CN108777777A - A kind of monitor video crop straw burning method for inspecting based on deep neural network - Google Patents
A kind of monitor video crop straw burning method for inspecting based on deep neural network Download PDFInfo
- Publication number
- CN108777777A CN108777777A CN201810419435.8A CN201810419435A CN108777777A CN 108777777 A CN108777777 A CN 108777777A CN 201810419435 A CN201810419435 A CN 201810419435A CN 108777777 A CN108777777 A CN 108777777A
- Authority
- CN
- China
- Prior art keywords
- neural network
- pyrotechnics
- crop straw
- straw burning
- recognition processing
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- 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
-
- 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
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/12—Alarms for ensuring the safety of persons responsive to undesired emission of substances, e.g. pollution alarms
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Signal Processing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Toxicology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Emergency Management (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Environmental & Geological Engineering (AREA)
- Alarm Systems (AREA)
- Image Analysis (AREA)
Abstract
The present invention discloses a kind of monitor video crop straw burning method for inspecting based on deep neural network, belongs to information technology field.It constructs the pyrotechnics recognition processing module based on neural network classifier based on deep learning neural network framework, the pyrotechnics recognition processing module takes every 10 frame of video to be truncated into picture and the method that increases data set and amplification data collection feature tag, optimize residual error network, to improve the accuracy of identification image and anomalous event in video；The pyrotechnics recognition processing module according to neural network classifier to the judgement of certain areas cigarette and fire as a result, alarm from trend patrolman person and ordinary user, the monitoring to realization to crop straw burning event.
Description
Technical field
The invention belongs to information technology field, especially a kind of monitor video crop straw burning based on deep neural network patrols
Detecting method is mainly used for environmental monitoring.
Background technology
With the economic development with science and technology, problem of environmental pollution getting worse, especially air pollution, haze phenomenon is spread
China, but under the mainstream of " environmental protection ", crop straw burning phenomenon still remains incessant after repeated prohibition.In conventional methods where, generally by patrolling
The video that personnel shoot according to monitoring camera is patrolled, related area processing crop straw burning scene is gone to.However, usually event without exception
When, a large amount of human and material resources will be wasted, therefore raising routing inspection efficiency, intelligent extraction key message are very necessary.
It is built based on deep learning neural network framework, the feature tag of pyrotechnics is captured using neural network classifier, just
The cigarette and fire in picture and video are may recognize that, to judge crop straw burning phenomenon.But the implementation of the method, in actual scene
In, can by night light, ponding is reflective, rainy day water mist etc. factor is influenced, and generates erroneous judgement or misjudgement, cause to identify thing
The inaccuracy of part sends the information of mistake.In addition, training data scarcity is also to optimize one of the difficult point of residual error network.In the following table 1
List the label characteristics of cigarette and fire and the difficult point of identifying processing.
1 pyrotechnics information of table identifies difficult point
Invention content
For the inefficiencies of solution traditional monitoring crop straw burning and since pyrotechnics is judged in the interference of other things in scene by accident
The problem of event, the present invention provide a kind of monitor video crop straw burning method for inspecting based on deep neural network, construct cigarette
Fiery recognition processing module using neural network classifier, automatic identification monitor video crop straw burning event, and actively sends short message
Alarm, realizes the high efficiency and interactivity of information, manpower and materials is greatly saved.
To achieve the above object, the present invention uses following technical proposals：
A kind of monitor video crop straw burning method for inspecting based on deep neural network is based on deep learning neural network frame
Frame constructs the pyrotechnics recognition processing module based on neural network classifier, which takes every 10 frame of video
The method for being truncated into picture and increasing data set and amplification data collection feature tag optimizes residual error network, to improve identification image
With the accuracy of anomalous event in video；The pyrotechnics recognition processing module is according to neural network classifier to certain areas cigarette and fire
Judgement as a result, alarming from trend patrolman person and ordinary user, to realize the monitoring to crop straw burning event.
