CN110503008A - Intelligent human-face identification and garbage classification system based on deep learning - Google Patents
Intelligent human-face identification and garbage classification system based on deep learning Download PDFInfo
- Publication number
- CN110503008A CN110503008A CN201910716095.XA CN201910716095A CN110503008A CN 110503008 A CN110503008 A CN 110503008A CN 201910716095 A CN201910716095 A CN 201910716095A CN 110503008 A CN110503008 A CN 110503008A
- Authority
- CN
- China
- Prior art keywords
- rubbish
- image
- garbage classification
- deep learning
- system based
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses Intelligent human-face identifications and garbage classification system based on deep learning, acquisition including rubbish image → detection of rubbish image category identifies → stores rubbish, video flowing is acquired to rubbish by the camera of rubbish storage door surfaces, identification, which is carried out, by image of the picture recognition device to rubbish judges whether object occur in image frame, image is resurveyed on last stage if returning without if, whether picture is analyzed and determined comprising acceptable rubbish if there is object, user is prompted not handle such rubbish if not including, image capture device is acquired face information after determining acceptable rubbish.The phenomenon that present invention carries out identification classification to rubbish by video image acquisition technology, keeps the processing of rubbish more intelligent, solves garbage classification managerial confusion on existing market, and beneficial and Harmful Waste are mixed to be put, difficult management, post-processing wastes vast resources.
Description
Technical field
The present invention relates to field of refuse classification, Intelligent human-face identification and garbage classification specially based on deep learning
System.
Background technique
Unordered, product standard missing that there are recovery systems in China regenerated resources field, backward in technique etc. are multiple to keep in check, a side
Face, a large amount of renewable resources are taken as garbage disposal to fall, such as waste top-pop, waste spinning fabric;On the other hand, a large amount of harmful rubbish
Rubbish is to be taken as conventional rubbish, without carrying out appropriate processing, causes environmental pollution, garbage classification socially causes extensively
General attention, many cells all come into effect garbage classification, and country is even more to have put into a large amount of manpower and material resources to remove production sorting rubbish
Case, the other resident in side carry out garbage classification, have also appeared intelligent classification dustbin.
In garbage reclamation and classification field, be broadly divided into Three models: the first mode be rubbish go-no-go factory it is unified into
Row is selected, and belongs to manual sort, after having collected all rubbish, factory is uniformly selected in rubbish go-no-go, defect: due to concentrating
It uniformly selects, the carrying transfer of rubbish takes time and effort, and treatment effeciency is low.
Second of mode is to punish class in source, most common is exactly in traditional dustbin using cabinet classification garbage can
Structurally, it adds as two cabinets, different colours or " recyclable rubbish ", " not recyclable rubbish " printed words and mark can be used
Distinguish rubbish, it is convenient directly to classify when recycling rubbish later, it class is punished in source, eliminates extreme portions to rubbish
The process sorted is the leap mark the nineties on one object of dustbin, with very big realistic meaning and conveniently
Property, defect: on the one hand, if depend on the self-consciousness of resident mostly to sorting rubbish, quite a few people will not actively into
Row garbage classification, on the other hand, classification garbage can need the thinking of rubbish thrower, distinguish the classification of rubbish in hand, if not having
There is the understanding to rubbish material and rubbish type style, property that there is a strong possibility judges the recyclable property of rubbish by accident,
To prevent rubbish from being correctly included into corresponding cabinet;The inspection for needing later stage work personnel can not achieve completely
Classification.
The third mode is the intelligent garbage bin of mechanical structure classification, and rubbish classification is punished class from source by intelligent garbage bin
For plastics, glass, metal and other, analysis tap module acquisition sound signal frequencies characteristic, detection judge plastics, glass and
Other classes detect compressibility with travel switch, and compressing garbage is considered other classes, is arranged between slot and cabinet and slides
Road, slip it is interior rubbish is detected, promote rubbish on slideway by pushing meanss after the completion of classification, be placed into corresponding case
In vivo, defect: relative cost is higher, and design structure is complicated, and then stability is relatively poor by force for linkage between machinery, is not easy to popularize
Develop and consumes energy larger.
