CN111709477A - Method and tool for garbage classification based on improved MobileNet network - Google Patents
Method and tool for garbage classification based on improved MobileNet network Download PDFInfo
- Publication number
- CN111709477A CN111709477A CN202010551607.4A CN202010551607A CN111709477A CN 111709477 A CN111709477 A CN 111709477A CN 202010551607 A CN202010551607 A CN 202010551607A CN 111709477 A CN111709477 A CN 111709477A
- Authority
- CN
- China
- Prior art keywords
- garbage
- convolution
- mobilenet network
- improved mobilenet
- network
- 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
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000012795 verification Methods 0.000 claims abstract description 47
- 238000012549 training Methods 0.000 claims abstract description 40
- 238000013145 classification model Methods 0.000 claims abstract description 23
- 239000000284 extract Substances 0.000 claims abstract description 5
- 230000004913 activation Effects 0.000 claims description 36
- 210000002569 neuron Anatomy 0.000 claims description 18
- 238000010276 construction Methods 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 7
- 238000000638 solvent extraction Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 3
- 238000005192 partition Methods 0.000 claims description 2
- 239000002699 waste material Substances 0.000 claims description 2
- 238000013135 deep learning Methods 0.000 abstract description 4
- 230000006870 function Effects 0.000 description 33
- 238000013527 convolutional neural network Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010200 validation analysis 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
- G06F18/214—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
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Biomedical Technology (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method and a tool for garbage classification based on an improved MobileNet network, relating to the technical field of deep learning, and the implementation of the method comprises the following steps: collecting a garbage image as an initial data set; marking the garbage images contained in the initial data set according to the garbage types; randomly dividing the marked initial data set into a training set and a verification set; constructing an improved MobileNet network, and training the improved MobileNet network by using a training set so that the improved MobileNet network extracts the characteristics of garbage images contained in the training set; inputting the garbage images contained in the verification set into the trained improved MobileNet network, if the classification result output by the trained improved MobileNet network is completely the same as the mark of the verification set, indicating that the garbage classification model passes the verification, and deploying the verified improved MobileNet network as the garbage classification model to the edge device to complete the classification of the garbage images. The invention can reduce the parameter quantity and the operation quantity of the improved MobileNet network under the condition of less loss of precision, and is deployed on edge equipment for use.
Description
Technical Field
The invention relates to the technical field of deep learning, in particular to a method and a tool for garbage classification based on an improved MobileNet network.
Background
The garbage classification refers to a general term of a series of activities for classifying, storing, putting and carrying garbage according to a certain rule or standard so as to convert the garbage into public resources. The classification aims to improve the resource value and the economic value of the garbage and strive for making the best use of the garbage. However, it is still difficult to accurately classify garbage in daily life, especially dry garbage, wet garbage, etc.
Garbage classification is essentially an image classification problem, and with the development of deep learning, Convolutional Neural Networks (CNNs) have made great progress in image classification. The convolutional neural network can extract image characteristic information more accurately, so that the target category can be determined more accurately. However, the target detection model trained by the traditional deep learning method usually contains a large number of parameters, the model is large in size and needs GPU support, and the model is difficult to deploy on the edge-end device.
Disclosure of Invention
Aiming at the requirements and the defects of the prior art development, the invention provides a method and a tool for classifying garbage based on an improved MobileNet network.
Firstly, the invention discloses a method for classifying garbage based on an improved MobileNet network, which adopts the following technical scheme for solving the technical problems:
a method for garbage classification based on an improved MobileNet network comprises the following implementation processes:
step 1, collecting a garbage image as an initial data set;
step 2, marking the garbage images contained in the initial data set according to the garbage types;
step 3, randomly dividing the marked initial data set into a training set and a verification set, wherein the number of samples contained in the training set is greater than that of samples contained in the verification set;
step 4, constructing an improved MobileNet network, and training the improved MobileNet network by using a training set so that the improved MobileNet network extracts the characteristics of the garbage images contained in the training set;
step 5, inputting the garbage images contained in the verification set into the trained improved MobileNet network, if the classification result output by the improved MobileNet network is completely the same as the mark of the verification set, indicating that the improved MobileNet network passes the verification, and taking the verified improved MobileNet network as a garbage classification model;
and 6, deploying the garbage classification model to the edge equipment, collecting the input garbage image through a camera of the edge equipment, and inputting the collected garbage image into the garbage classification model.
