CN111259977A - Garbage classification device based on deep learning - Google Patents
Garbage classification device based on deep learning Download PDFInfo
- Publication number
- CN111259977A CN111259977A CN202010075011.1A CN202010075011A CN111259977A CN 111259977 A CN111259977 A CN 111259977A CN 202010075011 A CN202010075011 A CN 202010075011A CN 111259977 A CN111259977 A CN 111259977A
- Authority
- CN
- China
- Prior art keywords
- garbage
- classification
- acquisition module
- image
- deep learning
- 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
- 239000010813 municipal solid waste Substances 0.000 title claims abstract description 161
- 238000013135 deep learning Methods 0.000 title claims abstract description 27
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 8
- 238000012549 training Methods 0.000 claims description 23
- 230000006870 function Effects 0.000 claims description 15
- 238000002790 cross-validation Methods 0.000 claims description 3
- 238000011478 gradient descent method Methods 0.000 claims description 2
- 238000000034 method Methods 0.000 description 12
- 238000005516 engineering process Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 239000002699 waste material Substances 0.000 description 5
- 238000010801 machine learning Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 238000003672 processing method Methods 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000010791 domestic waste Substances 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000013100 final test Methods 0.000 description 1
- 239000002920 hazardous waste Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 238000012795 verification Methods 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
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a garbage classification device based on deep learning, which comprises: the image acquisition module is used for acquiring images of the garbage to be classified; the garbage name recognition module is used for recognizing the garbage image to be classified by using a garbage name recognition model to obtain the garbage name of the garbage to be classified, and the garbage name recognition model is constructed and obtained on the basis of a convolutional neural network classifier; and the garbage category classification module is used for determining the garbage category to which the garbage name belongs by using a knowledge graph to realize garbage classification, and the knowledge graph expresses the relationship between the garbage name and the garbage category. The device has improved classification efficiency, has solved the manual work and has not understood the classification condition of part article, the division of rubbish classification is fuzzy scheduling problem.
Description
Technical Field
The invention relates to the field of garbage classification, in particular to a garbage classification device based on deep learning.
Background
The garbage classification is an improvement of the traditional garbage collection and disposal mode, and is a scientific management method for effectively disposing garbage. In the situation of increasing garbage yield and environmental condition deterioration, how to realize garbage resource utilization to the maximum extent, reduce garbage disposal amount and improve living environment quality through garbage classification management is one of the urgent problems of common attention of countries in the world at present. Although the concept of garbage classification has been proposed for a long time, it is not really implemented in china.
Deep learning is a new research direction in the field of machine learning, and is introduced into machine learning to make it closer to the original goal, artificial intelligence. Deep learning has achieved many achievements in search technology, data mining, machine learning, machine translation, natural language processing, multimedia learning, and other related fields. The deep learning enables the machine to imitate human activities such as audio-visual and thinking, solves a plurality of complex pattern recognition problems, and makes great progress on the artificial intelligence related technology. Deep learning is used as a further development idea of a neural network technology in machine learning, the characteristic representation of data is automatically learned by a distributed structure, and classification of garbage into new bright spots is realized by utilizing a deep learning algorithm.
Disclosure of Invention
In order to overcome the defects that the classification condition of partial articles is unknown manually, the classification efficiency is low, and the classification implementation condition is not ideal, the invention provides the deep learning-based garbage classification device which can realize garbage classification through five query modes.
The technical scheme adopted by the invention for solving the technical problems is as follows:
a garbage classification device based on deep learning, the garbage classification device comprising:
the image acquisition module is used for acquiring images of the garbage to be classified;
the garbage name recognition module is used for recognizing the garbage image to be classified by using a garbage name recognition model to obtain the garbage name of the garbage to be classified, and the garbage name recognition model is constructed and obtained on the basis of a convolutional neural network classifier;
and the garbage category classification module is used for determining the garbage category to which the garbage name belongs by using a knowledge graph to realize garbage classification, and the knowledge graph expresses the relationship between the garbage name and the garbage category.