Thus it is proposed that a kind of Intelligent human-face identification and garbage classification system based on deep learning are above-mentioned to solve
Problem.
Summary of the invention
The purpose of the present invention is to provide Intelligent human-face identifications and garbage classification system based on deep learning, have intelligence
The advantages of identification classification, solve the problems, such as that garbage classification equipment does not have intelligent recognition classification feature on existing market.
To achieve the above object, the invention provides the following technical scheme: Intelligent human-face identification and rubbish based on deep learning
Rubbish categorizing system, the acquisition → detection of rubbish image category identifies → including rubbish image store rubbish.
Preferably, video flowing is acquired to rubbish by the camera of rubbish storage door surfaces.
Preferably, identification is carried out by image of the picture recognition device to rubbish and judges whether object occur in image frame
Body resurveys image if returning without if on last stage, is analyzed and determined picture whether comprising that can connect if there is object
By rubbish, user is prompted if not including not handle such rubbish, determines image capture device after acceptable rubbish
Face information is acquired.
Preferably, by extracting garbage classification information after face information acquisition and recording, storage sub-unit is transmitted to according to rubbish
Rubbish classification opens corresponding gate, and rubbish is thrown in storage device by user, passes through the detection list being equipped in storage device
Whether member is to putting into rubbish and detecting, and closure gate returns to initial camera acquisition video flowing after monitoring time-out.
Preferably, rubbish enter after storage unit by the judgement of gate camera lose into rubbish whether with rubbish one before
It causes, if then record prompt garbage classification is correct together with face information, face information is then recorded prompt by equipment together if not
Garbage classification is wrong and returns to initial video acquisition step.
Compared with prior art, beneficial effects of the present invention are as follows:
1, the present invention carries out identification classification to rubbish by video image acquisition technology, keeps the processing of rubbish more intelligent, solves
It has determined garbage classification managerial confusion on existing market, beneficial and Harmful Waste are mixed to be put, difficult management, a large amount of moneys of post-processing waste
The phenomenon that source.
2, the present invention uses lesser identification granularity by intelligent video stream recognizer, and deep learning module is only returned
The essential attribute (such as: being plastic cup, toilet paper, carton, battery etc.) for returning object, is then further compared in the database
It is right, such scheme under conditions of guaranteeing speed and precision, by the image recognition section of system and junk data library part into
Decoupling is gone, in which: deep learning algorithm part, it is respective excellent with multistep image detection that we combine single step image detection
Gesture, i.e., in three scales, on convolution characteristic pattern from low to high, respectively using several different proportions (for the shape of rubbish)
Sliding window carries out object detection, and the speed being exceedingly fast may be implemented in pure single step detection algorithm, but recall rate is lower, while right
It is insensitive in wisp;And although pure multistep detection precision is high, due to needing additional generation Local Area Network to be checked,
Detection speed is higher for hardware performance requirements, and the modified single step detection scheme of this multi-scale sliding window mouth detection is being sacrificed
In certain performance basis, the overall accuracy and the susceptibility for wisp for substantially increasing detection can be such that video flowing acquires
Image is identified as rubbish, and the process for making to identify rubbish for possibility is more intelligent, avoids the money of manpower identification
Source waste, the time for launching rubbish is unrestricted, and garbage classification input situation becomes controllable.
Detailed description of the invention
Fig. 1 is flow chart of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
In the description of the present invention, it should be noted that unless otherwise clearly defined and limited, term " installation " " is set
Be equipped with ", " connection " etc., shall be understood in a broad sense, such as " connection ", may be a fixed connection, may be a detachable connection or one
Connect to body;It can be mechanical connection, be also possible to be electrically connected;It can be directly connected, it can also be indirect by intermediary
It is connected, can be the connection inside two elements.For the ordinary skill in the art, on being understood with concrete condition
State the concrete meaning of term in the present invention.
Referring to Fig. 1, Intelligent human-face identification and garbage classification system based on deep learning, the acquisition including rubbish image
→ detection of rubbish image category identifies → stores rubbish.