Further, the labeled initial data set is randomly divided into a training set and a validation set according to a ratio of 9:1, 8:2 or 7: 3.
Further, the marked initial data set is randomly divided by using a splitting function train _ test _ split ().
Further, the improved MobileNet network comprises:
1) depth separable convolution:
the depth separable Convolution decomposes the conventional Convolution into a depth Convolution Depthwise contribution and a point-by-point Convolution Pointwise contribution, wherein,
the deep Convolution Depthwise Convolution divides the input picture into three groups, performs 3 × 3 Convolution for each group, respectively, collects spatial features of each channel,
performing 1 × 1 Convolution on the input picture by point-by-point Convolution Pointwise Convolution, and collecting the characteristics of each point;
2) activation function:
the output layer is represented by a softmax activation function:
in the softmax activation function, z defines a vector input by an output layer, j is a fixed neuron of the output layer, namely a neuron to be calculated, and K is the number of the neurons;
all convolutional layers except the output layer use the ReLU activation function:
in the ReLU activation function, x is the value of the function on the x axis;
3) a residual model;
4) the network structure is as follows:
an improved MobileNet network model is constructed by using the depth separable convolution of MobileNet in combination with a residual error structure.
Preferably, in the modified MobileNet network, the classification of the softmax activation function is implemented using python.
Secondly, this send discloses a tool based on improve MobileNet network and carry out waste classification, solves the technical scheme that above-mentioned technical problem adopted as follows:
a tool for garbage classification based on an improved MobileNet network, which structurally comprises:
the acquisition module is used for acquiring the garbage images and storing the garbage images in the initial data set;
the marking module is used for marking the garbage images contained in the initial data set according to the garbage types;
the dividing module is used for randomly dividing the marked initial data set into a training set and a verification set, and the number of samples contained in the training set is greater than that of samples contained in the verification set;
the construction module is used for constructing an improved MobileNet network, training the improved MobileNet network by a training set and enabling the improved MobileNet network to extract the characteristics of the garbage images contained in the training set;
and the verification module is used for verifying the trained improved MobileNet network by utilizing the garbage images contained in the verification set, if the classification result output by the improved MobileNet network is completely the same as the mark of the verification set, the trained improved MobileNet network passes the verification, then the trained improved MobileNet network passing the verification is used as a garbage classification model, the garbage classification model is deployed in the edge equipment, and garbage classification is carried out according to the images acquired by the edge equipment.
Optionally, the related partitioning module randomly partitions the labeled initial data set into the training set and the verification set according to a ratio of 9:1, 8:2 or 7: 3.
Preferably, the partitioning module concerned uses the partitioning function train _ test _ split ().
Optionally, the improved MobileNet network constructed by the related construction modules includes:
1) depth separable convolution:
the depth separable Convolution decomposes the conventional Convolution into a depth Convolution Depthwise contribution and a point-by-point Convolution Pointwise contribution, wherein,
the deep Convolution Depthwise Convolution divides the input picture into three groups, performs 3 × 3 Convolution for each group, respectively, collects spatial features of each channel,
performing 1 × 1 Convolution on the input picture by point-by-point Convolution Pointwise Convolution, and collecting the characteristics of each point;
2) activation function:
the output layer is represented by a softmax activation function:
in the softmax activation function, z defines a vector input by an output layer, j is a fixed neuron of the output layer, namely a neuron to be calculated, and K is the number of the neurons;
all convolutional layers except the output layer use the ReLU activation function:
in the ReLU activation function, x is the value of the function on the x axis;
3) a residual model;
4) the network structure is as follows:
an improved MobileNet network model is constructed by using the depth separable convolution of MobileNet in combination with a residual error structure.
Preferably, the method relates to an improved MobileNet network, and classification of the softmax activation function is realized by using python.
