CN111814750A - Intelligent garbage classification method and system based on deep learning target detection and image recognition - Google Patents
Intelligent garbage classification method and system based on deep learning target detection and image recognition Download PDFInfo
- Publication number
- CN111814750A CN111814750A CN202010817192.0A CN202010817192A CN111814750A CN 111814750 A CN111814750 A CN 111814750A CN 202010817192 A CN202010817192 A CN 202010817192A CN 111814750 A CN111814750 A CN 111814750A
- Authority
- CN
- China
- Prior art keywords
- garbage
- target
- detection
- image
- module
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/63—Scene text, e.g. street names
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Abstract
The invention discloses an intelligent garbage classification method and system based on deep learning target detection and image recognition, which comprises the following steps: the image acquisition module is used for acquiring image information in the monitoring system; the garbage target detection model training module trains a garbage target detection model according to the data set obtained by the image acquisition module; the garbage target detection module extracts a target image acquired in the image acquisition module by using the trained detection model; the garbage classification module extracts corresponding target category information according to the target detected by the garbage detection module; the garbage classification model is used for classifying specific garbage according to the class information obtained by the garbage detection module; and the result output module outputs the corresponding target garbage category information according to the category information obtained by the garbage classification module. The invention can realize real-time classification of garbage according to four major classes of garbage, and is beneficial to the rapid classification of garbage and the smooth development of garbage classification work.
Description
Technical Field
The invention relates to computer vision, pattern recognition, video processing, artificial intelligence and an intelligent monitoring system, in particular to an intelligent garbage classification method and system based on deep learning target detection and image recognition.
Background
In recent years, with rapid development of economy and society, the living standard of people is continuously improved. Along with the improvement of living standard of people, more and more garbage is generated. Too much waste is not in time to be disposed of and can cause great damage to the ecology. About 800 million tons of plastic wastes enter the ocean every year, all together can surround 120 circles around the earth, and more than 50 fishes are found eating the plastic wastes, and at least 10 million marine organisms lose lives because of plastic products every year, which is just the damage of the plastic wastes to the ecology. Everyone throws away a lot of rubbish every day, and in some areas that refuse management is better, most rubbish can get innoxious processing such as sanitary landfill, burning, compost, and the rubbish in more places is often simply piled up or buried, leads to the spread of foul smell, and pollutes soil and groundwater. Meanwhile, in life, a lot of garbage cannot be decomposed by self, so that a lot of toxic substances are generated, soil is seriously polluted, the yield of agricultural products is gradually reduced, and animals die to a certain extent.
The cost of harmless treatment of garbage is very high, and the cost of treating one ton of garbage is about one hundred yuan to several hundred yuan according to different treatment modes. People consume a large amount of resources, produce the garbage in a large amount, and the result is unimaginable. The traditional garbage treatment methods comprise sanitary landfill, open stacking, incineration, composting and the like, and when the environmental pollution is serious, the garbage needs to be classified. The garbage classification is a precondition and an important link for performing classification treatment on the garbage, and the garbage classification and collection can reduce the garbage treatment amount and treatment equipment, reduce the treatment cost and reduce the land resource consumption. Through carrying out classification management to rubbish, realization rubbish resource recycle that can furthest reduces refuse treatment's quantity simultaneously, can carry out manual treatment again through the garbage rate classification and turn into the new forms of energy, can let these rubbish obtain effectual processing simultaneously, can reduce the harmfulness to soil like this, can also prevent the phenomenon of air pollution simultaneously. 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.