Preferably, the construction process of the garbage name recognition model comprises the following steps:
defining an input image size of 224 × 224 × 3 based on MobileNet _ v 2;
and training the MobileNet _ v2 by using a training sample to obtain a garbage name recognition model by taking the cross entropy of the prediction recognition result and the sample label as a loss function.
Preferably, in training, a small batch gradient descent method is adopted for training, and ten-fold cross validation is adopted.
Preferably, the image acquisition module comprises an image acquisition module, and the image acquisition module acquires the image of the garbage to be classified by accessing a system album or a file.
Preferably, the image acquisition module comprises a photographing acquisition module, and the photographing acquisition module is used for photographing the garbage through a camera of the mobile device to acquire an image of the garbage to be classified.
Preferably, the image acquisition module comprises a real-time image acquisition module, and the real-time image acquisition module performs real-time image pickup on the garbage through the image pickup function of the mobile device and accesses an image previewed by a camera of the mobile device to acquire an image of the garbage to be classified.
Preferably, the garbage classification device further comprises a text collection module, wherein the text collection module is used for collecting garbage names input by a user or scanning through a text box to obtain the garbage names.
Preferably, the garbage classification device further comprises a voice acquisition module, wherein the voice acquisition module acquires voice data and converts the voice data into a garbage name represented by characters.
The technical conception of the invention is as follows: and based on a deep learning algorithm, utilizing a MobileNet _ v2 network model to realize the classification of the garbage. Firstly, acquiring a data set, then constructing a convolutional neural network classifier, and training the classifier according to a sample data set to realize the classification of garbage. And a garbage classification knowledge graph is constructed, so that the classification and corresponding processing method of various domestic garbage can be obtained through five query modes of photo album picture identification, photo identification, picture real-time identification, text search identification and voice identification.
The invention has the following beneficial effects: the idea of classifying the garbage through a deep learning algorithm is provided, five query modes of photo album picture recognition, photo recognition, picture real-time recognition, text search recognition and voice recognition are provided to obtain the garbage classification and corresponding processing methods, and the household garbage classification method is effectively and conveniently provided for users. In actual conditions, the classification efficiency is improved, and the problems that manual classification conditions of partial articles are not known, classification of garbage categories is fuzzy and the like are solved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic structural diagram of a deep learning-based garbage classification device according to an embodiment of the present invention;
FIG. 2 is a detailed structure diagram of a MobileNet _ v2 network according to an embodiment of the present invention;
FIG. 3 is a diagram of a MobileNet _ v2 network model in an embodiment of the invention;
FIG. 4 is a knowledge graph of harmful garbage in an embodiment of the present invention;
FIG. 5 is a knowledge graph of dry garbage in an embodiment of the present invention;
FIG. 6 is a knowledge-graph of wet trash formation in an embodiment of the present invention;
FIG. 7 is a knowledge map of recoveries in an embodiment of the present invention;
FIG. 8 is a flow diagram of text search recognition in an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the detailed description and specific examples, while indicating the scope of the invention, are intended for purposes of illustration only and are not intended to limit the scope of the invention.
The garbage classification device based on deep learning is designed aiming at the problems of fuzzy classification, low classification efficiency, unsatisfactory classification implementation condition and the like of the current garbage categories, household garbage is classified into four kinds of garbage, namely dry garbage, wet garbage, recoverable garbage and harmful garbage, and automatic recognition and classification of the garbage can be realized by utilizing a deep learning technology. A user can inquire the specific classification conditions of various domestic wastes and corresponding processing methods by methods such as text search, object shooting, voice and the like, and the problems that partial wastes are difficult to distinguish and the classification efficiency is low are effectively solved.
Referring to fig. 1 to 8, the garbage classification device based on deep learning according to the embodiment includes
The image acquisition module is used for acquiring images of the garbage to be classified;
the garbage name recognition module is used for recognizing the garbage image to be classified by using a garbage name recognition model to obtain the garbage name of the garbage to be classified, and the garbage name recognition model is constructed and obtained on the basis of a convolutional neural network classifier;
and the garbage category classification module is used for determining the garbage category to which the garbage name belongs by using a knowledge graph to realize garbage classification, and the knowledge graph expresses the relationship between the garbage name and the garbage category.
