CN112270378A - A computer vision-based artificial intelligence sorting method for waste glass - Google Patents
A computer vision-based artificial intelligence sorting method for waste glass Download PDFInfo
- Publication number
- CN112270378A CN112270378A CN202011273045.8A CN202011273045A CN112270378A CN 112270378 A CN112270378 A CN 112270378A CN 202011273045 A CN202011273045 A CN 202011273045A CN 112270378 A CN112270378 A CN 112270378A
- Authority
- CN
- China
- Prior art keywords
- waste glass
- computer vision
- artificial intelligence
- classification
- intelligence sorting
- 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
- 239000011521 glass Substances 0.000 title claims abstract description 90
- 239000002699 waste material Substances 0.000 title claims abstract description 82
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 21
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000004458 analytical method Methods 0.000 claims description 19
- 239000000463 material Substances 0.000 claims description 12
- 238000013527 convolutional neural network Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 230000005284 excitation Effects 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 claims description 3
- 238000011176 pooling Methods 0.000 claims description 3
- 230000006835 compression Effects 0.000 claims description 2
- 238000007906 compression Methods 0.000 claims description 2
- 239000006185 dispersion Substances 0.000 claims description 2
- 238000000605 extraction Methods 0.000 claims description 2
- 238000007781 pre-processing Methods 0.000 claims description 2
- 230000011664 signaling Effects 0.000 claims description 2
- 238000004064 recycling Methods 0.000 abstract description 9
- 239000002910 solid waste Substances 0.000 abstract description 2
- 238000004140 cleaning Methods 0.000 description 5
- 239000012634 fragment Substances 0.000 description 5
- 238000012549 training Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 239000003153 chemical reaction reagent Substances 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 229910001385 heavy metal Inorganic materials 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000005693 optoelectronics Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2431—Multiple classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Sorting Of Articles (AREA)
Abstract
本发明属于固体废弃物资源化技术领域，具体涉及一种基于计算机视觉的废玻璃人工智能分选方法。该方法利用计算机视觉人工智能的方式对废玻璃图像信息进行采集分析，根据废玻璃的形状、尺寸，高效地对废玻璃进行识别分类，节省了大量的劳动力，分选得到的废玻璃具有更好的针对性和适用性，显著提高了废玻璃资源化的效率。
The invention belongs to the technical field of solid waste recycling, and in particular relates to an artificial intelligence sorting method for waste glass based on computer vision. The method uses computer vision artificial intelligence to collect and analyze waste glass image information, and efficiently identifies and sorts waste glass according to the shape and size of waste glass, saving a lot of labor, and the sorted waste glass has better quality The pertinence and applicability of the waste glass have significantly improved the efficiency of waste glass recycling.
Description
Technical Field
The invention belongs to the technical field of solid waste recycling. And more particularly, to a waste glass artificial intelligence sorting method based on computer vision.
Background
The natural degradation time of common glass and products thereof is as long as 4000 years, heavy metal elements are added into part of the glass in the processing process, the glass possibly causes irreversible influence on soil and water when entering the environment, and waste glass cannot be treated and disposed by traditional modes such as burning, landfill and the like. Therefore, recycling is a better treatment mode for the waste glass at present. China has a mature technology in the aspect of waste glass recycling technology, and various recycling methods and devices are more and more practical. Before recycling, the waste glass with different sources, complex shapes, various types and different compositions is classified and sorted through a sorting step.
The current common sorting methods mainly comprise manual sorting and mechanical sorting. Among them, manual sorting requires a lot of labor, and is also prone to cause problems such as injury and pollution during sorting, and has been gradually replaced by mechanical sorting. For example, the chinese patent application CN204485991U discloses a glass crushing and sorting device, which physically sorts and cleans the impurities in the waste glass, such as paper scraps, plastic fragments, stones, etc. which are not beneficial to the subsequent processing of the glass, by the combination of a crusher, a magnet, a vibrating screen and a suction fan; chinese patent application CN203044366U discloses an optical sorting device for recycling colored waste glass, which can sort waste glass with different optical characteristics by using different reflection characteristics of the surfaces of different colored glass and using optoelectronic components as the recognition core. However, at present, most of waste glass is usually required to be in a shape or size meeting the requirements of a specific process before being recycled, and no better method for sorting the shape and size of the glass is available for replacing manual sorting.
