CN110758932A - Automatic garbage classification mechanism and classification method - Google Patents
Automatic garbage classification mechanism and classification method Download PDFInfo
- Publication number
- CN110758932A CN110758932A CN201910999874.5A CN201910999874A CN110758932A CN 110758932 A CN110758932 A CN 110758932A CN 201910999874 A CN201910999874 A CN 201910999874A CN 110758932 A CN110758932 A CN 110758932A
- Authority
- CN
- China
- Prior art keywords
- garbage
- box
- motor drives
- move
- lower cover
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
- B65F1/00—Refuse receptacles; Accessories therefor
- B65F1/0033—Refuse receptacles; Accessories therefor specially adapted for segregated refuse collecting, e.g. receptacles with several compartments; Combination of receptacles
- B65F1/0053—Combination of several receptacles
- B65F1/006—Rigid receptacles stored in an enclosure or forming part of it
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
- B65F1/00—Refuse receptacles; Accessories therefor
- B65F1/10—Refuse receptacles; Accessories therefor with refuse filling means, e.g. air-locks
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
- B65F1/00—Refuse receptacles; Accessories therefor
- B65F1/14—Other constructional features; Accessories
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
- B65F1/00—Refuse receptacles; Accessories therefor
- B65F1/14—Other constructional features; Accessories
- B65F1/1484—Other constructional features; Accessories relating to the adaptation of receptacles to carry identification means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
- B65F1/00—Refuse receptacles; Accessories therefor
- B65F1/0033—Refuse receptacles; Accessories therefor specially adapted for segregated refuse collecting, e.g. receptacles with several compartments; Combination of receptacles
- B65F2001/008—Means for automatically selecting the receptacle in which refuse should be placed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
- B65F2210/00—Equipment of refuse receptacles
- B65F2210/138—Identification means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
- B65F2210/00—Equipment of refuse receptacles
- B65F2210/139—Illuminating means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
- B65F2210/00—Equipment of refuse receptacles
- B65F2210/196—Tape dispensers
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02W—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO WASTEWATER TREATMENT OR WASTE MANAGEMENT
- Y02W30/00—Technologies for solid waste management
- Y02W30/10—Waste collection, transportation, transfer or storage, e.g. segregated refuse collecting, electric or hybrid propulsion
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Refuse Collection And Transfer (AREA)
Abstract
The invention relates to an automatic garbage sorting mechanism and a sorting method, wherein the sorting mechanism comprises image acquisition equipment, image processing equipment, sorting equipment, an identification box and a plurality of sub-garbage boxes, wherein the identification box comprises a separable box body and a lower cover; the image processing equipment is connected with the image acquisition equipment and is used for identifying and classifying the garbage in the picture and determining the type of the garbage delivered into the identification box; the classification device is used for controlling the recognition box to move according to the garbage type determined by the image processing device, so that the garbage can fall into the sub-garbage box corresponding to the recognized garbage type. The invention can improve the accuracy of garbage identification and can reduce the size of the garbage can.
Description
Technical Field
The invention relates to the technical field of garbage classification, in particular to an automatic garbage classification mechanism and a classification method.
Background
Recycling is an important factor in waste utilization. Household garbage is used as a main source of municipal garbage, and if the household garbage can be classified in the collection process, the reduction and recovery efficiency of the municipal garbage can be greatly improved. The household garbage is increasing day by day, people's garbage classification concept is not kept up with, and in addition, most of people do not have a very definite concept as to which type the household garbage is classified; this results in the source classification of domestic waste only in the stage of starting, and the imperfection of the domestic waste classification link brings adverse effects to the efficiency and effect of municipal waste treatment.
Two main problems of the existing garbage type identification and automatic classification method are as follows: the recognition accuracy is low, and the common direct one-step recognition mode cannot effectively extract the distinct features of various wastes, so that the model generalization capability is low, and the method is not suitable for being popularized to practical use; secondly, the unreasonable design of the sorting mechanism results in extra space occupation, and in order to complete a sorting process, the common sorting mechanism design reserves the motor space at the limit position, which causes space waste and increases the volume of the garbage can.
Disclosure of Invention
The invention aims to provide an automatic garbage classification mechanism and a classification method, which can improve the accuracy of garbage identification and can reduce the quantity of garbage bins.