Compared with the prior art, the method and the tool for classifying the garbage based on the improved MobileNet network have the beneficial effects that:
the invention realizes the classification of the garbage images by improving the MobileNet network, can greatly reduce the parameters and the calculation amount of the improved MobileNet network under the condition of less precision loss, and the trained improved MobileNet network can be deployed on edge-end equipment as a garbage classification model.
Drawings
FIG. 1 is a flow chart of a method according to a first embodiment of the present invention;
fig. 2 is a structural frame diagram of a second embodiment of the present invention.
The reference information in the drawings indicates:
1. an acquisition module, 2, a marking module, 3, a dividing module, 4, a construction module,
5. and (3) improving a MobileNet network 6, a verification module 7 and a garbage classification model.
Detailed Description
In order to make the technical scheme, the technical problems to be solved and the technical effects of the present invention more clearly apparent, the following technical scheme of the present invention is clearly and completely described with reference to the specific embodiments.
The first embodiment is as follows:
with reference to fig. 1, this embodiment provides a method for performing garbage classification based on an improved MobileNet network, where the implementation process of the method includes:
and step S1, collecting the garbage image as an initial data set.
Step S2 is to mark the garbage image included in the initial data set according to the garbage type.
And step S3, randomly dividing the marked initial data set into a training set and a verification set, wherein the number of samples contained in the training set is greater than that of the samples contained in the verification set. In this embodiment, the marked initial data set is randomly divided into a training set and a verification set according to a ratio of 8:2 by using a splitting function train _ test _ split ().
Step S4, constructing an improved MobileNet network 5, where the improved MobileNet network 5 includes:
1) depth separable convolution:
the depth separable Convolution decomposes the conventional Convolution into a depth Convolution Depthwise contribution and a point-by-point Convolution Pointwise contribution, wherein,
the deep Convolution Depthwise Convolution divides the input picture into three groups, performs 3 × 3 Convolution for each group, respectively, collects spatial features of each channel,
performing 1 × 1 Convolution on the input picture by point-by-point Convolution Pointwise Convolution, and collecting the characteristics of each point;
2) activation function:
the output layer is represented by a softmax activation function:
in the softmax activation function, z defines a vector input by an output layer, j is a fixed neuron of the output layer, namely a neuron to be calculated, and K is the number of the neurons;
all convolutional layers except the output layer use the ReLU activation function:
in the ReLU activation function, x is the value of the function on the x axis;
3) a residual model;
4) the network structure is as follows:
an improved MobileNet network 5 model was constructed using the depth separable convolution of MobileNet in combination with the residual structure.
In the modified MobileNet network 5, classification of the softmax activation function is implemented using python.
And training the improved MobileNet network 5 by using the training set so that the improved MobileNet network 5 extracts the features of the garbage images contained in the training set.
And step S5, inputting the spam images contained in the verification set into the trained improved MobileNet network 5, and if the classification result output by the improved MobileNet network 5 is completely the same as the mark of the verification set, indicating that the improved MobileNet network 5 passes the verification and taking the verified improved MobileNet network 5 as a spam classification model 7.
And step S6, deploying the garbage classification model 7 to the edge device, collecting the input garbage image through a camera of the edge device, and inputting the collected garbage image into the garbage classification model 7.
Example two:
with reference to fig. 2, this embodiment provides a tool for classifying garbage based on an improved MobileNet network, and the structure of the tool includes:
the acquisition module 1 is used for acquiring garbage images and storing the garbage images in an initial data set;
the marking module 2 is used for marking the garbage images contained in the initial data set according to the garbage types;
the dividing module 3 is used for randomly dividing the marked initial data set into a training set and a verification set, wherein the number of samples contained in the training set is greater than that of samples contained in the verification set;
the construction module 4 is used for constructing an improved MobileNet network 5, training the improved MobileNet network 5 by a training set, and enabling the improved MobileNet network 5 to extract the characteristics of the garbage images contained in the training set;
and the verification module 6 is used for verifying the trained improved MobileNet network 5 by utilizing the spam images contained in the verification set, if the classification result output by the improved MobileNet network 5 is completely the same as the mark of the verification set, the trained improved MobileNet network 5 passes the verification, then the trained improved MobileNet network 5 passing the verification is used as a spam classification model 7, and the spam classification model 7 is deployed in the edge device and performs spam classification according to the images acquired by the edge device.
