CN113387073A - Classified trash can and control method thereof - Google Patents
Classified trash can and control method thereof Download PDFInfo
- Publication number
- CN113387073A CN113387073A CN202110584050.9A CN202110584050A CN113387073A CN 113387073 A CN113387073 A CN 113387073A CN 202110584050 A CN202110584050 A CN 202110584050A CN 113387073 A CN113387073 A CN 113387073A
- Authority
- CN
- China
- Prior art keywords
- garbage
- steering engine
- control panel
- classification
- 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
- 239000010813 municipal solid waste Substances 0.000 title claims abstract description 165
- 238000000034 method Methods 0.000 title claims abstract description 23
- 230000006870 function Effects 0.000 claims abstract description 18
- 238000012549 training Methods 0.000 claims description 21
- 238000012360 testing method Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 7
- 239000010806 kitchen waste Substances 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 230000004807 localization Effects 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- SHGAZHPCJJPHSC-NUEINMDLSA-N Isotretinoin Chemical compound OC(=O)C=C(C)/C=C/C=C(C)C=CC1=C(C)CCCC1(C)C SHGAZHPCJJPHSC-NUEINMDLSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 229960005280 isotretinoin Drugs 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
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
-
- 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
- B65F1/141—Supports, racks, stands, posts or the like for holding refuse receptacles
-
- 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
- B65F1/1468—Means for facilitating the transport of the receptacle, e.g. wheels, rolls
- B65F1/1473—Receptacles having wheels
-
- 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
- B65F1/14—Other constructional features; Accessories
- B65F1/16—Lids or covers
- B65F1/1623—Lids or covers with means for assisting the opening or closing thereof, e.g. springs
- B65F1/1638—Electromechanically operated lids
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
-
- 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
- B65F2210/176—Sorting means
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention provides a classified garbage can and a control method thereof, when the garbage can is used, a user sends out voice awakening words, a voice recognition and sound source positioning module transmits the voice awakening words to a control board to control a mobile chassis to start running, an infrared obstacle avoidance module is utilized to run to a specified position, the user presses a control button to start a photographing function, and a camera shoots garbage pictures and stores the pictures in the local; the control panel utilizes the tflite model to identify the garbage types, and compares the pictures with the learned garbage type parameters to obtain the types of the detected garbage; if the identification is not successful, classifying other garbage categories; the control panel starts the steering engine to open the bucket covers of corresponding categories according to the identification result of the garbage types, and the bucket covers are automatically closed after a certain time, so that the functions of calling at will, automatically turning over the lid, identifying the garbage types and the like are realized.
Description
Technical Field
The invention relates to the field of smart homes, in particular to a classification garbage can and a control method thereof.
Background
In recent years, with the rapid development of science and technology and the improvement of human environmental awareness, people pay more and more attention to environmental protection and sustainable development. Among them, the problem of putting garbage is particularly concerned. The garbage classification rule is put forward in each city of China one after another, and how to judge the garbage types is gradually a difficult problem in the life of each person. Meanwhile, the rapid development of the internet of things technology enables various intelligent household articles to appear in a large quantity, the support of the 5G technology is utilized, the mobile phone APP can be utilized to carry out operation control, and the operation control is convenient and rapid. At present, the existing intelligent garbage can mainly achieves the functions of automatic uncovering and the like, products similar to the intelligent garbage can are concentrated on the garbage classification technology, and the functions are single.
Disclosure of Invention
The invention provides a classification garbage can which can realize garbage classification and on-call and on-off automatic cover opening and closing.
The invention further aims to provide a control method of the classification garbage can.
In order to achieve the technical effects, the technical scheme of the invention is as follows:
a classification garbage can comprises a recyclable garbage can, an unrecyclable garbage can, a kitchen garbage can, a harmful garbage can, a recyclable garbage can cover, an unrecyclable garbage can cover, a kitchen garbage can cover, a harmful garbage can cover, a steering engine A, a steering engine B, a steering engine C, a steering engine D, a control panel, a voice recognition and sound source positioning module, an infrared obstacle avoidance module, a camera and a movable chassis; the recyclable garbage can cover is connected with the recyclable garbage can, and the steering engine A is installed at the joint; the non-recyclable garbage can cover is connected with the non-recyclable garbage can, and the steering engine B is installed at the joint; the kitchen waste garbage can cover is connected with the kitchen waste garbage can, and the steering engine C is installed at the connection position; the harmful garbage can cover is connected with the harmful garbage can, and the steering engine D is installed at the joint; the recyclable garbage can, the non-recyclable garbage can, the kitchen garbage can and the harmful garbage can are connected in sequence and are arranged above the movable chassis; the voice recognition and sound source positioning module and the control panel are arranged above the movable chassis and below the garbage can, the voice recognition and sound source positioning module is connected with the control panel, and the camera is arranged right in front of the movable chassis and connected with the control panel; the infrared obstacle avoidance module is installed in the left front and the right front of the movable chassis and connected with the control panel.
