CN110610201B - Kitchen waste recycling and classifying method and system, mobile terminal and storage medium - Google Patents
Kitchen waste recycling and classifying method and system, mobile terminal and storage medium Download PDFInfo
- Publication number
- CN110610201B CN110610201B CN201910813678.4A CN201910813678A CN110610201B CN 110610201 B CN110610201 B CN 110610201B CN 201910813678 A CN201910813678 A CN 201910813678A CN 110610201 B CN110610201 B CN 110610201B
- Authority
- CN
- China
- Prior art keywords
- kitchen waste
- data
- classification
- model
- kitchen
- 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.)
- Active
Links
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
- G06F18/241—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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Processing Of Solid Wastes (AREA)
Abstract
The invention is suitable for the technical field of kitchen waste recovery, and provides a kitchen waste recovery classification method, a system, a mobile terminal and a storage medium, wherein the method comprises the following steps: carrying out model construction on a preset SSD model according to a preset segmentation network to obtain a kitchen waste classification model; acquiring kitchen waste data and non-kitchen waste data, and labeling the kitchen waste data and the non-kitchen waste data respectively; performing model training on the kitchen waste classification model according to the labeling result; acquiring image data of the articles to be classified, inputting the image data into the kitchen waste classification model for classification analysis, and classifying the articles to be classified according to the classification result. According to the kitchen waste classification method, the kitchen waste classification model is constructed based on the kitchen waste classification model, kitchen waste is classified in an automatic mode, the classification efficiency and the recovery efficiency of kitchen waste or non-kitchen waste are greatly improved, manpower and material resources are saved, and the kitchen waste classification model is high in accuracy and high in data processing speed due to the combined design of the segmentation network and the SSD model.
Description
Technical Field
The invention belongs to the technical field of kitchen waste recycling, and particularly relates to a kitchen waste recycling and classifying method, a system, a mobile terminal and a storage medium.
Background
With the vigorous development of science and technology and the improvement of environmental awareness, many countries have utilized the concept of multi-waste treatment to classify kitchen wastes to achieve the purpose of effective resource utilization, however, the restaurant often faces the problems of kitchen wastes and non-kitchen wastes, and the waste in the restaurant is mixed with leftovers, chopsticks, bowls, toilet paper and the like, so that the kitchen waste recovery efficiency is low, and therefore, the classification problem of kitchen wastes and non-kitchen wastes is more and more emphasized by people.
Among the recovery process of current kitchen surplus and non-kitchen surplus, all carry out the classification of kitchen surplus and non-kitchen surplus through adopting artifical manual mode to make things convenient for the follow-up recovery to kitchen surplus or non-kitchen surplus, nevertheless owing to adopt artifical manual classification, make the dining room need additionally increase manpower and time and carry out waste classification, and then lead to the human cost higher and classification efficiency low.
Disclosure of Invention
The technical problems to be solved by the embodiment of the invention are that the manual classification of kitchen waste and non-kitchen waste is carried out manually, so that the labor cost is high and the classification efficiency is low.
The embodiment of the invention is realized in such a way that a kitchen waste recycling and classifying method comprises the following steps:
carrying out model construction on a preset SSD model according to a preset segmentation network to obtain a kitchen waste classification model;
acquiring kitchen waste data and non-kitchen waste data, and labeling the kitchen waste data and the non-kitchen waste data respectively;
performing model training on the kitchen waste classification model according to the labeling result;
and acquiring image data of the articles to be classified, inputting the image data into the kitchen waste classification model for classification analysis, and classifying the articles to be classified according to a classification result.
Further, after the step of labeling the kitchen waste data and the non-kitchen waste data, respectively, the method further includes:
and preprocessing the kitchen waste data and the non-kitchen waste data by utilizing a multi-mode two-dimensional discrete wavelet algorithm in combination with rotation, cutting and scaling operations, so that the size of the kitchen waste data after multiple analysis is utilized and the multiple time and frequency analysis of an original wavelet function is reserved.
Further, before the step of performing model training on the kitchen waste classification model according to the labeling result, the method further includes:
converting the kitchen waste data and the non-kitchen waste data into binary formats respectively, and packaging the binary formats with corresponding labels;
and serializing the kitchen waste data and the non-kitchen waste data into character strings according to the packaging result, and storing the character strings into a preset format file.
Furthermore, the network in the kitchen waste classification model adopts a loss function as a composite loss function, and comprises a class and a prediction frame, and a weighted sum of the loss of the target in the prediction frame, and the model parameters are updated through back propagation of the loss function, and the model training is completed through iteration for preset times.