Currently, garbage classification has been implemented in most two-line cities throughout the country, including Beijing, Shanghai, Guangzhou, Shenzhen, and the like. However, the current garbage classification mode is mainly that the residents classify the garbage before putting the garbage into the garbage. However, some community residents who do not realize the garbage classification in place still do not perform the garbage classification, which leads to the great improvement of the workload of garbage disposal workers. Meanwhile, when the residents perform garbage classification, the erroneous classification is easy to occur. Therefore, in order to solve the above problems, the present invention discloses an intelligent garbage classification system based on deep learning target detection and image recognition. The system adopts a deep learning technology in the field of computer vision, utilizes sensor equipment such as a camera and the like to acquire garbage pictures, inputs the garbage pictures into a deep learning target detection network, detects the category name and the position information of target garbage, obtains a specific certain type of the four types of garbage corresponding to the target garbage according to the mapping relation between the preset garbage name and the four types of garbage (kitchen garbage, harmful garbage, recoverable garbage and other garbage), and draws the specific position of the target garbage in an image according to the color corresponding to the four types of garbage cans, thereby facilitating people to carry out garbage putting according to the color information and improving the garbage classification efficiency. Compared with the comparison document "garbage classification AI image identification method", the comparison document adopts the image classification technology. When the proportion of the target in the image is small, the image classification error rate is high,
disclosure of Invention
1. Objects of the invention
The invention aims to provide an intelligent garbage classification system based on deep learning target detection and image recognition in the fields of intelligent security, monitoring and the like, and aims to detect position information and category information of garbage targets by using a deep learning technology, visualize the position information and the category information and facilitate automatic classification during garbage throwing.
2. The technical scheme adopted by the invention
The invention provides an intelligent garbage classification method based on deep learning target detection and image recognition, which comprises the following steps of:
an image acquisition step, which is used for acquiring video image information of the garbage and inputting the video image information to a garbage detection module;
training a garbage target detection model, namely training a garbage target detection module to obtain specific position and category information of single target garbage in an image for the garbage detection module to call;
the method comprises the steps of detecting the rubbish, namely extracting rubbish image information in an image acquired by an image acquisition module, wherein the rubbish image information refers to position coordinates of the rubbish in the image and specific names of the rubbish;
a garbage classification step, namely obtaining the specific category of the four types of garbage corresponding to the detected garbage according to the target position and the target category information obtained by the detection of the garbage detection module and the mapping relation between the preset multi-type target name and the four types of garbage;
and a result output step, namely displaying the specific name of the target rubbish on the image obtained by the image acquisition module and the category name in the corresponding four types of rubbish according to the related information obtained by the rubbish detection module and the rubbish classification module, and drawing a picture according to the position obtained by the rubbish detection module.
Preferably, in the result output step, according to a preset mapping relationship between the garbage name and four types of garbage, a specific certain type of the four types of garbage detected by the garbage detection module is obtained: green indicates kitchen waste, blue indicates recyclable waste, black indicates other waste, and red indicates harmful waste.
Preferably, the garbage target detection model training step includes cleaning and data labeling, and specific positions and actual category names of garbage are marked.
Preferably, the garbage detection model verification set and the garbage detection model training set are divided according to a certain proportion.
Preferably, the garbage target detection model training step:
establishing a garbage detection network structure based on a Pythrch framework, wherein the network structure mainly comprises three parts, namely a backbone part, a nack part and a head part, wherein the backbone part is mainly responsible for feature extraction and comprises semantic features and global features; the neck part is responsible for characteristic recombination, recombining the characteristics of different layers and realizing the multi-scale of the network; the head part is responsible for target detection and is built according to target categories and other information in the data set.
Preferably, the network structure of each part is built by adopting different quantities of convolutional layers, batchnorm layers and active layer network layers according to actual conditions, or other network blocks comprise FPNs (field programmable buses), Bottleneck and SPPs (SpPs).
Preferably, the data loader is constructed based on the garbage detection model verification set and the garbage detection model training set, and provides input data for the model in the model training process.
Preferably, based on the built data loader, data are read according to batches and sent into a built network structure, loss of the convolutional neural network is calculated according to the obtained prediction result and corresponding real labeling information, parameters of the convolutional neural network are circularly corrected through a back propagation algorithm until the convolutional neural network learns the position and the class attribute of the target in the image, and the parameters obtained through training are stored.
The invention discloses an intelligent garbage classification system based on deep learning target detection and image recognition, which comprises a memory and a processor, wherein the intelligent garbage classification system is used for recognition.