In this embodiment, the dividing module 3 selects a dividing function train _ test _ split (), and the dividing function train _ test _ split () randomly divides the marked initial data set into the training set and the verification set according to a ratio of 9: 1.
In this embodiment, the improved MobileNet network 5 constructed by the construction module 4 includes:
1) depth separable convolution:
the depth separable Convolution decomposes the conventional Convolution into a depth Convolution Depthwise contribution and a point-by-point Convolution Pointwise contribution, wherein,
the deep Convolution Depthwise Convolution divides the input picture into three groups, performs 3 × 3 Convolution for each group, respectively, collects spatial features of each channel,
performing 1 × 1 Convolution on the input picture by point-by-point Convolution Pointwise Convolution, and collecting the characteristics of each point;
2) activation function:
the output layer is represented by a softmax activation function:
in the softmax activation function, z defines a vector input by an output layer, j is a fixed neuron of the output layer, namely a neuron to be calculated, and K is the number of the neurons;
all convolutional layers except the output layer use the ReLU activation function:
in the ReLU activation function, x is the value of the function on the x axis;
3) a residual model;
4) the network structure is as follows:
an improved MobileNet network 5 model was constructed using the depth separable convolution of MobileNet in combination with the residual structure.
The MobileNet network 5 was modified to implement classification of softmax activation functions using python.
During the use, the garbage classification model 7 that passes this embodiment verification is deployed in edge device, and the image is gathered and is transmitted to garbage classification model 7 through the camera of edge device, and garbage classification model 7 can accomplish the classification according to the received image.
In summary, the method and the tool for classifying the garbage based on the improved MobileNet network realize the classification of the garbage images by the improved MobileNet network 5, can greatly reduce the parameters and the computation of the improved MobileNet network 5 under the condition of less loss of precision, and the trained improved MobileNet network 5 can be deployed on edge-end equipment as a garbage classification model 7.
The principles and embodiments of the present invention have been described in detail using specific examples, which are provided only to aid in understanding the core technical content of the present invention. Based on the above embodiments of the present invention, those skilled in the art should make any improvements and modifications to the present invention without departing from the principle of the present invention, and therefore, the present invention should fall into the protection scope of the present invention.
Claims (10)
1. A method for garbage classification based on an improved MobileNet network is characterized in that the implementation process of the method comprises the following steps:
step 1, collecting a garbage image as an initial data set;
step 2, marking the garbage images contained in the initial data set according to the garbage types;
step 3, randomly dividing the marked initial data set into a training set and a verification set, wherein the number of samples contained in the training set is greater than that of samples contained in the verification set;
step 4, constructing an improved MobileNet network, and training the improved MobileNet network by using a training set so that the improved MobileNet network extracts the characteristics of the garbage images contained in the training set;
step 5, inputting the garbage images contained in the verification set into the trained improved MobileNet network, if the classification result output by the improved MobileNet network is completely the same as the mark of the verification set, indicating that the improved MobileNet network passes the verification, and taking the verified improved MobileNet network as a garbage classification model;
and 6, deploying the garbage classification model to the edge equipment, collecting the input garbage image through a camera of the edge equipment, and inputting the collected garbage image into the garbage classification model.
2. The method of claim 1, wherein the labeled initial data set is randomly divided into training set and verification set according to a 9:1, 8:2 or 7:3 ratio.
3. The method of claim 2, wherein the labeled initial data set is randomly divided by a partition function train _ test _ split ().
