CN112407660A - Intelligent household garbage can based on multi-mode fusion machine perception - Google Patents
Intelligent household garbage can based on multi-mode fusion machine perception Download PDFInfo
- Publication number
- CN112407660A CN112407660A CN202011455685.0A CN202011455685A CN112407660A CN 112407660 A CN112407660 A CN 112407660A CN 202011455685 A CN202011455685 A CN 202011455685A CN 112407660 A CN112407660 A CN 112407660A
- Authority
- CN
- China
- Prior art keywords
- garbage
- module
- control module
- classification result
- voice
- 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
- 230000008447 perception Effects 0.000 title claims abstract description 14
- 230000004927 fusion Effects 0.000 title claims abstract description 13
- 230000006698 induction Effects 0.000 claims abstract description 24
- 230000003993 interaction Effects 0.000 claims abstract description 19
- 238000000034 method Methods 0.000 claims abstract description 10
- 238000013136 deep learning model Methods 0.000 claims abstract description 8
- 230000001939 inductive effect Effects 0.000 claims abstract description 3
- 230000000007 visual effect Effects 0.000 claims description 14
- 240000007651 Rubus glaucus Species 0.000 claims description 13
- 235000011034 Rubus glaucus Nutrition 0.000 claims description 13
- 235000009122 Rubus idaeus Nutrition 0.000 claims description 13
- 230000002093 peripheral effect Effects 0.000 claims description 13
- 238000004891 communication Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000013459 approach Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 238000003058 natural language processing Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000003203 everyday effect Effects 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 235000013361 beverage Nutrition 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 229920003023 plastic Polymers 0.000 description 1
- 239000004033 plastic Substances 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000011144 upstream manufacturing Methods 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
- B65F1/006—Rigid receptacles stored in an enclosure or forming part of it
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
- B65F1/00—Refuse receptacles; Accessories therefor
- B65F1/14—Other constructional features; Accessories
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
- B65F1/00—Refuse receptacles; Accessories therefor
- B65F1/14—Other constructional features; Accessories
- B65F1/16—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
-
- 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
- B65F2210/165—Remote controls
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Processing Of Solid Wastes (AREA)
Abstract
The invention discloses an intelligent household garbage can based on multi-mode fusion machine perception, and belongs to the field of household products: the garbage classification system comprises a human body induction module, a control module, a voice interaction module, a voice recognition module, a garbage box body, a power supply module, a cloud database, a mobile phone APP and a control module, wherein the human body induction module is used for inducing a garbage throwing person to obtain a human body induction signal, the garbage box body is used for classifying thrown garbage, the voice signal is converted into a text by the power supply module, the text is compared with the similarity of the text and a garbage name text library, each type of garbage corresponds to one type of garbage, and a classification result I is obtained; the method comprises the steps that image acquisition is carried out on thrown rubbish, a vision recognition module control module of image signals of the thrown rubbish is obtained, reasoning operation is carried out on the control module based on a lightweight deep learning model to obtain a classification result II, the classification result I is compared with the classification result II, and the classification result I is selected as a final classification result; this dustbin promotes refuse treatment's treatment effeciency, reduces rubbish and deposits and the influence of transportation link to the environment.
Description
Technical Field
The invention belongs to the field of household products, and particularly relates to an intelligent household garbage can based on multi-mode fusion machine perception.
Background
Regarding the novel intelligent garbage can, many invention patents exist at home and abroad, but most of the patents are design patents of mechanical structures such as appearance and the like. At present, the intelligent classification dustbin on the market, such as the code scanning recognition voice broadcast intelligent recognition classification dustbin manufactured by Koutong. And a garbage classification sound-light alarm intelligent system is introduced into Ninghai, and a garbage room capable of supervising and reminding can be carried out. The devices are too large in size and not suitable for being put into use in large quantities, so that the problem of the garbage classification and throwing process is mainly solved.
In addition, to intelligent classification rubbish system, all there are more different design thoughts domestic and abroad, have multiple drive control's full intelligent garbage bin, intelligent classification garbage bin based on STC89C52 singlechip, the "intelligent garbage bin" under the STEM theory, intelligent garbage bin based on Arduino etc.. And the software design for garbage classification by related intelligent identification and the like.
At present, the 'intelligence' of the intelligent garbage bin on the market is only embodied in that an automatic induction opening function and a sealing function are added, and automatic garbage classification cannot be realized.