Disclosure of Invention
The invention aims to solve the technical problem of overcoming the defect and the defect that the prior art is lack of mechanical sorting of the shape and the size of the waste glass, and provides an artificial intelligent sorting method of the waste glass based on computer vision.
The invention aims to provide a waste glass artificial intelligence sorting method based on computer vision.
Another object of the present invention is to provide a waste glass artificial intelligence sorting system based on computer vision.
The above purpose of the invention is realized by the following technical scheme:
a waste glass artificial intelligence sorting method based on computer vision, disperse the waste glass, carry on the information acquisition of the picture, utilize the intelligent analytic system of computer vision to simulate the artificial recognition to classify, get the waste glass that the shape, size meet requirements;
the intelligent analysis system utilizes a computer convolutional neural network to perform identification and classification.
Further, the artificial intelligence sorting method of the waste glass based on the computer vision specifically comprises the following steps:
s1, learning and classifying by an intelligent analysis system: adopting manual sorting to obtain various waste glass as a learning template of an intelligent analysis system, importing the collected picture information of the waste glass learning template, and completing the identification and classification of results through the treatment of a computer convolution neural network;
s2, production steps: the waste glass is dispersed and is transmitted to an image acquisition system one by one to acquire image information, the acquired image information is transmitted to an intelligent analysis system which finishes learning and classification in step S1 in advance, a calculated time signal is transmitted to a clearing system after comparison and judgment, the clearing system clears the waste glass which does not meet the requirement according to the time signal, the waste glass which meets the requirement is recovered, and sorting is finished.
In addition, the invention also provides a waste glass artificial intelligence sorting system based on computer vision, which comprises a material dispersing system, an image collecting system, an intelligent analyzing system and a clearing system, wherein the material dispersing system is used for dispersing waste glass and transmitting the waste glass one by one; wherein, each system is connected with the waste glass through a horizontal conveying belt and the waste glass is conveyed.
Further, material disperse system is including vibration material feeding unit and fixture block conveyer belt, and vibration material feeding unit conveys waste glass one by the fixture block conveyer belt after with waste glass dispersion.
Furthermore, a plurality of clamping blocks are vertically arranged on the surface of the clamping block conveying belt and used for conveying the waste glass one by one.
Further, the fixture block conveyor belt horizontally inclines upwards by 20-45 degrees.
Furthermore, the image acquisition system comprises a camera and a light shield, wherein the camera is arranged right above the horizontal conveyor belt, and the light shield is arranged above the camera and completely covers the camera and the image acquisition area.
Furthermore, the intelligent analysis system utilizes a computer convolutional neural network to perform identification and classification, comprises an input layer, a convolutional layer, a pooling layer, an excitation layer and a full-connection layer, and sequentially performs input information and preprocessing, feature extraction and identification, information filtering and compression, nonlinear change processing and identification and classification.
Further, the cleaning system includes a solenoid valve for recognizing the time signal and controlling a pneumatic kick for ejecting the unsatisfactory waste glass.
Preferably, the horizontal conveyor belt is uniformly black.
The invention has the following beneficial effects:
according to the artificial intelligence sorting method for waste glass based on computer vision, the image information of the waste glass is collected and analyzed in an artificial intelligence mode based on the computer vision, the waste glass is efficiently identified and classified according to the shape and the size of the waste glass, a large amount of labor force is saved, the sorted waste glass has better pertinence and applicability, and the waste glass recycling efficiency is remarkably improved.