4. The method of claim 1, wherein the improved MobileNet network comprises:
1) depth separable convolution:
the depth separable Convolution decomposes the conventional Convolution into a depth Convolution Depthwise contribution and a point-by-point Convolution Pointwise contribution, wherein,
the deep Convolution Depthwise Convolution divides the input picture into three groups, performs 3 × 3 Convolution for each group, respectively, collects spatial features of each channel,
performing 1 × 1 Convolution on the input picture by point-by-point Convolution Pointwise Convolution, and collecting the characteristics of each point;
2) activation function:
the output layer is represented by a softmax activation function:
in the softmax activation function, z defines a vector input by an output layer, j is a fixed neuron of the output layer, namely a neuron to be calculated, and K is the number of the neurons;
all convolutional layers except the output layer use the ReLU activation function:
in the ReLU activation function, x is the value of the function on the x axis;
3) a residual model;
4) the network structure is as follows:
an improved MobileNet network model is constructed by using the depth separable convolution of MobileNet in combination with a residual error structure.
5. The method of claim 4, wherein the classification of the softmax activation function is implemented using python in the modified MobileNet network.
6. The utility model provides a tool for waste classification based on improve MobileNet network which characterized in that, its structure includes:
the acquisition module is used for acquiring the garbage images and storing the garbage images in the initial data set;
the marking module is used for marking the garbage images contained in the initial data set according to the garbage types;
the dividing module is used for randomly dividing the marked initial data set into a training set and a verification set, and the number of samples contained in the training set is greater than that of samples contained in the verification set;
the construction module is used for constructing an improved MobileNet network, training the improved MobileNet network by a training set and enabling the improved MobileNet network to extract the characteristics of the garbage images contained in the training set;
and the verification module is used for verifying the trained improved MobileNet network by utilizing the garbage images contained in the verification set, if the classification result output by the improved MobileNet network is completely the same as the mark of the verification set, the trained improved MobileNet network passes the verification, then the trained improved MobileNet network passing the verification is used as a garbage classification model, the garbage classification model is deployed in the edge equipment, and garbage classification is carried out according to the images acquired by the edge equipment.
7. The tool for garbage classification based on the improved MobileNet network according to claim 6, wherein the dividing module randomly divides the marked initial data set into the training set and the verification set according to a ratio of 9:1, 8:2 or 7: 3.
8. The tool for garbage classification based on an improved MobileNet network as claimed in claim 7, wherein said partitioning module selects a partitioning function train _ test _ split ().
9. The tool for performing garbage classification based on the improved MobileNet network according to claim 6, wherein the improved MobileNet network constructed by the construction module comprises:
1) depth separable convolution:
the depth separable Convolution decomposes the conventional Convolution into a depth Convolution Depthwise contribution and a point-by-point Convolution Pointwise contribution, wherein,
the deep Convolution Depthwise Convolution divides the input picture into three groups, performs 3 × 3 Convolution for each group, respectively, collects spatial features of each channel,
performing 1 × 1 Convolution on the input picture by point-by-point Convolution Pointwise Convolution, and collecting the characteristics of each point;
2) activation function:
the output layer is represented by a softmax activation function:
in the softmax activation function, z defines a vector input by an output layer, j is a fixed neuron of the output layer, namely a neuron to be calculated, and K is the number of the neurons;
all convolutional layers except the output layer use the ReLU activation function:
in the ReLU activation function, x is the value of the function on the x axis;
3) a residual model;
4) the network structure is as follows:
an improved MobileNet network model is constructed by using the depth separable convolution of MobileNet in combination with a residual error structure.