Further, pyrotechnics recognition processing module includes movable signal tower video acquisition module, deep learning image pyrotechnics
Identification module and automatic alarm module；
Deep learning image pyrotechnics identification module extracts the spy of sample according to linear classifier function and loss function
Label and identification classification samples are levied, categorized data set is thus trained；During training data, using amplification data Ji Te
The method for levying label is accurately positioned extraction sample characteristics label, solves in a practical situation to the erroneous judgement of scene and misjudgement, and give
Related personnel sends the problem of error message, while carrying out repetition training and identification to special sample, optimizes residual error network layer by layer,
It excludes to identify inaccurate problem caused by the external factor such as night light, reflective, the rainy day water mist of ponding influence；Simultaneously certainly
It is dynamic to sort out the operation for collecting sample, being overturn, stretched and translated to sample using Python tools, to reach extension sample
Purpose solves the problems, such as data training set deficiency.
Further, automatic alarm module sends an SMS to patrol personnel automatically, and is taken the photograph by movable signal tower locating and monitoring
It as the position of head, is indicated with red point abnormal regional, and is pushed away from trend user by associated wechat small routine on GPS map
It delivers letters breath.
Advantageous effect：
1. the present invention utilizes movable signal tower video acquisition module, realize that stalk is burnt based on deep learning neural network framework
Automatic detection and alarm are burnt, compared with traditional crop straw burning monitoring method, on the one hand can reduce the workload of patrol personnel, it is another
Aspect can send related personnel to in-situ processing event in time, there is the advantages of high efficiency and promptness, can effectively reduce stalk
The phenomenon that burning；
2. for when tional identification classification cigarette is with fiery feature tag, often night light, the ponding in example scenario are anti-
The complex scenes such as light, rainy day water mist can influence the accuracy of identification, and the present invention constructs the pyrotechnics based on neural network classifier
Recognition processing module can carry out repetition training and identification to special sample, optimize residual error network layer by layer, and extend sample, arrange
Except the disturbing factor under special screne, keep recognition result more accurate.
3. the present invention is proposed based under Python environment, by amplification data collection feature tag, optimize residual error network
Method solves the problem of the erroneous judgement to scene and misjudgement in a practical situation and sends error message to related personnel；Simultaneously will
Special sample repetition training and identification, and the operations such as overturn, converted to it, to extend sample, solve training data not
The defect of foot.
4. the present invention proposes automatic alarm module.Processing of the monitor video through neural network classifier, pyrotechnics identification
As a result, on the one hand related patrol personnel can be informed in such a way that system sends short message automatically, notify them to go to in-situ processing
On the other hand crop straw burning phenomenon was photographed the monitoring camera of anomalous event by the positioning of movable signal tower, was marked out on GPS map
Corresponding red point is pushed from trend user by associated wechat small routine, manpower and materials is not only greatly saved, also enhance
The consciousness of masses' environmental protections mutually supervises, safeguards home jointly.
Description of the drawings
Fig. 1 is the structure diagram of the pyrotechnics identification module of one embodiment of the invention；
Fig. 2 is the logical schematic based on the training of neural network classifier data of one embodiment of the invention；
Fig. 3 is the flow diagram of the sample spread training of one embodiment of the invention；
Fig. 4 is the structure diagram of the automatic alarm module of one embodiment of the invention.
Specific implementation mode
Present invention will be further explained below with reference to the attached drawings and examples.
The present embodiment proposes a kind of monitor video crop straw burning method for inspecting based on deep neural network, for working as forward pass
System crop straw burning method for inspecting expends a large amount of manpowers and supervises the very low situation of implementation result, based on deep learning nerve
Network frame is constructed including movable signal tower video acquisition module 1, deep learning image pyrotechnics identification module 2 and automatic report
Intelligent service system including 3 these three modules of alert module, i.e. pyrotechnics recognition processing module, structure are as shown in Figure 1.Optimizing
While residual error network, for the inaccurate problem of pyrotechnics feature tag identification, the method for proposing amplification data collection feature tag,
The various example scenarios that will allow for are added data set and are trained, Optimized model, improve recognition accuracy；Automatic alarm is specific
Object is patrol officer and ordinary user, realizes that mark is abnormal regional by movable signal tower, to send short message and wechat little Cheng
The mode automatic push data of sequence.