The garbage name identification model is mainly used for identifying the name of garbage, and the specific construction process comprises the following steps:
(1) an imagenet data set is collected, and the data is saved in an image file type of a 'bmp' suffix to serve as a training set.
The data set used was a subset of the imagenet data set, where the training set was 128167 pictures + label, the verification set was 50000 pictures + label, the final test set was 100000 pictures, and the data were 1000 different categories.
(2) Construction of models
A convolutional neural network is widely applied to computer vision and image classification tasks as a classical deep learning network, a deep learning model is deployed at a mobile terminal, and in order to reduce the volume of an APP and increase the recognition speed of pictures, a MobileNet _ v2 network model (a new lightweight network) is determined to be adopted, please refer to FIGS. 2 and 3; for an initial sample image with the input size of 224 × 224 × 3, the length and the width of the initial sample image are both 224 pixels, the number of channels is 3, and a convolutional neural network classifier is constructed, which specifically comprises the following steps:
(a) the method comprises the steps that an obtained sample image passes through 1 layer of convolutional layer (conv2d), steps with the length of 2 are used in an initial convolutional layer, the size of a characteristic diagram output by each layer of the image in the network training process is rapidly reduced, in the convolutional layer, a ReLU6 activation function is used for avoiding the gradient saturation problem possibly brought by activation functions such as Sigmoid and the like, and the network training process is improved;
(b) then passing through 1 layer of convolution layer and then sequentially passing through 17 layers of bottleeck;
referring to fig. 2, t is the multiplication factor of the input channel (i.e. how many times the number of input channels the number of channels in the middle part is), n is the number of times the module is repeated, c is the number of output channels, and s is the step size when the module is repeated for the first time. It can be seen that 7 layers of bottleeck are respectively repeated 1, 2, 3, 4, 3, 1 times, and the total number of 17 layers of bottleeck are passed.
(c) After passing through 17 layers of bottleeck, the image is fed into a convolution layer (conv2d) with a step size of 1 and output as a 7X 1280 image. And then the image passes through a pooling layer (avgpool) to output an image of 1 × 1 × 1280.
(d) Finally, the 1 × 1 × 1280 image obtained in step 2.3) is output as classification values of K categories by passing through a 1-layer convolution layer (conv2d), where K represents a garbage name.
(3) Training the classifier according to the sample data set, specifically comprising:
obtaining a loss function; the selected loss function is based on the cross entropy of prediction classification and sample labels, and the format of the loss function is represented by one-hot coding, for example, the label of a sample represented by [0,0,1,0,0,0] is the 3 rd of 6 categories; the cross entropy expression is as follows:
wherein y isiIs a label of specimen i, yi' is the predicted value of sample i, HiIs the cross entropy of sample i.
Firstly, multiplying the prediction classification of the samples and the log function of the sample labels for negation, and accumulating the entropy values of the dimensions of one-hot to obtain cross entropy;
the loss function of the current training data is achieved by calculating the average of the cross entropies of all samples, and the expression is as follows:
the constructed convolutional neural network classifier is trained, a training method of small Batch Gradient Descent (MBGD) is adopted during training, a Batch of data is randomly selected from a training set each time for model training, training oscillation generated by random Gradient Descent (SGD) can be avoided, excessive consumption of resources by Batch Gradient Descent (BGD) can be avoided, and the Batch size is selected to be 128. Considering the stability of network updating, the learning rate is set to 0.045, an Adam optimizer with a super-parameter self-adaptive adjustment is used for training, the training target is to adjust the structural parameters of the network through the forward and backward propagation of the gradient, and the loss function value of the model is continuously reduced;
to avoid the interference of the experiment by chance, the experiment adopts ten-fold cross validation, namely, the data set is divided into 10 parts, 9 parts of the data set are selected for training each time, and one part of the data set is selected for testing.