Further, the step of inputting the image data into the kitchen waste classification model for classification analysis comprises:
converting the image data into a network input format, and inputting the image data after format conversion into the kitchen waste classification model for prediction;
and regressing a target frame, the center coordinates and the belonged category by adopting a softmax function, wherein the belonged category is a kitchen waste category or a non-kitchen waste category.
Further, the framework of the predetermined partition network has thirteen deconvolution layers, four upsampling layers, two maximum pooling layers of interest, and one fusion layer.
Another object of an embodiment of the present invention is to provide a kitchen waste recycling and sorting system, including:
the model construction module is used for carrying out model construction on a preset SSD model according to a preset segmentation network so as to obtain a kitchen waste classification model;
the data marking module is used for acquiring kitchen waste data and non-kitchen waste data and marking the kitchen waste data and the non-kitchen waste data respectively;
the model training module is used for carrying out model training on the kitchen waste classification model according to the labeling result;
and the article classification module is used for acquiring image data of the articles to be classified, inputting the image data into the kitchen waste classification model for classification analysis, and classifying the articles to be classified according to the classification result.
Further, the kitchen waste recycling and classifying system further comprises:
and the data preprocessing module is used for preprocessing the kitchen waste data and the non-kitchen waste data by utilizing a multi-mode two-dimensional discrete wavelet algorithm in combination with rotation, cutting and scaling operations so as to utilize the size of the kitchen waste data after multiple analysis and keep multiple time and frequency analysis of an original wavelet function.
Another object of an embodiment of the present invention is to provide a mobile terminal, including a storage device and a processor, where the storage device is used to store a computer program, and the processor runs the computer program to make the mobile terminal execute the kitchen waste recycling classification method.
Another object of an embodiment of the present invention is to provide a storage medium storing a computer program used in the mobile terminal, wherein the computer program, when executed by a processor, implements the steps of the kitchen waste recycling and classifying method.
According to the kitchen waste classification model and the kitchen waste recovery method, the kitchen waste classification model is built based on the kitchen waste classification model, kitchen waste is automatically classified, the classification efficiency and the recovery efficiency of kitchen waste or non-kitchen waste are greatly improved, manpower and material resources are saved, and the kitchen waste classification model is high in accuracy and high in data processing speed due to the combined design of the segmentation network and the SSD model.
Drawings
FIG. 1 is a flow chart of a kitchen waste recycling and sorting method according to a first embodiment of the present invention;
FIG. 2 is a flow chart of a kitchen waste recycling and sorting method according to a second embodiment of the present invention;
FIG. 3 is a schematic diagram of a kitchen waste recycling and sorting system according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a mobile terminal according to a fourth 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 is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
In order to explain the technical means of the present invention, the following description will be given by way of specific examples.
In the existing kitchen waste recycling process, the kitchen waste and the non-kitchen waste are classified in a manual mode, so that the restaurant needs extra manpower and time for waste classification, the manpower cost is high, and the classification efficiency is low.
Example one
Referring to fig. 1, a flowchart of a kitchen waste recycling and sorting method according to a first embodiment of the present invention includes the steps of:
step S10, performing model construction on a preset SSD model according to a preset segmentation network to obtain a kitchen waste classification model;
the method comprises the following steps that a global Instance segmentation network (Instance segmentation network) is newly added on the basis of an SSD model, pixel-level object segmentation is carried out on a background and a foreground, the object identification rate is enhanced, the framework of the preset segmentation network comprises thirteen deconvolution layers, four upper sampling layers, two interested maximum pooling layers and a fusion layer, the SSD network is a network structure combining the advantages of Yolo and Faster than that of Faster RCNN, and the speed is higher than that of the Faster RCNN, and the accuracy is better than that of the Yolo;
step S20, kitchen waste data and non-kitchen waste data are obtained and marked respectively;
the kitchen remainder data and the non-kitchen remainder data can be stored and transmitted in an image mode, a plurality of different images are stored in the kitchen remainder data and the non-kitchen remainder data, the images correspond to kitchen remainders and non-kitchen remainders, for example, the images stored in the kitchen remainder data comprise leftovers, remaining fruits and the like, and the non-kitchen remainders comprise chopsticks, bowls, spoons and the like;
preferably, the label in this step is used for marking positive data and negative data of the kitchen waste data and the non-kitchen waste data, that is, positive marking is performed on the picture stored in the kitchen waste data, and negative marking is performed on the picture stored in the non-kitchen waste data, so as to facilitate the subsequent training of the model;
step S30, performing model training on the kitchen waste classification model according to the labeling result;
the network in the kitchen waste classification model adopts a loss function as a composite loss function, and comprises a category and a prediction frame, and a weighted sum of target loss in the prediction frame, and model parameters are updated through back propagation of the loss function, and model training is completed through iteration of preset times;
step S40, acquiring image data of the articles to be classified, inputting the image data into the kitchen waste classification model for classification analysis, and classifying the articles to be classified according to the classification result;
in this embodiment, a camera is disposed on the garbage conveyor belt, and image data of the to-be-classified article is acquired based on the camera;
this embodiment through the construction based on kitchen remainder classification model to adopt automatic mode to classify kitchen remainder rubbish, improved classification efficiency and recovery efficiency to kitchen remainder or non-kitchen remainder article greatly, saved manpower and materials, and through adopting the combination design of cutting apart network and SSD model, make kitchen remainder classification model accuracy is high and data processing is fast.