3. Advantageous effects adopted by the present invention
(1) According to the invention, a target detection method is adopted to carry out garbage classification operation, the target is detected firstly, and is classified, so that the problem of high error rate when the classification is directly carried out is avoided;
(2) the invention constructs a data loader and provides input data for the model in the model training process; reading data according to batches and sending the data into a built network structure, calculating the loss of the convolutional neural network according to the obtained prediction result and corresponding real marking information, and automatically classifying the garbage by utilizing deep learning and computer vision technologies, so that the accuracy of garbage classification can be improved;
(3) the invention utilizes deep learning and computer vision technology to automatically classify the garbage, thereby greatly reducing the working intensity of the related working personnel for garbage disposal, improving the working efficiency and reducing the working cost;
(4) when the garbage classification result is displayed, a rectangle is drawn on the target garbage according to the colors of the garbage cans corresponding to the four types of garbage, so that the garbage can is convenient to throw in, and the garbage can be thrown in directly according to the colors.
Drawings
FIG. 1 is a schematic diagram of an overall architecture of an intelligent garbage classification system based on deep learning target detection and image recognition;
FIG. 2 is a flowchart of a training process of a garbage detection model in an intelligent garbage classification system based on deep learning target detection and image recognition;
FIG. 3 is a schematic diagram of a backbone in an intelligent garbage classification system based on deep learning target detection and image recognition;
FIG. 4 is a schematic diagram I of a detection result in an intelligent garbage classification system based on deep learning target detection and image recognition;
FIG. 5 is a schematic diagram of a detection result in an intelligent garbage classification system based on deep learning target detection and image recognition;
FIG. 6 is a schematic diagram of a detection result in an intelligent garbage classification system based on deep learning target detection and image recognition;
fig. 7 is a schematic diagram of a detection result in the intelligent garbage classification system based on deep learning target detection and image recognition.
Detailed Description
The technical solutions in the examples of the present invention are clearly and completely described below with reference to the drawings in the examples of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without inventive step, are within the scope of the present invention.
The present invention will be described in further detail with reference to the accompanying drawings.
Example 1
As shown in fig. 1, the overall architecture of the intelligent garbage classification system based on deep learning target detection and image recognition mainly includes five modules, which are respectively: the garbage classification system comprises an image acquisition module, a garbage target detection model training module, a garbage target detection module, a garbage classification module and a garbage classification result output module. The image acquisition module is used for acquiring image information of the garbage and used as the input of the garbage detection model training and garbage detection module; the garbage detection model training module is used for training the weight of the garbage detection model by utilizing the data set obtained by the image acquisition module; the garbage detection module is used for detecting the position coordinates of target garbage and the category information of the target in the image information acquired by the image acquisition module; the garbage classification module is used for obtaining specific category information in the four types of garbage corresponding to the garbage detected by the garbage detection module according to the target garbage category information obtained by the garbage detection module and a preset mapping relation between the garbage name and the four types of garbage; and the garbage classification result display module is used for framing the specific position of the target garbage in a rectangular frame form according to different colors according to the garbage position coordinates obtained by the garbage detection module, and the color of the rectangular frame is determined according to the garbage classification information obtained by the garbage classification module.
Specifically, the detailed steps of the intelligent garbage classification system are as follows:
step 1, data acquisition, namely acquiring video image information of garbage, processing a video image acquired by video acquisition equipment, extracting an image in the video, using the image as the input of a garbage detection module, and detecting the specific position of target garbage;
step 2, training a garbage target detection model, wherein the data set acquired and collected in the step one is used as input of the training of the garbage detection model, and the purpose is to train a garbage target detection model with high recall and high accuracy, and the garbage target detection model is used for acquiring specific position and category information of single target garbage in an image and calling the position and the category information by a garbage detection module;
specifically, the training of the garbage target detection model in the second step specifically includes the following substeps:
step 2-1, firstly, cleaning and data labeling are carried out on the data set collected and sorted by the camera in the step one, and specific positions and actual category names of the garbage are marked;
step 2-2, as described in substep 2-1, the cleaned and labeled data sets are scrambled in order according to the following sequence of 2: 8, wherein 20 percent of the garbage detection model verification set is used as a garbage detection model verification set, and 80 percent of the garbage detection model verification set is used as a garbage detection model training set;
and 2-3, establishing a garbage detection network structure based on the Pythrch framework, wherein the network structure mainly comprises three parts, namely a backhaul part, a neck part and a head part. Specifically, the network structure of each part can be built by adopting different quantities of convolutional layers, batchnorm layers, activation layers and other network layers according to actual conditions, and the existing network structure can also be adopted, such as FPN, Bottleneck, SPP and other network blocks. The backbone part is mainly responsible for feature extraction, including semantic features, global features and the like; the neck part is responsible for characteristic recombination, recombining the characteristics of different layers and realizing the multi-scale of the network; the head part is responsible for target detection and is built according to target categories and other information in the data set. FIG. 3 shows a specific structure of backbone of the present invention, which is obtained by combining Focus, CBL, Bottleneck CSP, and SPP layers.