In the embodiment, the knowledge graph is mainly used for garbage classification, and with reference to fig. 4 to 7, 1000 types of garbage are classified according to the national classification standard, and are divided into 4 types: dry waste, wet waste, recoverable waste and hazardous waste.
In one embodiment, the image acquisition module comprises an image acquisition module, and realizes garbage classification through an album image identification mode, wherein the garbage classification is mainly realized by accessing images in a system album or a file, performing garbage classification identification on the images, and giving a corresponding putting suggestion. The technology related to the module mainly comprises the following steps:
accessing pictures in a system photo album or files, and inputting the acquired pictures into a junk name identification model to acquire a junk name of the pictures so as to realize junk identification; and then matching the obtained garbage names by using the garbage classification knowledge graph to obtain the garbage categories and corresponding introduction and delivery requirements.
In one embodiment, the image acquisition module comprises a photographing acquisition module, the garbage classification is realized in a photographing identification mode, the photographing of garbage is mainly performed through a camera of the mobile device, the garbage classification of the obtained pictures is identified, and corresponding putting suggestions are given. The technology related to the module mainly comprises the following steps:
the method comprises the steps of using a camera of the mobile device to photograph the garbage, storing a picture obtained through photographing into a file, inputting the obtained picture into a garbage name recognition model to obtain a garbage name of the picture so as to realize garbage recognition, matching the obtained garbage name according to a garbage classification knowledge graph, and obtaining the garbage category and corresponding introduction and delivery requirements.
In one embodiment, the image acquisition module comprises a picture real-time acquisition module, and realizes garbage classification in a picture real-time identification mode, wherein the image previewed by a camera of the mobile device is mainly accessed, garbage classification is carried out on the obtained image in real time, and a result is output. On the function, the light weight model of MobileNet V2 and Tensorflow Lite (lightweight solution of Tensorflow for mobile and embedded devices) are adopted, so that the effect of real-time identification is greatly improved. The method specifically comprises the following steps:
the method comprises the steps of using a camera shooting function of the mobile equipment to shoot an article in real time, accessing an image previewed by a camera of the mobile equipment, inputting an obtained picture into a garbage name recognition model to obtain a garbage name of the picture so as to realize garbage recognition, matching the obtained garbage name according to a garbage classification knowledge map, and obtaining a garbage category and corresponding introduction and delivery requirements.
In an embodiment, the garbage classification device further includes a text collection module, which implements garbage classification by a text search recognition mode, please refer to fig. 8, and mainly implements garbage name recognition by matching the acquired text with the established database in a text search mode, and provides a corresponding delivery suggestion. The technology related to the module mainly comprises the following steps:
constructing a garbage classification database by using the established garbage classification knowledge map; initializing and reading database data; the user inputs the names of the articles to be classified at the user end; scanning the content of the text box to obtain a scanned garbage name; and comparing the scanned junk names with database data until matching is successful, acquiring pictures and junk category pictures corresponding to the retrieved articles, and giving corresponding delivery suggestions.
In one embodiment, the garbage classification device further comprises a voice acquisition module, which is used for realizing garbage classification in a voice recognition mode, mainly recognizing and converting the acquired voice into a text in a voice mode, matching the text with the established database to realize garbage name recognition, and giving a corresponding putting suggestion. The technology related to the module mainly comprises the following steps:
the method comprises the steps that a user speaks names of articles to be classified to a mobile terminal, voice recording is carried out, recording is carried out through a microphone, recorded data are compressed through speex voice and stored in a file, junk names are recorded, recording is completed, the collected voice is analyzed through a voice-to-text function achieved through an AipSpeech module (a hundred-degree voice recognition model), the collected voice is converted into characters, initialization is carried out, database data are read, the obtained junk names are compared with the database data until matching is successful, pictures corresponding to the retrieved articles and junk category pictures are obtained, and corresponding putting suggestions are given.
This deep learning's waste classification device has improved classification efficiency, has solved the manual work and has not understood the classification condition of part article, the division of rubbish classification is fuzzy scheduling problem.
The above-mentioned embodiments are intended to illustrate the technical solutions and advantages of the present invention, and it should be understood that the above-mentioned embodiments are only the most preferred embodiments of the present invention, and are not intended to limit the present invention, and any modifications, additions, equivalents, etc. made within the scope of the principles of the present invention should be included in the scope of the present invention.
Claims (8)
1. A garbage classification device based on deep learning is characterized in that the garbage classification device comprises:
the image acquisition module is used for acquiring images of the garbage to be classified;
the garbage name recognition module is used for recognizing the garbage image to be classified by using a garbage name recognition model to obtain the garbage name of the garbage to be classified, and the garbage name recognition model is constructed and obtained on the basis of a convolutional neural network classifier;
and the garbage category classification module is used for determining the garbage category to which the garbage name belongs by using a knowledge graph to realize garbage classification, and the knowledge graph expresses the relationship between the garbage name and the garbage category.
2. The deep learning-based garbage classification device according to claim 1, wherein the garbage name recognition model is constructed by the following steps:
defining an input image size of 224 × 224 × 3 based on MobileNet _ v 2;
and training the MobileNet _ v2 by using a training sample to obtain a garbage name recognition model by taking the cross entropy of the prediction recognition result and the sample label as a loss function.
3. The deep learning-based garbage classification device of claim 2, wherein in the training, a small batch gradient descent method is adopted for training, and ten-fold cross validation is adopted.
4. The deep learning based garbage classification device according to claim 1, wherein the image acquisition module comprises an image acquisition module, and the image acquisition module acquires an image of garbage to be classified by accessing a system photo album or a file.
5. The deep learning-based garbage classification device according to claim 1, wherein the image acquisition module comprises a photographing acquisition module, and the photographing acquisition module is used for photographing garbage through a camera of a mobile device to obtain an image of the garbage to be classified.
6. The deep learning-based garbage classification device according to claim 1, wherein the image acquisition module comprises a real-time picture acquisition module, and the real-time picture acquisition module performs real-time shooting on garbage through a shooting function of the mobile device and accesses an image previewed by a camera of the mobile device to obtain an image of garbage to be classified.
7. The deep learning based garbage classification device as claimed in claim 1, further comprising a text collection module for collecting garbage names inputted by a user or scanning through a text box to obtain garbage names.
8. The deep learning based spam classification device of claim 1 further comprising a voice collection module that collects voice data and converts the voice data into textual spam names.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010075011.1A CN111259977A (en) | 2020-01-22 | 2020-01-22 | Garbage classification device based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010075011.1A CN111259977A (en) | 2020-01-22 | 2020-01-22 | Garbage classification device based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111259977A true CN111259977A (en) | 2020-06-09 |
Family
ID=70942776
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010075011.1A Pending CN111259977A (en) | 2020-01-22 | 2020-01-22 | Garbage classification device based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111259977A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111695641A (en) * | 2020-06-22 | 2020-09-22 | 中国银行股份有限公司 | Garbage classification method and device |
