CN114572580A - Automatic garbage classification method based on deep learning - Google Patents
Automatic garbage classification method based on deep learning Download PDFInfo
- Publication number
- CN114572580A CN114572580A CN202210297399.9A CN202210297399A CN114572580A CN 114572580 A CN114572580 A CN 114572580A CN 202210297399 A CN202210297399 A CN 202210297399A CN 114572580 A CN114572580 A CN 114572580A
- Authority
- CN
- China
- Prior art keywords
- garbage
- placing platform
- garbage collection
- collection box
- platform
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
- B65F1/00—Refuse receptacles; Accessories therefor
- B65F1/0033—Refuse receptacles; Accessories therefor specially adapted for segregated refuse collecting, e.g. receptacles with several compartments; Combination of receptacles
- B65F2001/008—Means for automatically selecting the receptacle in which refuse should be placed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
- B65F2210/00—Equipment of refuse receptacles
- B65F2210/138—Identification means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
- B65F2210/00—Equipment of refuse receptacles
- B65F2210/184—Weighing 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)
- Physics & Mathematics (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Processing Of Solid Wastes (AREA)
Abstract
The invention provides a garbage automatic classification method based on deep learning, which utilizes a placing platform to carry out image acquisition and analysis on thrown garbage so as to determine the type of the garbage and carry out adaptive drying operation on the garbage; according to the judgment result of the type of the garbage, the steering engine is instructed to adjust the posture of the placement platform, the placement platform is aligned to the garbage collection box matched with the garbage type, the vibration motor is also instructed to drive the placement platform to vibrate, the garbage automatically vibrates and slides down from the placement platform to enter the garbage collection box, accurate classification can be refined for each piece of the thrown garbage, and the garbage is thrown into the appropriate garbage collection box, the garbage classification process does not need manual participation, comprehensive and reliable classification treatment can be carried out on all the garbage, the garbage classification device can be widely applied to occasions of mass garbage classification, and the efficiency of garbage classification is improved.
Description
Technical Field
The invention relates to the technical field of waste treatment, in particular to a garbage automatic classification method based on deep learning.
Background
Garbage classification has become an indispensable link of garbage disposal. According to the type of the substances contained in the garbage, the garbage is classified and processed, the garbage can be accurately subdivided, the available resources in the garbage can be recovered in a targeted mode, and the garbage of different types can be processed at appropriate tail ends. The existing garbage classification treatment is realized by manually screening one by one, so that the garbage classification is finished by consuming larger manpower and material resource time, and meanwhile, the comprehensive and reliable classification treatment on all the garbage cannot be ensured.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a garbage automatic classification method based on deep learning, which utilizes a placing platform to carry out image acquisition and analysis on the placed garbage so as to determine the type of the garbage and carry out adaptive drying operation on the garbage; according to the judgment result of the type of the garbage, the steering engine is instructed to adjust the posture of the placement platform, the placement platform is aligned to the garbage collection box matched with the garbage type, the vibration motor is instructed to drive the placement platform to vibrate, the garbage automatically vibrates and slides from the placement platform to enter the garbage collection box, each piece of thrown garbage can be classified accurately in a refined mode, and the garbage is thrown into a proper garbage collection box.
The invention provides a garbage automatic classification method based on deep learning, which comprises the following steps:
step S1, collecting images of the garbage thrown on a placing platform, analyzing the images, and judging the garbage type of the garbage; adjusting the drying operation state of the garbage according to the judgment result of the garbage type;
step S2, after the drying operation of the garbage is finished, according to the judgment result of the garbage type, a steering engine positioned in the placing platform is indicated to adjust the posture of the placing platform, so that the placing platform is aligned with the garbage collection box matched with the garbage type;
step S3, collecting the pressure data currently applied to the garbage carrying surface of the placing platform after the posture of the placing platform is adjusted; according to the pressure data, a vibration motor positioned in the placing platform is indicated to drive the placing platform to vibrate, so that the garbage is automatically vibrated and slid from the garbage carrying surface into the garbage collection box;
and step S4, collecting the current garbage collection amount of the garbage collection box, and controlling the working state of the placing platform according to the garbage collection amount.