The technical scheme adopted by the invention for solving the technical problems is as follows: the automatic garbage sorting mechanism comprises image acquisition equipment, image processing equipment, sorting equipment, an identification box and a plurality of sub-garbage boxes, wherein the identification box comprises a separable box body and a lower cover, the box body and the lower cover are respectively connected with respective transmission mechanisms, and the image acquisition equipment is used for acquiring pictures of garbage delivered into the identification box; the image processing equipment is connected with the image acquisition equipment and is used for identifying and classifying the garbage in the picture and determining the type of the garbage delivered into the identification box; the classification device is used for controlling the recognition box to move according to the garbage type determined by the image processing device, so that the garbage can fall into the sub-garbage box corresponding to the recognized garbage type.
The image processing equipment comprises a photosensitive sensor, a light source and a camera; the output end of the photosensitive sensor is connected with the light source and the control end of the camera; the photosensitive sensor is used for detecting the light intensity change before and after the upper cover of the identification box is opened and closed, and triggering the light source and the camera; the light source is used for emitting constant illumination so that the photographing environment is the same each time; the camera is used for acquiring pictures of the garbage delivered into the identification box.
The image processing equipment is arranged on the side face of the recognition box and comprises a card type computer, the card type computer is provided with a pre-trained two-step classification model, the two-step classification model comprises a garbage recognition model and a garbage classification model, the garbage recognition model is used for determining the secondary category to which the garbage in the picture information belongs, and the garbage classification model brings the secondary category to which the garbage determined by the garbage recognition model belongs into the specific garbage category.
The garbage recognition model is obtained by combining label-free features extracted from millions of pictures by a pre-training model and labeled features extracted from garbage picture samples; and the garbage classification model is used for carrying out secondary identification on the garbage picture information obtained by the garbage identification model to obtain classification information.
The classification device comprises a controller, and the controller is used for controlling the transmission mechanisms of the box body and the lower cover to enable garbage in the recognition box to fall into the sub-garbage box corresponding to the garbage type recognized by the image processing device.
The transmission mechanism of the box body comprises an upper motor, an upper belt and an upper sliding block, the upper belt is positioned above the plurality of sub-garbage boxes, and the box body is connected with one side of the upper belt through the upper sliding block; the upper motor drives the upper belt through a motor gear; the transmission mechanism of the lower cover comprises a lower motor, a lower belt and a lower sliding block; the lower belt is positioned between the sub-dustbin and the upper belt, and the lower cover is connected with one side of the lower belt through the lower sliding block; the lower motor drives the lower belt through a motor gear.
The technical scheme adopted by the invention for solving the technical problems is as follows: the automatic garbage sorting mechanism comprises the following steps:
(1) a photosensitive sensor of the image acquisition equipment senses the light intensity change of an upper cover of the identification box before and after the upper cover of the identification box is opened and closed, a trigger light source emits constant illumination to manufacture the same photographing environment, and a camera acquires pictures of garbage thrown into the identification box and transmits the pictures to a card type computer of the image processing equipment;
(2) loading the acquired picture into a pre-trained two-step classification model by a card computer, firstly determining the secondary category of the garbage in the picture by a garbage recognition model, and then bringing the secondary category of the garbage determined by the garbage recognition model into a specific garbage category by the garbage classification model to obtain a final garbage classification result;
(3) according to the garbage classification result, the controller of the classification device controls the upper motor and the lower motor to work simultaneously, after the recognition box and the lower cover are moved to the position above the sub-garbage box corresponding to the garbage classification result, the upper motor stops working, the lower motor continues working, the lower cover of the recognition box is separated from the box body, and therefore garbage falls into the sub-garbage box from the recognition box.
The four sub-garbage cans are four in number and are the same in size, and in the step (3), the strokes of the upper motor and the lower motor for driving the box body and the lower cover are controlled through the moving distance, so that the following four conditions are adopted: set up motor and lower motor and drive box and lower cover and be 4x from initial position to final position's total distance, then:
(A) if the garbage classification result is the first type of garbage, the upper motor keeps the box body still, the lower motor drives the lower cover to move for an x distance, and the lower motor drives the lower cover to move reversely for the x distance to return to the initial position;
(B) if the garbage classification result is second-class garbage, the upper motor drives the box body to move for an x distance and then keeps static, the lower motor drives the lower cover to move for a 2x distance, the upper motor drives the box body to move in the reverse direction for the x distance to return to the initial position, and the lower motor drives the lower cover of the identification box to move in the reverse direction for the 2x distance to return to the initial position;
(C) if the garbage classification result is the third type of garbage, the upper motor drives the box body to move for 2x distance and then keeps static, the lower motor drives the lower cover to move for 3x distance, the upper motor drives the box body to move reversely for 2x distance to return to the initial position, and the lower motor drives the lower cover of the identification box to move reversely for 3x distance to return to the initial position;
(D) if the garbage classification result is the fourth type of garbage, the upper motor drives the box body to move for 4x distance, and the lower motor drives the lower cover to move for 3x distance and then keep still; the upper motor drives the box body to move reversely for a distance of 4x to return to the initial position, and the lower motor drives the lower cover of the identification box to move reversely for a distance of 3x to return to the initial position.
