy of identification and classification, and provide a new intelligent solution for urban garbage disposal.

[0004] To achieve the above object, the present invention adopts the following technical solution:

[0005] A garbage classification method, characterized by comprising:

[0006] Step S1, separating multiple garbage put in at the same time into single garbage;

[0007] Step S2: Perform feature analysis on the garbage image of a single garbage through a garbage classification model to identify the type of garbage; wherein the garbage classification model is obtained by training the Yolo V5 model based on various types of garbage images.

[0008] Preferably, the method further includes: step S3, displaying the garbage type, quantity, classification success or failure result, full load result and packaging status.

[0009] The present invention also provides a garbage classification device, characterized in that it comprises:

[0010] A separation module is used to separate multiple garbages put in at the same time into individual garbages;

[0011] The classification module is used to perform feature analysis on the garbage image of a single garbage through a garbage classification model to identify the type of garbage; wherein the garbage classification model is obtained by training the Yolo V5 model based on historical garbage images.

[0012] The present invention also provides a garbage classification system, including: a garbage classification device and an embedded control device; the embedded control device includes: a display device, a conveyor belt start and stop control device, a full load detection device, a compression device, and an automatic packaging device, wherein:

[0013] A separation module is used to separate multiple garbages put in at the same time into individual garbages;

[0014] The classification module is used to perform feature analysis on the garbage image of a single garbage through a garbage classification model to identify the type of garbage; wherein the garbage classification model is obtained by training the Yolo V5 model based on historical garbage images.

[0015] Preferably, the display device is a serial port display screen for displaying garbage classification information, full load and packaging status.

[0016] Preferably, the conveyor belt start and stop control device and the full load detection device use infrared photoelectric sensors to control the conveyor belt and detect full load.

[0017] Preferably, the compression device includes: an electric push rod and two steel nail plates. When the electric push rod is extended, the two steel nail plates begin to squeeze the recyclable garbage clamped therein to achieve compressed storage.

[0018] Preferably, the automatic packaging device comprises: a closing structure and an electric soldering wire; wherein, when the closing is completed, the electric soldering wire is energized and heated, and the thermoplasticity of the garbage bag is utilized to seal and package it.

[0019] The present invention realizes automatic, efficient and accurate classification of multiple garbage, greatly improves the efficiency of garbage disposal, reduces the disposal cost, and also contributes to environmental protection and resource recycling. Compared with the traditional garbage sorting method, the present invention has higher efficiency and classification accuracy. In addition, the present invention also has good scalability and adaptability, and can be customized and optimized according to the needs of different regions and different scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] 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 embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0021] Figure 1 is a flow chart of the garbage classification method of the present invention;

[0022] Figure 2 Schematic diagram of garbage separation of the garbage classification device of the present invention. DETAILED DESCRIPTION

[0023] 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.

[0024] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0025] Embodiment 1:

[0026] like Figure 1 As shown, an embodiment of the present invention provides a garbage classification method, including:

[0027] Step S1, separating multiple garbage put in at the same time into single garbage;

[0028] Step S2: Perform feature analysis on the garbage image of a single garbage through a garbage classification model to identify the type of garbage; wherein the garbage classification model is obtained by training the Yolo V5 model based on various types of garbage images.

[0029] Step S3: Display the type and quantity of garbage, whether the classification is successful or not, the full load result and the packaging status.

[0030] Embodiment 2:

[0031] An embodiment of the present invention provides a garbage classification device, comprising:

[0032] A separation module is used to separate multiple garbages put in at the same time into individual garbages;

[0033] The classification module is used to perform feature analysis on the garbage image of a single garbage through a garbage classification model to identify the type of garbage; wherein the garbage classification model is obtained by training the Yolo V5 model based on historical garbage images.

[0034] As an implementation method of the embodiment of the present invention, the separation module separates multiple garbages put in at the same time into single garbages through a conveyor belt, specifically: Figure 2As shown, the first-stage conveyor belt is placed at an angle of 50° to the horizontal plane. After multiple garbage enters from the delivery port 10, five baffles are made of acrylic plates 20 to evenly divide the first-stage conveyor belt 30 horizontally into five areas 1, 2, 3, 4, and 5. A single baffle is placed offset from the adjacent baffles, and the middle baffle is slightly longer than the other baffles and slightly tilted forward. Five one-way trap doors 40 are installed at the bottom of the first-stage conveyor belt 30 to prevent garbage from falling downward while allowing the baffles to pass smoothly. When the one-way trap doors 40 are placed, they are perpendicular to the surface of the first-stage conveyor belt 30, so that the one-way trap doors are not affected by each other's opening and closing, and at the same time, garbage in other areas is prevented from falling when a single baffle opens the trap door. When a lot of garbage falls into the first-stage conveyor belt 30, under the influence of gravity and the smooth and inclined surface of the conveyor belt, the garbage will remain at the bottom of the first-stage conveyor belt 30. As the conveyor belt rotates, the baffles separate and transport the garbage individually. The lower baffles transport small garbage such as batteries and pebbles; the long baffles in the middle transport larger garbage such as cans and mineral water bottles. The first-stage conveyor belt 30 transports multiple garbage to the second-stage conveyor belt 50 in sequence. When the infrared photoelectric sensor 60 at the end of the second-stage conveyor belt 50 detects that an object has passed, the infrared photoelectric sensor 60 sends a signal to the control device to stop the first-stage conveyor belt 30 and the second-stage conveyor belt 50. After waiting for the garbage to be identified and classified in the previous cycle, the first-stage conveyor belt 30 and the second-stage conveyor belt 50 resume operation, and the cycle repeats.