Example two
Referring to fig. 2, a flowchart of a kitchen waste recycling and sorting method according to a second embodiment of the present invention is shown, which includes the steps of:
step S11, performing model construction on a preset SSD model according to a preset segmentation network to obtain a kitchen waste classification model;
the method comprises the following steps that a global Instance segmentation network (Instance segmentation network) is newly added on the basis of an SSD model, pixel-level object segmentation is carried out on a background and a foreground, the object identification rate is enhanced, the framework of the preset segmentation network comprises thirteen deconvolution layers, four upper sampling layers, two interested maximum pooling layers and a fusion layer, the SSD network is a network structure combining the advantages of Yolo and Faster than that of Faster RCNN, and the speed is higher than that of the Faster RCNN, and the accuracy is better than that of the Yolo;
step S21, kitchen waste data and non-kitchen waste data are obtained and marked respectively;
the labels in the step are used for marking positive data and negative data of the kitchen waste data and the non-kitchen waste data, namely, positive marks are carried out on pictures stored in the kitchen waste data, and negative marks are carried out on the pictures stored in the non-kitchen waste data, so that the subsequent training of the model is facilitated;
step S31, preprocessing the kitchen waste data and the non-kitchen waste data by using a multi-mode two-dimensional discrete wavelet algorithm in combination with rotation, clipping and scaling operations;
the size of the preprocessed image is utilized to perform multiple analysis, and multiple time and frequency analysis of the original wavelet function is reserved, so that the integrity of the finger vein texture information can be completely reserved by the step of obtaining lower space operation complexity and prediction of the directionality of the image, and the use amount of space memory can be reduced. In addition, compared with other image resolution reduction methods, the method retains more detail (texture) information after wavelet conversion, and is suitable for being applied to kitchen waste classification and identification;
in the step, by designing rotation, cutting and scaling, the diversity of training samples is effectively increased, and the training effect of the model is improved;
step S41, converting the kitchen waste data and the non-kitchen waste data into binary formats respectively, and packaging the binary formats with corresponding labels;
the preprocessed kitchen waste data and the preprocessed non-kitchen waste data are converted into a binary format design, so that the pictures and the corresponding labels thereof are corresponded and processed into data dimensionality of network input, further the subsequent training aiming at the model is effectively facilitated, and the training efficiency of the subsequent kitchen waste classification model is improved;
step S51, serializing the kitchen remainder data and the non-kitchen remainder data into character strings according to the packaging result, and storing the character strings into a preset format file;
the preset format file can be set according to the requirements of a user, and in the embodiment, the preset format file is in a tfrecrd format;
step S61, performing model training on the kitchen waste classification model according to the preset format file;
the network in the kitchen waste classification model adopts a loss function as a composite loss function, and comprises a category and a prediction frame, and a weighted sum of target loss in the prediction frame, and model parameters are updated through back propagation of the loss function, and model training is completed through iteration of preset times;
step S71, acquiring image data of an article to be classified, converting the image data into a network input format, and inputting the image data after format conversion into the kitchen waste classification model for prediction;
in this embodiment, a camera is disposed on the garbage conveyor belt, and image data of the to-be-classified article is acquired based on the camera;
step S81, a target frame, a center coordinate and a belonging category are regressed by adopting a softmax function, and the articles to be classified are classified according to the belonging category;
wherein the category is a kitchen waste category or a non-kitchen waste category;
this embodiment through the construction based on kitchen remainder classification model to adopt automatic mode to classify kitchen remainder rubbish, improved classification efficiency and recovery efficiency to kitchen remainder or non-kitchen remainder article greatly, saved manpower and materials, and through adopting the combination design of cutting apart network and SSD model, make kitchen remainder classification model accuracy is high and data processing is fast.