Disclosure of Invention
According to the problems existing in the prior art, the invention discloses an intelligent household garbage can based on multi-mode fusion machine perception, which comprises
The human body induction module is used for inducing a person who puts garbage to obtain a human body induction signal;
the control module is used for receiving the human body induction signal transmitted by the human body induction module;
the voice interaction module receives the control signal transmitted by the control module, carries out voice communication with a person throwing the garbage and obtains a voice signal answered by the person throwing the garbage, the voice interaction module transmits the garbage voice signal answered by the person throwing the garbage to the control module, the control module converts the voice signal into a text and carries out similarity comparison with a garbage name text library, and each garbage corresponds to one category to obtain a classification result I;
the voice recognition module receives voice signals sent by the control module and answered by the voice of people who throw the garbage, and recognizes the voice signals to obtain voice signals of garbage throwing varieties, and the voice recognition module sends the obtained voice signals of the garbage throwing varieties to the control module;
the garbage classification method comprises the steps that image acquisition is carried out on thrown garbage to obtain a vision recognition module of a thrown garbage image signal, the vision recognition module transmits the obtained thrown garbage image signal to a control module, the control module carries out reasoning operation based on a lightweight deep learning model to obtain a classification result II, the control module compares the classification result I with the classification result II, when the obtained classification result I is consistent with the classification result II, a final garbage classification result is obtained, and when the obtained classification result I is inconsistent with the obtained classification result II, the classification result I is selected as a final classification result;
the garbage bin body is used for receiving the garbage classification result transmitted by the control module and classifying the thrown garbage;
the power supply module is used for supplying power to the control module, the human body induction module, the voice interaction module and the visual recognition module;
the cloud database is used for storing the classification result I of the input garbage, which is transmitted by the control module and identified by the control module;
and receiving the mobile phone APP of the classification result I of the garbage transmitted by the cloud database, and counting the total amount of the single garbage and the total amount of the four types of garbage by the mobile phone APP.
Further, the garbage can body comprises an upper shell I arranged at the top;
a feeding port I for feeding garbage is arranged on the upper shell;
a peripheral housing integrally connected with the upper housing;
an automatic rotating upper shell II arranged below the upper shell I;
an automatic cover opening and closing module for garbage thrown from the throwing port I is arranged (connected) below the upper shell I;
an automatic cover opening and closing module is arranged below the upper shell I;
the automatic cover opening and closing module forms a feeding opening II after being opened;
a sliding inlet is arranged below the putting-in port II,
the feeding port I and the feeding port II are integrally connected through a shell I;
the sliding inlet and the throwing port II are integrally connected through a shell II to form an eccentric funnel;
four barrel bodies with the same caliber and used for containing different types of garbage are arranged below the automatic cover opening and closing module;
the central point of the sliding inlet is arranged on the circumference formed by the four barrel bodies with the same caliber.
Further, the automatic opening and closing cover module comprises
A bearing is arranged outside the lower side of the edge of the automatic rotating upper shell II, the inner ring of the bearing is fixedly connected with the upper side of the edge of the upper plane of the eccentric funnel, and the outer ring of the bearing is fixedly connected with the upper plane of the peripheral shell; the middle of the outer ring and the outer ring is filled with balls;
the meshing gear ring is connected with the lower side of the edge of the upper plane of the eccentric funnel;
the driving gear is meshed with the meshing gear;
the motor is connected with the driving gear and is connected with the control module;
the automatic opening and closing cover is connected with the upper shell I and comprises 3N sliding blocks, a tray frame and a sliding block fixing disc, the tray frame is connected with the sliding block fixing disc, a layer of gaps are reserved between the tray frame and the sliding block fixing disc for placing the sliding blocks, and N is larger than or equal to 2; the 3N sliding blocks are matched into a plane when being closed;
3N sliding grooves are formed in the automatic opening and closing cover, each sliding groove is formed in the side edge of the sliding block, and the 3N sliding grooves correspond to the 3N sliding blocks one by one;
the two electric cylinders are symmetrically arranged on the periphery of the 3N sliding blocks, one end of each electric cylinder is connected with the corresponding sliding block, and the other end of each electric cylinder is connected with the control module.
Furthermore, the caliber size of the input opening I is larger than or equal to that of the input opening II.
Furthermore, four opening and closing doors are averagely arranged on the periphery of the peripheral shell.
Further: the vision recognition module is connected with the control module and the power module.
Further, the control module adopts a raspberry pie.
