CN110893956A - Intelligent garbage classification and management system, garbage classification identification method and self-inspection method - Google Patents
Intelligent garbage classification and management system, garbage classification identification method and self-inspection method Download PDFInfo
- Publication number
- CN110893956A CN110893956A CN201911124195.XA CN201911124195A CN110893956A CN 110893956 A CN110893956 A CN 110893956A CN 201911124195 A CN201911124195 A CN 201911124195A CN 110893956 A CN110893956 A CN 110893956A
- Authority
- CN
- China
- Prior art keywords
- module
- garbage
- self
- information
- classification
- 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
-
- 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
- B65F2210/00—Equipment of refuse receptacles
- B65F2210/128—Data transmitting 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
- B65F2210/138—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
-
- 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
- B65F2210/182—Volume determining means
-
- 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)
- Processing Of Solid Wastes (AREA)
Abstract
The invention discloses an intelligent garbage classification and management system, a garbage classification identification method and a self-checking method, which belong to the field of information technology control, wherein the system visually identifies thrown garbage by using an artificial intelligence technology, controls a motor driving module according to identification information, accurately and intelligently finishes automatic classification and throwing of the garbage, reduces garbage classification burden of residents and promotes the residents to change the existing garbage throwing behavior mode; meanwhile, an intelligent voice technology is carried, and knowledge of domestic general garbage classification is provided for residents through a voice interaction function, so that environmental protection and resource saving consciousness of the residents in China is improved; the content state of the garbage can is measured in real time through an ultrasonic capacity detection technology, capacity data are sent to a remote monitoring and management center, sanitation workers are helped to monitor the overflow degree of the garbage capacity in the garbage can of each garbage throwing point in real time at a remote end, and information management is achieved; by setting the system fault self-checking function, the maintenance efficiency of the intelligent garbage classification and management system is improved.
Description
Technical Field
The invention belongs to the field of information technology control, and particularly relates to an intelligent garbage classification and management system, a garbage classification identification method and a self-checking method.
Background
Since 2008, the garbage yield of China is rapidly increased, and the garbage yield of China is estimated to reach 3.23 hundred million tons, which is equivalent to the total weight of the global population, in 2020. Moreover, although the quantity of garbage produced by everyone in China is lower than that in developed countries, the garbage recovery rate in China is far lower than that in developed countries, only 15.6%, far lower than 62% in Germany and 59% in Singapore. Therefore, in order to better promote environmental protection in China, the implementation of garbage classified delivery is an essential link.
Nowadays, various garbage classification devices are also increasingly put into daily life of people by virtue of the rapid development of artificial intelligence technology, but the existing garbage classification devices have the following difficulties and problems in practical use:
(1) the automatic classification and the feeding of the garbage cannot be realized, and the feeding efficiency is not high. Current waste classification equipment still relies on artifical subjective classification, has information such as waste classification propaganda poster manual guide through the equipment fuselage to and the explanation of categorised putting operation flow, thereby help the person of puting in self-judgement rubbish type is accomplished to categorised putting in, though the explanation is detailed, still can bring the puzzlement for the person of puting in, reduces and puts in efficiency.
(2) Lack of detailed and concrete knowledge of garbage classification. The garbage classification knowledge can only be explained in general by being influenced by the area limitation of garbage putting points, but lacks detailed explanation about a specific type, and can not solve the puzzlement of distinguishing garbage types when residents put garbage in daily.
(3) The information management of real-time monitoring of the garbage capacity in the can cannot be realized, and the scientific arrangement and the overall scheduling of garbage clearing work are not facilitated. At different places at the same time, the overflowing degree of the garbage storage in the garbage throwing point barrel is different, sanitation personnel need to clean the garbage at fixed points in the whole area, and government garbage cleaning resources are greatly wasted. Moreover, the garbage can not be cleaned in time, so that the thrown garbage overflows, and the appearance of the city is seriously influenced.
(4) The fault self-checking function is lacked, and the equipment maintenance is poor. The maintenance of the equipment mainly depends on regular and fixed-point inspection by maintenance personnel, a large amount of time is needed to carry out one-to-one troubleshooting on the whole equipment, all modules of each equipment need to be inspected, an intelligent customized troubleshooting flow is lacked, the overhaul cost of the maintenance personnel is greatly wasted, and the maintenance efficiency is low.
Based on the above problems, a new intelligent garbage classification and management system is needed.
Disclosure of Invention
Aiming at the technical problems in the prior art, the invention provides an intelligent garbage classification and management system and a garbage classification and identification method, which are reasonable in design, overcome the defects of the prior art and have good effects.