Drawings
FIG. 1 is a schematic view of a material dispersing system and an image acquisition system in example 1 of the present invention;
FIG. 2 is a schematic view of a cleaning system according to embodiment 1 of the present invention;
the device comprises a vibration feeding device 11, a fixture block conveyor belt 12, a fixture block 121, a camera 21, a light shield 22, a horizontal conveyor belt 31, an electromagnetic valve 41 and a pneumatic kicking leg 42.
Detailed Description
The invention is further described with reference to the drawings and the following detailed description, which are not intended to limit the invention in any way. Reagents, methods and apparatus used in the present invention are conventional in the art unless otherwise indicated.
Unless otherwise indicated, reagents and materials used in the following examples are commercially available.
Embodiment 1 artificial intelligent sorting method for waste glass based on computer vision
The artificial intelligent sorting method of the waste glass based on the computer vision comprises the following specific steps:
s1, learning and classifying by an intelligent analysis system: firstly, manually sorting to obtain various waste glasses as learning templates of an intelligent analysis system, wherein the sorting accuracy is higher when the number of the learning templates is larger; the collected waste glass learning template is shot by an industrial camera 21 and then is led into an intelligent analysis system, and image information is transmitted to a computer convolution neural network consisting of four layers of structures: an input layer of a first layer of the convolutional neural network receives input image information and preprocesses data; the convolution layer of the second layer of the network extracts and identifies partial features of the image, reduces the information amount of the image and only acquires information which can be used for classification; the third layer of pooling layer further filters and compresses images and information, so that the fault tolerance of the whole model is improved; the fourth excitation layer carries out nonlinear change on the output result of the convolutional layer so as to assist in expressing complex characteristics; the final full connection layer completes the identification and classification of the results;
s2, production steps: waste glass is conveyed to an image acquisition system one by one in a material dispersing system through a vibration feeding device 11 and a fixture block conveying belt 12, wherein the fixture block conveying belt 12 horizontally inclines upwards by 20-45 degrees, and a plurality of fixture blocks 121 are vertically arranged on the surface of the fixture block conveying belt and used for conveying the waste glass materials to a horizontal conveying belt 31 one by one; when the waste glass arrives at the image acquisition system, the industrial camera 21 arranged right above the horizontal conveyor belt 31 finishes acquisition of fragment image information, the image information is transmitted to an intelligent analysis system which finishes learning and classification in advance, the intelligent analysis system carries out binarization filtering processing on the image information to highlight the outline and then compares the outline with a learning and classification template, judgment is carried out, the time for the waste glass to arrive at the cleaning system is calculated according to the transmission speed, a time signal is transmitted to the cleaning system, when the waste glass does not meet the requirement, an electromagnetic valve 41 in the cleaning system is started according to the time for the waste glass to arrive at an output port, a pneumatic kicking leg 42 on the side surface of the horizontal conveyor belt 31 is driven to push the fragments out of the horizontal conveyor belt 31 and fall into a corresponding fragment outlet, and the waste glass meeting the requirements on shape and size is recycled to a corresponding container by the.
Wherein, in order to guarantee the image acquisition effect, the image acquisition system has still included the lens hood 22 of setting directly over horizontal conveyor 31, the lens hood 22 covers industrial camera 21 and image acquisition region completely, and industrial camera 21 carries out image acquisition under the shading effect. The horizontal conveyor belt 31 is uniformly black so that the industrial camera 21 can capture an easily recognized image.
The intelligent analysis system can be trained by utilizing the learning template of the intelligent analysis system, the system generates a training set loss according to the error between the prediction result and the real result of the corresponding shape, the training set loss gradually decreases along with the increase of the number of the learning templates, and when the training set loss approaches to a stable numerical value of 0, the system finishes training and can accurately identify the learned glass fragments.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.
Claims (10)
1. A waste glass artificial intelligence sorting method based on computer vision is characterized in that after waste glass is dispersed, image information is collected, and a computer vision intelligence analysis system is used for simulating artificial recognition and classification to obtain waste glass with the shape and the size meeting the requirements;
the intelligent analysis system utilizes a computer convolutional neural network to perform identification and classification.