[0035] As an implementation method of an embodiment of the present invention, the classification module uses the YOLOv5 visual algorithm to identify and classify various types of garbage. The specific operation is as follows: first, the YOLOv5 environment is installed on the Jetson Nano control board, and pictures of various types of garbage are annotated to make a data set. Then, the data set is trained using GPU acceleration on the Windows system. Then, the garbage classification model obtained after the data set training is completed is installed on the Jetson Nano control board. Then, the garbage classification model is started, and the camera is called to identify and detect various types of garbage. The detection results of the camera on various types of garbage are displayed in real time on the expansion screen. The coordinates and labels obtained from the detection results are passed to the STM32F427 development board, and then the garbage is classified and processed. As shown in the figure, the garbage identified by the camera is selected with a green rectangular frame, and the labels and confidence levels of the identified garbage are displayed above the frame. The confidence level of cans is 0.99, the confidence level of bottles is 1.0, the confidence level of carrots is 1.0, the confidence level of white radishes is 0.98, the confidence level of potatoes is 0.99, the confidence level of expired medicine bags is 1.0, the confidence level of expired medicine bottles is 1.0, the confidence level of expired pills is 0.99, the confidence level of batteries is 0.98, the confidence level of bricks is 0.99, the confidence level of tiles is 1.0, and the confidence level of pebbles is 1.0.

[0036] Embodiment 3:

[0037] The embodiment of the present invention provides a garbage classification system, comprising: a garbage classification device and an embedded control device; wherein:

[0038] A separation module is used to separate multiple garbages put in at the same time into individual garbages;

[0039] The classification module is used to perform feature analysis on the garbage image of a single garbage through a garbage classification model to identify the type of garbage; wherein the garbage classification model is obtained by training the Yolo V5 model based on historical garbage images.

[0040] The embedded control device includes: the embedded control device includes: a display device, a conveyor belt start and stop control device, a full load detection device, a compression device, and an automatic packaging device.

[0041] Furthermore, the display device is a serial port display screen for displaying the type and quantity of garbage, whether the classification is successful or not, the full load result and the packaging status.

[0042] Furthermore, the conveyor belt start and stop control device is an infrared photoelectric sensor. When the garbage passes through the infrared detection area, it sends a low-level signal to the main controller to stop the conveyor belt and wait for identification and classification to be completed.

[0043] Furthermore, the full load detection device is an infrared photoelectric sensor, which is installed at a fixed height of the trash can. When the garbage reaches this height, the trash can is considered to be full, and a low-level signal is sent to the main controller to display the full load status through the display device.

[0044] Furthermore, the compression device includes an electric push rod and two steel nail plates. When the electric push rod is extended, the two steel nail plates begin to squeeze the recyclable garbage clamped therein to achieve compressed storage.

[0045] Furthermore, the automatic packaging device includes a closing structure design and an electric soldering wire. After the closing is completed, the electric soldering wire is energized and heated, and the thermoplasticity of the garbage bag is used to seal and package it.

[0046] Multiple garbages are separated into individual garbages by conveyor belts, and then Jetson nano identifies and classifies individual garbages; Jetson nano sends the identified garbage information to the main controller through the serial communication module, and the main controller controls the classification of individual garbages; the main controller sends Jetson nano's garbage identification and classification information and specific garbage classification information to the display module, and the main controller controls the compression device and automatic packaging device to realize compressed storage and automatic packaging.

[0047] The embodiments described above are only descriptions of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should all fall within the protection scope determined by the claims of the present invention.

Claims

1. A method for sorting garbage, characterized in that: include: Step S1, separating multiple garbage put in at the same time into single garbage; Step S2: Perform feature analysis on the garbage image of a single garbage through a garbage classification model to identify the type of garbage; wherein the garbage classification model is obtained by training the Yolo V5 model based on various types of garbage images.

2. The garbage classification method according to claim 1, characterized in that: The method also includes: step S3, displaying the garbage type, quantity, classification success or failure result, full load result and packaging status.

3. A garbage sorting device, characterized in that: include: A separation module is used to separate multiple garbages put in at the same time into individual garbages; The classification module is used to perform feature analysis on the garbage image of a single garbage through a garbage classification model to identify the type of garbage; wherein the garbage classification model is obtained by training the Yolo V5 model based on historical garbage images.

4. A garbage classification system, characterized in that: include: Waste sorting devices and embedded control devices; The embedded control device includes: display device, conveyor belt start and stop control device, full load detection device, compression device, automatic packaging device, among which, A separation module is used to separate multiple garbages put in at the same time into individual garbages; The classification module is used to perform feature analysis on the garbage image of a single garbage through a garbage classification model to identify the type of garbage; wherein the garbage classification model is obtained by training the Yolo V5 model based on historical garbage images.

5. The garbage classification system according to claim 4, characterized in that: The display device is a serial port display screen, which is used to display garbage classification information, full load and packaging status.

6. The garbage classification system according to claim 5, characterized in that: The conveyor belt start and stop control device and full load detection device use infrared photoelectric sensors to control the conveyor belt and detect full load.

7. The garbage classification system according to claim 6, characterized in that: The compression device includes: an electric push rod and two steel nail plates. When the electric push rod is extended, the two steel nail plates begin to squeeze the recyclable garbage sandwiched therein to achieve compressed storage.

8. The garbage classification system according to claim 7, characterized in that: The automatic packaging device comprises: a closing structure and an electric soldering wire; wherein, when the closing is completed, the electric soldering wire is energized and heated, and the thermoplasticity of the garbage bag is utilized to seal and package it.