As shown in Figure 1, pyrotechnics recognition processing module includes movable signal tower video acquisition module 1, deep learning image cigarette
Fiery identification module 2 and automatic alarm module 3.After shooting video by monitoring camera, by data transport to receiving platform, god is given
Through network classifier, classification is identified according to the feature tag of cigarette and fire, its recognition result is finally automatically processed, on the one hand gives
Patrol personnel send alarming short message automatically, and notice is gone to in-situ processing crop straw burning event, on the other hand determined by movable signal tower
Position is abnormal regional, and corresponding red point is marked out on GPS map, user is automatically pushed to by associated wechat small routine.
Wherein, it is key component, neural network classifier to be based on deep learning neural network framework classification based training data set
The logical schematic of training data as shown in Fig. 2, by the data single cent part being collected into be respectively labeled as cigarette, fire, normal scene 1,
Normal scene 2, specific implementation process are to be stored in 4 files respectively, and the picture that a file is set fire a, file folds up cigarette
Picture, there are two files to fold up the picture of normal field scape, and the picture number of four files keeps balance, forms data
Collection is put into training in residual error network.
Using loss function, loss is preferably minimized, and extracts the feature tag of sample, while weighing weight matrix W and reflecting
Penetrate result and the goodness of fit of concrete class：
Wherein, xiIndicate the data of the i-th pictures, W is weight matrix, and Δ is a fixed parameter, scores to
Amount is by sj=f (xi, W) and it indicates, then the score of jth class can be denoted as Again loss function is obtained with regularization：
Classification processing is carried out then according to linear classifier function pair sample：
F (x, W, b)=Wx+b (4)
Wherein, x indicates that inputted 3072 dimensional vectors, W are weight matrix, and b is indicated independent as bias
Weight parameter.X can not change, but can change W, and be set to the value that can be correctly exported per pictures in training set, use
The method of this linear classification obtains the optimum value of W and b, keeps in balance, keep classification results more accurate.
After training, then with four files, it is respectively put into corresponding picture, quantity is the 1/ of training picture number
4, to detect the accuracy of this Model Identification pyrotechnics and normal scene.
While classification based training pyrotechnics picture, and continue to optimize the process of residual error network.The stream of sample spread training
Journey schematic diagram is as shown in Figure 3, wherein is faced with two problems, one is accuracy that external factor influences identification pyrotechnics, another
A is the deficiency of data set.
For in actual scene, because of external condition, such as：The factors such as reflective, the rainy day water mist of night light, ponding influence and
The inaccurate problem of caused identification, the method for taking amplification data collection feature tag.It will become clear in picture and color be partially orange red
One piece of region according to coordinate mark off come, as fire feature tag be individually trained, increase identification fire accuracy.Needle
To identify cigarette normal scene the problem of, the figures such as reflective, the rainy day water mist of a large amount of ponding can be added in the file of normal scene
Piece is trained identification, optimizes residual error network.
Insufficient defect for data sets is handled using the increased method of data set.Specific implementation process is training
In the process automatic clustering collect sample, using Python tools to sample overturning, stretch, translation etc. operations, reach extension sample
Purpose, solve the problems, such as because data set deficiency due to cause to identify it is inaccurate.
After the result for having received monitoring camera data, output pyrotechnics detection, artificial treatment information is not needed, is directly passed through
Automatic alarm module 3 achievees the purpose that announce information to the external world.On the one hand patrol personnel are sent an SMS to automatically, and notice is related
Personnel go to in-situ processing crop straw burning event；On the other hand by the position of movable signal tower locating and monitoring camera, in GPS
Its abnormal area is indicated with red point, on figure by associated wechat small routine from trend user's pushed information.Automatic alarm
The structure diagram of module is as shown in Figure 4.