Further, in step S1, collecting an image of the garbage deposited on the placement platform, analyzing the image, and determining the garbage type to which the garbage belongs specifically includes:
performing binocular shooting on the garbage thrown on the placing platform to obtain a garbage binocular image;
generating a corresponding garbage three-dimensional image according to the binocular parallax of the garbage binocular image;
and carrying out deep learning analysis processing on the three-dimensional image of the garbage, and judging whether the garbage belongs to kitchen garbage, recoverable garbage, toxic and harmful garbage, unrecoverable garbage or other garbage which cannot be classified.
Further, in step S1, the adjusting the drying operation state of the garbage according to the judgment result of the garbage type specifically includes:
when the garbage belongs to kitchen garbage, performing hot air drying operation on the garbage, and acquiring an infrared image of the garbage; analyzing and processing the infrared image to determine the real-time water content of the garbage; stopping the hot air drying operation until the real-time water content is less than or equal to a preset water content threshold value;
and when the garbage does not belong to kitchen garbage, performing hot air drying operation on the garbage.
Further, in step S2, after the drying operation on the garbage is completed, according to the determination result of the garbage type, instructing a steering engine located inside the placing platform to adjust the posture of the placing platform, so that the aligning of the placing platform and the garbage collection box matched with the garbage type specifically includes:
after the drying operation of the garbage is finished, a steering engine positioned in the placing platform is indicated to adjust the pitching angle of the placing platform according to the judgment result of the garbage type by using the following formula (1),
in the formula (1), θ (t) represents a corresponding pitch direction angle of the steering engine after the platform is adjusted at the current moment t; t represents the current time; b (t) represents a judgment result value of the garbage type at the current time t, and when b (t) is 0,1,2,3,4, the judgment result value corresponds to other garbage which cannot be classified, kitchen garbage, recyclable garbage, toxic and harmful garbage or unrecoverable garbage; when theta (t) is 288 degrees, 0 degrees, 72 degrees, 144 degrees or 216 degrees, the placing platform is adjusted by the steering engine to be respectively obliquely aligned with other non-classifiable garbage collection boxes, kitchen garbage collection boxes, recyclable garbage collection boxes, toxic and harmful garbage collection boxes or non-recyclable garbage collection boxes.
Further, in step S2, according to the pressure data, instructing a vibration motor located inside the placing platform to drive the placing platform to vibrate, so that the step of automatically vibrating and sliding the garbage from the garbage carrying surface into the garbage collection box specifically includes:
determining the vibration frequency of the vibration motor for driving the placing platform to vibrate according to the pressure data by using the following formula (2),
in the above formula (2), f (t) represents the vibration frequency of the vibration motor driving the placing platform to vibrate at the current time t; fz(t) the pressure value of the garbage carrying surface of the placing platform is acquired at the current moment t; fmaxRepresenting a maximum pressure value that the placement platform can withstand; f. ofmaxRepresenting a maximum vibration frequency of the vibration motor; f. ofminRepresenting a minimum vibration frequency of the vibration motor;
and instructing the vibration motor to drive the placing platform to vibrate at the vibration frequency f (t), so that the garbage is automatically vibrated and slides down from the garbage carrying surface into the garbage collection box.
Further, in step S3, the method further includes:
collecting pressure data received by the bottom of the garbage collection box, adjusting the working states of the steering engine and the vibration motor by using the following formula (3),
in the above formula (3), e (t) represents a control value of the operating state of the steering engine and the vibration motor at the present time; fc(t) the pressure value applied to the bottom of the garbage collection box is acquired at the current moment; fc(t0) Denotes t0Constantly acquiring the pressure value applied to the bottom of the garbage collection box; t is t0Representing the initial moment of each piece of rubbish put on the placing platform; fz(t0) Represents t0Constantly acquiring the pressure value borne by the garbage bearing surface of the placing platform;
when E (t) is 0, indicating that the steering engine is not reset at the current moment, and indicating the vibration motor to continuously drive the placing platform to vibrate;
and when E (t) is 1, indicating that the steering engine is instructed to perform reset operation at the current moment so as to enable the placing platform to recover to a horizontal posture and instruct the vibration motor to stop working.