Step 2-4, respectively constructing data loaders of a training set and a verification set according to the data set divided in the substep 2-2, and providing input data for the model in the model training process;
step 2-5, based on the data loader built in the substep 2-4, reading data according to batches and sending the data into the garbage detection network structure built in the substep 2-3, calculating the loss of the convolutional neural network according to the obtained prediction result and corresponding real labeling information, and correcting the parameters of the convolutional neural network through a back propagation algorithm;
step 2-6, using the data loader established in the substep 2-4 to circularly perform the substep 2-5, continuously correcting the parameters of the convolutional neural network until the convolutional neural network learns to predict the position and the class attribute of the image target, and storing the parameters obtained by training;
and 2-7, in the network weight updating process, when a certain number of epochs are circulated, verifying the model performance, recording the optimal performance index, and storing the model parameter when the network achieves the optimal performance.
Step 3, a garbage detection module detects the position and the category name of a garbage target in the image according to the garbage detection model obtained by training in the step 2, and inputs related information into a subsequent module;
step 4, the garbage classification module obtains a specific certain class of the four classes of garbage detected by the garbage detection module according to the class name of the garbage target on the image obtained in the step 3 and a preset mapping relation between the garbage name and the four classes of garbage;
and step 5, a result output module displays the garbage classification result according to the garbage classification result obtained by the garbage classification module in the step 4.
Specifically, the method comprises the following steps:
step 5-1, performing picture frame on the garbage target according to the coordinate position of the garbage target obtained by the garbage detection module in the step 3;
and 5-2, obtaining the color information of the target frame to be drawn according to a specific certain class of the four classes of garbage to which the garbage target belongs, which is obtained by the garbage classification module in the step 4. Specifically, green represents kitchen waste, blue represents recoverable waste, black represents other waste, and red represents harmful waste. The specific target detection results are shown in fig. 4-7, which show the garbage detection results.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (9)
1. An intelligent garbage classification method based on deep learning target detection and image recognition is characterized by comprising the following steps:
an image acquisition step, which is used for acquiring video image information of the garbage and inputting the video image information to a garbage detection module;
training a garbage target detection model, namely training a garbage target detection module to obtain specific position and category information of single target garbage in an image for the garbage detection module to call;
the method comprises the steps of detecting the rubbish, namely extracting rubbish image information in an image acquired by an image acquisition module, wherein the rubbish image information refers to position coordinates of the rubbish in the image and specific names of the rubbish;
a garbage classification step, namely obtaining the specific category of the four types of garbage corresponding to the detected garbage according to the target position and the target category information obtained by the detection of the garbage detection module and the mapping relation between the preset multi-type target name and the four types of garbage;
and a result output step, namely displaying the specific name of the target rubbish on the image obtained by the image acquisition module and the category name in the corresponding four types of rubbish according to the related information obtained by the rubbish detection module and the rubbish classification module, and drawing a picture according to the position obtained by the rubbish detection module.
2. The intelligent garbage classification method based on deep learning target detection and image recognition according to claim 1, characterized in that in the result output step, according to the mapping relationship between preset garbage names and four types of garbage, a specific certain type of the four types of garbage detected by the garbage detection module is obtained: green indicates kitchen waste, blue indicates recyclable waste, black indicates other waste, and red indicates harmful waste.
3. The intelligent garbage classification method based on deep learning target detection and image recognition according to claim 1, characterized in that: and a garbage target detection model training step, namely cleaning and data labeling are carried out firstly, and the specific position and the actual category name of garbage are labeled.
4. The intelligent garbage classification method based on deep learning target detection and image recognition according to claim 3, characterized in that: and dividing a garbage detection model verification set and a garbage detection model training set according to a certain proportion.