The four sub-garbage cans are four in number and are the same in size, and in the step (3), the strokes of the upper motor and the lower motor for driving the box body and the lower cover are controlled through the moving time, so that the following four conditions are adopted: set up motor and lower motor and drive box and lower cover total time from initial position to final position and be 4t, then:
(a) if the garbage classification result is the first type of garbage, the upper motor keeps the box body still, the lower motor drives the lower cover to move for t time, and the lower motor drives the lower cover to move reversely for t time to return to the initial position;
(b) if the garbage classification result is the second type of garbage, the upper motor drives the box body to move for t time, then the box body is static for t time, and the lower motor drives the lower cover to move for 2t time; the upper motor drives the box body to move reversely for t time to return to the initial position, and the lower motor drives the lower cover to move reversely for 2t time to return to the initial position;
(c) if the garbage classification result is the third type of garbage, the upper motor drives the box body to move for 2t, then the box body is static for t, and the lower motor drives the lower cover to move for 3 t; the upper motor drives the box body to move reversely for 2t to return to the initial position, and the lower motor drives the lower cover to move reversely for 3t to return to the initial position;
(d) if the garbage classification result is the fourth type of garbage, the upper motor drives the box body to move for 4t, and the lower motor drives the lower cover to move for 3t and then stands still for t; the upper motor drives the box body to move reversely for 4t to return to the initial position, and the lower motor drives the lower cover to move reversely for 3t to return to the initial position.
Advantageous effects
Due to the adoption of the technical scheme, compared with the prior art, the invention has the following advantages and positive effects: the invention adopts a two-step classification model to realize the identification and classification of the garbage, and improves the accuracy of garbage identification compared with the traditional method. In addition, the identification box and the identification box lower cover are driven by the upper motor, the lower motor and the belt, so that the whole device is more compact in structure, and the whole volume of the garbage can is reduced.
Drawings
FIG. 1 is a schematic view of the automatic garbage sorting mechanism according to the present invention;
fig. 2 is a schematic view of the internal structure of the automatic garbage sorting mechanism of the present invention.
Detailed Description
The invention will be further illustrated with reference to the following specific examples. It should be understood that these examples are for illustrative purposes only and are not intended to limit the scope of the present invention. Further, it should be understood that various changes or modifications of the present invention may be made by those skilled in the art after reading the teaching of the present invention, and such equivalents may fall within the scope of the present invention as defined in the appended claims.
The embodiment of the invention relates to an automatic garbage sorting mechanism, which comprises a cubic frame 2, wherein a screen 4 and an upper cover 1 of an identification box are arranged on the upper side of the frame 2, and a shell 3 is arranged on the outer side surface of the frame 2, as shown in figures 1 and 2. An image acquisition device 6, an image processing device 9, a classification device, an identification box 7 and four sub-garbage boxes 5 are arranged in the frame 2.
The identification box 7 comprises a box body and a lower cover which can be separated, the box body and the lower cover are respectively connected with respective transmission mechanisms, and the image acquisition equipment 6 is arranged at an opening of the identification box 7 and is used for acquiring pictures of garbage delivered into the identification box 7; the image processing device 9 is connected with the image acquisition device 6 and is used for identifying and classifying the garbage in the pictures and determining the type of the garbage delivered into the identification box 7; the classification device is used for controlling the recognition box 7 to move according to the garbage type determined by the image processing device 9, so that the garbage can fall into the sub-garbage box 5 corresponding to the recognized garbage type.
In this embodiment, the image processing apparatus includes a photosensor, a light source, and a camera; the output end of the photosensitive sensor is connected with the light source and the control end of the camera; the photosensitive sensor is used for detecting the light intensity change before and after the upper cover of the identification box is opened and closed, and triggering the light source and the camera; the light source is used for emitting constant illumination so that the photographing environment is the same each time; the camera is used for acquiring pictures of the garbage delivered into the identification box.