Further, in step S4, the collecting the current garbage collection amount of the garbage collection box, and controlling the working state of the placing platform according to the garbage collection amount specifically includes:
collecting the current total garbage collection weight of the garbage collection box, and comparing the total garbage collection weight with a preset threshold value; if the total garbage collection weight is smaller than a preset threshold value, keeping the working state of the steering engine and the vibration motor continuously acting on the placing platform unchanged; and if the total weight of the garbage collection is greater than or equal to a preset threshold value, indicating the placing platform to be in a locking state, so that the steering engine and the vibration motor cannot act on the placing platform.
Further, in step S4, the method further includes:
if the total garbage collection weight is larger than or equal to a preset threshold value, instructing a mobile terminal in the placement platform to send a garbage disposal notification message to a garbage disposal platform control center; wherein the garbage disposal notification message comprises the position information of the placement platform and the current garbage collection total weight information of the garbage collection box.
Compared with the prior art, the automatic garbage classification method based on deep learning utilizes the placement platform to perform image acquisition and analysis on the placed garbage so as to determine the type of the garbage and perform adaptive drying operation on the garbage; according to the judgment result of the type of the garbage, the steering engine is instructed to adjust the posture of the placement platform, the placement platform is aligned to the garbage collection box matched with the garbage type, the vibration motor is also instructed to drive the placement platform to vibrate, the garbage automatically vibrates and slides down from the placement platform to enter the garbage collection box, accurate classification can be refined for each piece of the thrown garbage, and the garbage is thrown into the appropriate garbage collection box, the garbage classification process does not need manual participation, comprehensive and reliable classification treatment can be carried out on all the garbage, the garbage classification device can be widely applied to occasions of mass garbage classification, and the efficiency of garbage classification is improved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings 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 of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of the automatic garbage classification method based on deep learning according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flow chart of an automatic garbage classification method based on deep learning according to an embodiment of the present invention. The garbage automatic classification method based on deep learning comprises the following steps:
step S1, collecting images of the garbage thrown on the placing platform, analyzing the images, and judging the garbage type of the garbage; adjusting the drying operation state of the garbage according to the judgment result of the garbage type;
step S2, after the garbage is dried, according to the judgment result of the garbage type, a steering engine positioned in the placing platform is indicated to adjust the posture of the placing platform, so that the placing platform is aligned with the garbage collection box matched with the garbage type;
step S3, collecting the pressure data currently applied to the garbage carrying surface of the placing platform after the posture adjustment of the placing platform is completed; according to the pressure data, indicating a vibration motor positioned in the placing platform to drive the placing platform to vibrate, so that the garbage automatically vibrates and slides from the garbage bearing surface into the garbage collection box;
step S4, collecting the current garbage collection amount of the garbage collection box, and controlling the working state of the placing platform according to the garbage collection amount.
The beneficial effects of the above technical scheme are: the automatic garbage classification method based on deep learning utilizes a placing platform to carry out image acquisition and analysis on the placed garbage so as to determine the type of the garbage and carry out adaptive drying operation on the garbage; according to the judgment result of the type of the garbage, the steering engine is instructed to adjust the posture of the placement platform, the placement platform is aligned to the garbage collection box matched with the garbage type, the vibration motor is also instructed to drive the placement platform to vibrate, the garbage automatically vibrates and slides down from the placement platform to enter the garbage collection box, accurate classification can be refined for each piece of the thrown garbage, and the garbage is thrown into the appropriate garbage collection box, the garbage classification process does not need manual participation, comprehensive and reliable classification treatment can be carried out on all the garbage, the garbage classification device can be widely applied to occasions of mass garbage classification, and the efficiency of garbage classification is improved.