5. The intelligent garbage classification method based on deep learning target detection and image recognition according to claim 4, characterized in that the training step of the garbage target detection model comprises:
establishing a garbage detection network structure based on a Pythrch framework, wherein the network structure mainly comprises three parts, namely a backbone part, a nack part and a head part, wherein the backbone part is mainly responsible for feature extraction and comprises semantic features and global features; the neck part is responsible for characteristic recombination, recombining the characteristics of different layers and realizing the multi-scale of the network; the head part is responsible for target detection and is built according to target categories and other information in the data set.
6. The intelligent garbage classification method based on deep learning target detection and image recognition according to claim 5, wherein the network structure of each part is built by adopting different quantities of convolutional layers, batchnorm layers and active layer network layers according to actual conditions, or other network blocks comprise FPNs, Bottleneck and SPPs.
7. The intelligent garbage classification method based on deep learning object detection and image recognition according to claim 6, characterized in that a data loader is constructed based on a garbage detection model validation set and a garbage detection model training set, and provides input data for the model during the model training process.
8. The intelligent garbage classification method based on deep learning target detection and image recognition according to claim 7 is characterized in that based on the built data loader, data are read according to batches and sent into the built network structure, loss of the convolutional neural network is calculated according to the obtained prediction result and corresponding real labeling information, parameters of the convolutional neural network are circularly corrected through a back propagation algorithm until the convolutional neural network learns the position and the class attribute of the target in the predicted image, and the parameters obtained through training are stored.
9. The utility model provides an intelligence waste classification system based on deep learning target detects and image recognition which characterized in that: comprising a memory and a processor, identified using the method according to any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010817192.0A CN111814750A (en) | 2020-08-14 | 2020-08-14 | Intelligent garbage classification method and system based on deep learning target detection and image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010817192.0A CN111814750A (en) | 2020-08-14 | 2020-08-14 | Intelligent garbage classification method and system based on deep learning target detection and image recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111814750A true CN111814750A (en) | 2020-10-23 |
Family
ID=72859326
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010817192.0A Pending CN111814750A (en) | 2020-08-14 | 2020-08-14 | Intelligent garbage classification method and system based on deep learning target detection and image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111814750A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112257623A (en) * | 2020-10-28 | 2021-01-22 | 长沙立中汽车设计开发股份有限公司 | Road surface cleanliness judging and automatic cleaning method and automatic cleaning environmental sanitation device |
| CN112861979A (en) * | 2021-02-20 | 2021-05-28 | 数贸科技（北京）有限公司 | Trademark identification method and device, computing equipment and computer storage medium |
| CN113487551A (en) * | 2021-06-30 | 2021-10-08 | 佛山市南海区广工大数控装备协同创新研究院 | Gasket detection method and device for improving performance of dense target based on deep learning |
| CN113592002A (en) * | 2021-08-04 | 2021-11-02 | 江苏网进科技股份有限公司 | Real-time garbage monitoring method and system |
| CN114821440A (en) * | 2022-05-12 | 2022-07-29 | 清研灵智信息咨询(北京)有限公司 | Mobile video stream content identification and analysis method based on deep learning |
| CN117496274A (en) * | 2023-12-29 | 2024-02-02 | 墨卓生物科技(浙江)有限公司 | Classification counting method, system and storage medium based on liquid drop images |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110427896A (en) * | 2019-08-07 | 2019-11-08 | 成都理工大学 | A kind of garbage classification intelligence system based on convolutional neural networks |
| CN110473130A (en) * | 2019-07-30 | 2019-11-19 | 五邑大学 | A kind of garbage classification evaluation method, device and storage medium based on deep learning |
| CN111126138A (en) * | 2019-11-18 | 2020-05-08 | 施博凯 | AI image recognition method for garbage classification |
| CN111259977A (en) * | 2020-01-22 | 2020-06-09 | 浙江工业大学 | Garbage classification device based on deep learning |