10. The tool for performing garbage classification based on the modified MobileNet network recited in claim 9, wherein the modified MobileNet network uses python to perform classification of softmax activation function.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010551607.4A CN111709477A (en) | 2020-06-16 | 2020-06-16 | Method and tool for garbage classification based on improved MobileNet network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010551607.4A CN111709477A (en) | 2020-06-16 | 2020-06-16 | Method and tool for garbage classification based on improved MobileNet network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111709477A true CN111709477A (en) | 2020-09-25 |
Family
ID=72540682
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010551607.4A Pending CN111709477A (en) | 2020-06-16 | 2020-06-16 | Method and tool for garbage classification based on improved MobileNet network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111709477A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112257799A (en) * | 2020-10-30 | 2021-01-22 | 电子科技大学中山学院 | Method, system and device for detecting household garbage target |
CN112560576A (en) * | 2020-11-09 | 2021-03-26 | 华南农业大学 | AI map recognition garbage classification and intelligent recovery method |
CN113269300A (en) * | 2021-04-14 | 2021-08-17 | 广州晟烨信息科技股份有限公司 | Face collection feature training method, system and storage medium |
CN113562355A (en) * | 2021-08-10 | 2021-10-29 | 南京航空航天大学 | Intelligent garbage sorting device and method based on deep learning technology |
CN114782762A (en) * | 2022-06-23 | 2022-07-22 | 南京信息工程大学 | Garbage image detection method and community garbage station |
CN115409993A (en) * | 2022-08-12 | 2022-11-29 | 通号智慧城市研究设计院有限公司 | Detection method of environmental garbage, electronic equipment and computer readable medium |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110119662A (en) * | 2018-03-29 | 2019-08-13 | 王胜春 | A kind of rubbish category identification system based on deep learning |
CN110598800A (en) * | 2019-09-23 | 2019-12-20 | 山东浪潮人工智能研究院有限公司 | Garbage classification and identification method based on artificial intelligence |
CN110697275A (en) * | 2019-09-01 | 2020-01-17 | 阿尔飞思(昆山)智能物联科技有限公司 | Embedded intelligent garbage classification system and working method thereof |
CN110723432A (en) * | 2019-09-20 | 2020-01-24 | 精锐视觉智能科技(深圳)有限公司 | Garbage classification method and augmented reality equipment |
CN110852420A (en) * | 2019-11-11 | 2020-02-28 | 北京智能工场科技有限公司 | Garbage classification method based on artificial intelligence |
CN111079639A (en) * | 2019-12-13 | 2020-04-28 | 中国平安财产保险股份有限公司 | Method, device and equipment for constructing garbage image classification model and storage medium |
CN111104961A (en) * | 2019-10-31 | 2020-05-05 | 太原理工大学 | Method for classifying breast cancer based on improved MobileNet network |
CN111126333A (en) * | 2019-12-30 | 2020-05-08 | 齐齐哈尔大学 | Garbage classification method based on light convolutional neural network |
CN111144496A (en) * | 2019-12-27 | 2020-05-12 | 齐齐哈尔大学 | Garbage classification method based on hybrid convolutional neural network |
CN111259977A (en) * | 2020-01-22 | 2020-06-09 | 浙江工业大学 | Garbage classification device based on deep learning |
-
2020
- 2020-06-16 CN CN202010551607.4A patent/CN111709477A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110119662A (en) * | 2018-03-29 | 2019-08-13 | 王胜春 | A kind of rubbish category identification system based on deep learning |
CN110697275A (en) * | 2019-09-01 | 2020-01-17 | 阿尔飞思(昆山)智能物联科技有限公司 | Embedded intelligent garbage classification system and working method thereof |
CN110723432A (en) * | 2019-09-20 | 2020-01-24 | 精锐视觉智能科技(深圳)有限公司 | Garbage classification method and augmented reality equipment |
CN110598800A (en) * | 2019-09-23 | 2019-12-20 | 山东浪潮人工智能研究院有限公司 | Garbage classification and identification method based on artificial intelligence |
CN111104961A (en) * | 2019-10-31 | 2020-05-05 | 太原理工大学 | Method for classifying breast cancer based on improved MobileNet network |
CN110852420A (en) * | 2019-11-11 | 2020-02-28 | 北京智能工场科技有限公司 | Garbage classification method based on artificial intelligence |
CN111079639A (en) * | 2019-12-13 | 2020-04-28 | 中国平安财产保险股份有限公司 | Method, device and equipment for constructing garbage image classification model and storage medium |
CN111144496A (en) * | 2019-12-27 | 2020-05-12 | 齐齐哈尔大学 | Garbage classification method based on hybrid convolutional neural network |
CN111126333A (en) * | 2019-12-30 | 2020-05-08 | 齐齐哈尔大学 | Garbage classification method based on light convolutional neural network |