Limiting the scope of the invention, those skilled in the art should understand that, in technical scheme of the present invention
On the basis of, the various modifications or variations that can be made by those skilled in the art with little creative work still the present invention's
Within protection domain.
Claims (3)
1. a kind of monitor video crop straw burning method for inspecting based on deep neural network, it is characterised in that：Based on deep learning
Neural network framework constructs the pyrotechnics recognition processing module based on neural network classifier, which takes
The method that video interception increases data set and amplification data collection feature tag；The pyrotechnics recognition processing module is according to neural network point
Class device is to certain areas cigarette with fiery judgement as a result, alarming from trend patrolman person and ordinary user.
2. the monitor video crop straw burning method for inspecting according to claim 1 based on deep neural network, feature exist
In：The pyrotechnics recognition processing module includes movable signal tower video acquisition module (1), deep learning image pyrotechnics identification module
(2) and automatic alarm module (3)；
The deep learning image pyrotechnics identification module (2) extracts sample according to linear classifier function and loss function
Feature tag and identification classification samples, thus train categorized data set；During training data, using amplification data
Collect the method for feature tag, and repetition training and identification are carried out to special sample；Automatic clustering is collected sample, is used simultaneously
The operation that Python tools overturn sample, stretched and translated.
3. the monitor video crop straw burning method for inspecting according to claim 2 based on deep neural network, feature exist
In：The automatic alarm module (3) sends an SMS to patrol personnel automatically, and by the position of movable signal tower locating and monitoring camera
Set, indicated with red point on GPS map it is abnormal regional, and by associated wechat small routine from trend user's pushed information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810419435.8A CN108777777A (en) | 2018-05-04 | 2018-05-04 | A kind of monitor video crop straw burning method for inspecting based on deep neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810419435.8A CN108777777A (en) | 2018-05-04 | 2018-05-04 | A kind of monitor video crop straw burning method for inspecting based on deep neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108777777A true CN108777777A (en) | 2018-11-09 |
Family
ID=64026999
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810419435.8A Pending CN108777777A (en) | 2018-05-04 | 2018-05-04 | A kind of monitor video crop straw burning method for inspecting based on deep neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108777777A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109410497A (en) * | 2018-11-20 | 2019-03-01 | 江苏理工学院 | A kind of monitoring of bridge opening space safety and alarm system based on deep learning |
| CN110062208A (en) * | 2019-04-23 | 2019-07-26 | 上海赫煊自动化系统工程有限公司 | A kind of security protection intelligence real-time analyzer and method |
| CN110351522A (en) * | 2019-07-12 | 2019-10-18 | 四川长虹电子系统有限公司 | Community grid management system and method based on positioning terminal |
| CN110855940A (en) * | 2019-11-01 | 2020-02-28 | 武汉纺织大学 | Method for processing video stream in straw burning detection |
| CN111432182A (en) * | 2020-04-29 | 2020-07-17 | 上善智城(苏州)信息科技有限公司 | Safety supervision method and system for oil discharge place of gas station |
| CN111462451A (en) * | 2019-11-01 | 2020-07-28 | 武汉纺织大学 | Straw burning detection alarm system based on video information |