The image processing equipment is arranged on the side face of the recognition box and comprises a card type computer, the card type computer is provided with a pre-trained two-step classification model, the two-step classification model comprises a garbage recognition model and a garbage classification model, the garbage recognition model is used for determining the secondary category to which the garbage in the picture information belongs, and the garbage classification model brings the secondary category to which the garbage determined by the garbage recognition model belongs into the specific garbage category.
The garbage recognition model is trained on the basis of a pre-training model, the pre-training model comprises label-free features extracted from millions of pictures, and the label-free features and label-containing features extracted from garbage picture samples are combined to obtain the garbage recognition model. The huge sample characteristic quantity after the garbage recognition model is integrated enables the recognition accuracy rate to be improved.
The garbage classification model is used for carrying out secondary identification on garbage picture information obtained by the garbage identification model to obtain classification information, and the classification information is classified into four garbage categories to obtain a specific garbage category.
Under the condition of dual recognition of the garbage recognition model and the garbage classification model, the recognition accuracy of the two-step classification model is obviously improved compared with that of the traditional one-step classification model. In the process that the secondary category of the garbage belongs to the garbage classification model is brought into the specific garbage category, the fault tolerance is obviously improved, and therefore the identification stability is enhanced.
The transmission mechanism of the box body comprises an upper motor 8, an upper belt 10 and an upper sliding block 11, the upper belt 10 is positioned above the plurality of sub-dustbin 5, and the box body is connected with one side of the upper belt 10 through the upper sliding block 11; the upper motor 8 drives the upper belt 10 through a motor gear; the transmission mechanism of the lower cover comprises a lower motor 12, a lower belt 13 and a lower sliding block 14; the lower belt 13 is positioned between the sub-dustbin 5 and the upper belt 10, and the lower cover is connected with one side of the lower belt 13 through a lower sliding block 14; the lower motor 13 drives the lower belt 13 through a motor gear. The classification equipment comprises a controller, the controller is used for controlling an upper motor and a lower motor, and the garbage in the identification box falls into the sub-garbage box corresponding to the garbage type identified by the image processing equipment through the cooperation of the upper motor and the lower motor. As can be seen from the graph 2, the box body and the lower cover are conveyed by the belt, and the motor space at the limit position is not required to be reserved, so that the structure of the whole mechanism is more compact, and the whole volume of the dustbin is reduced.
The method for classifying the garbage by adopting the automatic garbage classification mechanism of the embodiment comprises the following steps:
(1) a user opens the upper cover of the identification box and puts the garbage into the identification box of the garbage classification mechanism, and then the upper cover of the identification box is covered;
(2) the photosensitive sensor senses the light intensity change of the upper cover of the identification box before and after the upper cover of the identification box is opened and closed, so that the light source is triggered to emit constant illumination to manufacture the same photographing environment, the camera acquires garbage pictures and stores the pictures in the card type computer, and the light source is closed after photographing is completed. The pictures acquired by the camera at each time are stored in a specific folder of the card computer, and the pictures are named according to an accumulation principle; and if the total number of the junk pictures in the folder reaches the upper limit, replacing the oldest picture in the folder with the newest picture obtained by photographing, so that the total number of the pictures in the folder is maintained at the upper limit. When the total number of the pictures in the folder reaches an upper limit k, the card computer uploads all the pictures in the folder to the cloud through the 5G module to serve as a sample set required by the two-step classification model iterative training.
(3) The card type computer loads the acquired garbage pictures into a pre-trained two-step classification model, firstly, the secondary category of the garbage is determined by the garbage recognition model, and then the secondary category of the garbage determined by the garbage recognition model is brought into one of four categories of the garbage through the garbage classification model, so that the final garbage classification result is obtained. The garbage recognition model and the garbage classification model are in the same pre-trained two-step classification model, the output of the garbage recognition model is used as the input of the garbage classification model, the whole garbage classification process only executes the pre-trained two-step classification model once, and the recognition accuracy is improved while the recognition time is not too long.
(4) According to the obtained garbage classification result, the upper motor and the lower motor work simultaneously, the recognition box and the lower cover are conveyed to the upper part of the sub-garbage box corresponding to the garbage classification result, the upper motor stops working, the lower motor continues working, the lower cover of the recognition box is driven to be separated from the recognition box, and therefore the garbage falls into the sub-garbage box from the recognition box.