Due to the adoption of the technical scheme, the intelligent household garbage can based on multi-mode fusion machine perception comprehensively improves the treatment efficiency of an upstream link of garbage treatment and reduces the influence of the garbage storage and transportation link on the environment; designing a collecting and transporting line according to the garbage classification condition to realize an integrated garbage collecting and transporting system; through big data sorting, an intelligent classification and internet emerging garbage classification mode is established, a related industrial chain is developed to increase the output value, and resources are recycled to the maximum extent; the energy-saving and environment-friendly concept is popularized, and the sustainable development is promoted; according to the invention, through the combination of the raspberry group, the image recognition technology, the voice technology and the deep learning technology, the accuracy of garbage recognition is greatly improved, the intelligent classification and the accurate recognition of garbage classification are realized, and the recognition accuracy can reach more than 95%; the garbage fine type recognition technology based on computer vision and deep learning and the garbage type recognition technology based on voice recognition and natural language processing technology can accurately recognize the types of garbage and solve the difficulty of garbage classification sources, the garbage classification internet of things system based on man-machine intelligent interaction can upload garbage classification information to a cloud database, garbage information thrown in every day is collected and stored, and after statistical analysis, the quantity of various garbage generated and the throwing habits of residents and the like are obtained; real-time dynamic monitoring is realized through a mobile phone APP; the quantity and the positions of the garbage cans in the community are reasonably configured according to the quantity and the positions of the garbage cans in the community, so that a garbage classification scheme which is more suitable for local conditions is formed; meanwhile, the garbage collecting and transporting line can be planned and designed to form an integrated garbage collecting and transporting system.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a block diagram of the present invention;
FIG. 2 is a flow diagram of a multi-modal recognition technique of the present invention;
FIG. 3 is a flow chart of an automated classified delivery technique of the present invention;
FIG. 4 is an overall external view of the present invention;
FIG. 5 is a front view of the present invention;
FIG. 6 is a left half sectional view of the present invention;
FIG. 7 is a right half sectional view of the present invention;
FIG. 8 is a view showing the closing of the automatic opening/closing cover;
FIG. 9 is a schematic view of the automatic opening and closing cover being opened;
FIG. 10 is a top view of the present invention;
FIG. 11 is a top view I of the present invention;
FIG. 12 is a drawing of the automatic lid opening and closing apparatus of the present invention;
FIG. 13 is a view of the automatic lid opening and closing apparatus of the present invention II;
FIG. 14 is a top view II of the present invention;
FIG. 15 is a schematic view of four barrels of the present invention.
In the figure: 1. human response module, 2, control module, 3, voice interaction module, 4, voice recognition module, 5, visual recognition module, 6, the rubbish box body, 7, power module, 8, the high in the clouds database, 9, cell-phone APP, 10, go up casing I, 11, input mouth I, 12, go up casing II, 13, automatic lid module that opens and shuts, 14, input mouth II, 15, casing I, 16, casing II, 17, eccentric funnel, 18 staving, 19, the bearing, 20, the ball, 21, the interlock ring gear, 22, the driving gear, 23, the motor, 24, motor support, 25, automatic lid that opens and shuts, 26, the slider, 27, the tray frame, 28, the slider fixed disk, 29, the spout, 30, electronic jar, 31, the light source module, 32, peripheral casing, 33, the door that opens and shuts, 34, the door handle, 35, the hinge, 36, electronic jar support.
Detailed Description
In order to make the technical solutions and advantages of the present invention clearer, the following describes the technical solutions in the embodiments of the present invention clearly and completely with reference to the drawings in the embodiments of the present invention:
an intelligent classification garbage can based on multi-mode fusion machine perception comprises a human body induction module 1, a control module 2, a voice interaction module 3, a voice recognition module 4, a visual recognition module 5, a garbage can body 6, a power supply module 7, a cloud database 8 and a mobile phone APP 9;
FIG. 1 is a block diagram of the present invention; FIG. 2 is a flow diagram of a multi-modal recognition technique of the present invention;
FIG. 3 is a flow chart of an automated classified delivery technique of the present invention; the human body induction module 1 induces a person who puts garbage to obtain a human body induction signal;
the control module 2 receives the human body induction signal transmitted by the human body induction module 1;
the voice interaction module 3 receives the control signal transmitted by the control module 2 and carries out voice communication with a person throwing garbage, namely a voice instruction of the person, and when the person approaches a garbage bin in the specific process, the voice interaction module sends out voice 'whether garbage throwing is carried out' to obtain a voice signal answered by the person throwing garbage, the voice interaction module 3 transmits a garbage voice signal answered by the person throwing garbage to the control module 2, the control module 2 converts the voice signal into a text and carries out similarity comparison with a garbage name text library, and each type of garbage corresponds to one type to obtain a classification result I;
the voice recognition module 4 receives the voice signal of the voice answer of the person who puts in the rubbish, which is transmitted by the control module 2, and recognizes the voice signal to obtain the voice signal of the rubbish throwing variety, and the voice recognition module 4 transmits the obtained voice signal of the rubbish throwing variety to the control module 2;
the vision recognition module 5 obtains images of the thrown garbage to obtain image signals of the thrown garbage, the vision recognition module 5 transmits the obtained image signals of the thrown garbage to the control module 2, the control module 2 performs reasoning operation based on a lightweight deep learning model to obtain a classification result II, the control module 2 compares the classification result I with the classification result II, when the obtained classification result I is consistent with the classification result II, a final garbage classification result is obtained, and when the obtained classification result I is inconsistent with the obtained classification result II, the classification result I is selected as a final classification result;
the garbage can body 6 receives the final garbage classification result transmitted by the control module 2 and classifies the thrown garbage;
the power module 7 is a power supply provided by the control module 2, the human body induction module 1, the voice interaction module 2, the visual recognition module 4 and the visual recognition module 5;
the cloud database 7 stores the classification result I of the input garbage identified by the control module 2;
the mobile phone APP8 receives the classification result i of the garbage transmitted by the cloud database 7, the mobile phone APP8 counts the total amount of single garbage and the total amount of four types of garbage, the mobile phone APP9 is connected with the cloud server 7 through Wi-Fi, and the total amount of single garbage and the total amount of four types of garbage of the cloud database 7 are displayed on the mobile phone APP9 and the WeChat applet;
the cloud database 8 stores the classification result I of the recognized input garbage transmitted by the control module 2; sending the classification result I to a cloud database 8 through Wi-Fi every day to construct a household garbage database, wherein the cloud database 8 periodically performs big data analysis on the database;
a garbage cloud database of the community can be constructed according to the cloud databases 8 of the garbage cans of multiple families; if the proportion of a certain type of garbage in the cloud database 8 is maximum, increasing the number of classification buckets of the garbage in nearby garbage buckets; if the amount of garbage of a user in a certain house in the cloud database 8 is the largest, the garbage can be placed closer to the user.
The human body induction module 1 adopts an infrared sensor, and if a throwing person approaches the intelligent garbage can, the human body induction module 1 collects information of the infrared sensor and transmits the information to the control module 2;
the visual identification module 5 adopts a camera; selecting a public picture data set of Hua as a garbage classification match as a basic data set, and performing data training by adopting a deep neural network Resnet50 model; the camera in the visual recognition module 5 can also adopt a garbage fine type recognition technology based on computer vision and deep learning, a garbage classification image database is constructed by taking a large number of photos of different types of garbage, a deep convolutional neural network model (ResNet50) is trained, and the type (such as beverage bottles, fruits, packaging paper, plastics and the like) recognition of the garbage in the garbage box body 6 is realized by matching with an image segmentation technology in a structured environment;
the voice interaction module 3 adopts a microphone;
adopt the human-computer interaction technology based on speech recognition and natural language processing technology among the voice interaction module 3, carry out speech content recognition according to the speech signal that the microphone returned, and establish the associativity model of different sentences and instruction commonly used, thereby allow rubbish input person to interact with this dustbin with the form of pronunciation, through turning into the text with the speech signal who gathers and carry out the similarity comparison with the template, thereby assign the instruction to dustbin 6, carry out rubbish recognition, if rubbish is full in the bucket, voice interaction module 3 still can remind through reporting voice message.
The control module 2 adopts a raspberry pie, a lightweight deep learning model is embedded in the raspberry pie, the camera is used for capturing garbage pictures poured into the garbage can and feeding the images back to the deep learning model, and the deep learning model carries out reasoning operation to obtain a classification result; the raspberry group is embedded with correlation models between different vocabularies and garbage categories, the microphone is used for capturing voice signals, the raspberry group converts the received signals into texts, similarity comparison is carried out on the texts and the texts in a template, the texts are compared with a visual recognition result to obtain a final result, and then the raspberry group sends out a related control instruction.
The voice recognition module 4 adopts a garbage type recognition technology based on voice recognition and natural language processing technology, carries out voice content recognition according to voice signals returned by a microphone, and establishes a correlation model between different vocabularies and garbage categories, so as to allow a garbage thrower to inform an intelligent garbage can in a voice form, and a garbage can converts the collected voice signals into texts and compares the texts with a template for similarity comparison, and the texts are compared with a garbage classification model trained by a deep neural network Resnet50 model in a visual recognition module so as to realize garbage classification; the specific category of the currently thrown object helps to not know the garbage classification criteria, but the thrower with certain garbage classification awareness better realizes garbage classification.