In order to achieve the purpose, the invention adopts the following technical scheme:
an intelligent garbage classification and management system comprises a mainboard controller, an image recognition module, a voice interaction module, a driving and detection module, a remote communication module and a remote monitoring and management center;
the main board controller mainly comprises an embedded microcontroller, a self-checking button, a barrier type indicator light and a basic circuit;
the embedded microcontroller is respectively connected with the image recognition module, the voice interaction module and the remote communication module through three serial communication interfaces;
the embedded microcontroller is connected with the image recognition module and is configured to receive recognition result information data of the image recognition module;
the embedded microcontroller is connected with the voice interaction module and is configured to receive voice recognition information data of the voice interaction module and control to generate corresponding voice broadcast data;
the embedded microcontroller is connected with the remote communication module and is configured to realize the remote wireless transmission function of the information data;
meanwhile, the embedded microcontroller is connected with the driving and detecting module through a general I/O port, sends a corresponding control signal to the driving and detecting module according to the image identification information, controls a motor driving module in the driving and detecting module to rotate, and controls the work of an ultrasonic detecting module in the driving and detecting module at the same time, so that the detection of the garbage capacity in the garbage can is realized;
in addition, the embedded microcontroller is connected with a self-checking button and a fault type indicator lamp through an I/O port, and the self-checking function of the system is manually started through the self-checking button;
the self-checking button is configured for diagnosing whether each module works normally under the condition of functional failure of remote self-checking and voice interaction self-checking;
the fault type indicator lamp is configured to be used for displaying fault result information of a manual self-checking function in the system self-checking module;
a base circuit configured to provide power and a clock signal for an overall system;
the image recognition module mainly comprises an industrial camera, a microcomputer, a photosensitive sensor and a light source control module;
the industrial camera is connected with the microcomputer through a USB interface and is configured to be used for collecting image data of garbage input and transmitting video data to the microcomputer;
the microcomputer carries an artificial intelligence-based convolution classification neural network image recognition algorithm, receives video data transmitted by an industrial camera, obtains identification information data of the category to which the image belongs by classifying and recognizing the video data, and sends the image identification information data to the embedded microcontroller through a serial port; in addition, the microcomputer receives the data of the photosensitive sensor through the port and controls the light source control module to realize the on or off of the light source according to the data;
a photosensor configured to detect a brightness level of ambient light;
the light source control module is configured to turn on the light source when the light is insufficient, so that the industrial camera acquires a clear image;
the voice interaction module mainly comprises a voice recognition and synthesis module, a microphone and a loudspeaker;
the voice recognition and synthesis module is connected with the embedded microcontroller through a port, carries a voice recognition unit and a voice synthesis unit, is configured to receive audio data collected by a microphone, performs voice recognition through the voice recognition unit to obtain voice recognition information, and sends the voice recognition information to the embedded microcontroller; receiving voice broadcast data sent by an embedded microcontroller, synthesizing audio data through a voice synthesis unit, and sending the audio data to a loudspeaker to complete voice interaction;
the microphone is connected with the voice recognition and synthesis module through a port and is configured to be used for collecting audio data and sending the audio data to the voice recognition and synthesis module;
the loudspeaker is connected with the voice recognition and synthesis module through a port and is configured to be used for receiving the audio data sent by the voice recognition and synthesis module and outputting voice;
the driving and detecting module mainly comprises a motor driving module and an ultrasonic detecting module;
the motor driving module is connected with the embedded microcontroller through a port and is configured to receive a pulse width modulation wave sent by the embedded microcontroller and control the motor driving module to rotate;
the ultrasonic detection module is connected with the embedded microcontroller through a port and is configured to record the sending and returning duration of ultrasonic waves, calculate the distance data of the volume in the barrel and send the measurement result to the embedded microcontroller;
the remote communication module is composed of a wireless 4G communication module, is connected with the embedded microcontroller through a port and is configured to be used for carrying out remote data bidirectional transmission with a remote monitoring and management center so as to realize remote self-checking and information management functions;
the remote monitoring and management center comprises a network switch and monitoring and management software; monitoring and management software configured to implement remote self-test or related information management functions;
after the system is started, the light and shade degree of light in a working environment is detected through a photosensitive sensor, and if the brightness does not meet the requirement, a light source is turned on to correct the light source; then starting the industrial camera, collecting a video, transmitting the video data into a microcomputer through a USB interface, judging whether the garbage to be detected exists or not by the microcomputer according to an image processing result, and repeating the cycle if the garbage to be detected does not exist; if yes, obtaining garbage classification information data through an image recognition algorithm, and transmitting the garbage classification information data into the embedded microcontroller through a serial port; the embedded microcontroller generates voice broadcast classification information according to the garbage classification information data, transmits the voice broadcast classification information data into the voice recognition and synthesis module, generates corresponding audio signals and transmits the audio signals to the loudspeaker, and the loudspeaker receives the audio signals transmitted by the voice recognition and synthesis module and outputs the voice of the classification information; meanwhile, the embedded microcontroller generates a corresponding pulse width modulation signal according to the garbage classification information data, transmits the pulse width modulation signal into the motor driving module, and controls the motor driving module to rotate so as to finish automatic classification and throwing of garbage; after the garbage is put in, the embedded microcontroller measures the content in the barrel through the ultrasonic detection module to obtain capacity data; then, the motor driving module is controlled to enable the garbage throwing device to return to the initial position, and then the embedded microcontroller sends the spatial data to a remote monitoring and management center through the remote communication module, so that automatic classification throwing and management of garbage are achieved.
Preferably, the embedded microcontroller selects stm32f 103; the microcomputer selects a raspberry pie 4 b; the wireless 4G communication module selects an LTE wireless communication module LE922A 6; industrial camera 500 ten thousand pixels industrial camera with USB3.0 data interface is selected; the motor driving module is an L298N motor driving module; the ultrasonic detection module adopts HC-SR 04; the voice recognition and synthesis module selects the XFMT-101 voice module.
In addition, the invention also provides a garbage classification and identification method, which adopts the intelligent garbage classification and management system and comprises the following steps:
step 1: when the industrial camera intercepts the images of the throwing areas in the garbage can when the garbage is not thrown in, and the images are stored as template images;
step 2: when the system runs, a template matching algorithm is used for comparing the image of the garbage throwing area with the template image in real time, if the comparison result is the same, the step 2 is executed in a circulating mode, and garbage throwing is waited; if the comparison results are different, the garbage input is proved to be present at this time, and the step 3 is executed;
and step 3: initializing an image transfer learning algorithm, performing feature extraction on the collected image by using the transfer learning algorithm, and storing image feature information for classification and identification of a following neural network;
and 4, step 4: inputting image characteristic information into a trained classification neural network to obtain a classification result, setting an accumulation algorithm for identifying the type of the thrown garbage, counting the classification result with the maximum probability within a certain time, and taking the classification result as a garbage classification identification result;
and 5: and outputting classification recognition result information, delaying to wait for automatic classification and putting of the garbage by the motor driving module, initializing the whole network after putting is finished, and repeating the steps 1-5 again.