2. The artificial intelligence sorting method for waste glass based on computer vision as claimed in claim 1, characterized by comprising the following steps:
s1, learning and classifying by an intelligent analysis system: adopting manual sorting to obtain various waste glass as a learning template of an intelligent analysis system, importing the collected picture information of the waste glass learning template, and completing the identification and classification of results through the treatment of a computer convolution neural network;
s2, production steps: the waste glass is dispersed and is transmitted to an image acquisition system one by one to acquire image information, the acquired image information is transmitted to an intelligent analysis system which finishes learning and classification in step S1 in advance, a calculated time signal is transmitted to a clearing system after comparison and judgment, the clearing system clears the waste glass which does not meet the requirement according to the time signal, the waste glass which meets the requirement is recovered, and sorting is finished.
3. A waste glass artificial intelligence sorting system based on computer vision is characterized by comprising a material dispersing system, an image collecting system, an intelligent analyzing system and a clearing system, wherein the material dispersing system is used for dispersing waste glass and transmitting the waste glass one by one; wherein, each system is connected with the waste glass through a horizontal conveying belt and the waste glass is conveyed.
4. The artificial intelligence sorting system of waste glass based on computer vision of claim 3, characterized in that the material dispersion system comprises a vibration feeding device and a fixture block conveyor belt, and after the vibration feeding device disperses the waste glass, the fixture block conveyor belt conveys the waste glass one by one.
5. The artificial intelligence sorting system for waste glass based on computer vision as claimed in claim 4, wherein a plurality of blocks are vertically arranged on the surface of the block conveyer belt for conveying the waste glass one by one.
6. The artificial intelligence sorting system for waste glass based on computer vision as claimed in claim 5, wherein the fixture block conveyor belt is inclined upwards by 20-45 ° horizontally.
7. The computer vision-based artificial intelligence sorting system for waste glass according to claim 3, wherein the image acquisition system comprises a camera and a light shield, the camera is arranged right above the horizontal conveyor belt, and the light shield is arranged above the camera to completely cover the camera and the image acquisition area.
8. The artificial intelligence sorting system for waste glass based on computer vision as claimed in claim 3, wherein the intelligent analysis system utilizes a computer convolutional neural network to perform recognition and classification, the intelligent analysis system comprises an input layer, a convolutional layer, a pooling layer, an excitation layer and a full connection layer, and input information and preprocessing, feature extraction recognition, information filtering and compression, nonlinear change processing and recognition and classification are sequentially performed.
9. The computer vision based artificial intelligence sorting system for waste glass according to claim 3 wherein the removal system includes a solenoid valve for identifying a time signal and controlling a pneumatic kick for ejecting unsatisfactory waste glass.
10. The computer vision based artificial intelligence sorting system for waste glass according to claim 3 wherein the horizontal conveyor is uniformly black.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011273045.8A CN112270378A (en) | 2020-11-13 | 2020-11-13 | A computer vision-based artificial intelligence sorting method for waste glass |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011273045.8A CN112270378A (en) | 2020-11-13 | 2020-11-13 | A computer vision-based artificial intelligence sorting method for waste glass |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112270378A true CN112270378A (en) | 2021-01-26 |
Family
ID=74340081
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011273045.8A Pending CN112270378A (en) | 2020-11-13 | 2020-11-13 | A computer vision-based artificial intelligence sorting method for waste glass |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112270378A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114925756A (en) * | 2022-05-07 | 2022-08-19 | 上海燕龙基再生资源利用有限公司 | Waste glass classified recovery method and device based on fine management |
| CN115672789A (en) * | 2022-12-21 | 2023-02-03 | 西安海联石化科技有限公司 | Method for sorting oxidation scraps recovered from titanium and titanium alloy |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108339834A (en) * | 2018-02-12 | 2018-07-31 | 李奕菲 | A kind of waste and old glass treatment device of intelligence |
| CN110210635A (en) * | 2019-06-05 | 2019-09-06 | 周皓冉 | A kind of intelligent classification recovery system that can identify waste |
| CN110577037A (en) * | 2018-06-08 | 2019-12-17 | 王俊杰 | Method for classifying, checking and recycling household garbage |
-
2020
- 2020-11-13 CN CN202011273045.8A patent/CN112270378A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108339834A (en) * | 2018-02-12 | 2018-07-31 | 李奕菲 | A kind of waste and old glass treatment device of intelligence |
| CN110577037A (en) * | 2018-06-08 | 2019-12-17 | 王俊杰 | Method for classifying, checking and recycling household garbage |
| CN110210635A (en) * | 2019-06-05 | 2019-09-06 | 周皓冉 | A kind of intelligent classification recovery system that can identify waste |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114925756A (en) * | 2022-05-07 | 2022-08-19 | 上海燕龙基再生资源利用有限公司 | Waste glass classified recovery method and device based on fine management |
| CN114925756B (en) * | 2022-05-07 | 2022-11-11 | 上海燕龙基再生资源利用有限公司 | Waste glass classified recovery method and device based on fine management |
| CN115672789A (en) * | 2022-12-21 | 2023-02-03 | 西安海联石化科技有限公司 | Method for sorting oxidation scraps recovered from titanium and titanium alloy |
| CN115672789B (en) * | 2022-12-21 | 2024-04-30 | 西安海联石化科技有限公司 | Sorting method for titanium and titanium alloy recovered oxidized scraps |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107486415B (en) | Thin bamboo strip defect online detection system and detection method based on machine vision | |
| CN103913468B (en) | Many defects of vision checkout equipment and the method for large-scale LCD glass substrate on production line | |
| CN108971190A (en) | A kind of separating domestic garbage method based on machine vision | |
| CN207238542U (en) | A kind of thin bamboo strip defect on-line detecting system based on machine vision | |
| CN111805541B (en) | Deep learning-based traditional Chinese medicine decoction piece cleaning and selecting device and cleaning and selecting method | |
| CN1485616A (en) | Equipment and method for non-destructive automatic detection and grading of poultry egg quality | |
| CN112270378A (en) | A computer vision-based artificial intelligence sorting method for waste glass | |
| CN109308479B (en) | An automatic classification and recycling method of campus garbage based on deep learning | |
| CN110261391A (en) | A kind of LED chip appearance detection system and method | |
| CN104297439B (en) | A method for automatic recognition and detection of double-yellow duck eggs based on computer vision | |
| CN104056790A (en) | Intelligent potato sorting method and apparatus | |
| CN109331990A (en) | A rapid automatic recycling and sorting process for waste glass | |
| CN110349125A (en) | A kind of LED chip open defect detection method and system based on machine vision | |
| Aishwarya et al. | A waste management technique to detect and separate non-biodegradable waste using machine learning and YOLO algorithm | |
| CN112560941A (en) | Coal and gangue identification method based on image detection | |
| CN112364944A (en) | Deep learning-based household garbage classification method | |
| CN107153067A (en) | A kind of surface defects of parts detection method based on MATLAB | |
| CN113592813B (en) | New energy battery welding defect detection method based on deep learning semantic segmentation | |
| CN108875725A (en) | A kind of the mail automatic sorting device and method of view-based access control model identification | |
| CN114778561A (en) | A method and system for quality traceability of cut tobacco based on machine vision | |
| CN207222383U (en) | Plank sorting system | |
| CN105127110B (en) | A kind of automatic fraction collector of universal multispectral imaging mixed plastic | |
| CN103091330A (en) | Copper strip surface defect identifying device for simulating human visual perception mechanism and method thereof | |
| CN210477480U (en) | Waste plastic bottle sorting system | |
| CN102519971A (en) | On-line identification apparatus and method for impurities in edible fungi |
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: 20210126 |