FIG. 4 is an overall external view of the present invention; FIG. 5 is a front view of the present invention; FIG. 6 is a left half sectional view of the present invention; FIG. 7 is a right half sectional view of the present invention; the garbage can body 7 comprises an upper shell I10 arranged at the top and a throwing port I11 arranged on the upper shell I10 and used for throwing garbage; a peripheral housing 32 integrally connected to the upper housing i 10; a peripheral housing 12 integrally connected to the upper housing i 10; an automatic rotating upper shell II 12 arranged below the upper shell I10; the automatic cover opening and closing module 13 is arranged below the upper shell I10 and used for throwing in garbage from the throwing port I11; the automatic cover opening and closing module 13 forms a feeding opening II 14 after being opened; a sliding inlet is arranged below the putting-in port II 14,
the feeding port I12 and the feeding port II 14 are integrally connected through a shell I15; the sliding inlet and the throwing port II 14 are integrally connected through a shell II 16 to form an eccentric funnel 17; four barrel bodies 18 with the same caliber and used for storing different types of garbage are arranged below the automatic cover opening and closing module 13; the barrel body 18 is divided into four areas through vertical partitions, the four areas are provided with four barrel bodies 18, the peripheral shell 32 can not rotate, and the barrel bodies 18 can be cylinders, polygonal bodies or cuboids; the central point of the sliding inlet is arranged on the circumference formed by the four barrel bodies 18 with the same caliber.
Further, the automatic cover opening and closing module 13 comprises a bearing 19 arranged outside the lower side of the edge of the upper shell ii 12, the inner ring of the bearing 19 is fixedly connected with the upper side of the edge of the upper plane of the eccentric funnel 18, and the outer ring of the bearing 19 is fixedly connected with the upper plane of the peripheral shell 11; the middle of the outer ring and the inner ring of the bearing is filled with balls 20; the two can slide relatively, thereby ensuring that the eccentric funnel 17 can rotate relatively to the lower three-dimensional geometric center; the automatic cover opening and closing module 13 further comprises a meshing gear ring 21 connected with the lower side of the edge of the upper plane of the eccentric funnel 17; a drive gear 22 engaged with the engagement ring gear 21; a motor 23 connected to the drive gear 22; the control module 2 is connected with the motor 23, the control module 2 identifies garbage images collected by a camera, and the motor 23 is controlled to rotate according to the obtained classification result, so that the meshing gear ring 21 is driven to rotate; the motor 23 is fixed on the inner wall of the upper shell I12 through a motor bracket 24; an automatic opening and closing cover 25 connected with the upper shell I12;
FIG. 8 is a view showing the closing of the automatic opening/closing cover; FIG. 9 is a schematic view of the automatic opening and closing cover being opened; FIG. 10 is a top view of the present invention; FIG. 11 is a top view I of the present invention; FIG. 12 is a drawing of the automatic lid opening and closing apparatus of the present invention; FIG. 13 is a drawing II of the automatic lid opening and closing apparatus of the present invention; FIG. 14 is a top view II of the present invention;
the automatic opening and closing cover 25 comprises 3N sliding blocks 26, a tray frame 27 and a sliding block fixing disc 28, wherein the sliding blocks 26 are polygonal, and the 3N sliding blocks 26 are matched into a plane when being closed; wherein N is more than or equal to 2; 3N sliding grooves 29 are formed in the upper automatic opening and closing cover, each sliding groove 29 is formed in the side edge of the sliding block 26, and the 3N sliding grooves 29 correspond to the 3N sliding blocks 26 one by one; two electric cylinders 30 symmetrically arranged on the periphery of the 3N sliding blocks 26, wherein one end of each electric cylinder 30 is connected with the corresponding sliding block 26, and the other end of each electric cylinder 30 is connected with the control module 2; when N is 2, six polygonal sliding blocks 26 are symmetrically distributed between the sliding block fixing disc 28, since the tray frame 27 is provided with a matched aperture, the tray frame 27 is connected with the sliding block fixing disc 28, a layer of gap is reserved between the sliding blocks 26, two symmetrical electric cylinders 30 can be used for driving the sliding blocks 26 to move, since the six sliding blocks 26 are mutually matched, the sliding blocks move relatively together, and then the opening and closing of the automatic opening and closing cover 25 are completed, and the electric cylinders 30 are provided with electric cylinder supports 36;
further, the caliber size of the input opening I10 is larger than or equal to that of the input opening II 14;
further, four opening and closing doors 33 which are convenient for taking out the barrel body are evenly arranged on the periphery of the peripheral shell 32; a door handle 34 is arranged on the opening and closing door 33, and the door handle 34 is connected with the peripheral shell 32 through a hinge 35; FIG. 15 is a schematic view of four barrels of the present invention;
further, the garbage can further comprises a light source module 31 for providing light conditions for the visual recognition module 5, and the light source module 31 is connected with the visual recognition module 5, the control module 2 and the power module 7.