EXAMPLE III
Referring to fig. 3, a schematic structural diagram of a kitchen waste recycling and sorting system 100 according to a third embodiment of the present invention is shown, including: a model building module 10, a data labeling module 11, a model training module 12 and an article classification module 13, wherein:
the model construction module 10 is configured to perform model construction on a preset SSD model according to a preset segmentation network to obtain a kitchen waste classification model, where a framework of the preset segmentation network includes thirteen deconvolution layers, four upsampling layers, two interested maximum pooling layers, and one fusion layer.
And the data marking module 11 is used for acquiring kitchen waste data and non-kitchen waste data and marking the kitchen waste data and the non-kitchen waste data respectively.
And the model training module 12 is used for performing model training on the kitchen waste classification model according to the labeling result, wherein a loss function is adopted by a network in the kitchen waste classification model as a composite loss function, the composite loss function comprises a class and a prediction frame, and the weighted sum of the target loss in the prediction frame is obtained, model parameters are updated through back propagation of the loss function, and the model training is completed through iteration of preset times.
And the article classification module 13 is used for acquiring image data of an article to be classified, inputting the image data into the kitchen waste classification model for classification analysis, and classifying the article to be classified according to a classification result.
Wherein the item sorting module 13 is further configured to: converting the image data into a network input format, and inputting the image data after format conversion into the kitchen waste classification model for prediction; and regressing a target frame, the center coordinates and the belonged category by adopting a softmax function, wherein the belonged category is a kitchen waste category or a non-kitchen waste category.
Preferably, the kitchen waste recycling and sorting system 100 further includes:
and the data preprocessing module 14 is used for preprocessing the kitchen waste data and the non-kitchen waste data by using a multi-mode two-dimensional discrete wavelet algorithm in combination with rotation, clipping and scaling operations, so that the size of the kitchen waste data after multiple analysis is used and multiple time and frequency analysis of an original wavelet function is reserved.
The format conversion module 15 is used for converting the kitchen waste data and the non-kitchen waste data into binary formats respectively and packaging the binary formats with corresponding labels; and serializing the kitchen waste data and the non-kitchen waste data into character strings according to the packaging result, and storing the character strings into a preset format file.
This embodiment through the construction based on kitchen remainder classification model to adopt automatic mode to classify kitchen remainder rubbish, improved classification efficiency and recovery efficiency to kitchen remainder or non-kitchen remainder article greatly, saved manpower and materials, and through adopting the combination design of cutting apart network and SSD model, make kitchen remainder classification model accuracy is high and data processing is fast.
Example four
Referring to fig. 4, a mobile terminal 101 according to a fourth embodiment of the present invention includes a storage device and a processor, where the storage device is used to store a computer program, and the processor runs the computer program to make the mobile terminal 101 execute the kitchen waste recycling classification method.
The present embodiment also provides a storage medium on which a computer program used in the above-mentioned mobile terminal 101 is stored, which when executed, includes the steps of:
carrying out model construction on a preset SSD model according to a preset segmentation network to obtain a kitchen waste classification model;
acquiring kitchen waste data and non-kitchen waste data, and labeling the kitchen waste data and the non-kitchen waste data respectively;
performing model training on the kitchen waste classification model according to the labeling result;
and acquiring image data of the articles to be classified, inputting the image data into the kitchen waste classification model for classification analysis, and classifying the articles to be classified according to a classification result. The storage medium, such as: ROM/RAM, magnetic disk, optical disk, etc.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is used as an example, in practical applications, the above-mentioned function distribution may be performed by different functional units or modules according to needs, that is, the internal structure of the storage device is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit, and the integrated unit may be implemented in a form of hardware, or may be implemented in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application.