Video flowing is acquired to rubbish by the camera of rubbish storage door surfaces;
Identification is carried out by image of the picture recognition device to rubbish and judges whether object occur in image frame, is returned if without if
Image is resurveyed on last stage, and whether picture is analyzed and determined comprising acceptable rubbish, if not wrapping if there is object
Containing then prompting can not to handle such rubbish to user, image capture device carries out face information after determining acceptable rubbish
Acquisition;
By extracting garbage classification information after face information acquisition and recording, storage sub-unit is transmitted to according to the unlatching pair of rubbish classification
Whether rubbish is thrown in storage device by the gate answered, user, by the detection unit that is equipped in storage device to putting into
Rubbish is detected, and closure gate returns to initial camera acquisition video flowing after monitoring time-out;
Rubbish, which enters after storage unit, to be lost by the judgement of gate camera into whether rubbish consistent with rubbish before, if then with people
Face information records together prompts garbage classification correct, and it is wrong simultaneously then to be recorded prompt garbage classification by equipment together for face information if not
Return to initial video acquisition step.
In use, using lesser identification granularity by intelligent video stream recognizer, deep learning module is only returned
The essential attribute (such as: being plastic cup, toilet paper, carton, battery etc.) of object, is then further compared in the database
It is right, such scheme under conditions of guaranteeing speed and precision, by the image recognition section of system and junk data library part into
Decoupling is gone, in which: deep learning algorithm part, it is respective excellent with multistep image detection that we combine single step image detection
Gesture, i.e., in three scales, on convolution characteristic pattern from low to high, respectively using several different proportions (for the shape of rubbish)
Sliding window carries out object detection, and the speed being exceedingly fast may be implemented in pure single step detection algorithm, but recall rate is lower, while right
It is insensitive in wisp;And although pure multistep detection precision is high, due to needing additional generation Local Area Network to be checked,
Detection speed is higher for hardware performance requirements, and the modified single step detection scheme of this multi-scale sliding window mouth detection is being sacrificed
In certain performance basis, the overall accuracy and the susceptibility for wisp for substantially increasing detection can be such that video flowing acquires
Image is identified as rubbish, and the process for making to identify rubbish for possibility is more intelligent, avoids the money of manpower identification
Source waste, the time for launching rubbish is unrestricted, and garbage classification input situation becomes controllably, to be suitble to promote the use of.
It although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
A variety of variations, modification, replacement can be carried out to these embodiments without departing from the principles and spirit of the present invention by understanding
And modification, the scope of the present invention is defined by the appended.
Claims (5)
1. Intelligent human-face identification and garbage classification system based on deep learning, the acquisition including rubbish image → rubbish image class
Other detection identification → storage rubbish.
2. a kind of Intelligent human-face identification and garbage classification system based on deep learning according to claim 1, feature
It is: video flowing is acquired to rubbish by the camera of rubbish storage door surfaces.
3. a kind of Intelligent human-face identification and garbage classification system based on deep learning according to claim 2, feature
It is: identification is carried out by image of the picture recognition device to rubbish and judges whether object occur in image frame, is returned if without if
It returns and resurveys image on last stage, whether picture is analyzed and determined comprising acceptable rubbish, if not if there is object
Comprising then prompting can not to handle such rubbish to user, determine after acceptable rubbish image capture device to face information into
Row acquisition.
4. a kind of Intelligent human-face identification and garbage classification system based on deep learning according to claim 3, feature
It is: extracts garbage classification information after face information acquisition and recording, is transmitted to storage sub-unit according to rubbish classification and opens correspondence
Gate, rubbish is thrown in storage device by user, by the detection unit that is equipped in storage device to whether putting into rubbish
Rubbish is detected, and closure gate returns to initial camera acquisition video flowing after monitoring time-out.