Preferably, the control panel is a Raspberry Pi control panel; the steering engine A, the steering engine B, the steering engine C and the steering engine D are MG996R steering engines; the voice recognition and sound source positioning module is a ReSpeaker 4-Mics array.
A control method for classifying trash cans comprises the following steps:
s1: a user sends out voice awakening words, the voice identification and sound source positioning module transmits the voice awakening words to the control panel to control the mobile chassis to start running, the infrared obstacle avoidance module is utilized to run to a specified position, the user presses a control button to start a photographing function, and the camera shoots garbage photos and stores the garbage photos locally;
s2: the control panel utilizes the tflite model to identify the garbage types, and compares the pictures with the learned garbage type parameters to obtain the types of the detected garbage; if the identification is not successful, classifying other garbage categories;
s3: and the control panel starts the steering engine to open the bucket covers of the corresponding categories according to the identification result of the garbage types, and the bucket covers are automatically closed after a certain time.
Further, the operation process of the speech recognition and sound source localization module in step S1 is as follows:
the method comprises the steps of adopting snowboy voice recognition, starting a python file of a respeaker4 by using a wakening word sent by a user and a user position, sending an angle signal angle, converting an angle into corresponding high level holding time through a conversion function time T-angle, wherein T is a constant, and is the time required for indicating a certain angle, the angle signal is obtained through an actual steering test of a mobile chassis, the mobile chassis receives the time signal, and the angle signal angle is converted into the angle signal time T, so that the mobile chassis is driven to move.
Furthermore, the mobile chassis is a four-motor driving wheel, so that pivot steering is realized, the left driving wheel moves forwards, the right driving wheel moves backwards, any pivot left-turning angle is realized, and the running of the mobile chassis is determined by the turning time; the obstacle is detected by the infrared module in the driving process, and when the obstacle exists on the right side, the right infrared obstacle avoidance module outputs 1 to drive the chassis to rotate left; when an obstacle exists on the left side, the left infrared obstacle avoidance module outputs 1 to drive the chassis to rotate right; when the infrared obstacle avoidance modules output 1, the destination is reached or an insurmountable obstacle exists, the mobile chassis stops, and garbage classification and identification are started.
Furthermore, after a garbage classification recognition result is obtained, the control panel controls the steering engine to automatically open the corresponding garbage can cover and automatically close the corresponding garbage can cover after 5 seconds.
Further, a yolov3 model is adopted as a pre-training model for identifying garbage types by utilizing the tflite model, a yolov3 model is trained on a training set by utilizing a keras auxiliary frame, and an epoch parameter is set to obtain a final accuracy accure and a loss rate loss; and judging the fitting degree according to the result, setting and improving the learning rate parameter of the yolov3 network, improving the network structure of the original tflite model and the loss function and optimization algorithm of the yolov3 network, improving the accuracy and the loss rate, and finishing the training of the network in the recognition model.
Further, after the tflite model is trained sufficiently, whether a new picture belongs to the category of the training data or not can be predicted, namely, a corresponding probability matrix is output, each probability corresponds to one label in the training data, the label with obviously dominant probability is the classification predicted by the model, in the identification process, a test picture is input, the tflite model outputs a corresponding label serial number k, wherein the k is more than or equal to 0 and less than or equal to 39, and the result of the identification classification is output through the serial number.
Compared with the prior art, the technical scheme of the invention has the beneficial effects that:
when the intelligent garbage shooting device is used, a user sends out voice awakening words, the voice identification and sound source positioning module transmits the voice awakening words to the control panel to control the mobile chassis to start running, the infrared obstacle avoidance module is used for running to a specified position, the user presses the control button to start a shooting function, and the camera shoots garbage photos and stores the garbage photos in the local place; the control panel utilizes the tflite model to identify the garbage types, and compares the pictures with the learned garbage type parameters to obtain the types of the detected garbage; if the identification is not successful, classifying other garbage categories; the control panel starts the steering engine to open the bucket covers of corresponding categories according to the identification result of the garbage types, and the bucket covers are automatically closed after a certain time, so that the functions of calling at will, automatically turning over the lid, identifying the garbage types and the like are realized.