Those skilled in the art will appreciate that the configuration shown in fig. 3 is not intended to be limiting of the present invention and may include more or fewer components than shown, or some components in combination, or a different arrangement of components, and that the method of classifying kitchen waste in fig. 1-2 may be implemented using more or fewer components than shown, or some components in combination, or a different arrangement of components. The units, modules, etc. referred to herein are a series of computer programs that can be executed by a processor (not shown) in the target kitchen waste recycling and sorting system and that can perform specific functions, and all of the computer programs can be stored in a storage device (not shown) of the target kitchen waste recycling and sorting system.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (7)
1. A method of recycling and sorting kitchen waste, the method comprising:
the method comprises the steps that a preset SSD model is modeled according to a preset segmentation network to obtain a kitchen waste classification model, wherein the network in the kitchen waste classification model comprises a classification layer, a prediction frame and a weighted sum of loss of objects in the prediction frame, and the framework of the preset segmentation network comprises thirteen deconvolution layers, four upper sampling layers, two interested maximum pooling layers and a fusion layer;
acquiring kitchen waste data and non-kitchen waste data, and labeling the kitchen waste data and the non-kitchen waste data respectively;
preprocessing the kitchen waste data and the non-kitchen waste data by utilizing a multi-mode two-dimensional discrete wavelet algorithm in combination with rotation, cutting and scaling operations, and performing model training on the kitchen waste classification model according to a labeling result;
and acquiring image data of the articles to be classified, inputting the image data into the kitchen waste classification model for classification analysis, and classifying the articles to be classified according to a classification result.
2. The method of claim 1, wherein prior to the step of performing model training on the kitchen waste classification model based on the labeled results, the method further comprises:
converting the kitchen waste data and the non-kitchen waste data into binary formats respectively, and packaging the binary formats with corresponding labels;
and serializing the kitchen waste data and the non-kitchen waste data into character strings according to the packaging result, and storing the character strings into a preset format file.
3. The method of claim 1, wherein the network in the kitchen waste classification model uses a loss function as a composite loss function, updates model parameters by back propagation of the loss function, and performs iteration for a predetermined number of times to complete model training.
4. The method of claim 1, wherein the step of inputting the image data into the food waste classification model for classification analysis comprises:
converting the image data into a network input format, and inputting the image data after format conversion into the kitchen waste classification model for prediction;
and regressing a target frame, the center coordinates and the belonged category by adopting a softmax function, wherein the belonged category is a kitchen waste category or a non-kitchen waste category.
5. A kitchen waste recycling and sorting system, the system comprising:
the model construction module is used for carrying out model construction on a preset SSD model according to a preset segmentation network to obtain a kitchen waste classification model, wherein the network in the kitchen waste classification model comprises a class, a prediction frame and a weighted sum of target loss and target loss in the prediction frame, and the framework of the preset segmentation network comprises thirteen inverse convolution layers, four upper sampling layers, two interested maximum pooling layers and a fusion layer;
the data marking module is used for acquiring kitchen waste data and non-kitchen waste data and marking the kitchen waste data and the non-kitchen waste data respectively;
the model training module is used for carrying out model training on the kitchen waste classification model according to the labeling result;
the article classification module is used for acquiring image data of an article to be classified, inputting the image data into the kitchen waste classification model for classification analysis, and classifying the article to be classified according to a classification result;
the kitchen waste recycling and sorting system further comprises:
and the data preprocessing module is used for preprocessing the kitchen waste data and the non-kitchen waste data by utilizing a multi-mode two-dimensional discrete wavelet algorithm in combination with rotation, cutting and scaling operations so as to utilize the size of the kitchen waste data after multiple analysis and keep multiple time and frequency analysis of an original wavelet function.
6. A mobile terminal, characterized in that it comprises a storage device for storing a computer program and a processor running the computer program to make the mobile terminal execute the kitchen waste recycling classification method according to any of claims 1 to 5.