Preferably, in step S1, the collecting step collects an image of the garbage deposited on the placing platform, and the analyzing step analyzes the image, and the determining the type of the garbage includes:
performing binocular shooting on the garbage thrown on the placing platform to obtain a garbage binocular image;
generating a corresponding garbage three-dimensional image according to the binocular parallax of the garbage binocular image;
and carrying out deep learning analysis processing on the three-dimensional image of the garbage, and judging whether the garbage belongs to kitchen garbage, recoverable garbage, toxic and harmful garbage, unrecoverable garbage or other garbage which cannot be classified.
The beneficial effects of the above technical scheme are: after the garbage is thrown to the placing platform, binocular cameras shoot the garbage in a binocular mode to obtain corresponding binocular images of the garbage, and then binocular parallax of the binocular images of the garbage is calculated, so that corresponding three-dimensional images of the garbage are obtained. Then, the three-dimensional garbage image is input into a deep learning model for deep learning analysis processing, the deep learning model comprises image big data of different types of garbage, and the garbage on the placing platform can be divided into kitchen garbage, recoverable garbage, toxic and harmful garbage, unrecoverable garbage or other garbage which cannot be classified in a refining mode through the deep learning analysis processing, so that the accuracy of automatic classification and identification of the garbage is improved.
Preferably, in step S1, the adjusting the drying operation state of the garbage according to the judgment result of the garbage type specifically includes:
when the garbage belongs to kitchen garbage, performing hot air drying operation on the garbage, and acquiring an infrared image of the garbage; analyzing and processing the infrared image to determine the real-time water content of the garbage; stopping the hot air drying operation until the real-time water content is less than or equal to a preset water content threshold;
when the garbage does not belong to kitchen garbage, hot air drying operation is not performed on the garbage.
The beneficial effects of the above technical scheme are: when rubbish on the placing platform belongs to kitchen garbage, the rubbish contains more moisture, and the adhesion between rubbish and the placing platform surface is great this moment, if direct drive placing platform slope and vibration are difficult to make rubbish automatic landing to garbage collection box. At this moment, to the infrared image of collection and analysis rubbish to confirm the real-time water content of rubbish, carry out hot air drying to rubbish simultaneously and handle, with the water content that reduces rubbish, until the real-time water content of rubbish is less than or equal to and predetermines the water content threshold value, can carry out abundant dehydration to rubbish like this, avoid rubbish to adhere to and can't freely fall on placement platform's the surface.
Preferably, in step S2, after the drying operation on the garbage is completed, according to the determination result of the garbage type, the steering engine inside the placing platform is instructed to adjust the posture of the placing platform, so that the aligning of the placing platform and the garbage collection box matched with the garbage type specifically includes:
after the drying operation of the garbage is finished, the steering engine positioned in the placing platform is indicated to adjust the pitching angle of the placing platform according to the judgment result of the garbage type by using the following formula (1),
in the formula (1), θ (t) represents the corresponding pitch direction angle of the steering engine after the steering engine adjusts the placing platform at the current moment t; t represents the current time; b (t) represents the determination result value of the garbage type at the current time t, and when b (t) is 0,1,2,3,4, b (t) corresponds to other garbage which cannot be classified, kitchen garbage, recyclable garbage, toxic and harmful garbage or unrecoverable garbage; when theta (t) is 288 degrees, 0 degrees, 72 degrees, 144 degrees or 216 degrees, the placing platform is adjusted by the steering engine to be respectively obliquely aligned with other non-classifiable garbage collection boxes, kitchen garbage collection boxes, recyclable garbage collection boxes, toxic and harmful garbage collection boxes or non-recyclable garbage collection boxes.
The beneficial effects of the above technical scheme are: utilize above-mentioned formula (1), according to the judged result of this rubbish type, instruct the steering wheel that is located this place the platform inside to adjust this place the platform's gesture to make this place the platform align with the garbage collection box that this rubbish type matches, place the platform can incline to the garbage collection box that matches like this, guarantee that the rubbish on follow-up place the platform surface can aim at corresponding garbage collection box landing, improve rubbish automatic classification's reliability.
Preferably, in step S2, instructing a vibration motor located inside the placing platform to drive the placing platform to vibrate according to the pressure data, so that the automatically vibrating and sliding the garbage from the garbage carrying surface into the garbage collection box specifically includes:
determining the vibration frequency of the placing platform driven by the vibration motor to vibrate according to the pressure data by using the following formula (2),
in the above formula (2), f (t) represents the vibration frequency of the vibration motor driving the placing platform to vibrate at the current time t; fz(t) the pressure value of the garbage carrying surface of the placing platform is acquired at the current moment t; fmaxRepresents the maximum pressure value that the placing platform can bear; f. ofmaxRepresents a maximum vibration frequency of the vibration motor; f. ofminRepresents a minimum vibration frequency of the vibration motor;
and instructing the vibration motor to drive the placing platform to vibrate at the vibration frequency f (t), so that the garbage is automatically vibrated and slides down from the garbage carrying surface into the garbage collection box.
The beneficial effects of the above technical scheme are: utilize above-mentioned formula (2), according to the current pressure data that receives of place the platform's rubbish loading end, control vibrating motor drive place the platform and carry out the vibration frequency of vibration, guarantee like this through the vibration mode that tiny rubbish can both be jolted to the garbage collection case by the vibration, avoid the rubbish adhesion to adhere to on place the platform surface.
Preferably, in step S3, the method further includes:
collecting pressure data received by the bottom of the garbage collection box, adjusting the working states of the steering engine and the vibration motor by using the following formula (3),
in the above formula (3), e (t) represents a control value of the operating states of the steering engine and the vibration motor at the present time; fc(t) the pressure value received by the bottom of the garbage collection box is acquired at the current moment; fc(t0) Represents t0Constantly acquiring the pressure value applied to the bottom of the garbage collection box; t is t0Representing the initial moment of each piece of rubbish put on the placing platform; fz(t0) Represents t0Constantly acquiring the pressure value of the garbage carrying surface of the placing platform;
when E (t) is 0, indicating that the steering engine is not reset at the current moment, and indicating the vibration motor to continuously drive the placing platform to vibrate;
and when E (t) is 1, indicating that the steering engine is instructed to reset at the current moment so as to enable the placing platform to recover to the horizontal posture and instruct the vibration motor to stop working.
The beneficial effects of the above technical scheme are: by utilizing the formula (3), the stop of the vibration motor and the homing of the steering engine are controlled according to the pressure data received at the bottom of the garbage collection box, so that the vibration of the vibration motor can be stopped and the steering engine can be homed after the garbage enters the corresponding garbage collection box, and the reliable identification and subsequent control of the next garbage can be ensured.
Preferably, in step S4, the collecting the current garbage collection amount of the garbage collection box, and controlling the working state of the placing platform according to the garbage collection amount specifically includes:
collecting the current total garbage collection weight of the garbage collection box, and comparing the total garbage collection weight with a preset threshold value; if the total garbage collection weight is smaller than a preset threshold value, keeping the working state of the steering engine and the vibration motor continuously acting on the placing platform unchanged; if the total weight of the garbage collection is larger than or equal to the preset threshold value, the placing platform is indicated to be in a locking state, and therefore the steering engine and the vibration motor cannot act on the placing platform.
The beneficial effects of the above technical scheme are: when the current total garbage collection weight of the garbage collection box is smaller than a preset threshold value, the garbage collection box can still continue to collect garbage, and at the moment, the steering engine and the vibration motor are kept to continue to change the inclined posture of the placing platform and drive the placing platform to vibrate according to the throwing state of the garbage on the placing platform. When the total current garbage collection weight of the garbage collection box is larger than or equal to the preset threshold value, the garbage collection box is indicated to be in a garbage storage full-scale state, the placing platform is indicated to be in a locking state, and the steering engine and the vibration motor cannot act on the placing platform, so that the placing platform is prevented from continuously throwing garbage into the garbage collection box.
Preferably, in step S4, the method further includes:
if the total garbage collection weight is greater than or equal to a preset threshold value, indicating the mobile terminal in the placement platform to send a garbage disposal notification message to a garbage disposal platform control center; wherein the garbage disposal notification message includes the location information of the placement platform and the current garbage collection total weight information of the garbage collection box.
The beneficial effects of the above technical scheme are: when the total current garbage collection weight of the garbage collection box is larger than or equal to the preset threshold value, the garbage collection box is indicated to be in a garbage storage full-scale state, at the moment, the mobile terminal inside the placing platform is indicated to send a garbage disposal notification message to the garbage disposal platform control center, and therefore the garbage of the garbage collection box can be cleaned in time.
According to the contents of the embodiment, the automatic garbage classification method based on deep learning utilizes the placing platform to perform image acquisition and analysis on the placed garbage, so as to determine the type of the garbage and perform adaptive drying operation on the garbage; according to the judgment result of the type of the garbage, the steering engine is instructed to adjust the posture of the placement platform, the placement platform is aligned to the garbage collection box matched with the garbage type, the vibration motor is also instructed to drive the placement platform to vibrate, the garbage automatically vibrates and slides down from the placement platform to enter the garbage collection box, accurate classification can be refined for each piece of the thrown garbage, and the garbage is thrown into the appropriate garbage collection box, the garbage classification process does not need manual participation, comprehensive and reliable classification treatment can be carried out on all the garbage, the garbage classification device can be widely applied to occasions of mass garbage classification, and the efficiency of garbage classification is improved.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (8)
1. The automatic garbage classification method based on deep learning is characterized by comprising the following steps of:
step S1, collecting images of the garbage thrown on a placing platform, analyzing the images, and judging the garbage type of the garbage; adjusting the drying operation state of the garbage according to the judgment result of the garbage type;
step S2, after the drying operation of the garbage is finished, according to the judgment result of the garbage type, a steering engine positioned in the placing platform is indicated to adjust the posture of the placing platform, so that the placing platform is aligned with the garbage collection box matched with the garbage type;
step S3, collecting the pressure data currently applied to the garbage carrying surface of the placing platform after the posture of the placing platform is adjusted; according to the pressure data, a vibration motor positioned in the placing platform is indicated to drive the placing platform to vibrate, so that the garbage is automatically vibrated and slid from the garbage carrying surface into the garbage collection box;
and step S4, collecting the current garbage collection amount of the garbage collection box, and controlling the working state of the placing platform according to the garbage collection amount.
2. The automatic garbage classification method based on deep learning of claim 1, characterized in that: in step S1, collecting images of the trash placed on the placement platform, analyzing the images, and determining the type of the trash specifically includes:
performing binocular shooting on the garbage thrown on the placing platform to obtain a garbage binocular image;
generating a corresponding garbage three-dimensional image according to the binocular parallax of the garbage binocular image;
and carrying out deep learning analysis processing on the three-dimensional image of the garbage, and judging whether the garbage belongs to kitchen garbage, recoverable garbage, toxic and harmful garbage, unrecoverable garbage or other garbage which cannot be classified.
3. The automatic garbage classification method based on deep learning of claim 2, characterized in that: in step S1, the adjusting the drying operation state of the garbage according to the judgment result of the garbage type specifically includes:
when the garbage belongs to kitchen garbage, performing hot air drying operation on the garbage, and acquiring an infrared image of the garbage; analyzing and processing the infrared image to determine the real-time water content of the garbage; stopping the hot air drying operation until the real-time water content is less than or equal to a preset water content threshold value;
and when the garbage does not belong to kitchen garbage, performing hot air drying operation on the garbage.