5. a kind of Intelligent human-face identification and garbage classification system based on deep learning according to claim 4, feature
Be: rubbish, which enters after storage unit, to be lost by the judgement of gate camera into whether rubbish consistent with rubbish before, if then with
Face information records together prompts garbage classification correct, and it is wrong then to be recorded prompt garbage classification by equipment together for face information if not
And return to initial video acquisition step.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910716095.XA CN110503008A (en) | 2019-08-05 | 2019-08-05 | Intelligent human-face identification and garbage classification system based on deep learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910716095.XA CN110503008A (en) | 2019-08-05 | 2019-08-05 | Intelligent human-face identification and garbage classification system based on deep learning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110503008A true CN110503008A (en) | 2019-11-26 |
Family
ID=68587850
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910716095.XA Pending CN110503008A (en) | 2019-08-05 | 2019-08-05 | Intelligent human-face identification and garbage classification system based on deep learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110503008A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111027450A (en) * | 2019-12-04 | 2020-04-17 | 深圳市新国都金服技术有限公司 | Bank card information identification method and device, computer equipment and storage medium |
CN111178329A (en) * | 2020-01-17 | 2020-05-19 | 小圾(上海)环保科技有限公司 | Big data collection method for garbage image |
CN112712029A (en) * | 2020-12-31 | 2021-04-27 | 涵古观智能科技(苏州)有限公司 | Waste product delivery method, device and system based on computer vision algorithm |
CN113255804A (en) * | 2021-06-03 | 2021-08-13 | 图灵人工智能研究院(南京)有限公司 | Garbage traceability method and device based on image change detection |
-
2019
- 2019-08-05 CN CN201910716095.XA patent/CN110503008A/en active Pending
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111027450A (en) * | 2019-12-04 | 2020-04-17 | 深圳市新国都金服技术有限公司 | Bank card information identification method and device, computer equipment and storage medium |
CN111178329A (en) * | 2020-01-17 | 2020-05-19 | 小圾(上海)环保科技有限公司 | Big data collection method for garbage image |
CN111178329B (en) * | 2020-01-17 | 2023-05-26 | 小圾(上海)环保科技有限公司 | Big data collection method of garbage image |
CN112712029A (en) * | 2020-12-31 | 2021-04-27 | 涵古观智能科技(苏州)有限公司 | Waste product delivery method, device and system based on computer vision algorithm |
CN113255804A (en) * | 2021-06-03 | 2021-08-13 | 图灵人工智能研究院(南京)有限公司 | Garbage traceability method and device based on image change detection |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110503008A (en) | Intelligent human-face identification and garbage classification system based on deep learning | |
CN112407653B (en) | Garbage classification system based on Internet of things | |
CN204549078U (en) | Rubbish bottle automatic classification collection box | |
CN102880873A (en) | Personnel behavior identification implementation system and method based on image segmentation and semantic extraction | |
CN107330839A (en) | A kind of Intelligent mobile refuse classification service centre | |
CN111846693A (en) | Intelligent garbage classification putting supervision and control system based on real-name system | |
CN111573039A (en) | Intelligent garbage classification processing system based on big data | |
CN106275945A (en) | A kind of garbage recovery device, garbage classification system and using method | |
CN206798308U (en) | A kind of automatic recovery rewarding device of refuse classification detection | |
CN105344701B (en) | A kind of intelligent comprehensive recycling machine and its analysis recognition method | |
CN112298844B (en) | Garbage classification supervision method and device | |
CN113003054A (en) | Garbage classification method | |
CN105710044A (en) | Intelligent classification system for recoverable garbage | |
CN108357818A (en) | The dustbin of automatic sorting | |
CN109754520A (en) | Automatic carton recyclable device and distributed carton recovery system | |
CN116682098A (en) | Automatic urban household garbage identification and classification system and method | |
CN207020722U (en) | A kind of Intelligent mobile refuse classification service centre | |
CN212048939U (en) | Intelligent garbage recycling device for community | |
CN204210972U (en) | A kind of waste intelligent classification reclaims module | |
CN113255550A (en) | Pedestrian garbage throwing frequency counting method based on videos | |
CN106742908B (en) | A kind of Intelligent refuse classification device based on single-chip microcontroller multisensor | |
CN205183312U (en) | Intelligent comprehensive recovery machine | |
CN209922092U (en) | Material recycling bin capable of automatically identifying human face and garbage types | |
CN110775483A (en) | Community intelligent garbage recycling device and method, electronic equipment and storage medium | |
CN115082863A (en) | Intelligent garbage classified putting scanning system and method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20191126 |
|
WD01 | Invention patent application deemed withdrawn after publication |