Drawings
FIG. 1 is a schematic view of the overall structure of the present invention;
FIG. 2 is a hardware schematic of the present invention;
FIG. 3 is a software flow diagram of the present invention;
wherein, 1 is a barrel body; 2 is a barrel cover; 3 is a steering engine; 4 is a movable chassis; and 5, a control panel, a voice recognition and sound source positioning module, an infrared obstacle avoidance module and a camera are assembled together.
Detailed Description
The drawings are for illustrative purposes only and are not to be construed as limiting the patent;
for the purpose of better illustrating the embodiments, certain features of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product;
it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The technical solution of the present invention is further described below with reference to the accompanying drawings and examples.
Example 1
As shown in fig. 1-2, a classification trash can comprises a recyclable trash can, an unrecoverable trash can, a kitchen garbage can, a harmful trash can, a recyclable trash can cover, an unrecoverable trash can cover, a kitchen garbage can cover, a harmful trash can cover, a steering engine a, a steering engine B, a steering engine C, a steering engine D, a control panel, a voice recognition and sound source positioning module, an infrared obstacle avoidance module, a camera and a mobile chassis; the recyclable garbage can cover is connected with the recyclable garbage can, and the steering engine A is installed at the joint; the non-recyclable garbage can cover is connected with the non-recyclable garbage can, and the steering engine B is installed at the joint; the kitchen waste garbage can cover is connected with the kitchen waste garbage can, and the steering engine C is installed at the connection position; the harmful garbage can cover is connected with the harmful garbage can, and the steering engine D is installed at the joint; the recyclable garbage can, the non-recyclable garbage can, the kitchen garbage can and the harmful garbage can are connected in sequence and are arranged above the movable chassis; the voice recognition and sound source positioning module and the control panel are arranged above the movable chassis and below the garbage can, the voice recognition and sound source positioning module is connected with the control panel, and the camera is arranged right in front of the movable chassis and connected with the control panel; the infrared obstacle avoidance module is installed in the left front and the right front of the movable chassis and connected with the control panel.
In the embodiment, the control panel is a Raspberry Pi control panel; the steering engine A, the steering engine B, the steering engine C and the steering engine D are MG996R steering engines; the voice recognition and sound source positioning module is a ReSpeaker 4-Mics array.
Example 2
As shown in fig. 3, a control method for sorting garbage cans includes the following steps:
s1: a user sends out voice awakening words, the voice identification and sound source positioning module transmits the voice awakening words to the control panel to control the mobile chassis to start running, the infrared obstacle avoidance module is utilized to run to a specified position, the user presses a control button to start a photographing function, and the camera shoots garbage photos and stores the garbage photos locally;
s2: the control panel utilizes the tflite model to identify the garbage types, and compares the pictures with the learned garbage type parameters to obtain the types of the detected garbage; if the identification is not successful, classifying other garbage categories;
s3: and the control panel starts the steering engine to open the bucket covers of the corresponding categories according to the identification result of the garbage types, and the bucket covers are automatically closed after a certain time.
Because this categorised garbage bin includes four garbage bins of receiving different kinds of rubbish, realizes the steering wheel device of switch lid, realizes waste classification's image recognition module, realizes speech recognition and sound source location's speech recognition and sound source location module, realizes moving the removal chassis of function and the infrared obstacle avoidance module that plays the obstacle avoidance effect at the removal in-process. When the garbage shooting device is used, a user sends out voice awakening words, the mobile chassis starts to drive to a specified position, the user presses a control button to start a shooting function, and the camera shoots garbage pictures and stores the garbage pictures locally. Performing garbage type identification by using the tflite model, and comparing the pictures with the learned garbage type parameters to obtain the type of the detected garbage; if the identification is not successful, other garbage categories are classified. And sending the identification result to the control panel for the next operation. The user can identify the garbage by repeatedly pressing the control button for many times, and can exit the identification program through Ctrl + C. And starting the steering engine to open the bucket covers of the corresponding categories according to the recognition result of the garbage types, and automatically closing the bucket covers after a certain time.
And the voice recognition and the sound source positioning of the garbage can adopt snowboy voice recognition, so that keyword voice awakening can be realized. The user sends out a wakeup word, a python file of the respeaker4 is started, an angle signal is sent out, and the angle is changed to a corresponding high level holding time through a conversion function time which is T. T is a constant, and the physical meaning is that the time required for rotating a certain angle is expressed and is obtained through an actual steering test of the moving chassis. The microphone array receives the angle signal and generates a high level. The high-level voltage is transmitted to a control board GPIO13 interface of the mobile chassis through a control board GPIO12 interface of the microphone array, the mobile chassis receives a time signal and converts the time signal into an angle signal time/T, and therefore the mobile chassis is driven to move.
The movable chassis is a four-motor driving wheel, so that pivot steering can be realized, the left driving wheel moves forwards, the right driving wheel moves backwards, pivot left-turning can be realized by a certain angle, and the traveling of the movable chassis is determined by the rotation time. The obstacle is detected by the infrared module in the driving process, and when the obstacle exists on the right side, the right infrared obstacle avoidance module outputs 1 to drive the chassis to rotate left; when an obstacle exists on the left side, the left infrared obstacle avoidance module outputs 1 to drive the chassis to rotate right. When the infrared obstacle avoidance modules output 1, the destination is reached or an insurmountable obstacle exists, the mobile chassis stops, and garbage classification and identification are started.
When identifying the garbage, a user firstly presses a button to take a picture, the picture is stored locally, and the garbage type is identified by utilizing the tflite model. The garbage classification is realized through an image recognition function, a yolov3 model is adopted as a pre-training model, training pictures are from a Huashi cloud 2019 garbage classification competition training set, and 40 kinds of common garbage are obtained through screening and sorting. Dividing the data images into 4 types according to the Shenzhen city garbage classification standard: can recover garbage, kitchen garbage, harmful garbage and other garbage. Image enhancement is completed by data preprocessing, a sample data set is expanded, and the sample data set is converted into a data set available to yolov 3. And performing model training on the training set by using auxiliary frames such as keras and the like, and setting parameters such as epoch and the like to obtain the final accuracy accurve and the loss rate loss. And judging the fitting degree according to the result, setting and improving the learning rate parameter of the yolov3 network, improving the network structure of the original recognition model and the loss function and optimization algorithm of the yolov3 network, improving the accuracy and the loss rate, and finishing the training of the network in the recognition model.
After sufficient training is carried out, the image classification model can learn and predict whether a new picture belongs to the category in the training data, namely, a corresponding probability matrix is output, each probability corresponds to a label in the training data, and the label with obviously dominant probability is the classification predicted by the model. In the target detection process, a test picture is input, the model outputs a corresponding label serial number k (k is more than or equal to 0 and less than or equal to 39), and the identification and classification result is output through the serial number. And converting the model trained under the PC-side training Tensorflow framework into a required conversion tflite file through a specific model converter. Where some accuracy is lost in exchange for model reduction and computation speed. Through tests, the identification time is less than 0.5 second, and the accuracy rate reaches more than 80%.
When the garbage classification file is started to run, the program loads the model and the classification json file first and then waits for image input. The call of the control panel to the camera can be realized by utilizing the py library of the OpenCV, and the call comprises multiple times of photographing, video recording and the like. Firstly, photographing an article for multiple times, storing the article in a local test set, then calling an identification program for multiple times to obtain multiple output k _ i (garbiage _ classify), and selecting a mode from the result to obtain an output garbage classification result.
After the garbage classification recognition result is obtained, the control panel controls the steering engine to automatically open the corresponding garbage can cover and automatically close the corresponding garbage can cover after a certain time (about 5 seconds). In addition, the button may be pressed repeatedly a number of times to identify trash.
The same or similar reference numerals correspond to the same or similar parts;
the positional relationships depicted in the drawings are for illustrative purposes only and are not to be construed as limiting the present patent;
it should be understood that the above-described embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the claims of the present invention.
Claims (10)
1. A classification garbage can is characterized by comprising a recyclable garbage can, an unrecyclable garbage can, a kitchen garbage can, a harmful garbage can, a recyclable garbage can cover, an unrecyclable garbage can cover, a kitchen garbage can cover, a harmful garbage can cover, a steering engine A, a steering engine B, a steering engine C, a steering engine D, a control panel, a voice recognition and sound source positioning module, an infrared obstacle avoidance module, a camera and a mobile chassis; the recyclable garbage can cover is connected with the recyclable garbage can, and the steering engine A is installed at the joint; the non-recyclable garbage can cover is connected with the non-recyclable garbage can, and the steering engine B is installed at the joint; the kitchen waste garbage can cover is connected with the kitchen waste garbage can, and the steering engine C is installed at the connection position; the harmful garbage can cover is connected with the harmful garbage can, and the steering engine D is installed at the joint; the recyclable garbage can, the non-recyclable garbage can, the kitchen garbage can and the harmful garbage can are connected in sequence and are arranged above the movable chassis; the voice recognition and sound source positioning module and the control panel are arranged above the movable chassis and below the garbage can, the voice recognition and sound source positioning module is connected with the control panel, and the camera is arranged right in front of the movable chassis and connected with the control panel; the infrared obstacle avoidance module is installed in the left front and the right front of the movable chassis and connected with the control panel.
2. A sorting bin according to claim 1, wherein the control panel is a Raspberry Pi control panel.
3. The classification trash can of claim 1, wherein the steering engine A, the steering engine B, the steering engine C and the steering engine D are MG996R steering engines.
4. The sortation bin of claim 1, wherein said speech recognition and sound source location module is a ReSpeaker 4-Mics array.
5. A method of controlling a sorting bin according to any one of claims 1 to 4, comprising the steps of:
s1: a user sends out voice awakening words, the voice identification and sound source positioning module transmits the voice awakening words to the control panel to control the mobile chassis to start running, the infrared obstacle avoidance module is utilized to run to a specified position, the user presses a control button to start a photographing function, and the camera shoots garbage photos and stores the garbage photos locally;
s2: the control panel utilizes the tflite model to identify the garbage types, and compares the pictures with the learned garbage type parameters to obtain the types of the detected garbage; if the identification is not successful, classifying other garbage categories;
s3: and the control panel starts the steering engine to open the bucket covers of the corresponding categories according to the identification result of the garbage types, and the bucket covers are automatically closed after a certain time.
6. The method for controlling garbage can sorting according to claim 5, wherein the voice recognition and sound source localization module in step S1 is operated as follows:
the method comprises the steps of adopting snowboy voice recognition, starting a python file of a respeaker4 by using a wakening word sent by a user and a user position, sending an angle signal angle, converting an angle into corresponding high level holding time through a conversion function time T-angle, wherein T is a constant, and is the time required for indicating a certain angle, the angle signal is obtained through an actual steering test of a mobile chassis, the mobile chassis receives the time signal, and the angle signal angle is converted into the angle signal time T, so that the mobile chassis is driven to move.
7. The method for controlling the classification trash can of claim 6, wherein the moving chassis is a four-motor driving wheel, so that pivot steering is realized, a left driving wheel moves forwards, a right driving wheel moves backwards, so that any pivot left-turning angle is realized, and the moving chassis is determined by the rotation time to travel; the obstacle is detected by the infrared module in the driving process, and when the obstacle exists on the right side, the right infrared obstacle avoidance module outputs 1 to drive the chassis to rotate left; when an obstacle exists on the left side, the left infrared obstacle avoidance module outputs 1 to drive the chassis to rotate right; when the infrared obstacle avoidance modules output 1, the destination is reached or an insurmountable obstacle exists, the mobile chassis stops, and garbage classification and identification are started.
8. The control method for classifying trash cans according to claim 7, wherein after the trash classification recognition result is obtained, the control board controls the steering engine to automatically open the corresponding trash can cover and automatically close the trash can cover after 5 seconds.
9. The method for controlling the classification of the trash can of claim 8, wherein a pre-training model for identifying trash types by using the tflite model adopts a yolov3 model, a keypress auxiliary frame is used for training a yolov3 model on a training set, and an epoch parameter is set to obtain a final accuracy and a loss rate loss; and judging the fitting degree according to the result, setting and improving the learning rate parameter of the yolov3 network, improving the network structure of the original tflite model and the loss function and optimization algorithm of the yolov3 network, improving the accuracy and the loss rate, and finishing the training of the network in the recognition model.
10. The method for controlling the classification of the trash can according to claim 9, wherein after the tflite model is trained sufficiently, whether a new picture belongs to the category in the training data or not can be predicted, namely, a corresponding probability matrix is output, each probability corresponds to a label in the training data, the label with the obviously dominant probability is the classification predicted by the model, in the identification process, a test picture is input, the tflite model outputs a corresponding label serial number k, wherein k is more than or equal to 0 and less than or equal to 39, and the identification classification result is output through the serial number.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110584050.9A CN113387073A (en) | 2021-05-27 | 2021-05-27 | Classified trash can and control method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110584050.9A CN113387073A (en) | 2021-05-27 | 2021-05-27 | Classified trash can and control method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113387073A true CN113387073A (en) | 2021-09-14 |
Family
ID=77619171
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110584050.9A Pending CN113387073A (en) | 2021-05-27 | 2021-05-27 | Classified trash can and control method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113387073A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108146903A (en) * | 2016-12-06 | 2018-06-12 | 岳池县高垭小学校 | A kind of remote controlled environment-friendly trash can |
| CN109230031A (en) * | 2018-08-27 | 2019-01-18 | 蒋昊天 | Classified-refuse recovery system |
| CN110844402A (en) * | 2019-11-01 | 2020-02-28 | 贵州大学 | Garbage bin system is summoned to intelligence |
| CN111453244A (en) * | 2020-05-28 | 2020-07-28 | 淮南师范学院 | Full-automatic classification garbage can based on cloud identification and classification method thereof |
| CN112288909A (en) * | 2020-11-02 | 2021-01-29 | 曹琳 | Vehicle event data recorder of instant video information that conveys of intelligence voice command |
| CN112327871A (en) * | 2020-11-19 | 2021-02-05 | 上海电机学院 | Intelligent trolley, self-obstacle avoidance method thereof and remote control obstacle avoidance method |
| CN112455969A (en) * | 2020-11-30 | 2021-03-09 | 广东海洋大学 | Automatic intelligent garbage can |
-
2021
- 2021-05-27 CN CN202110584050.9A patent/CN113387073A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108146903A (en) * | 2016-12-06 | 2018-06-12 | 岳池县高垭小学校 | A kind of remote controlled environment-friendly trash can |
| CN109230031A (en) * | 2018-08-27 | 2019-01-18 | 蒋昊天 | Classified-refuse recovery system |
| CN110844402A (en) * | 2019-11-01 | 2020-02-28 | 贵州大学 | Garbage bin system is summoned to intelligence |
| CN111453244A (en) * | 2020-05-28 | 2020-07-28 | 淮南师范学院 | Full-automatic classification garbage can based on cloud identification and classification method thereof |
| CN112288909A (en) * | 2020-11-02 | 2021-01-29 | 曹琳 | Vehicle event data recorder of instant video information that conveys of intelligence voice command |
| CN112327871A (en) * | 2020-11-19 | 2021-02-05 | 上海电机学院 | Intelligent trolley, self-obstacle avoidance method thereof and remote control obstacle avoidance method |
| CN112455969A (en) * | 2020-11-30 | 2021-03-09 | 广东海洋大学 | Automatic intelligent garbage can |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rabano et al. | Common garbage classification using mobilenet | |
| CN110697273B (en) | Household garbage intelligent recognition and automatic classification system and method based on iterative learning control | |
| CN110076782A (en) | A kind of intelligence control garbage classification machine people of computer vision target identification | |
| EP3398110A1 (en) | Automatic detection of objects in video images | |
| CN111169848A (en) | Device and method for intelligently classifying and recycling garbage | |
| CN111846693A (en) | Intelligent garbage classification putting supervision and control system based on real-name system | |
| CN110228673A (en) | A kind of intelligent classification dustbin | |
| CN111268302A (en) | Garbage classifier based on voice recognition and working method thereof | |
| CN108824278A (en) | A kind of intelligent environment protection robot | |
| WO2021179596A1 (en) | Garbage classification method and smart household appliance | |
| CN112407660A (en) | Intelligent household garbage can based on multi-mode fusion machine perception | |
| Yang et al. | Garbage classification system with yolov5 based on image recognition | |
| CN110654738A (en) | Automatic garbage classification and recovery device and method based on natural language processing | |
| CN111775151A (en) | Intelligent control system of robot | |
| CN112099500A (en) | Household intelligent garbage can based on voice control, system and control method thereof | |
| CN112651318A (en) | Image recognition-based garbage classification method, device and system | |
| CN215507875U (en) | Beverage bottle and can classification device based on artificial intelligence neural network | |
| CN113387073A (en) | Classified trash can and control method thereof | |
| CN113859803A (en) | Intelligent identification trash can and intelligent identification method thereof | |
| CN117088015A (en) | Intelligent garbage disposal method, system and storage medium | |
| KR102537738B1 (en) | Method for automatic classficating of recycling resource | |
| CN212100339U (en) | Intelligent classification retrieves device of rubbish | |
| CN111814026A (en) | WeChat applet-based garbage classification system | |
| CN111186654A (en) | Automatic voice classification intelligent recycling garbage can | |
| CN111086796A (en) | Perfecting method for garbage type identification and background server |
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: 20210914 |