4. The automatic garbage classification method based on deep learning of claim 3, wherein: in step S2, after the drying operation on the garbage is completed, according to the determination result of the garbage type, the steering engine located inside the placing platform is instructed to adjust the posture of the placing platform, so that the aligning of the placing platform and the garbage collection box matched with the garbage type specifically includes:
after the drying operation of the garbage is finished, a steering engine positioned in the placing platform is indicated to adjust the pitching angle of the placing platform according to the judgment result of the garbage type by using the following formula (1),
in the formula (1), θ (t) represents a corresponding pitch direction angle of the steering engine after the platform is adjusted at the current moment t; t represents the current time; b (t) represents a judgment result value of the garbage type at the current time t, and when b (t) is 0,1,2,3,4, the judgment result value corresponds to other garbage which cannot be classified, kitchen garbage, recyclable garbage, toxic and harmful garbage or unrecoverable garbage; when theta (t) is 288 degrees, 0 degrees, 72 degrees, 144 degrees or 216 degrees, the placing platform is adjusted by the steering engine to be respectively obliquely aligned with other non-classifiable garbage collection boxes, kitchen garbage collection boxes, recyclable garbage collection boxes, toxic and harmful garbage collection boxes or non-recyclable garbage collection boxes.
5. The automatic garbage classification method based on deep learning of claim 4, wherein: in step S2, according to the pressure data, instructing a vibration motor located inside the placing platform to drive the placing platform to vibrate, so that the step of automatically vibrating and sliding the garbage from the garbage carrying surface into the garbage collection box specifically includes:
determining the vibration frequency of the vibration motor for driving the placing platform to vibrate according to the pressure data by using the following formula (2),
in the above formula (2), f (t) represents the vibration frequency of the vibration motor driving the placing platform to vibrate at the current time t; fz(t) the pressure value of the garbage bearing surface of the placing platform is acquired at the current moment t; fmaxRepresents the maximum pressure value that the placing platform can bear;fmaxRepresenting a maximum vibration frequency of the vibration motor; f. ofminRepresenting a minimum vibration frequency of the vibration motor;
and instructing the vibration motor to drive the placing platform to vibrate at the vibration frequency f (t), so that the garbage is automatically vibrated and slid from the garbage carrying surface into the garbage collection box.
6. The automatic garbage classification method based on deep learning of claim 5, wherein: in step S3, the method further includes:
collecting pressure data received by the bottom of the garbage collection box, adjusting the working states of the steering engine and the vibration motor by using the following formula (3),
in the formula (3), e (t) represents a control value of the operating state of the steering engine and the vibration motor at the current time; fc(t) the pressure value received by the bottom of the garbage collection box is acquired at the current moment; fc(t0) Represents t0Constantly acquiring the pressure value applied to the bottom of the garbage collection box; t is t0Representing the initial moment of each piece of rubbish put on the placing platform; fz(t0) Denotes t0Constantly acquiring the pressure value borne by the garbage bearing surface of the placing platform;
when E (t) is 0, indicating that the steering engine is not reset at the current moment, and indicating the vibration motor to continuously drive the placing platform to vibrate;
and when E (t) is 1, indicating that the steering engine is instructed to perform reset operation at the current moment so as to enable the placing platform to recover to the horizontal posture and instruct the vibration motor to stop working.
7. The automatic garbage classification method based on deep learning of claim 6, wherein: in step S4, the collecting the current garbage collection amount of the garbage collection box, and controlling the working state of the placing platform according to the garbage collection amount specifically includes:
collecting the current total garbage collection weight of the garbage collection box, and comparing the total garbage collection weight with a preset threshold value; if the total garbage collection weight is smaller than a preset threshold value, keeping the working state of the steering engine and the vibration motor continuously acting on the placing platform unchanged; and if the total weight of the garbage collection is greater than or equal to a preset threshold value, indicating the placing platform to be in a locking state, so that the steering engine and the vibration motor cannot act on the placing platform.