Further, the input port I11 and the input port II 14 can be round, rectangular or other multiple variants.
The working principle of the invention is that when a user approaches a garbage can within a meter, an infrared sensor can detect a human body induction signal and feed the human body induction signal back to the raspberry group control module 2, the person throwing garbage starts to perform voice interaction through a loudspeaker, at the moment, a microphone starts to collect a voice signal of the user and transmits the voice signal to the raspberry group control module 2 in real time, and a voice classification result is obtained through judgment of the control module 2; when the garbage falls into the automatic opening and closing cover 25, the light source module 31 is lightened, the camera starts to capture images and feeds the images back to the raspberry group control module 2, and the control module 2 obtains a visual classification result after calculation of a deep learning model; and integrating the two types of results, finally giving out a total classification result by a classification control algorithm, and controlling a loudspeaker to perform voice broadcast on the classification result by the raspberry group, wherein the function can be closed.
According to the total classification result, the raspberry group control module 2 sends a related control command to the automatic cover opening and closing module 13, and the related motor 23 drives the driving gear 22 to rotate, so that the eccentric funnel 17 matched with the driving gear is driven to rotate, the lower layer opening of the eccentric funnel 17 is aligned to the barrel body 18 corresponding to the classification result, the classification function of different garbage categories is realized, and the barrel body 18 is divided into four areas by two mutually vertical partition plates and can be used for accommodating circular garbage inner barrels of four types of garbage. When the eccentric funnel 17 rotates to the designated position, the control module 2 can send a control command to the electric cylinder 30 to enable the electric cylinder to contract, the sliding block 26 can slide relatively, the sliding block 26 is fixed inside the sliding block fixing disc 28, garbage on the sliding block fixing disc 28 falls into the eccentric funnel 17 and finally falls into an inner garbage barrel, accurate recognition and collection of the garbage are completed, after the action is completed, the electric cylinder 30 can extend, the sliding block 26 is drawn to slide relatively, the sliding block fixing disc 28 extends out, an automatic opening and closing cover is formed again, and the closed state of the lower barrel body is kept.
The automatic opening and closing cover 25 has two states, namely the automatic opening and closing cover 25 is closed and the automatic opening and closing cover 25 is opened, and the using process is as follows: the initial state is that the automatic opening and closing cover 25 is closed, the barrel body 18 is in a closed state, when garbage is thrown in, visual recognition is firstly carried out, after a classification result is obtained, the control module 2 sends an instruction to the motor 23 for controlling the eccentric funnel 17 to rotate, the motor is enabled to rotate to a corresponding classification area, then the automatic opening and closing cover 25 is opened, the garbage falls into the corresponding classification area, the automatic opening and closing cover 25 is closed, and the closed state of the barrel body 18 is kept.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (7)
1. The utility model provides an intelligent domestic dustbin based on machine perception is fused to multimode which characterized in that: comprises that
The human body induction module is used for inducing a person who puts garbage to obtain a human body induction signal;
the control module is used for receiving the human body induction signal transmitted by the human body induction module;
the voice interaction module receives the control signal transmitted by the control module, carries out voice communication with a person throwing the garbage and obtains a voice signal answered by the person throwing the garbage, the voice interaction module transmits the garbage voice signal answered by the person throwing the garbage to the control module, the control module converts the voice signal into a text and carries out similarity comparison with a garbage name text library, and each garbage corresponds to one category to obtain a classification result I;
the voice recognition module receives voice signals sent by the control module and answered by the voice of people who throw the garbage, and recognizes the voice signals to obtain voice signals of garbage throwing varieties, and the voice recognition module sends the obtained voice signals of the garbage throwing varieties to the control module;
the garbage classification method comprises the steps that image acquisition is carried out on thrown garbage to obtain a vision recognition module of a thrown garbage image signal, the vision recognition module transmits the obtained thrown garbage image signal to a control module, the control module carries out reasoning operation based on a lightweight deep learning model to obtain a classification result II, the control module compares the classification result I with the classification result II, when the obtained classification result I is consistent with the classification result II, a final garbage classification result is obtained, and when the obtained classification result I is inconsistent with the obtained classification result II, the classification result I is selected as a final classification result;
the garbage bin body is used for receiving the garbage classification result transmitted by the control module and classifying the thrown garbage;
the power supply module is used for supplying power to the control module, the human body induction module, the voice interaction module and the visual recognition module;
the cloud database is used for storing the classification result I of the input garbage, which is transmitted by the control module and identified by the control module;
and receiving the mobile phone APP of the classification result I of the garbage transmitted by the cloud database, and counting the total amount of the single garbage and the total amount of the four types of garbage by the mobile phone APP.