(5) The lower motor drives the lower cover of the identification box to return to the original position below the identification box, and the upper motor and the lower motor work simultaneously to convey the identification box and the lower cover of the identification box back to the initial position of the opening of the dustbin.
Go up the motor and drive the stroke of box and lower cover with lower motor and can control through migration distance, specifically do:
set up motor and lower motor and drive box and lower cover and be 4x from initial position to final position's total distance, and from initial position to final position, each sub-dustbin arranges the order and is recoverable dustbin, dry dustbin, wet dustbin, harmful dustbin, then:
(1) if the garbage classification result is recyclable garbage, the upper motor keeps the recognition box still, and the lower motor drives the lower cover to move for an x distance; the lower motor drives the lower cover to move in the reverse direction for an x distance to return to the initial position;
(2) if the garbage classification result is dry garbage, the upper motor drives the box body to move for x distance and then keeps still, and the lower motor drives the lower cover to move for 2x distance; the upper motor drives the box body to move in the reverse direction for a distance x to return to the initial position, and the lower motor drives the lower cover to move in the reverse direction for a distance 2x to return to the initial position;
(3) if the garbage classification result is wet garbage, the upper motor drives the box body to move for 2x distance and then keeps still, and the lower motor drives the lower cover to move for 3x distance; the upper motor drives the box body to move reversely for 2x to return to the initial position, and the lower motor drives the lower cover to move reversely for 3x to return to the initial position;
(4) if the garbage classification result is harmful garbage, the upper motor drives the box body to move for 4x distance, and the lower motor drives the lower cover to move for 3x distance and then keep still; the upper motor drives the box body to move reversely for a distance of 4x to return to the initial position, and the lower motor drives the lower cover of the identification box to move reversely for a distance of 3x to return to the initial position.
Go up the motor and drive the stroke of box and lower cover with lower motor and can also control through the travel time, specifically do:
set up motor and lower motor and drive identification box and identification box lower cover from initial position to final position's total time be 4t, and from initial position to final position, each sub-dustbin arrangement order is recoverable dustbin, dry dustbin, wet dustbin, harmful dustbin, then:
(1) if the garbage classification result is recyclable garbage, keeping the identification box stationary by the upper motor, and driving the lower cover to move for t time by the lower motor; the lower motor drives the lower cover to move reversely for t time to return to the initial position;
(2) if the garbage classification result is dry garbage, the upper motor drives the box body to move for t time, the box body is still for t time, and the lower motor drives the lower cover to move for 2t time; the upper motor drives the box body to move reversely for t time to return to the initial position, and the lower motor drives the lower cover to move reversely for 2t time to return to the initial position;
(3) if the garbage classification result is wet garbage, the upper motor drives the box body to move for 2t, the box body is still for t, and the lower motor drives the lower cover to move for 3 t; the upper motor drives the box body to move reversely for 2t to return to the initial position, and the lower motor drives the lower cover to move reversely for 3t to return to the initial position;
(4) if the garbage classification result is harmful garbage, the upper motor drives the box body to move for 4t, the lower motor drives the lower cover to move for 3t, and the box body is static for t; the upper motor drives the box body to move reversely for 4t to return to the initial position, and the lower motor drives the lower cover to move reversely for 3t to return to the initial position.
Claims (9)
1. An automatic garbage sorting mechanism comprises image acquisition equipment, image processing equipment, sorting equipment, an identification box and a plurality of sub-garbage boxes, wherein the identification box comprises a separable box body and a lower cover; the image processing equipment is connected with the image acquisition equipment and is used for identifying and classifying the garbage in the picture and determining the type of the garbage delivered into the identification box; the classification device is used for controlling the recognition box to move according to the garbage type determined by the image processing device, so that the garbage can fall into the sub-garbage box corresponding to the recognized garbage type.
2. The automatic sorting mechanism of refuse according to claim 1, characterized in that said image processing device comprises a light sensitive sensor, a light source and a camera; the output end of the photosensitive sensor is connected with the light source and the control end of the camera; the photosensitive sensor is used for detecting the light intensity change before and after the upper cover of the identification box is opened and closed, and triggering the light source and the camera; the light source is used for emitting constant illumination so that the photographing environment is the same each time; the camera is used for acquiring pictures of the garbage delivered into the identification box.