8. The automatic garbage classification method based on deep learning of claim 7, wherein: in step S4, the method further includes:
if the total garbage collection weight is larger than or equal to a preset threshold value, instructing a mobile terminal in the placement platform to send a garbage disposal notification message to a garbage disposal platform control center; wherein the garbage disposal notification message comprises the position information of the placement platform and the current garbage collection total weight information of the garbage collection box.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210297399.9A CN114572580A (en) | 2022-03-24 | 2022-03-24 | Automatic garbage classification method based on deep learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210297399.9A CN114572580A (en) | 2022-03-24 | 2022-03-24 | Automatic garbage classification method based on deep learning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114572580A true CN114572580A (en) | 2022-06-03 |
Family
ID=81776966
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210297399.9A Pending CN114572580A (en) | 2022-03-24 | 2022-03-24 | Automatic garbage classification method based on deep learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114572580A (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110562646A (en) * | 2019-09-09 | 2019-12-13 | 重庆懿熙品牌策划有限公司 | Put in case and categorised recovery system of rubbish thereof |
CN112141563A (en) * | 2020-10-26 | 2020-12-29 | 孙益博 | Garbage classification and recovery device |
CN212449013U (en) * | 2019-12-17 | 2021-02-02 | 科大讯飞股份有限公司 | Garbage classification system |
CN113335789A (en) * | 2021-05-14 | 2021-09-03 | 华南理工大学 | Integrated intelligent classification recycling dustbin and garbage classification recycling method |
-
2022
- 2022-03-24 CN CN202210297399.9A patent/CN114572580A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110562646A (en) * | 2019-09-09 | 2019-12-13 | 重庆懿熙品牌策划有限公司 | Put in case and categorised recovery system of rubbish thereof |
CN212449013U (en) * | 2019-12-17 | 2021-02-02 | 科大讯飞股份有限公司 | Garbage classification system |
CN112141563A (en) * | 2020-10-26 | 2020-12-29 | 孙益博 | Garbage classification and recovery device |
CN113335789A (en) * | 2021-05-14 | 2021-09-03 | 华南理工大学 | Integrated intelligent classification recycling dustbin and garbage classification recycling method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110516570B (en) | Vision-based garbage classification and identification method and device | |
CN110884791A (en) | Vision garbage classification system and classification method based on TensorFlow | |
CN110001875B (en) | Water surface robot for cleaning and classifying water surface garbage and classified salvaging method | |
CN110053903B (en) | Household garbage classification and recovery management system and method | |
CN110861852A (en) | Automatic classification garbage can based on visual identification and classification method | |
CN109703939A (en) | Intelligent garbage recovery system and method | |
CN112777169B (en) | Internet of things monitoring method and system applied to garbage classification putting points | |
CN105564864A (en) | Garbage can, garbage sorting method for garage can and garbage sorting system for garage can | |
CN109987364A (en) | A kind of New Intelligent Garbage Can and its control method | |
CN110589282A (en) | Intelligent garbage classification method based on machine learning and automatic garbage sorting device | |
CN117085970B (en) | Multi-class solid waste recycling intelligent system based on AI (advanced technology attachment) identification | |
CN110516625A (en) | A kind of method, system, terminal and the storage medium of rubbish identification classification | |
CN114572580A (en) | Automatic garbage classification method based on deep learning | |
CN113319007A (en) | Household garbage sorting method based on machine vision recognition | |
CN211392481U (en) | Image recognition big data-based garbage classification system | |
CN113859803A (en) | Intelligent identification trash can and intelligent identification method thereof | |
CN111137602B (en) | Garbage classification method and garbage classification system based on artificial intelligence | |
CN113850124A (en) | Recoverable garbage supervision method, transportation equipment and storage medium | |
CN218691566U (en) | Intelligent sorting device based on machine vision and control system | |
CN112455614A (en) | Water surface garbage collection and classification device, control method and garbage cleaning ship | |
CN215708916U (en) | Intelligent recognition garbage can | |
CN109911465A (en) | A kind of rubbish from cooking collecting device and method | |
CN115026015A (en) | Ground rubbish detection system based on image processing | |
CN112291547B (en) | Impurity removal system with image recognition function | |
CN210150022U (en) | Kitchen waste collecting device |
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 |