CN111259977A (en) * | 2020-01-22 | 2020-06-09 | 浙江工业大学 | Garbage classification device based on deep learning |
Non-Patent Citations (2)
Title |
---|
STEPHENN L.RABANO等: "Common GarbageClassification Using MobileNet", 《2018IEEE 10TH INTERNATIONAL CONFERENCE ONHUMANOID,NANOTECHNOLOGY,INFORMATION TECHNOLOGY,COMMUNICATION AND CONTROL,ENVIRONMENT AND MANAGEMENT(HNICEM)》 * |
陈宇超等: "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 (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112257799A (en) * | 2020-10-30 | 2021-01-22 | 电子科技大学中山学院 | Method, system and device for detecting household garbage target |
CN112560576A (en) * | 2020-11-09 | 2021-03-26 | 华南农业大学 | AI map recognition garbage classification and intelligent recovery method |
CN112560576B (en) * | 2020-11-09 | 2022-09-16 | 华南农业大学 | AI map recognition garbage classification and intelligent recovery method |
CN113269300A (en) * | 2021-04-14 | 2021-08-17 | 广州晟烨信息科技股份有限公司 | Face collection feature training method, system and storage medium |
CN113562355A (en) * | 2021-08-10 | 2021-10-29 | 南京航空航天大学 | Intelligent garbage sorting device and method based on deep learning technology |
CN114782762A (en) * | 2022-06-23 | 2022-07-22 | 南京信息工程大学 | Garbage image detection method and community garbage station |
CN114782762B (en) * | 2022-06-23 | 2022-08-26 | 南京信息工程大学 | Garbage image detection method and community garbage station |
CN115409993A (en) * | 2022-08-12 | 2022-11-29 | 通号智慧城市研究设计院有限公司 | Detection method of environmental garbage, electronic equipment and computer readable medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111709477A (en) | Method and tool for garbage classification based on improved MobileNet network | |
CN111738315B (en) | Image classification method based on countermeasure fusion multi-source transfer learning | |
CN107633255A (en) | A kind of rock lithology automatic recognition classification method under deep learning pattern | |
CN112308158A (en) | Multi-source field self-adaptive model and method based on partial feature alignment | |
CN108388927A (en) | Small sample polarization SAR terrain classification method based on the twin network of depth convolution | |
CN109639481A (en) | A kind of net flow assorted method, system and electronic equipment based on deep learning | |
CN107506722A (en) | One kind is based on depth sparse convolution neutral net face emotion identification method | |
CN107341506A (en) | A kind of Image emotional semantic classification method based on the expression of many-sided deep learning | |
CN105825511A (en) | Image background definition detection method based on deep learning | |
CN107016405A (en) | A kind of insect image classification method based on classification prediction convolutional neural networks | |
CN106790019A (en) | The encryption method for recognizing flux and device of feature based self study | |
CN107506793A (en) | Clothes recognition methods and system based on weak mark image | |
CN112668630B (en) | Lightweight image classification method, system and equipment based on model pruning | |
CN109919252A (en) | The method for generating classifier using a small number of mark images | |
CN106650823A (en) | Probability extreme learning machine integration-based foam nickel surface defect classification method | |
CN112232328A (en) | Remote sensing image building area extraction method and device based on convolutional neural network | |
CN112818969A (en) | Knowledge distillation-based face pose estimation method and system | |
CN108875482A (en) | Object detecting method and device, neural network training method and device | |
CN110827260A (en) | Cloth defect classification method based on LBP (local binary pattern) features and convolutional neural network | |
CN109410184A (en) | Live streaming pornographic image detection method based on dense confrontation network semi-supervised learning | |
CN115862073A (en) | Transformer substation harmful bird species target detection and identification method based on machine vision | |
CN108447048B (en) | Convolutional neural network image feature processing method based on attention layer | |
CN115359353A (en) | Flower identification and classification method and device | |
CN106203296A (en) | The video actions recognition methods of one attribute auxiliary | |
CN107886065A (en) | A kind of Serial No. recognition methods of mixing script |
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 |
Application publication date: 20200925 |
|
RJ01 | Rejection of invention patent application after publication |