3. The automatic garbage classification mechanism according to claim 1, wherein the image processing device is disposed at a side of the recognition box and comprises a card computer, the card computer is installed with a pre-trained two-step classification model, the two-step classification model comprises a garbage recognition model and a garbage classification model, the garbage recognition model is used for determining a secondary category to which the garbage in the picture information belongs, and the garbage classification model includes the secondary category to which the garbage determined by the garbage recognition model belongs into a specific garbage category.
4. The automatic garbage classification mechanism according to claim 3, wherein the garbage recognition model is obtained by combining unlabeled features extracted from millions of pictures by a pre-trained model with labeled features extracted from garbage picture samples; and the garbage classification model is used for carrying out secondary identification on the garbage picture information obtained by the garbage identification model to obtain classification information.
5. The automatic garbage sorting mechanism according to claim 1, wherein the sorting device comprises a controller for controlling the transmission mechanisms of the box body and the lower cover to drop the garbage in the recognition box into the sub-garbage box corresponding to the garbage type recognized by the image processing device.
6. The automatic garbage sorting mechanism according to claim 1, wherein the transmission mechanism of the box body comprises an upper motor, an upper belt and an upper sliding block, the upper belt is positioned above the plurality of sub-garbage boxes, and the box body is connected with one side of the upper belt through the upper sliding block; the upper motor drives the upper belt through a motor gear; the transmission mechanism of the lower cover comprises a lower motor, a lower belt and a lower sliding block; the lower belt is positioned between the sub-dustbin and the upper belt, and the lower cover is connected with one side of the lower belt through the lower sliding block; the lower motor drives the lower belt through a motor gear.
7. An automatic garbage sorting method, characterized in that the automatic garbage sorting mechanism according to any one of claims 1-6 is adopted, and the method comprises the following steps:
(1) a photosensitive sensor of the image acquisition equipment senses the light intensity change of an upper cover of the identification box before and after the upper cover of the identification box is opened and closed, a trigger light source emits constant illumination to manufacture the same photographing environment, and a camera acquires pictures of garbage thrown into the identification box and transmits the pictures to a card type computer of the image processing equipment;
(2) loading the acquired picture into a pre-trained two-step classification model by a card computer, firstly determining the secondary category of the garbage in the picture by a garbage recognition model, and then bringing the secondary category of the garbage determined by the garbage recognition model into a specific garbage category by the garbage classification model to obtain a final garbage classification result;
(3) according to the garbage classification result, the controller of the classification device controls the upper motor and the lower motor to work simultaneously, after the recognition box and the lower cover are moved to the position above the sub-garbage box corresponding to the garbage classification result, the upper motor stops working, the lower motor continues working, the lower cover of the recognition box is separated from the box body, and therefore garbage falls into the sub-garbage box from the recognition box.
8. The automatic garbage classification method according to claim 7, wherein the number of the sub-garbage bins is four, and the four sub-garbage bins have the same size, and the stroke of the upper motor and the lower motor for driving the bin body and the lower cover in the step (3) is controlled by the moving distance, which is divided into the following four cases: set up motor and lower motor and drive box and lower cover and be 4x from initial position to final position's total distance, then:
(A) if the garbage classification result is the first type of garbage, the upper motor keeps the box body still, the lower motor drives the lower cover to move for an x distance, and the lower motor drives the lower cover to move reversely for the x distance to return to the initial position;
(B) if the garbage classification result is second-class garbage, the upper motor drives the box body to move for an x distance and then keeps static, the lower motor drives the lower cover to move for a 2x distance, the upper motor drives the box body to move in the reverse direction for the x distance to return to the initial position, and the lower motor drives the lower cover of the identification box to move in the reverse direction for the 2x distance to return to the initial position;
(C) if the garbage classification result is the third type of garbage, the upper motor drives the box body to move for 2x distance and then keeps static, the lower motor drives the lower cover to move for 3x distance, the upper motor drives the box body to move reversely for 2x distance to return to the initial position, and the lower motor drives the lower cover of the identification box to move reversely for 3x distance to return to the initial position;
(D) if the garbage classification result is the fourth type of garbage, the upper motor drives the box body to move for 4x distance, and the lower motor drives the lower cover to move for 3x distance and then keep still; the upper motor drives the box body to move reversely for a distance of 4x to return to the initial position, and the lower motor drives the lower cover of the identification box to move reversely for a distance of 3x to return to the initial position.