In addition, the invention also provides a self-checking method, which adopts the intelligent garbage classification and management system and comprises the following steps:
when the system self-check is carried out, firstly, a remote self-check command is sent to the system through a remote monitoring and management center;
if the remote communication is normal, the remote self-checking operation is carried out according to the following procedures: the mainboard controller sequentially sends information to the image recognition module, the driving and detecting module and the voice interaction module through the ports, and sequentially collects feedback information of the modules, if the corresponding modules have information feedback, the modules work normally; if the feedback information is not received, the module is judged to have a fault, and finally, the self-checking result is wirelessly transmitted back to the remote monitoring and management center;
if the remote communication is faulty, informing the staff to arrive at the site, and firstly carrying out site voice interaction self-checking;
if the voice interaction module works normally, the operation is carried out according to the following flow: the self-checking function is started through specific voice, the mainboard controller sequentially sends information to the image recognition module and the driving and detecting module through the port, feedback information of the modules is sequentially collected, and if the information is fed back, the module works normally; if the feedback information is not received, the module is indicated to have a fault, and finally, a self-checking result is fed back in a voice broadcasting mode;
if the voice interaction module is abnormal, performing field manual self-inspection, and operating according to the following procedures: after the self-checking button is manually triggered, the mainboard controller sequentially sends information to the image identification module and the driving and detecting module through the port, and sequentially collects feedback information of the modules, and if the information is fed back, the module works normally; if the feedback information is not received, the module is indicated to have a fault, and finally, a self-checking result is fed back in a fault type indicator lamp mode.
The invention has the following beneficial technical effects:
according to the invention, the visual recognition is carried out on the thrown garbage through an artificial intelligence technology, the motor driving module is controlled according to the recognition information, the automatic classification and throwing of the garbage are accurately and intelligently completed, the garbage classification burden of residents is reduced, and the resident is promoted to change the existing garbage throwing behavior mode; meanwhile, through a voice interaction function, the puzzlement problem of the residents about the garbage classification related knowledge is solved to the resident popular science garbage classification related knowledge, and the consciousness of the residents in China on environmental protection and resource saving is improved; the content state of the garbage can is measured in real time through an ultrasonic capacity detection technology, capacity data are sent to a remote monitoring and management center, sanitation workers are helped to monitor the overflow degree of the garbage capacity in the garbage can of each garbage throwing point in real time at a remote end, and information management is achieved; by setting the system fault self-checking function, the working state and the fault type of the system are intelligently and dynamically displayed, and the maintenance efficiency of the intelligent garbage classification system is improved.
Drawings
Fig. 1 is a schematic structural diagram of an intelligent garbage classification and management system.
FIG. 2 is a flow chart of an automatic sorting operation for input waste.
Fig. 3 is a flow chart of the operation of the voice interaction function.
Fig. 4 is a flow chart of a self-test function operation.
Fig. 5 is an operation flowchart related to the remote self-checking function, the voice interaction self-checking function, and the manual self-checking function.
Fig. 6 is a flowchart of a garbage classification recognition method.
Detailed Description
The invention is described in further detail below with reference to the following figures and detailed description:
example 1:
as shown in fig. 1, an intelligent garbage classification and management system includes a motherboard controller, an image recognition module, a voice interaction module, a driving and detecting module, a remote communication module, and a remote monitoring and management center;
the system takes a mainboard controller as a core, and the mainboard controller mainly comprises an embedded microcontroller, a self-checking button, a barrier type indicator light and a basic circuit;
the embedded microcontroller is respectively connected with the image recognition module, the voice interaction module and the remote communication module through three serial communication interfaces;
the embedded microcontroller is connected with the image recognition module and is configured to receive recognition result information data of the image recognition module;
the embedded microcontroller is connected with the voice interaction module and is configured to receive voice recognition information data of the voice interaction module and control to generate corresponding voice broadcast data;
the embedded microcontroller is connected with the remote communication module and is configured to realize the remote wireless transmission function of the information data;
meanwhile, the embedded microcontroller is connected with the driving and detecting module through a general I/O port, sends a corresponding control signal to the driving and detecting module according to the image identification information, controls a motor driving module in the driving and detecting module to rotate, and controls the work of an ultrasonic detecting module in the driving and detecting module at the same time, so that the detection of the garbage capacity in the garbage can is realized;
in addition, the embedded microcontroller is connected with a self-checking button and a fault type indicator lamp through an I/O port, and the self-checking function of the system is manually started through the self-checking button;
the self-checking button is configured for diagnosing whether each module works normally under the condition of functional failure of remote self-checking and voice interaction self-checking;
the fault type indicator lamp is configured to be used for displaying fault result information of a manual self-checking function in the system self-checking module;
a base circuit configured to provide power and a clock signal for an overall system;
the image recognition module mainly comprises an industrial camera, a microcomputer, a photosensitive sensor and a light source control module;
the industrial camera is connected with the microcomputer through a USB interface and is configured to be used for collecting image data of garbage input and transmitting video data to the microcomputer;
the microcomputer carries an artificial intelligence-based convolution classification neural network image recognition algorithm, receives video data transmitted by an industrial camera, obtains identification information data of the category to which the image belongs by classifying and recognizing the video data, and sends the image identification information data to the embedded microcontroller through a serial port; in addition, the microcomputer receives the data of the photosensitive sensor through the port and controls the light source control module to realize the on or off of the light source according to the data;