| CN111709477A (en) * | 2020-06-16 | 2020-09-25 | 浪潮集团有限公司 | Method and tool for garbage classification based on improved MobileNet network |
| CN111814750A (en) * | 2020-08-14 | 2020-10-23 | 深延科技(北京)有限公司 | Intelligent garbage classification method and system based on deep learning target detection and image recognition |
| CN112508094A (en) * | 2020-07-24 | 2021-03-16 | 完美世界(北京)软件科技发展有限公司 | Junk picture identification method, device and equipment |
| CN112732962A (en) * | 2021-01-12 | 2021-04-30 | 南京大学 | Online real-time junk image category prediction method based on deep learning and Flink |
| CN113052005A (en) * | 2021-02-08 | 2021-06-29 | 湖南工业大学 | Garbage sorting method and garbage sorting device for home service |
| CN113076992A (en) * | 2021-03-31 | 2021-07-06 | 武汉理工大学 | Household garbage detection method and device |
| CN114723999A (en) * | 2022-05-24 | 2022-07-08 | 航天宏图信息技术股份有限公司 | Garbage identification method and device based on unmanned aerial vehicle orthographic image |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014179667A2 (en) * | 2013-05-03 | 2014-11-06 | Ecowastehub Corp. | Solid waste identification & segregation system |
| CN105501744A (en) * | 2015-12-22 | 2016-04-20 | 周现荣 | Intelligent network garbage can capable of classifying garbage according to garbage names |
| DE202019103055U1 (en) * | 2018-08-03 | 2019-06-12 | Yu Hsuan Yang | Automatic waste sorting facility |
| CN110119662A (en) * | 2018-03-29 | 2019-08-13 | 王胜春 | A kind of rubbish category identification system based on deep learning |
| CN110245559A (en) * | 2019-05-09 | 2019-09-17 | 平安科技（深圳）有限公司 | Real-time object identification method, device and computer equipment |
| CN110498152A (en) * | 2019-09-18 | 2019-11-26 | 福州大学 | A kind of intelligent classification dustbin and its method based on AI |
| CN110502616A (en) * | 2019-08-29 | 2019-11-26 | 上海墨百意信息科技有限公司 | A kind of method, equipment and the computer storage medium of determining garbage classification |
| CN110543573A (en) * | 2019-08-28 | 2019-12-06 | 珠海格力电器股份有限公司 | knowledge graph-based garbage classification method and device |
-
2020
- 2020-01-22 CN CN202010075011.1A patent/CN111259977A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014179667A2 (en) * | 2013-05-03 | 2014-11-06 | Ecowastehub Corp. | Solid waste identification & segregation system |
| CN105501744A (en) * | 2015-12-22 | 2016-04-20 | 周现荣 | Intelligent network garbage can capable of classifying garbage according to garbage names |
| CN110119662A (en) * | 2018-03-29 | 2019-08-13 | 王胜春 | A kind of rubbish category identification system based on deep learning |
| DE202019103055U1 (en) * | 2018-08-03 | 2019-06-12 | Yu Hsuan Yang | Automatic waste sorting facility |
| CN110245559A (en) * | 2019-05-09 | 2019-09-17 | 平安科技（深圳）有限公司 | Real-time object identification method, device and computer equipment |
| CN110543573A (en) * | 2019-08-28 | 2019-12-06 | 珠海格力电器股份有限公司 | knowledge graph-based garbage classification method and device |
| CN110502616A (en) * | 2019-08-29 | 2019-11-26 | 上海墨百意信息科技有限公司 | A kind of method, equipment and the computer storage medium of determining garbage classification |
| CN110498152A (en) * | 2019-09-18 | 2019-11-26 | 福州大学 | A kind of intelligent classification dustbin and its method based on AI |
Non-Patent Citations (5)
| Title |
|---|
| MARK SANDLER: "MobileNetV2: Inverted Residuals and Linear Bottlenecks", 《ARXIV:1801.04381V4 [CS.CV]》 * |
| STEPHENN L. RABANO: "Common Garbage Classification Using MobileNet", 《 2018 IEEE 10TH INTERNATIONAL CONFERENCE ON HUMANOID, NANOTECHNOLOGY, INFORMATION TECHNOLOGY,COMMUNICATION AND CONTROL, ENVIRONMENT AND MANAGEMENT (HNICEM)》 * |
| 吴嘉凯: "基于谷歌TensorFlow Object Detection 的"智慧"分类垃圾桶设计", 《科技与创新》 * |
| 张国基，张政国，林聿中: "《基于流记录的网络流量识别关键技术研究》", 北京：北京工业大学出版社, pages: 103 - 104 * |
| 陈超宇: "基于机器视觉与深度学习的医疗垃圾分类系统", 《电脑编程技巧与维护》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111709477A (en) * | 2020-06-16 | 2020-09-25 | 浪潮集团有限公司 | Method and tool for garbage classification based on improved MobileNet network |
| CN111695641A (en) * | 2020-06-22 | 2020-09-22 | 中国银行股份有限公司 | Garbage classification method and device |
| CN112508094A (en) * | 2020-07-24 | 2021-03-16 | 完美世界(北京)软件科技发展有限公司 | Junk picture identification method, device and equipment |