7. A storage medium storing a computer program for use in the mobile terminal of claim 6, the computer program, when executed by a processor, implementing the steps of the kitchen waste recycling classification method of any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910813678.4A CN110610201B (en) | 2019-08-30 | 2019-08-30 | Kitchen waste recycling and classifying method and system, mobile terminal and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910813678.4A CN110610201B (en) | 2019-08-30 | 2019-08-30 | Kitchen waste recycling and classifying method and system, mobile terminal and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110610201A CN110610201A (en) | 2019-12-24 |
CN110610201B true CN110610201B (en) | 2022-06-07 |
Family
ID=68890724
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910813678.4A Active CN110610201B (en) | 2019-08-30 | 2019-08-30 | Kitchen waste recycling and classifying method and system, mobile terminal and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110610201B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111144480A (en) * | 2019-12-25 | 2020-05-12 | 深圳蓝胖子机器人有限公司 | Visual classification method, system and equipment for recyclable garbage |
CN113191176A (en) * | 2020-06-08 | 2021-07-30 | 阿里巴巴集团控股有限公司 | Data processing method and device |
CN112884033B (en) * | 2021-02-06 | 2021-10-22 | 浙江净禾智慧科技有限公司 | Household garbage classification detection method based on convolutional neural network |
TWI766674B (en) * | 2021-05-05 | 2022-06-01 | 長庚大學 | Food waste identification system and its identification method |
CN113688825A (en) * | 2021-05-17 | 2021-11-23 | 海南师范大学 | AI intelligent garbage recognition and classification system and method |
CN113849776B (en) * | 2021-11-19 | 2022-03-11 | 中译语通科技(青岛)有限公司 | Optimization method for anaerobic process for kitchen waste treatment |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109165582A (en) * | 2018-08-09 | 2019-01-08 | 河海大学 | A kind of detection of avenue rubbish and cleannes appraisal procedure |
CN109598303A (en) * | 2018-12-03 | 2019-04-09 | 江西洪都航空工业集团有限责任公司 | A kind of rubbish detection method based on City scenarios |
CN109834063A (en) * | 2019-04-11 | 2019-06-04 | 苏州嘉诺环境工程有限公司 | Garbage sorting system and refuse classification method |
CN109928107A (en) * | 2019-04-08 | 2019-06-25 | 江西理工大学 | A kind of automatic classification system |
-
2019
- 2019-08-30 CN CN201910813678.4A patent/CN110610201B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109165582A (en) * | 2018-08-09 | 2019-01-08 | 河海大学 | A kind of detection of avenue rubbish and cleannes appraisal procedure |
CN109598303A (en) * | 2018-12-03 | 2019-04-09 | 江西洪都航空工业集团有限责任公司 | A kind of rubbish detection method based on City scenarios |
CN109928107A (en) * | 2019-04-08 | 2019-06-25 | 江西理工大学 | A kind of automatic classification system |
CN109834063A (en) * | 2019-04-11 | 2019-06-04 | 苏州嘉诺环境工程有限公司 | Garbage sorting system and refuse classification method |
Non-Patent Citations (2)
Title |
---|
DSSD: Deconvolutional Single Shot Detector;Cheng-Yang Fu et al.;《arXiv:1701.06659v1》;20170123;第1-11页 * |
基于SSD算法的垃圾识别分类研究;彭昕昀 等;《韶关学院学报•自然科学》;20190630;第40卷(第6期);摘要,第2节 * |
Also Published As
Publication number | Publication date |
---|---|
CN110610201A (en) | 2019-12-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110610201B (en) | Kitchen waste recycling and classifying method and system, mobile terminal and storage medium | |
US11972569B2 (en) | Segmenting objects in digital images utilizing a multi-object segmentation model framework | |
Hossain et al. | Improving consumer satisfaction in smart cities using edge computing and caching: A case study of date fruits classification | |
CN112232425B (en) | Image processing method, device, storage medium and electronic equipment | |
US7958068B2 (en) | Method and apparatus for model-shared subspace boosting for multi-label classification | |
Tian et al. | Review of object instance segmentation based on deep learning | |
CN110348294A (en) | The localization method of chart, device and computer equipment in PDF document | |
JP2018195293A (en) | Image processing system, method for performing multi-label meaning edge detection in image, and non-transitory computer-readable storage medium | |
CN106372648A (en) | Multi-feature-fusion-convolutional-neural-network-based plankton image classification method | |
CN107368614A (en) | Image search method and device based on deep learning | |
CN103995889A (en) | Method and device for classifying pictures | |
CN111368636B (en) | Object classification method, device, computer equipment and storage medium | |
CN107330027B (en) | Weak supervision depth station caption detection method | |
CN112069319A (en) | Text extraction method and device, computer equipment and readable storage medium | |
CN113191235B (en) | Sundry detection method, sundry detection device, sundry detection equipment and storage medium | |
CN111273905B (en) | Application retrieval method and device based on interface sketch | |
CN112328823A (en) | Training method and device for multi-label classification model, electronic equipment and storage medium | |
JP2018081719A (en) | Method for improving classification result of classifier | |
CN111814913A (en) | Training method and device for image classification model, electronic equipment and storage medium | |
Huang et al. | Fine-art painting classification via two-channel deep residual network | |
CN110969641A (en) | Image processing method and device | |
Wu et al. | RGBD co-saliency detection via multiple kernel boosting and fusion | |
CN107506407A (en) | A kind of document classification, the method and device called | |
WO2021000411A1 (en) | Neural network-based document classification method and apparatus, and device and storage medium | |
CN113868449B (en) | Image retrieval method based on fusion of multi-scale features and spatial attention mechanism |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |