CN111086796A - Perfecting method for garbage type identification and background server - Google Patents
Perfecting method for garbage type identification and background server Download PDFInfo
- Publication number
- CN111086796A CN111086796A CN201911072609.9A CN201911072609A CN111086796A CN 111086796 A CN111086796 A CN 111086796A CN 201911072609 A CN201911072609 A CN 201911072609A CN 111086796 A CN111086796 A CN 111086796A
- Authority
- CN
- China
- Prior art keywords
- garbage
- photos
- marked
- module
- user
- 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
- B65F1/14—Other constructional features; Accessories
- B65F1/1484—Other constructional features; Accessories relating to the adaptation of receptacles to carry identification means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
- B65F2210/00—Equipment of refuse receptacles
- B65F2210/138—Identification means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
- B65F2210/00—Equipment of refuse receptacles
- B65F2210/176—Sorting means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
- B65F2210/00—Equipment of refuse receptacles
- B65F2210/184—Weighing means
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Refuse Collection And Transfer (AREA)
Abstract
The invention discloses a perfecting method for identifying garbage types and a background server, wherein the perfecting method for identifying the garbage types comprises the following steps: the method comprises the steps of obtaining photos sent by a camera module, identifying the type of at least one garbage image in the photos through a garbage type identification module, and marking the garbage images of which the garbage types cannot be identified in the photos to form photos to be marked, so that a user can obtain the photos to be marked through a client, and mark the types of the garbage images of which the garbage types cannot be identified in the photos to be marked to form finished marked photos; and acquiring the finishing marking photos, taking the finishing marking photos as a training set of a garbage classification training module, and outputting training results to the garbage type identification module, so that the intelligent garbage collection box can automatically perform intelligent learning, and finally, the intelligent garbage collection box is added to identify garbage types.
Description
Technical Field
The invention relates to the field of garbage recovery, in particular to a perfecting method for garbage type identification and a background server.
Background
Along with the development of society, people's material living standard and quality level constantly promote, the classification of rubbish, retrieve and begin to get into people's daily life gradually, under the vigorous promotion of each world of society, public occasions such as some communities, schools and markets all begin to set up the intelligent garbage collection box that is used for waste classification, and various intelligent garbage collection boxes begin to appear on the market simultaneously.
However, most of the existing intelligent garbage recycling boxes still have many problems, such as the automatic classification capability of the intelligent garbage recycling boxes is low, the intelligent garbage recycling boxes cannot be matched with the increasingly improved environmental awareness of users, and the problem of wrong classification of the intelligent garbage recycling boxes often occurs.
Disclosure of Invention
In order to overcome the defects of the prior art, one of the objectives of the present invention is to provide a perfecting method for garbage type identification, which can solve the problems that the automatic classification capability of an intelligent garbage recycling bin is low and the automatic garbage type identification capability of the intelligent garbage recycling bin needs to be continuously upgraded by a worker.
The invention also aims to provide a background server, which can solve the problems that the automatic classification capability of an intelligent garbage collection box is low, and the automatic garbage type identification capability of the intelligent garbage collection box needs to be continuously upgraded by workers.
In order to achieve one of the above purposes, the technical scheme adopted by the invention is as follows:
a perfection method for identifying garbage types is applied to a background server of an intelligent garbage recycling bin, and comprises the following steps:
s1: the method comprises the steps of obtaining photos sent by a camera module, identifying the type of at least one garbage image in the photos through a garbage type identification module, and marking the garbage images of which the garbage types cannot be identified in the photos to form photos to be marked, so that a user can obtain the photos to be marked through a client, and mark the types of the garbage images of which the garbage types cannot be identified in the photos to be marked to form finished marked photos;
s2: and acquiring the finished marked photos, taking the finished marked photos as a training set of a garbage classification training module, and outputting training results to the garbage type identification module.
Preferably, intelligence garbage collection box still includes open-top's box, is used for the lid to close open-ended lid, user identification module, user are apart from identification module and be located actuating mechanism, camera module, weighing module and the garbage bin of box respectively, camera module sets up the top at the box, weighing module sets up the bottom at the box, the garbage bin is placed on the weighing module, actuating mechanism is used for the drive the lid motion, so that the opening is in and opens and close one of them state, user identification module and user are apart from identification module fixed mounting at the box outer wall, actuating mechanism, camera module, user identification module, user are apart from identification module and weighing module all are connected with backstage server.
Preferably, the driving mechanism comprises a motor, a gear set and a connecting rod which are connected with the background server, the output end of the motor is connected with the input end of the gear set, and the output end of the gear set is connected with the cover body through the connecting rod.
Preferably, the side wall of the box body is provided with a side door for allowing the garbage bin to pass through.
Preferably, the step S1 is specifically implemented by the following steps:
s11: acquiring identity information of a current user sent by a user identity identification module;
s12, sending a box opening signal to the driving mechanism to enable the driving mechanism to drive the cover body to be opened, so that the opening of the box body is in an opened state, and the garbage can in the box body receives garbage thrown by a user after bag breaking or bag breaking;
s13: acquiring a current user leaving signal sent by a user distance identification module, and sending a box closing signal to a driving mechanism to enable the driving mechanism to drive a cover body to be closed, so that an opening of a box body is in a closed state;
s14: the method comprises the steps that the weight of garbage in a garbage can at the current time is obtained through a weighing module, the weight of the garbage in the garbage can at the current time is subtracted from the weight of the garbage in the garbage can at the last time to obtain the weight of the garbage thrown by a current user, and identity information of the current user is associated with the weight of the garbage thrown by the current user and stored in a memory;
s15: shooting the garbage in the garbage can through a camera module to obtain a photo;
s16: acquiring photos sent by a camera module, identifying the type of at least one type of garbage image in the photos through a garbage type identification module, marking the garbage image of which the garbage type cannot be identified in the photos to form a photo to be marked, associating the identity information of the current user with the photo to be marked, and storing the photo to be marked in a memory;
s17: judging whether the memory has a photo to be marked of the current user, if so, executing the step S18, otherwise, executing the step S19;
s18: sending the photos to be marked to a client conforming to the operation rules so that a second user can obtain the photos to be marked through the client, marking the types of the garbage images of which the garbage types cannot be identified in the photos to be marked so as to form finished marked photos, and returning to the step S17;
s19: judging whether the type of the garbage thrown by the current user is wrong or not, if so, deleting the weight of the garbage thrown by the current user, and if not, saving the weight of the garbage thrown by the current user.
Preferably, the user identity identification module comprises a near field communication device and a voiceprint identification device, the user distance identification module is a pyroelectric device, and the near field communication device, the voiceprint identification device and the pyroelectric device are all connected with the background server.
Preferably, the step S11 is specifically implemented by the following steps:
s111: acquiring identity information of a current user sent by a near field communication device or acquiring identity information of the current user sent by a voiceprint recognition device, and sending a recognition instruction to a pyroelectric device so that the pyroelectric device can acquire a heat signal of the current user;
s112: step S12 is performed when the heat signal reaches a preset threshold.
Preferably, step S112 is followed by the following steps:
step S13 is performed when the heat signal is less than a preset threshold.
Preferably, the following steps are further performed between the step S1 and the step S2:
receiving a signal from a system administrator to modify the marking of the finish marked photograph.
In order to achieve the second purpose, the technical scheme adopted by the invention is as follows:
a background server is applied to an intelligent garbage recycling bin and comprises a processor and a memory;
a memory for storing program instructions;
and the processor is used for operating the program instructions to execute the perfect method for identifying the garbage types.
Compared with the prior art, the invention has the beneficial effects that:
1. adopt backend server to adopt the rubbish classification training module will accomplish the mark photo and as the training set, carry out analog recognition many times to improve the rate of accuracy of discerning rubbish, after the number of times of analog recognition reachs numerical value, the rate of accuracy of discerning rubbish will rise to expected value, will calculate flowsheet and weight file again and carry to rubbish kind identification module, make rubbish kind identification module can the automatic identification training concentrate the image of the rubbish that contains, thereby realize intelligent learning of intelligent rubbish collection box, increase the rubbish kind that intelligent rubbish collection box can discern.
2. The user just can leave at once after breaking the bag and throwing in rubbish, and the rubbish kind is judged and the rubbish weight of correctly throwing in automatically to intelligence rubbish collection box, avoids lining up and puts in rubbish, improves the efficiency and the user experience of putting in rubbish.
Drawings
FIG. 1 is a flow chart of a sophisticated method for garbage category identification of the present invention.
Fig. 2 is a schematic structural diagram of the intelligent garbage recycling bin of the invention.
Fig. 3 is a front view of the intelligent garbage collection box of the present invention.
Fig. 4 is a sectional view taken along the line a-a of fig. 3.
Fig. 5 is a sectional view taken along the direction B-B of fig. 3.
Fig. 6 is a sectional view taken along the direction C-C of fig. 3.
In the figure: 1-a box body; 2-a cover body; 3-a user identity identification module; 31-a near field communication device; 32-voiceprint recognition means; 4-a drive mechanism; 41-a motor; 42-gear set; 43-connecting rod; 5-a camera module; 6-a weighing module; 7-side door; 8-pyroelectric device.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
The invention will be further described with reference to the accompanying drawings and the detailed description below:
the perfecting method for garbage type identification is applied to an intelligent garbage recycling bin, and the intelligent garbage recycling bin can realize autonomous learning garbage type identification through the method, so that the garbage types which can be identified by the intelligent garbage recycling bin are continuously increased above the garbage types which can be identified by the intelligent garbage recycling bin, and the learning algorithm of the garbage type identification of the intelligent garbage recycling bin is continuously perfected, wherein a camera module 5, a weighing module 6, a driving mechanism 4, a near field communication device 31, a voiceprint identification device 32 and a pyroelectric device 8 are in data connection with a background server through the Internet of things, the background server can be a local server (a control system in the intelligent garbage recycling bin) or a cloud server, and when the background server is the cloud server, the control system in the intelligent garbage recycling bin is communicated with the cloud server through a network, the client can be an intelligent device such as a computer, a mobile phone and a tablet personal computer, and is in data connection with the background server through the internet.
The first embodiment is as follows:
as shown in fig. 1, a perfection method for identifying garbage types, which is applied to a background server of an intelligent garbage recycling bin, includes the following steps:
s1: the method comprises the steps of obtaining photos sent by a camera module 5, identifying the type of at least one type of rubbish image in the photos through a rubbish type identification module, marking the rubbish image of which the rubbish type cannot be identified in the photos to form a to-be-marked photo, enabling a user to obtain the to-be-marked photo through a client, and marking the type of the rubbish image of which the rubbish type cannot be identified in the to-be-marked photo to form a finished mark photo.
Specifically, the intelligent garbage recycling bin comprises a box body 1 with an open top, a cover body 2 used for covering the open top, a user identity recognition module 3, a user distance recognition module, and a driving mechanism 4, a camera module 5, a weighing module 6 and a garbage can which are respectively positioned in the box body 1, wherein a side door 7 used for allowing the garbage can to pass through is arranged on the side wall of the box body 1, the camera module 5 is arranged at the top of the box body 1, the weighing module 6 is arranged at the bottom of the box body 1, the garbage can is placed on the weighing module 6, one side of the cover body 2 is movably connected with one side of the open top, in the embodiment, the driving mechanism 4 is used for driving one side of the cover body 2 to rotate around one side of the open top so that the open top is in one of an open state and a closed state, and the user identity recognition module 3 and the user distance recognition module are fixedly arranged on the outer, the driving mechanism 4, the camera module 5, the user identity recognition module 3, the user distance recognition module and the weighing module 6 are all connected with the background server.
In this embodiment, the step S1 is specifically implemented by the following steps:
s11: acquiring identity information of a current user, which is sent by a user identity identification module 3; in this embodiment, the user identification module 3 is a near field communication device 31 and a voiceprint recognition device 32, the user distance recognition module is a pyroelectric device 8, and the near field communication device 31, the voiceprint recognition device 32 and the pyroelectric device 8 are all connected to a background server.
In the embodiment, if the current user is the first user, when the first user puts garbage, the first user only needs to walk to the intelligent garbage recycling bin and directly opens the bin through card punching or voice; wherein, open the case by punching the card: firstly, the identity information IC card is pre-recorded and is attached to the near field communication device 31 of the intelligent garbage recycling bin, preferably, the near field communication device 31 is an IC card reader, after the background server acquires the identity information of the first through the IC card reader, the first is identified by the pyroelectric device 8 beside the intelligent garbage recycling bin, then the background server sends a bin opening signal to the driving mechanism 4, and the background server identifies that the first is identified by the pyroelectric device 8 beside the intelligent garbage recycling bin according to the principle that: the human body is constant in temperature, when the external temperature is relatively stable, the heat released by the human body to the outside is stable, so a threshold value is preset in the background server, the threshold value is set by referring to the heat released by a normal human body to the outside, when the background server recognizes that the heat reaches the preset threshold value through the pyroelectric device 8, a person is beside the intelligent garbage recycling bin, the background server sends a bin opening signal to the driving mechanism 4, and otherwise, the background server sends a bin closing signal to the driving mechanism 4;
opening a box by voice: a says a specific unpacking word for the intelligent garbage recycling bin, for example: when the sesame opens the door, opens the door and the like, the voiceprint recognition device 32 can obtain the voiceprint of the nail from the sound of the specific unpacking word spoken by the nail and send the voiceprint of the nail to the background server, the background server finds out the identity information of the nail in the memory according to the voiceprint of the nail, the first is recognized by the heat electricity release device 8 to be beside the intelligent garbage recycling bin, and then the background server can send an unpacking signal to the driving mechanism 4.
S12, sending a box opening signal to the driving mechanism 4 to enable the driving mechanism 4 to drive the cover body 2 to be opened, so that the opening of the box body 1 is in an opened state, and the garbage can in the box body receives garbage thrown by a user after bag breaking or bag breaking; preferably, the driving mechanism 4 includes a motor 41, a gear set 42 and a connecting rod 43 connected to the backend server, an output end of the motor 41 is connected to an input end of the gear set 42, and an output end of the gear set 42 is connected to the cover 2 through the connecting rod 43.
Specifically, in this embodiment, after the driving mechanism 4 receives the box opening signal sent by the backend server, the motor 41 starts to rotate forward, and the gear set 42 enables the connecting rod 43 to push the cover body 2 covering the opening of the box body 1, so that the cover body 2 rotates around the side where the cover body 2 is hinged to the opening of the box body 1, and the opening of the box body 1 is in an open state, at this time, the first can put the garbage into the trash can of the intelligent garbage collection box, that is, the current user dumps all the garbage into the trash can of the intelligent garbage collection box at this time, the garbage must not be contained in the garbage bag, that is, the whole garbage bag cannot be put into the trash can, but the garbage bag must be untied or damaged, and the garbage in the garbage bag is completely dumped into the trash can.
S13: acquiring a current user leaving signal sent by the user distance identification module 3, and sending a box closing signal to the driving mechanism 4 so as to enable the driving mechanism to drive the cover body to be closed, so that the opening of the box body 1 is in a closed state;
specifically, in the present embodiment, the pyroelectric device 8 is kept in operation when the box opening operation is performed from the nail. When the first leaves the intelligent garbage recycling bin, namely the first leaves the range of the pyroelectric device 8 for thermal identification, the pyroelectric device 8 cannot identify the heat released by the body of the first, at the moment, the pyroelectric device 8 sends the information that the first leaves to the background server, the background server sends a closing signal to the pyroelectric device 8 after receiving the information that the first leaves, the pyroelectric device 8 stops thermal identification after receiving the closing signal, meanwhile, the background server sends a box closing signal to the driving mechanism 4, after the driving mechanism 4 receives the box closing signal sent by the background server, the motor 41 starts to rotate reversely, and the link 43 pushes the cover 2 covering the opening of the case 1 through the gear train 42, so that the cover body 2 for covering the opening of the case body 1 is rotated around the side where the cover body 2 is hinged with the opening of the case body 1, and the opening of the case body 1 is in a closed state.
S14: the method comprises the steps of obtaining the weight of garbage in a garbage can at the current time through a weighing module 6, subtracting the weight of the garbage in the garbage can at the last time from the weight of the garbage in the garbage can at the current time to obtain the weight of the garbage thrown by a current user, associating the identity information of the current user with the weight of the garbage thrown by the current user, and storing the identity information of the current user and the weight of the garbage thrown by the current user into a memory;
specifically, in this embodiment, it is assumed that after the second step of putting the garbage into the intelligent garbage collection box, the first step of putting the garbage into the intelligent garbage collection box is started. The backstage server sends the signal of closing the case to actuating mechanism 4, make 1 opening of box be in the state of closing after, the backstage server obtains the total weight of rubbish in the garbage bin after first throwing in rubbish through weighing module 6, and save to the memory, call out the total weight of rubbish in the garbage bin after second throwing in rubbish simultaneously from the memory, subtract the total weight of rubbish in the garbage bin after second throwing in rubbish with the total weight of rubbish in the garbage bin after first throwing in rubbish again, just obtain the weight of the rubbish of first throwing in this time, then associate the identity information of first with the weight of the rubbish of first throwing in this time and save to the memory.
S15: shooting the garbage in the garbage can through the camera module 5 to obtain a photo;
specifically, after the weight of the garbage thrown in the first time is obtained, the background server photographs all garbage in the garbage can through the camera module 5, and then sends corresponding photographs to the background server.
S16: the method comprises the steps of obtaining photos sent by a camera module 5, identifying the type of at least one type of garbage image in the photos through a garbage type identification module, marking the garbage images of which the garbage types cannot be identified in the photos to form photos to be marked, associating the identity information of a current user with the photos to be marked, and storing the photos to be marked in a memory;
specifically, after the background server obtains a photo of the garbage thrown into the garbage can by the first, the background server identifies the type of at least one garbage image in the photo, marks the garbage image in the photo, wherein the garbage image cannot identify the garbage type, so as to form a to-be-marked photo, and finally associates the identity information of the first with the to-be-marked photo and stores the to-be-marked photo in a memory; in this embodiment, it is assumed that the first trash is plastic bottles and eggplants, in step S15, the photos taken by the camera module 5 include images of plastic bottles and eggplants, and after the backend server obtains the photos, the trash type recognition module in the backend server recognizes the images in the photos, wherein the trash type recognition module recognizes that the plastic bottles belong to recyclable trash but cannot recognize trash types of the eggplants, so the backend server marks the images of the eggplants in the photos to form photos to be marked, and associates and stores the identity information of the first trash and the photos to be marked in the memory. It should be noted that the garbage thrown in the first time can naturally fall onto the garbage thrown in the last user, so that the garbage can be judged to belong to the garbage thrown in the first time by comparing the difference and the sameness of the two photos, that is, plastic bottles and eggplants are recognized as the garbage thrown in the first time, and the photos to be marked containing the eggplants are associated with the first time.
S17: and judging whether the photo to be marked of the current user exists in the server memory, if so, executing the step S18, and if not, executing the step S19.
Specifically, after associating the identity information of the nail with the photo to be marked and storing the associated information in the memory, the background server automatically determines whether the photo to be marked of the nail exists in the memory, if so, performs step S18, and if not, performs step S19.
S18: sending the photos to be marked to a client conforming to the operation rules so that a second user can obtain the photos to be marked through the client, marking the types of the garbage images of which the garbage types cannot be identified in the photos to be marked so as to form finished marked photos, and returning to the step S17;
specifically, the operation rule meeting is a preset rule meeting, for example, the photo to be marked may be sent according to the user registered at the latest time, or may be sent randomly to the registered user, or may be sent randomly among 100 registered users with top-ranked mark accuracy, or may be a self-order-grabbing list of the registered user. A specific example of the self-service order grabbing is that registered users are assumed to be a, b, c and d. When the background server judges that the photo to be marked associated with the first photo exists in the memory, the background server sends the photo to be marked to clients (registered users except the current user) logged in by the second and third photo servers, if the time of the acquisition signal sent by the second client is earlier than the time of the acquisition signal sent by the third client and the fourth client, the second photo to be marked is acquired preferentially, after the second photo to be marked is acquired, marking the type of the garbage according to the garbage image in the photo to change the photo to be marked into a finished mark photo, sending the finished mark photo to a background server, meanwhile, the background server judges whether the picture to be marked of the nail still exists in the memory again, and in addition, after the second photo preferentially obtains the photo to be marked, the second photo can choose to give up, and the third photo and the fourth photo are used for order grabbing, and preferentially acquiring the photo to be marked by the bit which is sent by the client and has the earlier time for acquiring the signal.
S19: judging whether the type of the garbage thrown by the current user is wrong or not, if so, deleting the weight of the garbage thrown by the current user, and if not, saving the weight of the garbage thrown by the current user.
Specifically, after the background server judges that the memory does not have the photo to be marked of the first garbage, the background server calls the garbage type which can be recovered by the pre-stored intelligent garbage collection box for recovering the first garbage from the memory, the garbage type identified by the garbage type identification module and the garbage type of the garbage image in the mark finishing photo from the memory to be compared, if the garbage type identified by the garbage type identification module or any one of the garbage types of the garbage image in the mark finishing photo does not accord with the garbage type which can be recovered by the garbage collection box, the weight of the first garbage from the first garbage is deleted, the wrong garbage from the first garbage collection box is recorded, if the weight of the first garbage from the first garbage collection box accords with the mark finishing photo, the weight of the first garbage from the first garbage collection box is continuously stored.
In the present embodiment, the following steps are also performed between step S1 and step S2:
receiving a signal from a system administrator to modify the marking of the finish marked photograph.
Specifically, in this embodiment, after the second finishes sending the marked photo to the background server, the finished marked photo is sent to the system management module, the system administrator finishes checking the mark of the marked photo, if the mark of the finished marked photo conforms to the type of the garbage displayed by the garbage image in the photo, the system administrator confirms that the check is passed, step S17 is executed again, the finished marked photo that is passed through the check is sent to the garbage classification training module, if the mark of the finished marked photo does not conform to the type of the garbage displayed by the garbage image in the photo, the system administrator confirms that the check is not passed, the system administrator modifies the mark of the finished marked photo, step S17 is executed again, and the finished marked photo that is modified by the system administrator is sent to the garbage classification training module.
In this embodiment, S2: and acquiring the finished marked photos, taking the finished marked photos as a training set of a garbage classification training module, and outputting training results to the garbage type identification module.
Specifically, after the garbage classification training module acquires the completion marking photos sent by the system management module, the completion marking photos are stored in the memory, the completion marking photos form a training set of the garbage classification training module, the garbage classification training module adopts the training set to perform multiple times of simulation recognition so as to improve the accuracy of garbage recognition, when the times of simulation recognition reach values, the accuracy of garbage recognition can rise to an expected value, and then the calculation flow graph and the weight file thereof are conveyed to the garbage type recognition module, so that the garbage type recognition module can automatically recognize the garbage types of all garbage images in the completion marking photos.
Example two:
a background server is applied to an intelligent garbage recycling bin and comprises a processor and a memory;
a memory for storing program instructions;
and the processor is used for operating the program instructions to execute the perfect method for identifying the garbage types.
Various other modifications and changes may be made by those skilled in the art based on the above-described technical solutions and concepts, and all such modifications and changes should fall within the scope of the claims of the present invention.
Claims (10)
1. A perfection method for garbage type identification is applied to a background server of an intelligent garbage recycling bin, and is characterized in that: the method comprises the following steps:
s1: the method comprises the steps of obtaining photos sent by a camera module, identifying the type of at least one garbage image in the photos through a garbage type identification module, and marking the garbage images of which the garbage types cannot be identified in the photos to form photos to be marked, so that a user can obtain the photos to be marked through a client, and mark the types of the garbage images of which the garbage types cannot be identified in the photos to be marked to form finished marked photos;
s2: and acquiring the finished marked photos, taking the finished marked photos as a training set of a garbage classification training module, and outputting training results to the garbage type identification module.
2. A sophisticated method for garbage category identification as claimed in claim 1, characterized in that: the intelligent garbage recycling bin further comprises a top opening box body, a cover used for covering the box body, an opening cover body, a user identity recognition module, a user distance recognition module and a driving mechanism, a camera module, a weighing module and a garbage bin which are respectively located in the box body, wherein the camera module is arranged at the top of the box body, the weighing module is arranged at the bottom of the box body, the garbage bin is placed on the weighing module, the driving mechanism is used for driving the cover body to move, so that the opening is in one of states of opening and closing, the user identity recognition module and the user distance recognition module are fixedly installed on the outer wall of the box body, and the driving mechanism, the camera module, the user identity recognition module, the user distance recognition module and the weighing module are all connected with a background server.
3. A perfected method for the identification of refuse types according to claim 2, characterized in that: the driving mechanism comprises a motor, a gear set and a connecting rod, wherein the motor, the gear set and the connecting rod are connected with the background server, the output end of the motor is connected with the input end of the gear set, and the output end of the gear set is connected with the cover body through the connecting rod.
4. A perfected method for the identification of refuse types according to claim 2, characterized in that: the side wall of the box body is provided with a side door for allowing the garbage can to pass through.
5. A perfected method for the identification of refuse types according to claim 2, characterized in that: the S1 is specifically realized by the following steps:
s11: acquiring identity information of a current user sent by a user identity identification module;
s12, sending a box opening signal to the driving mechanism to enable the driving mechanism to drive the cover body to be opened, so that the opening of the box body is in an opened state, and the garbage can in the box body receives garbage thrown by a user after bag breaking or bag breaking;
s13: acquiring a current user leaving signal sent by a user distance identification module, and sending a box closing signal to a driving mechanism to enable the driving mechanism to drive a cover body to be closed, so that an opening of a box body is in a closed state;
s14: the method comprises the steps that the weight of garbage in a garbage can at the current time is obtained through a weighing module, the weight of the garbage in the garbage can at the current time is subtracted from the weight of the garbage in the garbage can at the last time to obtain the weight of the garbage thrown by a current user, and identity information of the current user is associated with the weight of the garbage thrown by the current user and stored in a memory;
s15: shooting the garbage in the garbage can through a camera module to obtain a photo;
s16: acquiring photos sent by a camera module, identifying the type of at least one type of garbage image in the photos through a garbage type identification module, marking the garbage image of which the garbage type cannot be identified in the photos to form a photo to be marked, associating the identity information of the current user with the photo to be marked, and storing the photo to be marked in a memory;
s17: judging whether the memory has a photo to be marked of the current user, if so, executing the step S18, otherwise, executing the step S19;
s18: sending the photos to be marked to a client conforming to the operation rules so that a second user can obtain the photos to be marked through the client, marking the types of the garbage images of which the garbage types cannot be identified in the photos to be marked so as to form finished marked photos, and returning to the step S17;
s19: judging whether the type of the garbage thrown by the current user is wrong or not, if so, deleting the weight of the garbage thrown by the current user, and if not, saving the weight of the garbage thrown by the current user.
6. A sophisticated method for garbage category identification as per claim 5, characterized in that: the user identity identification module comprises a near field communication device and a voiceprint identification device, the user distance identification module is a pyroelectric device, and the near field communication device, the voiceprint identification device and the pyroelectric device are all connected with the background server.
7. A sophisticated method for garbage category identification as per claim 6, characterized in that: the S11 is specifically realized by the following steps:
s111: acquiring identity information of a current user sent by a near field communication device or acquiring identity information of the current user sent by a voiceprint recognition device, and sending a recognition instruction to a pyroelectric device so that the pyroelectric device can acquire a heat signal of the current user;
s112: step S12 is performed when the heat signal reaches a preset threshold.
8. A sophisticated method for garbage category identification as claimed in claim 7, characterized in that: the following steps are also included after step S112:
step S13 is performed when the heat signal is less than a preset threshold.
9. A sophisticated method for garbage category identification as claimed in claim 1, characterized in that: the following steps are also performed between the step S1 and the step S2:
receiving a signal from a system administrator to modify the marking of the finish marked photograph.
10. A background server is applied to an intelligent garbage recycling bin and is characterized by comprising a processor and a memory;
a memory for storing program instructions;
a processor for executing said program instructions to perform a perfected method for garbage category identification as claimed in any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911072609.9A CN111086796A (en) | 2019-11-05 | 2019-11-05 | Perfecting method for garbage type identification and background server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911072609.9A CN111086796A (en) | 2019-11-05 | 2019-11-05 | Perfecting method for garbage type identification and background server |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111086796A true CN111086796A (en) | 2020-05-01 |
Family
ID=70393072
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911072609.9A Pending CN111086796A (en) | 2019-11-05 | 2019-11-05 | Perfecting method for garbage type identification and background server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111086796A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112158483A (en) * | 2020-09-18 | 2021-01-01 | 安徽工业经济职业技术学院 | Automatic garbage collection, identification and classification system based on artificial intelligence |
| CN113879724A (en) * | 2021-09-23 | 2022-01-04 | 宁波大学 | Garbage classification system based on crowdsourcing intelligence |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1508535A1 (en) * | 2003-08-20 | 2005-02-23 | Bruno Perlini | Apparatus for sorted waste collection |
| CN104355017A (en) * | 2014-05-19 | 2015-02-18 | 张志勇 | Intelligent waste classifying and recovering equipment |
| CN205582078U (en) * | 2015-12-14 | 2016-09-14 | 杭州金砖环保科技有限公司 | Recoverable rubbish intelligence recovery system |
| CN106874954A (en) * | 2017-02-20 | 2017-06-20 | 佛山市络思讯科技有限公司 | The method and relevant apparatus of a kind of acquisition of information |
| CN107054937A (en) * | 2017-03-23 | 2017-08-18 | 广东数相智能科技有限公司 | A kind of refuse classification suggestion device and system based on image recognition |
| CN108082775A (en) * | 2018-01-24 | 2018-05-29 | 湖南酷陆网络科技有限公司 | Intelligent refuse classification retrieval management method and system |
| CN109292312A (en) * | 2018-09-28 | 2019-02-01 | 宁波暇客物联科技有限公司 | A kind of accessible garbage recovery device used, recycling excitation method and system |
| CN109389161A (en) * | 2018-09-28 | 2019-02-26 | 广州大学 | Rubbish identification evolutionary learning method, apparatus, system and medium based on deep learning |
| CN110053903A (en) * | 2019-04-25 | 2019-07-26 | 重庆左岸环境服务股份有限公司 | Categorized consumer waste retrieval management system and method |
| CN110119662A (en) * | 2018-03-29 | 2019-08-13 | 王胜春 | A kind of rubbish category identification system based on deep learning |
| CN110316486A (en) * | 2019-07-31 | 2019-10-11 | 罗亮 | A kind of wisdom dustbin |
-
2019
- 2019-11-05 CN CN201911072609.9A patent/CN111086796A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1508535A1 (en) * | 2003-08-20 | 2005-02-23 | Bruno Perlini | Apparatus for sorted waste collection |
| CN104355017A (en) * | 2014-05-19 | 2015-02-18 | 张志勇 | Intelligent waste classifying and recovering equipment |
| CN205582078U (en) * | 2015-12-14 | 2016-09-14 | 杭州金砖环保科技有限公司 | Recoverable rubbish intelligence recovery system |
| CN106874954A (en) * | 2017-02-20 | 2017-06-20 | 佛山市络思讯科技有限公司 | The method and relevant apparatus of a kind of acquisition of information |
| CN107054937A (en) * | 2017-03-23 | 2017-08-18 | 广东数相智能科技有限公司 | A kind of refuse classification suggestion device and system based on image recognition |
| CN108082775A (en) * | 2018-01-24 | 2018-05-29 | 湖南酷陆网络科技有限公司 | Intelligent refuse classification retrieval management method and system |
| CN110119662A (en) * | 2018-03-29 | 2019-08-13 | 王胜春 | A kind of rubbish category identification system based on deep learning |
| CN109292312A (en) * | 2018-09-28 | 2019-02-01 | 宁波暇客物联科技有限公司 | A kind of accessible garbage recovery device used, recycling excitation method and system |
| CN109389161A (en) * | 2018-09-28 | 2019-02-26 | 广州大学 | Rubbish identification evolutionary learning method, apparatus, system and medium based on deep learning |
| CN110053903A (en) * | 2019-04-25 | 2019-07-26 | 重庆左岸环境服务股份有限公司 | Categorized consumer waste retrieval management system and method |
| CN110316486A (en) * | 2019-07-31 | 2019-10-11 | 罗亮 | A kind of wisdom dustbin |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112158483A (en) * | 2020-09-18 | 2021-01-01 | 安徽工业经济职业技术学院 | Automatic garbage collection, identification and classification system based on artificial intelligence |
| CN113879724A (en) * | 2021-09-23 | 2022-01-04 | 宁波大学 | Garbage classification system based on crowdsourcing intelligence |
| CN113879724B (en) * | 2021-09-23 | 2022-08-19 | 宁波大学 | Garbage classification system based on crowdsourcing intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rabano et al. | Common garbage classification using mobilenet | |
| CN110294236B (en) | Garbage classification monitoring device and method and server system | |
| CN110428019B (en) | Intelligent garbage classification method and modularized intelligent garbage classification processing system | |
| CN104495139B (en) | Garbage dropping box and class-based dropping method of garbage | |
| CN112606796B (en) | Automatic opening and closing control method and system for vehicle trunk and vehicle | |
| CN110697273A (en) | Intelligent household garbage identification and automatic classification system and method based on iterative learning control | |
| CN106005837A (en) | Intelligent garbage throwing device and use method thereof | |
| CN107792561A (en) | A kind of sorting rubbish smartphone system and method | |
| CN111086796A (en) | Perfecting method for garbage type identification and background server | |
| CN108877035A (en) | A kind of intelligent garbage recycling cabinet and rubbish recovering method | |
| CN110606292A (en) | Automatic classification garbage can based on artificial intelligence and classification method | |
| CN110789883A (en) | Classified garbage management system, working method and intelligent classified garbage can | |
| CN110428352B (en) | Intelligent garbage classification method for wearable equipment and modularized garbage classification system | |
| CN111559588A (en) | Intelligent garbage can for classified garbage throwing and classified garbage throwing method | |
| CN111169848A (en) | Device and method for intelligently classifying and recycling garbage | |
| CN110570856A (en) | intelligent garbage can based on voice interaction auxiliary classification putting and auxiliary putting method | |
| CN112537582B (en) | Video intelligent garbage classification equipment | |
| CN110615209A (en) | Garbage classification recycling device and garbage classification recycling monitoring system | |
| CN108910340A (en) | A kind of control method and system of intelligent garbage bin | |
| CN111738118A (en) | Garbage classification management method and system based on visual recognition | |
| CN113291666A (en) | Novel intelligent classification dustbin and working method thereof | |
| CN112099500A (en) | Household intelligent garbage can based on voice control, system and control method thereof | |
| CN115564376A (en) | Garbage throwing management system and garbage storage system | |
| CN107499784A (en) | A kind of dustbin and its refuse classification monitoring system | |
| CN204210972U (en) | A kind of waste intelligent classification reclaims module |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200501 |