a photosensor configured to detect a brightness level of ambient light;
the light source control module is configured to turn on the light source when the light is insufficient, so that the industrial camera acquires a clear image;
the voice interaction module mainly comprises a voice recognition and synthesis module, a microphone and a loudspeaker;
the voice recognition and synthesis module is connected with the embedded microcontroller through a port, carries a voice recognition unit and a voice synthesis unit, is configured to receive audio data collected by a microphone, performs voice recognition through the voice recognition unit to obtain voice recognition information, and sends the voice recognition information to the embedded microcontroller; receiving voice broadcast data sent by an embedded microcontroller, synthesizing audio data through a voice synthesis unit, and sending the audio data to a loudspeaker to complete voice interaction;
the microphone is connected with the voice recognition and synthesis module through a port and is configured to be used for collecting audio data and sending the audio data to the voice recognition and synthesis module;
the loudspeaker is connected with the voice recognition and synthesis module through a port and is configured to be used for receiving the audio data sent by the voice recognition and synthesis module and outputting voice;
the driving and detecting module mainly comprises a motor driving module and an ultrasonic detecting module;
the motor driving module is connected with the embedded microcontroller through a port and is configured to receive a pulse width modulation wave sent by the embedded microcontroller and control the motor driving module to rotate;
the ultrasonic detection module is connected with the embedded microcontroller through a port and is configured to record the sending and returning duration of ultrasonic waves, calculate the distance data of the volume in the barrel and send the measurement result to the embedded microcontroller;
the remote communication module is composed of a wireless 4G communication module, is connected with the embedded microcontroller through a port and is configured to be used for carrying out remote data bidirectional transmission with a remote monitoring and management center so as to realize remote self-checking and information management functions;
the remote monitoring and management center comprises a network switch and monitoring and management software; and the monitoring and management software is configured to realize remote self-checking or related information management functions.
The embedded microcontroller selects stm32f 103; the microcomputer selects a raspberry pie 4 b; the wireless 4G communication module selects an LTE wireless communication module LE922A 6; industrial camera 500 ten thousand pixels industrial camera with USB3.0 data interface is selected; the motor driving module is an L298N motor driving module; the ultrasonic detection module adopts HC-SR 04; the voice recognition and synthesis module selects the XFMT-101 voice module.
The implementation mode of the invention is illustrated by taking garbage classification in a scene of a scenic spot as an example, and only one type of garbage can be thrown at a time.
Example 2: the automatic classification of putting into rubbish is put in and voice broadcast discernment result, remote monitoring garbage bin capacity simultaneously to the realization. Fig. 2 is an operational flow diagram of an automatic classification of input waste.
The working flow of the garbage classification of the system is shown in fig. 2, after the system is started, the light and shade degree of light in a working environment is detected through a photosensitive sensor, and if the brightness does not meet the requirement, a light source is turned on to correct the light source; then starting the industrial camera, collecting a video, transmitting the video data into a microcomputer through a USB interface, judging whether the garbage to be detected exists or not by the microcomputer according to an image processing result, and repeating the cycle if the garbage to be detected does not exist; if yes, obtaining garbage classification information data through an image recognition algorithm, and transmitting the garbage classification information data into the embedded microcontroller through a serial port; the embedded microcontroller generates voice broadcast classification information according to the garbage classification information data, transmits the voice broadcast classification information data into the voice recognition and synthesis module, generates corresponding audio signals and transmits the audio signals to the loudspeaker, and the loudspeaker receives the audio signals transmitted by the voice recognition and synthesis module and outputs the voice of the classification information; meanwhile, the embedded microcontroller generates a corresponding pulse width modulation signal according to the garbage classification information data, transmits the pulse width modulation signal into the motor driving module, and controls the motor driving module to rotate so as to finish automatic classification and throwing of garbage; after the garbage is put in, the embedded microcontroller measures the content in the barrel through the ultrasonic detection module to obtain capacity data; then, the motor driving module is controlled to enable the garbage throwing device to return to the initial position, and then the embedded microcontroller sends the spatial data to a remote monitoring and management center through the remote communication module, so that automatic classification throwing and management of garbage are achieved.
Example 3: knowledge for classifying domestic science popularization garbage by using voice interaction function
The voice interaction work flow of the system is shown in fig. 3, after voice awakening, audio signal collection is carried out on input sound through a microphone, the audio signal is transmitted to a voice recognition unit in a voice recognition and synthesis module for voice recognition, and recognition information is finally transmitted to an embedded microcontroller; the embedded microcontroller generates corresponding voice broadcast information according to the voice recognition information and sends the voice broadcast information to a voice synthesis unit in the voice recognition and synthesis module through a port; finally, voice is output through a loudspeaker, and voice interaction is completed. As a specific operation:
for example, asked "what is the apple peel? The method comprises the following steps of firstly, carrying out audio acquisition through a microphone, sending the audio acquisition to a voice recognition unit in a voice interaction module, sending a recognition result to an embedded microcontroller, generating corresponding response voice information by the embedded microcontroller, sending the response voice information to a voice synthesis unit, and outputting 'apple peel is wet garbage' through a loudspeaker; the science popularization of knowledge for realizing garbage classification is realized.
Example 4: realizing the self-checking function of the system
Fig. 4 is a flow chart providing a self-checking function operation.
Fig. 5 is a flowchart providing an operation related to the remote self-checking function, the voice interaction self-checking function and the manual self-checking function.
The self-checking function is performed according to the system conditions as shown in the flow charts of fig. 4 and 5. When performing system self-check, as shown in fig. 4, first, a remote self-check command is sent to the system through the remote monitoring and management center, and if the remote communication is normal, the remote self-check operation is performed according to the flow shown in fig. 5 (a): the main control panel sequentially sends information to the image processing module, the driving and detecting module and the voice interaction module through the ports, feedback information of the modules is collected in a secondary mode, and if information is fed back by the corresponding modules, the unit modules work normally; if the feedback information is not received, the unit module is judged to have a fault, and finally, the self-checking result is wirelessly transmitted back to the remote monitoring and management center; if the remote communication is faulty, a worker is informed to arrive at the site, the site voice interaction self-check is firstly carried out, if the voice interaction module works normally, the operation is carried out according to the flow shown in the figure 5(b), the self-check function is started through specific voice, the main control panel sequentially sends information to the image processing module and the driving and detecting module through the port, the feedback information of the modules is collected in a secondary mode, and if the information is fed back, the unit module works normally; if the feedback information is not received, the unit module is indicated to have a fault, and finally, a self-checking result is fed back in a voice broadcasting mode; if the voice interaction module does not work normally, performing field manual self-inspection, such as operation in fig. 5(c), after manually triggering a self-inspection button, sending information to the image processing module by the main control panel through the port, driving and detecting the module, and collecting feedback information again, wherein if the information is fed back, the unit module works normally; if the feedback information is not received, the unit module is indicated to have a fault, and finally, a self-checking result is fed back in a fault type indicator lamp mode.
Example 5
On the basis of the above embodiment, the present invention further provides a garbage classification and identification method, the flow of which is shown in fig. 6, and the method is performed according to the following steps:
step 1: when the industrial camera intercepts the images of the throwing areas in the garbage can when the garbage is not thrown in, and the images are stored as template images;
step 2: when the system runs, a template matching algorithm is used for comparing the image of the garbage throwing area with the template image in real time, if the comparison result is the same, the step 2 is executed in a circulating mode, and garbage throwing is waited; if the comparison results are different, the garbage input is proved to be present at this time, and the step 3 is executed;
and step 3: initializing an image transfer learning algorithm, performing feature extraction on the collected image by using the transfer learning algorithm, and storing image feature information for classification and identification of a following neural network;
and 4, step 4: inputting image characteristic information into a trained classification neural network to obtain a classification result, setting an accumulation algorithm for identifying the type of the thrown garbage, counting the classification result with the maximum probability within a certain time, and taking the classification result as a garbage classification identification result;
and 5: and outputting classification recognition result information, delaying to wait for automatic classification and putting of the garbage by the motor driving module, initializing the whole network after putting is finished, and repeating the steps 1-5 again.
The intelligent garbage classification and management system and the garbage classification and identification method carry out visual identification on the thrown garbage by using an artificial intelligence technology, control a motor driving module according to identification information, accurately and intelligently finish automatic classification and throwing of the garbage, reduce the garbage classification burden of residents and promote the residents to change the existing garbage throwing behavior mode; meanwhile, an intelligent voice technology is carried, and knowledge of domestic general garbage classification is provided for residents through a voice interaction function, so that environmental protection and resource saving consciousness of the residents in China is improved; the content state of the garbage can is measured in real time through an ultrasonic capacity detection technology, capacity data are sent to a remote monitoring and management center, sanitation workers are helped to monitor the overflow degree of the garbage capacity in the garbage can of each garbage throwing point in real time at a remote end, and information management is achieved; by setting a system fault self-checking function, the working state and the fault type of the system are intelligently and dynamically displayed, and the maintenance efficiency of the intelligent garbage classification and management system is improved.
It is to be understood that the above description is not intended to limit the present invention, and the present invention is not limited to the above examples, and those skilled in the art may make modifications, alterations, additions or substitutions within the spirit and scope of the present invention.
Claims (4)
1. Rubbish intelligent classification and management system, its characterized in that: the system comprises a mainboard controller, an image recognition module, a voice interaction module, a driving and detecting module, a remote communication module and a remote monitoring and management center;
the main board controller mainly comprises an embedded microcontroller, a self-checking button, a barrier type indicator light and a basic circuit;
the embedded microcontroller is respectively connected with the image recognition module, the voice interaction module and the remote communication module through three serial communication interfaces;
the embedded microcontroller is connected with the image recognition module and is configured to receive recognition result information data of the image recognition module;
the embedded microcontroller is connected with the voice interaction module and is configured to receive voice recognition information data of the voice interaction module and control to generate corresponding voice broadcast data;
the embedded microcontroller is connected with the remote communication module and is configured to realize the remote wireless transmission function of the information data;
meanwhile, the embedded microcontroller is connected with the driving and detecting module through a general I/O port, sends a corresponding control signal to the driving and detecting module according to the image identification information, controls a motor driving module in the driving and detecting module to rotate, and controls the work of an ultrasonic detecting module in the driving and detecting module at the same time, so that the detection of the garbage capacity in the garbage can is realized;
in addition, the embedded microcontroller is connected with a self-checking button and a fault type indicator lamp through an I/O port, and the self-checking function of the system is manually started through the self-checking button;
the self-checking button is configured for diagnosing whether each module works normally under the condition of functional failure of remote self-checking and voice interaction self-checking;
the fault type indicator lamp is configured to be used for displaying fault result information of a manual self-checking function in the system self-checking module;
a base circuit configured to provide power and a clock signal for an overall system;
the image recognition module mainly comprises an industrial camera, a microcomputer, a photosensitive sensor and a light source control module;
the industrial camera is connected with the microcomputer through a USB interface and is configured to be used for collecting image data of garbage input and transmitting video data to the microcomputer;
the microcomputer carries an artificial intelligence-based convolution classification neural network image recognition algorithm, receives video data transmitted by an industrial camera, obtains identification information data of the category to which the image belongs by classifying and recognizing the video data, and sends the image identification information data to the embedded microcontroller through a serial port; in addition, the microcomputer receives the data of the photosensitive sensor through the port and controls the light source control module to realize the on or off of the light source according to the data;
a photosensor configured to detect a brightness level of ambient light;
the light source control module is configured to turn on the light source when the light is insufficient, so that the industrial camera acquires a clear image;
the voice interaction module mainly comprises a voice recognition and synthesis module, a microphone and a loudspeaker;
the voice recognition and synthesis module is connected with the embedded microcontroller through a port, carries a voice recognition unit and a voice synthesis unit, is configured to receive audio data collected by a microphone, performs voice recognition through the voice recognition unit to obtain voice recognition information, and sends the voice recognition information to the embedded microcontroller; receiving voice broadcast data sent by an embedded microcontroller, synthesizing audio data through a voice synthesis unit, and sending the audio data to a loudspeaker to complete voice interaction;
the microphone is connected with the voice recognition and synthesis module through a port and is configured to be used for collecting audio data and sending the audio data to the voice recognition and synthesis module;
the loudspeaker is connected with the voice recognition and synthesis module through a port and is configured to be used for receiving the audio data sent by the voice recognition and synthesis module and outputting voice;
the driving and detecting module mainly comprises a motor driving module and an ultrasonic detecting module;
the motor driving module is connected with the embedded microcontroller through a port and is configured to receive a pulse width modulation wave sent by the embedded microcontroller and control the motor driving module to rotate;
the ultrasonic detection module is connected with the embedded microcontroller through a port and is configured to record the sending and returning duration of ultrasonic waves, calculate the distance data of the volume in the barrel and send the measurement result to the embedded microcontroller;
the remote communication module is composed of a wireless 4G communication module, is connected with the embedded microcontroller through a port and is configured to be used for carrying out remote data bidirectional transmission with a remote monitoring and management center so as to realize remote self-checking and information management functions;
the remote monitoring and management center comprises a network switch and monitoring and management software; monitoring and management software configured to implement remote self-test or related information management functions;
after the system is started, the light and shade degree of light in a working environment is detected through a photosensitive sensor, and if the brightness does not meet the requirement, a light source is turned on to correct the light source; then starting the industrial camera, collecting a video, transmitting the video data into a microcomputer through a USB interface, judging whether the garbage to be detected exists or not by the microcomputer according to an image processing result, and repeating the cycle if the garbage to be detected does not exist; if yes, obtaining garbage classification information data through an image recognition algorithm, and transmitting the garbage classification information data into the embedded microcontroller through a serial port; the embedded microcontroller generates voice broadcast classification information according to the garbage classification information data, transmits the voice broadcast classification information data into the voice recognition and synthesis module, generates corresponding audio signals and transmits the audio signals to the loudspeaker, and the loudspeaker receives the audio signals transmitted by the voice recognition and synthesis module and outputs the voice of the classification information; meanwhile, the embedded microcontroller generates a corresponding pulse width modulation signal according to the garbage classification information data, transmits the pulse width modulation signal into the motor driving module, and controls the motor driving module to rotate so as to finish automatic classification and throwing of garbage; after the garbage is put in, the embedded microcontroller measures the content in the barrel through the ultrasonic detection module to obtain capacity data; then, the motor driving module is controlled to enable the garbage throwing device to return to the initial position, and then the embedded microcontroller sends the spatial data to a remote monitoring and management center through the remote communication module, so that automatic classification throwing and management of garbage are achieved.
2. The intelligent garbage classification and management system according to claim 1, characterized in that: the embedded microcontroller selects stm32f 103; the microcomputer selects a raspberry pie 4 b; the wireless 4G communication module selects an LTE wireless communication module LE922A 6; industrial camera 500 ten thousand pixels industrial camera with USB3.0 data interface is selected; the motor driving module is an L298N motor driving module; the ultrasonic detection module adopts HC-SR 04; the voice recognition and synthesis module selects the XFMT-101 voice module.
3. The garbage classification and identification method is characterized by comprising the following steps: the intelligent garbage classification and management system of claim 1 is adopted, and the intelligent garbage classification and management method comprises the following steps:
step 1: when the industrial camera intercepts the images of the throwing areas in the garbage can when the garbage is not thrown in, and the images are stored as template images;
step 2: when the system runs, a template matching algorithm is used for comparing the image of the garbage throwing area with the template image in real time, if the comparison result is the same, the step 2 is executed in a circulating mode, and garbage throwing is waited; if the comparison results are different, the garbage input is proved to be present at this time, and the step 3 is executed;
and step 3: initializing an image transfer learning algorithm, performing feature extraction on the collected image by using the transfer learning algorithm, and storing image feature information for classification and identification of a following neural network;
and 4, step 4: inputting image characteristic information into a trained classification neural network to obtain a classification result, setting an accumulation algorithm for identifying the type of the thrown garbage, counting the classification result with the maximum probability within a certain time, and taking the classification result as a garbage classification identification result;
and 5: and outputting classification recognition result information, delaying to wait for automatic classification and putting of the garbage by the motor driving module, initializing the whole network after putting is finished, and repeating the steps 1-5 again.