| CN111368895A (en) * | 2020-02-28 | 2020-07-03 | 上海海事大学 | Garbage bag target detection method and detection system in wet garbage |
-
2020
- 2020-08-14 CN CN202010817192.0A patent/CN111814750A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110473130A (en) * | 2019-07-30 | 2019-11-19 | 五邑大学 | A kind of garbage classification evaluation method, device and storage medium based on deep learning |
| CN110427896A (en) * | 2019-08-07 | 2019-11-08 | 成都理工大学 | A kind of garbage classification intelligence system based on convolutional neural networks |
| CN111126138A (en) * | 2019-11-18 | 2020-05-08 | 施博凯 | AI image recognition method for garbage classification |
| CN111259977A (en) * | 2020-01-22 | 2020-06-09 | 浙江工业大学 | Garbage classification device based on deep learning |
| CN111368895A (en) * | 2020-02-28 | 2020-07-03 | 上海海事大学 | Garbage bag target detection method and detection system in wet garbage |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112257623A (en) * | 2020-10-28 | 2021-01-22 | 长沙立中汽车设计开发股份有限公司 | Road surface cleanliness judging and automatic cleaning method and automatic cleaning environmental sanitation device |
| CN112861979A (en) * | 2021-02-20 | 2021-05-28 | 数贸科技（北京）有限公司 | Trademark identification method and device, computing equipment and computer storage medium |
| CN112861979B (en) * | 2021-02-20 | 2024-01-30 | 数贸科技（北京）有限公司 | Trademark identification method, trademark identification device, computing equipment and computer storage medium |
| CN113487551A (en) * | 2021-06-30 | 2021-10-08 | 佛山市南海区广工大数控装备协同创新研究院 | Gasket detection method and device for improving performance of dense target based on deep learning |
| CN113487551B (en) * | 2021-06-30 | 2024-01-16 | 佛山市南海区广工大数控装备协同创新研究院 | Gasket detection method and device for improving dense target performance based on deep learning |
| CN113592002A (en) * | 2021-08-04 | 2021-11-02 | 江苏网进科技股份有限公司 | Real-time garbage monitoring method and system |
| CN114821440A (en) * | 2022-05-12 | 2022-07-29 | 清研灵智信息咨询(北京)有限公司 | Mobile video stream content identification and analysis method based on deep learning |
| CN117496274A (en) * | 2023-12-29 | 2024-02-02 | 墨卓生物科技(浙江)有限公司 | Classification counting method, system and storage medium based on liquid drop images |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111814750A (en) | Intelligent garbage classification method and system based on deep learning target detection and image recognition | |
| CN111974704A (en) | Garbage classification detection system and method based on computer vision | |
| CN110298957A (en) | A kind of urban family domestic garbage categorised collection transaction operational system | |
| CN110844403B (en) | Garbage classification identification method and device based on target identification | |
| CN111301886A (en) | Garbage classification and recovery system based on RBF neural network and control method | |
| CN110834835A (en) | Intelligent garbage classification processing method and system based on internet big data | |
| CN206639234U (en) | Intelligent monitoring garbage classification device and its refuse classification management system | |
| CN110606299A (en) | Garbage classification tracing method and system | |
| CN111619992A (en) | Intelligent garbage classification system and method based on machine vision | |
| CN116152748B (en) | River and lake supervision method and system based on blue algae identification | |
| CN111453249A (en) | Intelligent kitchen garbage classification barrel based on image analysis | |
| CN110355188A (en) | Based on the multiple wisdom garbage classification sludge reduction onsite recycling system utilized in soil | |
| CN212442146U (en) | Household garbage recognition system | |
| CN104609078A (en) | Rubbish monitoring method | |
| CN112978146A (en) | Intelligent throw-away garbage detection method based on video analysis | |
| CN110065746B (en) | Shipping garbage classification system based on Internet of things | |
| CN110694934A (en) | Intelligent dry garbage classification cloud system and working method thereof | |
| CN111723772B (en) | Perishable garbage identification method and device based on image identification and computer equipment | |
| CN211418362U (en) | Artificial intelligence classification garbage can | |
| Md et al. | Intelligent waste sorting bin for recyclable municipal solid waste | |
| CN113971746B (en) | Garbage classification method and device based on single hand teaching and intelligent sorting system | |
| CN110348586A (en) | A kind of garbage classification system based on Internet of Things | |
| CN115082863A (en) | Intelligent garbage classified putting scanning system and method | |
| CN113399283A (en) | Household garbage classification system capable of automatically identifying garbage types | |
| CN113837336A (en) | Garbage classification tracing method and system |
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 |