2. The intelligent household garbage can based on multi-modal fusion machine perception according to claim 1, characterized in that: the garbage can body comprises an upper shell I arranged at the top;
a feeding port I for feeding garbage is arranged on the upper shell;
a peripheral housing integrally connected with the upper housing;
an automatic rotating upper shell II arranged below the upper shell I;
an automatic cover opening and closing module for garbage thrown from the throwing port I is arranged (connected) below the upper shell I;
an automatic cover opening and closing module is arranged below the upper shell I;
the automatic cover opening and closing module forms a feeding opening II after being opened;
a sliding inlet is arranged below the putting-in port II,
the feeding port I and the feeding port II are integrally connected through a shell I;
the sliding inlet and the throwing port II are integrally connected through a shell II to form an eccentric funnel;
four barrel bodies with the same caliber and used for containing different types of garbage are arranged below the automatic cover opening and closing module;
the central point of the sliding inlet is arranged on the circumference formed by the four barrel bodies with the same caliber.
3. The intelligent household garbage can based on multi-modal fusion machine perception according to claim 1, characterized in that: the automatic opening and closing cover module comprises
A bearing is arranged outside the lower side of the edge of the automatic rotating upper shell II, the inner ring of the bearing is fixedly connected with the upper side of the edge of the upper plane of the eccentric funnel, and the outer ring of the bearing is fixedly connected with the upper plane of the peripheral shell; the middle of the outer ring and the outer ring is filled with balls;
the meshing gear ring is connected with the lower side of the edge of the upper plane of the eccentric funnel;
the driving gear is meshed with the meshing gear;
the motor is connected with the driving gear and is connected with the control module;
the automatic opening and closing cover is connected with the upper shell I and comprises 3N sliding blocks, a tray frame and a sliding block fixing disc, the tray frame is connected with the sliding block fixing disc, a layer of gaps are reserved between the tray frame and the sliding block fixing disc for placing the sliding blocks, and N is larger than or equal to 2; the 3N sliding blocks are matched into a plane when being closed;
3N sliding grooves are formed in the automatic opening and closing cover, each sliding groove is formed in the side edge of the sliding block, and the 3N sliding grooves correspond to the 3N sliding blocks one by one;
the two electric cylinders are symmetrically arranged on the periphery of the 3N sliding blocks, one end of each electric cylinder is connected with the corresponding sliding block, and the other end of each electric cylinder is connected with the control module.
4. The intelligent household garbage can based on multi-modal fusion machine perception according to claim 1, characterized in that: the caliber size of the input opening I is larger than or equal to that of the input opening II.
5. The intelligent household garbage can based on multi-modal fusion machine perception according to claim 1, characterized in that: four opening and closing doors are averagely arranged on the periphery of the peripheral shell.
6. The intelligent household garbage can based on multi-modal fusion machine perception according to claim 1, characterized in that: the vision recognition module is connected with the control module and the power module.
7. The intelligent household garbage can based on multi-modal fusion machine perception according to claim 1, characterized in that: the control module adopts a raspberry pie.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011455685.0A CN112407660A (en) | 2020-12-10 | 2020-12-10 | Intelligent household garbage can based on multi-mode fusion machine perception |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011455685.0A CN112407660A (en) | 2020-12-10 | 2020-12-10 | Intelligent household garbage can based on multi-mode fusion machine perception |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112407660A true CN112407660A (en) | 2021-02-26 |
Family
ID=74776764
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011455685.0A Pending CN112407660A (en) | 2020-12-10 | 2020-12-10 | Intelligent household garbage can based on multi-mode fusion machine perception |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112407660A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113086450A (en) * | 2021-04-16 | 2021-07-09 | 武汉理工大学 | Rotary classification garbage can |
| CN113119082A (en) * | 2021-03-18 | 2021-07-16 | 深圳市优必选科技股份有限公司 | Visual recognition circuit, visual recognition device, and robot |
| CN113335789A (en) * | 2021-05-14 | 2021-09-03 | 华南理工大学 | Integrated intelligent classification recycling dustbin and garbage classification recycling method |