4. The self-checking method is characterized in that: the intelligent garbage classification and management system of claim 1 is adopted, and the intelligent garbage classification and management method comprises the following steps:
when the system self-check is carried out, firstly, a remote self-check command is sent to the system through a remote monitoring and management center;
if the remote communication is normal, the remote self-checking operation is carried out according to the following procedures: the mainboard controller sequentially sends information to the image recognition module, the driving and detecting module and the voice interaction module through the ports, and sequentially collects feedback information of the modules, if the corresponding modules have information feedback, the modules work normally; if the feedback information is not received, the module is judged to have a fault, and finally, the self-checking result is wirelessly transmitted back to the remote monitoring and management center;
if the remote communication is faulty, informing the staff to arrive at the site, and firstly carrying out site voice interaction self-checking;
if the voice interaction module works normally, the operation is carried out according to the following flow: the self-checking function is started through specific voice, the mainboard controller sequentially sends information to the image recognition module and the driving and detecting module through the port, feedback information of the modules is sequentially collected, and if the information is fed back, the module works normally; if the feedback information is not received, the module is indicated to have a fault, and finally, a self-checking result is fed back in a voice broadcasting mode;
if the voice interaction module is abnormal, performing field manual self-inspection, and operating according to the following procedures: after the self-checking button is manually triggered, the mainboard controller sequentially sends information to the image identification module and the driving and detecting module through the port, and sequentially collects feedback information of the modules, and if the information is fed back, the module works normally; if the feedback information is not received, the module is indicated to have a fault, and finally, a self-checking result is fed back in a fault type indicator lamp mode.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911124195.XA CN110893956A (en) | 2019-11-18 | 2019-11-18 | Intelligent garbage classification and management system, garbage classification identification method and self-inspection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911124195.XA CN110893956A (en) | 2019-11-18 | 2019-11-18 | Intelligent garbage classification and management system, garbage classification identification method and self-inspection method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110893956A true CN110893956A (en) | 2020-03-20 |
Family
ID=69786664
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911124195.XA Pending CN110893956A (en) | 2019-11-18 | 2019-11-18 | Intelligent garbage classification and management system, garbage classification identification method and self-inspection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110893956A (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111661526A (en) * | 2020-05-09 | 2020-09-15 | 北京电子工程总体研究所 | Intelligent garbage classification box |
CN111874487A (en) * | 2020-07-29 | 2020-11-03 | 浙江工贸职业技术学院 | Environment-friendly garbage bin that possesses automatic waste classification |
CN112158486A (en) * | 2020-08-28 | 2021-01-01 | 山东科技大学 | Intelligent garbage classification device and classification method |
CN112235388A (en) * | 2020-10-10 | 2021-01-15 | 达昌技术发展有限公司 | Smart community operation management system |
CN112597804A (en) * | 2020-11-27 | 2021-04-02 | 上海阅目环境科技有限公司 | Voice prompt and video image supervision method for garbage classification delivery site |
CN113135368A (en) * | 2021-04-29 | 2021-07-20 | 怀化学院 | Intelligent garbage front-end classification system and method |
CN113450401A (en) * | 2021-07-19 | 2021-09-28 | 北京航空航天大学杭州创新研究院 | Trash can fullness degree determining method, device and equipment and trash can |
CN113443296A (en) * | 2020-08-17 | 2021-09-28 | 刘炎 | Automatic garbage classification system based on big data |
FR3118763A1 (en) * | 2021-01-08 | 2022-07-15 | Bh Technologies | Device and method for counting and identifying bottles |
CN115610868A (en) * | 2022-11-09 | 2023-01-17 | 江苏华旭环卫科技有限公司 | Wisdom classification system based on thing networking |
CN116342895A (en) * | 2023-05-31 | 2023-06-27 | 浙江联运知慧科技有限公司 | Method and system for improving sorting efficiency of renewable resources based on AI (advanced technology attachment) processing |
CN116430769A (en) * | 2023-03-17 | 2023-07-14 | 安徽大学 | Intelligent garbage classification system and method for large-scale management |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101150788A (en) * | 2007-11-12 | 2008-03-26 | 北京豪仪测控工程有限公司 | Self modulation radio broadcast terminal system and its monitoring processor |
CA2806876A1 (en) * | 2010-07-28 | 2012-02-02 | Big Belly Solar, Inc. | Electrically-powered programmable waste enclosure |
CN102843612A (en) * | 2012-08-31 | 2012-12-26 | 深圳市龙视传媒有限公司 | Method and device for intelligently processing fault of digital television terminal according to voice |
CN105059782A (en) * | 2015-07-31 | 2015-11-18 | 浙江联运知慧科技有限公司 | Intelligent garbage classification device, system and method |
CN106241105A (en) * | 2016-08-31 | 2016-12-21 | 浙江村口环境服务有限公司 | A kind of Intelligent classification dustbin based on colour recognition |
CN108861226A (en) * | 2018-07-05 | 2018-11-23 | 宁波暇客物联科技有限公司 | A kind of intelligence rubbish from cooking case |
CN109368092A (en) * | 2018-12-10 | 2019-02-22 | 上海良韶智能科技有限公司 | Intelligent classification dustbin |
CN109911451A (en) * | 2019-04-18 | 2019-06-21 | 东华大学 | A kind of intelligent classification dustbin based on machine vision |