9. The automatic garbage classification method according to claim 7, wherein the number of the sub-garbage bins is four, and the four sub-garbage bins have the same size, and the stroke of the upper motor and the lower motor for driving the bin body and the lower cover in the step (3) is controlled by the moving time, which is divided into the following four cases: set up motor and lower motor and drive box and lower cover total time from initial position to final position and be 4t, then:
(a) if the garbage classification result is the first type of garbage, the upper motor keeps the box body still, the lower motor drives the lower cover to move for t time, and the lower motor drives the lower cover to move reversely for t time to return to the initial position;
(b) if the garbage classification result is the second type of garbage, the upper motor drives the box body to move for t time, then the box body is static for t time, and the lower motor drives the lower cover to move for 2t time; the upper motor drives the box body to move reversely for t time to return to the initial position, and the lower motor drives the lower cover to move reversely for 2t time to return to the initial position;
(c) if the garbage classification result is the third type of garbage, the upper motor drives the box body to move for 2t, then the box body is static for t, and the lower motor drives the lower cover to move for 3 t; the upper motor drives the box body to move reversely for 2t to return to the initial position, and the lower motor drives the lower cover to move reversely for 3t to return to the initial position;
(d) if the garbage classification result is the fourth type of garbage, the upper motor drives the box body to move for 4t, and the lower motor drives the lower cover to move for 3t and then stands still for t; the upper motor drives the box body to move reversely for 4t to return to the initial position, and the lower motor drives the lower cover to move reversely for 3t to return to the initial position.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910999874.5A CN110758932A (en) | 2019-10-21 | 2019-10-21 | Automatic garbage classification mechanism and classification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910999874.5A CN110758932A (en) | 2019-10-21 | 2019-10-21 | Automatic garbage classification mechanism and classification method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110758932A true CN110758932A (en) | 2020-02-07 |
Family
ID=69331467
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910999874.5A Pending CN110758932A (en) | 2019-10-21 | 2019-10-21 | Automatic garbage classification mechanism and classification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110758932A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111498326A (en) * | 2020-04-03 | 2020-08-07 | 成都禧来科技有限公司 | Automatic garbage classifier based on two-class recognition model |
| CN111582336A (en) * | 2020-04-23 | 2020-08-25 | 海信集团有限公司 | Image-based garbage type identification device and method |
| CN111907961A (en) * | 2020-08-25 | 2020-11-10 | 辽宁鑫知界科技有限公司 | Rust-proof garbage layered classified storage and consignment box |
| CN112407655A (en) * | 2020-11-26 | 2021-02-26 | 重庆广播电视大学重庆工商职业学院 | Garbage classification and recovery system based on Internet of things |
| CN113184406A (en) * | 2021-05-12 | 2021-07-30 | 徐州木牛流马机器人科技有限公司 | Kitchen waste classification method and equipment based on machine vision |
| CN113800146A (en) * | 2020-06-16 | 2021-12-17 | 天津工业大学 | Independent power supply intelligent classification dustbin |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104648865A (en) * | 2015-02-11 | 2015-05-27 | 苏州德品医疗器械技术开发有限公司 | Intelligent classified recovery system of medical waste and control method of intelligent classified recovery system |
| CN205076326U (en) * | 2015-09-17 | 2016-03-09 | 苏州优函信息科技有限公司 | Intelligence trash classification recycling device |
| CN106241103A (en) * | 2016-08-25 | 2016-12-21 | 新昌县伊格机械有限公司 | A kind of full-automatic intelligent refuse bin and control method thereof |
| CN109389161A (en) * | 2018-09-28 | 2019-02-26 | 广州大学 | Rubbish identification evolutionary learning method, apparatus, system and medium based on deep learning |
| CN109911451A (en) * | 2019-04-18 | 2019-06-21 | 东华大学 | A kind of intelligent classification dustbin based on machine vision |
| CN109948506A (en) * | 2019-03-14 | 2019-06-28 | 南通大学 | A kind of multi-angle garbage classification cloud platform based on deep learning |
| CN110119662A (en) * | 2018-03-29 | 2019-08-13 | 王胜春 | A kind of rubbish category identification system based on deep learning |
| CN110210635A (en) * | 2019-06-05 | 2019-09-06 | 周皓冉 | A kind of intelligent classification recovery system that can identify waste |
| CN110254997A (en) * | 2019-06-10 | 2019-09-20 | 徐娇娇 | Automatic classification dustbin |