| CN113859813A (en) * | 2021-10-12 | 2021-12-31 | 朱雨昕 | Artificial intelligence garbage classification system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104495139A (en) * | 2014-12-31 | 2015-04-08 | 东南大学 | Garbage dropping box and class-based dropping method of garbage |
| CN109720752A (en) * | 2019-01-28 | 2019-05-07 | 中国地质大学（武汉） | A kind of sort-type automatic shutter dustbin and its control method based on speech recognition |
| CN110255014A (en) * | 2019-08-07 | 2019-09-20 | 中竞科技有限公司 | Intelligent sound identifies automatic sorting garbage bin |
| CN110371514A (en) * | 2019-07-19 | 2019-10-25 | 蔡宏波 | One kind being based on Internet of Things intelligent sound Classification and Identification rubbish control system and method |
| CN111591622A (en) * | 2020-05-21 | 2020-08-28 | 大连海事大学 | Intelligent image voice recognition garbage can based on Internet of things |
| 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 |
| CN111959995A (en) * | 2020-08-10 | 2020-11-20 | 昆明理工大学 | Garbage classification voice interaction system based on ROS |
-
2020
- 2020-12-10 CN CN202011455685.0A patent/CN112407660A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104495139A (en) * | 2014-12-31 | 2015-04-08 | 东南大学 | Garbage dropping box and class-based dropping method of garbage |
| CN109720752A (en) * | 2019-01-28 | 2019-05-07 | 中国地质大学（武汉） | A kind of sort-type automatic shutter dustbin and its control method based on speech recognition |
| CN110371514A (en) * | 2019-07-19 | 2019-10-25 | 蔡宏波 | One kind being based on Internet of Things intelligent sound Classification and Identification rubbish control system and method |
| CN110255014A (en) * | 2019-08-07 | 2019-09-20 | 中竞科技有限公司 | Intelligent sound identifies automatic sorting garbage bin |
| CN111591622A (en) * | 2020-05-21 | 2020-08-28 | 大连海事大学 | Intelligent image voice recognition garbage can based on Internet of things |
| 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 |
| CN111959995A (en) * | 2020-08-10 | 2020-11-20 | 昆明理工大学 | Garbage classification voice interaction system based on ROS |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113119082A (en) * | 2021-03-18 | 2021-07-16 | 深圳市优必选科技股份有限公司 | Visual recognition circuit, visual recognition device, and robot |
| CN113086450A (en) * | 2021-04-16 | 2021-07-09 | 武汉理工大学 | Rotary classification garbage can |
| CN113335789A (en) * | 2021-05-14 | 2021-09-03 | 华南理工大学 | Integrated intelligent classification recycling dustbin and garbage classification recycling method |
| CN113859813A (en) * | 2021-10-12 | 2021-12-31 | 朱雨昕 | Artificial intelligence garbage classification system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112407660A (en) | Intelligent household garbage can based on multi-mode fusion machine perception | |
| CN110697273B (en) | Household garbage intelligent recognition and automatic classification system and method based on iterative learning control | |
| WO2020206862A1 (en) | Automatic sorting system | |
| CN110428019B (en) | Intelligent garbage classification method and modularized intelligent garbage classification processing system | |
| CN110316496A (en) | A kind of intelligent garbage identification sorter Internet-based | |
| CN109911451A (en) | A kind of intelligent classification dustbin based on machine vision | |
| CN110626662A (en) | Image recognition-based garbage self-classification method and device | |
| CN109305490B (en) | Intelligent classification dustbin based on image recognition technology | |
| CN111846693A (en) | Intelligent garbage classification putting supervision and control system based on real-name system | |
| CN111591622A (en) | Intelligent image voice recognition garbage can based on Internet of things | |
| WO2021179596A1 (en) | Garbage classification method and smart household appliance | |
| CN107942695A (en) | emotion intelligent sound system | |
| CN110428352A (en) | The method and modularization garbage classification system of wearable device intelligent classification rubbish | |
| CN111619992A (en) | Intelligent garbage classification system and method based on machine vision | |
| CN113335789A (en) | Integrated intelligent classification recycling dustbin and garbage classification recycling method | |
| CN110723431A (en) | Garbage classification method based on BP neural network recognition system | |
| CN112365758A (en) | Education version garbage classification method, device and system | |
| CN111874487A (en) | Environment-friendly garbage bin that possesses automatic waste classification | |
| CN111646045A (en) | Four-classification garbage can for intelligently identifying and automatically classifying garbage | |
| CN214877352U (en) | Intelligent garbage accurate classification equipment | |
| CN110155556A (en) | A kind of intelligent classification dustbin | |
| CN214297580U (en) | Intelligent garbage recognition and classification device based on internet | |
| CN117088015A (en) | Intelligent garbage disposal method, system and storage medium | |
| CN111319888A (en) | Garbage classification method suitable for triangular garbage can and triangular intelligent garbage can | |
| CN211392533U (en) | Intelligent garbage bin based on image recognition |
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: 20210226 |
|
| RJ01 | Rejection of invention patent application after publication |