| CN112508094B (en) * | 2020-07-24 | 2023-10-20 | 完美世界(北京)软件科技发展有限公司 | Garbage picture identification method, device and equipment |
| CN111814750A (en) * | 2020-08-14 | 2020-10-23 | 深延科技(北京)有限公司 | Intelligent garbage classification method and system based on deep learning target detection and image recognition |
| CN112732962A (en) * | 2021-01-12 | 2021-04-30 | 南京大学 | Online real-time junk image category prediction method based on deep learning and Flink |
| CN112732962B (en) * | 2021-01-12 | 2023-10-13 | 南京大学 | Online real-time garbage picture category prediction method based on deep learning and Flink |
| CN113052005A (en) * | 2021-02-08 | 2021-06-29 | 湖南工业大学 | Garbage sorting method and garbage sorting device for home service |
| CN113052005B (en) * | 2021-02-08 | 2024-02-02 | 湖南工业大学 | Garbage sorting method and garbage sorting device for household service |
| CN113076992A (en) * | 2021-03-31 | 2021-07-06 | 武汉理工大学 | Household garbage detection method and device |
| CN114723999A (en) * | 2022-05-24 | 2022-07-08 | 航天宏图信息技术股份有限公司 | Garbage identification method and device based on unmanned aerial vehicle orthographic image |
| CN114723999B (en) * | 2022-05-24 | 2022-08-23 | 航天宏图信息技术股份有限公司 | Garbage identification method and device based on unmanned aerial vehicle orthographic image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111259977A (en) | Garbage classification device based on deep learning | |
| CN108664996B (en) | Ancient character recognition method and system based on deep learning | |
| CN111242033B (en) | Video feature learning method based on discriminant analysis of video and text pairs | |
| CN113221687A (en) | Training method of pressing plate state recognition model and pressing plate state recognition method | |
| CN115049966A (en) | GhostNet-based lightweight YOLO pet identification method | |
| CN111581368A (en) | Intelligent expert recommendation-oriented user image drawing method based on convolutional neural network | |
| CN112488162A (en) | Garbage classification method based on active learning | |
| CN111079511A (en) | Document automatic classification and optical character recognition method and system based on deep learning | |
| CN107633058B (en) | Deep learning-based data dynamic filtering system and method | |
| CN112883931A (en) | Real-time true and false motion judgment method based on long and short term memory network | |
| CN110852263A (en) | Mobile phone photographing garbage classification recognition method based on artificial intelligence | |
| CN116597406A (en) | User intention vehicle type recognition method and device based on multiple modes and storage medium | |
| CN115062727A (en) | Graph node classification method and system based on multi-order hypergraph convolutional network | |
| CN111460100A (en) | Criminal legal document and criminal name recommendation method and system | |
| CN114742211A (en) | Convolutional neural network deployment and optimization method facing microcontroller | |
| CN109344309A (en) | Extensive file and picture classification method and system are stacked based on convolutional neural networks | |
| CN113705215A (en) | Meta-learning-based large-scale multi-label text classification method | |
| CN112287836A (en) | Image recognition system and image recognition device based on artificial intelligence | |
| CN111445545A (en) | Text-to-map method, device, storage medium and electronic equipment | |
| CN116758451A (en) | Audio-visual emotion recognition method and system based on multi-scale and global cross attention | |
| CN115565219A (en) | Face quality evaluation model training method based on fusion knowledge distillation | |
| CN112101559B (en) | Case crime name deducing method based on machine learning | |
| CN115348551A (en) | Lightweight service identification method and device, electronic equipment and storage medium | |
| CN114492658A (en) | Real-time household garbage detection method and device, electronic equipment and medium | |
| CN113378627A (en) | Automatic garbage classification method and device based on DSP chip and single chip microcomputer control |
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 |