-
2019
- 2019-10-21 CN CN201910999874.5A patent/CN110758932A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104648865A (en) * | 2015-02-11 | 2015-05-27 | 苏州德品医疗器械技术开发有限公司 | Intelligent classified recovery system of medical waste and control method of intelligent classified recovery system |
| CN205076326U (en) * | 2015-09-17 | 2016-03-09 | 苏州优函信息科技有限公司 | Intelligence trash classification recycling device |
| CN106241103A (en) * | 2016-08-25 | 2016-12-21 | 新昌县伊格机械有限公司 | A kind of full-automatic intelligent refuse bin and control method thereof |
| CN110119662A (en) * | 2018-03-29 | 2019-08-13 | 王胜春 | A kind of rubbish category identification system based on deep learning |
| CN109389161A (en) * | 2018-09-28 | 2019-02-26 | 广州大学 | Rubbish identification evolutionary learning method, apparatus, system and medium based on deep learning |
| CN109948506A (en) * | 2019-03-14 | 2019-06-28 | 南通大学 | A kind of multi-angle garbage classification cloud platform based on deep learning |
| CN109911451A (en) * | 2019-04-18 | 2019-06-21 | 东华大学 | A kind of intelligent classification dustbin based on machine vision |
| CN110210635A (en) * | 2019-06-05 | 2019-09-06 | 周皓冉 | A kind of intelligent classification recovery system that can identify waste |
| CN110254997A (en) * | 2019-06-10 | 2019-09-20 | 徐娇娇 | Automatic classification dustbin |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111498326A (en) * | 2020-04-03 | 2020-08-07 | 成都禧来科技有限公司 | Automatic garbage classifier based on two-class recognition model |
| CN111582336A (en) * | 2020-04-23 | 2020-08-25 | 海信集团有限公司 | Image-based garbage type identification device and method |
| CN111582336B (en) * | 2020-04-23 | 2023-11-03 | 海信集团有限公司 | Device and method for identifying garbage types based on images |
| CN113800146A (en) * | 2020-06-16 | 2021-12-17 | 天津工业大学 | Independent power supply intelligent classification dustbin |
| CN111907961A (en) * | 2020-08-25 | 2020-11-10 | 辽宁鑫知界科技有限公司 | Rust-proof garbage layered classified storage and consignment box |
| CN112407655A (en) * | 2020-11-26 | 2021-02-26 | 重庆广播电视大学重庆工商职业学院 | Garbage classification and recovery system based on Internet of things |
| CN113184406A (en) * | 2021-05-12 | 2021-07-30 | 徐州木牛流马机器人科技有限公司 | Kitchen waste classification method and equipment based on machine vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110758932A (en) | Automatic garbage classification mechanism and classification method | |
| Rabano et al. | Common garbage classification using mobilenet | |
| CN109606991B (en) | Intelligent garbage can and garbage classification method based on deep learning | |
| CN110861852A (en) | Automatic classification garbage can based on visual identification and classification method | |
| US20210357879A1 (en) | Automatic classification system | |
| Rad et al. | A computer vision system to localize and classify wastes on the streets | |
| CN110884791A (en) | Vision garbage classification system and classification method based on TensorFlow | |
| US20200342240A1 (en) | Systems and methods for detecting waste receptacles using convolutional neural networks | |
| CN110697273B (en) | Household garbage intelligent recognition and automatic classification system and method based on iterative learning control | |
| CN110861854B (en) | Intelligent garbage classification device and intelligent garbage classification method | |
| CN204595990U (en) | Coin classifier | |
| CN110053903A (en) | Categorized consumer waste retrieval management system and method | |
| CN112478493B (en) | Household intelligent classification garbage can | |
| CN106275945A (en) | A kind of garbage recovery device, garbage classification system and using method | |
| US20220301299A1 (en) | Device and method for automatically identifying and categorizing waste, and directing a desired user action | |
| CN110861853B (en) | Intelligent garbage classification method combining vision and touch | |
| CN112827846B (en) | Automatic garbage classification device and method | |
| CN111259977A (en) | Garbage classification device based on deep learning | |
| KR20200068853A (en) | Smart trash bin, Management system and method for the same | |
| CN111332651A (en) | Photoelectric sensing garbage bin based on degree of depth study | |
| CN113371363A (en) | Classified garbage can, intelligent classified garbage can based on deep learning and classification method | |
| CN106803308B (en) | Polychrome compensated scanning method and application and application system | |
| CN217576626U (en) | Classification garbage can | |
| CN113859803A (en) | Intelligent identification trash can and intelligent identification method thereof | |
| KR102537738B1 (en) | Method for automatic classficating of recycling resource |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200207 |