CN110222676A (en) * | 2019-07-04 | 2019-09-10 | 谷建勇 | A kind of garbage classification learning system and its application method |
-
2019
- 2019-11-18 CN CN201911124195.XA patent/CN110893956A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101150788A (en) * | 2007-11-12 | 2008-03-26 | 北京豪仪测控工程有限公司 | Self modulation radio broadcast terminal system and its monitoring processor |
CA2806876A1 (en) * | 2010-07-28 | 2012-02-02 | Big Belly Solar, Inc. | Electrically-powered programmable waste enclosure |
CN102843612A (en) * | 2012-08-31 | 2012-12-26 | 深圳市龙视传媒有限公司 | Method and device for intelligently processing fault of digital television terminal according to voice |
CN105059782A (en) * | 2015-07-31 | 2015-11-18 | 浙江联运知慧科技有限公司 | Intelligent garbage classification device, system and method |
CN106241105A (en) * | 2016-08-31 | 2016-12-21 | 浙江村口环境服务有限公司 | A kind of Intelligent classification dustbin based on colour recognition |
CN108861226A (en) * | 2018-07-05 | 2018-11-23 | 宁波暇客物联科技有限公司 | A kind of intelligence rubbish from cooking case |
CN109368092A (en) * | 2018-12-10 | 2019-02-22 | 上海良韶智能科技有限公司 | Intelligent classification dustbin |
CN109911451A (en) * | 2019-04-18 | 2019-06-21 | 东华大学 | A kind of intelligent classification dustbin based on machine vision |
CN110222676A (en) * | 2019-07-04 | 2019-09-10 | 谷建勇 | A kind of garbage classification learning system and its application method |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111661526A (en) * | 2020-05-09 | 2020-09-15 | 北京电子工程总体研究所 | Intelligent garbage classification box |
CN111874487A (en) * | 2020-07-29 | 2020-11-03 | 浙江工贸职业技术学院 | Environment-friendly garbage bin that possesses automatic waste classification |
CN113443296A (en) * | 2020-08-17 | 2021-09-28 | 刘炎 | Automatic garbage classification system based on big data |
CN112158486A (en) * | 2020-08-28 | 2021-01-01 | 山东科技大学 | Intelligent garbage classification device and classification method |
CN112235388A (en) * | 2020-10-10 | 2021-01-15 | 达昌技术发展有限公司 | Smart community operation management system |
CN112597804A (en) * | 2020-11-27 | 2021-04-02 | 上海阅目环境科技有限公司 | Voice prompt and video image supervision method for garbage classification delivery site |
FR3118763A1 (en) * | 2021-01-08 | 2022-07-15 | Bh Technologies | Device and method for counting and identifying bottles |
CN113135368A (en) * | 2021-04-29 | 2021-07-20 | 怀化学院 | Intelligent garbage front-end classification system and method |
CN113450401A (en) * | 2021-07-19 | 2021-09-28 | 北京航空航天大学杭州创新研究院 | Trash can fullness degree determining method, device and equipment and trash can |
CN115610868A (en) * | 2022-11-09 | 2023-01-17 | 江苏华旭环卫科技有限公司 | Wisdom classification system based on thing networking |
CN116430769A (en) * | 2023-03-17 | 2023-07-14 | 安徽大学 | Intelligent garbage classification system and method for large-scale management |
CN116342895A (en) * | 2023-05-31 | 2023-06-27 | 浙江联运知慧科技有限公司 | Method and system for improving sorting efficiency of renewable resources based on AI (advanced technology attachment) processing |
CN116342895B (en) * | 2023-05-31 | 2023-08-11 | 浙江联运知慧科技有限公司 | Method and system for improving sorting efficiency of renewable resources based on AI (advanced technology attachment) processing |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110893956A (en) | Intelligent garbage classification and management system, garbage classification identification method and self-inspection method | |
CN205490915U (en) | Power saving intelligence cat eye | |
CN203629603U (en) | Intelligent electric energy meter detection device based on image identification technology | |
CN106993358A (en) | A kind of multipurpose based on radio communication is met an urgent need light intelligent control system | |
CN103743436B (en) | Remote-controlled environmental monitoring system and realize environment and patrol and examine the method patrolled and examined with system | |
CN109809060A (en) | A kind of automatic sorting garbage bin and its management system | |
CN103258260A (en) | Campus dormitory management system based on face recognition | |
CN101674469A (en) | Recording and transmission system of monitoring and alarming images of small optical fiber circuit | |
CN104535953B (en) | A kind of intelligent electric energy meter liquid crystal display automatic checkout system and its detection method | |
CN106023512A (en) | Intelligent fireproof alarm system | |
CN203287934U (en) | Campus dormitory management system based on face recognition | |
CN107995762A (en) | A kind of solar street light Lighting Control Assembly | |
CN203193903U (en) | System for positioning and monitoring mobile phones in examination hall | |
CN105931454A (en) | Low-power-consumption wireless communication detection device and detection method | |
CN110031041A (en) | A kind of nature lightning discharge sound, light, electricity, the more physical processes of magnetic monitor systems | |
CN112543536B (en) | Automatic closing device and method for classroom lighting facilities | |
CN107785984A (en) | A kind of Double-battery powered equipment with intelligent handoff functionality | |
CN107610260B (en) | Intelligent attendance system and attendance method based on machine vision | |
CN207283704U (en) | Monitoring system and solar energy violation snap-shooting system | |
CN203728340U (en) | Automatically driving device for illumination of elevator taking target floor | |
CN208335306U (en) | Identification terminal and management system | |
CN113581690A (en) | Intelligent classification garbage bin control system based on image recognition | |
CN110562623A (en) | Intelligent garbage classification system | |
CN210181242U (en) | Garbage bin overflow monitoring system | |
CN112735093A (en) | Earthquake is easily sent out and is taken data collection robot |
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 |
Application publication date: 20200320 |
|
RJ01 | Rejection of invention patent application after publication |