| US11334759B2 (en) * | 2019-01-31 | 2022-05-17 | Canon Kabushiki Kaisha | Information processing apparatus, information processing method, and medium |
| CN115409073A (en) * | 2022-10-31 | 2022-11-29 | 之江实验室 | I/Q signal identification-oriented semi-supervised width learning method and device |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101010892A (en) * | 2004-12-07 | 2007-08-01 | 株式会社日立国际电气 | Radio communication system |
| CN102163358A (en) * | 2011-04-11 | 2011-08-24 | 杭州电子科技大学 | Smoke/flame detection method based on video image analysis |
| CN102594595A (en) * | 2012-02-08 | 2012-07-18 | 中国科学院上海微系统与信息技术研究所 | Hybrid system for pipe network monitoring based on wireless sensor networks |
| CN104408469A (en) * | 2014-11-28 | 2015-03-11 | 武汉大学 | Firework identification method and firework identification system based on deep learning of image |
| CN105869341A (en) * | 2016-04-20 | 2016-08-17 | 中国石油化工股份有限公司 | Visual fire alarm integrated monitoring method |
| CN106056690A (en) * | 2016-05-24 | 2016-10-26 | 国网天津武清供电有限公司 | Line-protecting intelligent inspection method and system based on big data, cloud platform and internet of things |
| CN106339657A (en) * | 2015-07-09 | 2017-01-18 | 张�杰 | Straw incineration monitoring method and device based on monitoring video |
| CN106603973A (en) * | 2016-11-15 | 2017-04-26 | 彭小林 | Internet based intelligent monitoring and alarming system |
| CN107507134A (en) * | 2017-09-21 | 2017-12-22 | 大连理工大学 | Super-resolution method based on convolutional neural networks |
-
2018
- 2018-05-04 CN CN201810419435.8A patent/CN108777777A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101010892A (en) * | 2004-12-07 | 2007-08-01 | 株式会社日立国际电气 | Radio communication system |
| CN102163358A (en) * | 2011-04-11 | 2011-08-24 | 杭州电子科技大学 | Smoke/flame detection method based on video image analysis |
| CN102594595A (en) * | 2012-02-08 | 2012-07-18 | 中国科学院上海微系统与信息技术研究所 | Hybrid system for pipe network monitoring based on wireless sensor networks |
| CN104408469A (en) * | 2014-11-28 | 2015-03-11 | 武汉大学 | Firework identification method and firework identification system based on deep learning of image |
| CN106339657A (en) * | 2015-07-09 | 2017-01-18 | 张�杰 | Straw incineration monitoring method and device based on monitoring video |
| CN105869341A (en) * | 2016-04-20 | 2016-08-17 | 中国石油化工股份有限公司 | Visual fire alarm integrated monitoring method |
| CN106056690A (en) * | 2016-05-24 | 2016-10-26 | 国网天津武清供电有限公司 | Line-protecting intelligent inspection method and system based on big data, cloud platform and internet of things |
| CN106603973A (en) * | 2016-11-15 | 2017-04-26 | 彭小林 | Internet based intelligent monitoring and alarming system |
| CN107507134A (en) * | 2017-09-21 | 2017-12-22 | 大连理工大学 | Super-resolution method based on convolutional neural networks |
Non-Patent Citations (2)
| Title |
|---|
| 汪彩霞: "基于深度学习的动态纹理分类方法研究及其在森林防火中的应用", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 董海鹰: "《智能控制理论及应用》", 30 September 2016 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109410497A (en) * | 2018-11-20 | 2019-03-01 | 江苏理工学院 | A kind of monitoring of bridge opening space safety and alarm system based on deep learning |
| US11334759B2 (en) * | 2019-01-31 | 2022-05-17 | Canon Kabushiki Kaisha | Information processing apparatus, information processing method, and medium |
| CN110062208A (en) * | 2019-04-23 | 2019-07-26 | 上海赫煊自动化系统工程有限公司 | A kind of security protection intelligence real-time analyzer and method |
| CN110351522A (en) * | 2019-07-12 | 2019-10-18 | 四川长虹电子系统有限公司 | Community grid management system and method based on positioning terminal |
| CN110855940A (en) * | 2019-11-01 | 2020-02-28 | 武汉纺织大学 | Method for processing video stream in straw burning detection |
| CN111462451A (en) * | 2019-11-01 | 2020-07-28 | 武汉纺织大学 | Straw burning detection alarm system based on video information |
| CN111462451B (en) * | 2019-11-01 | 2022-04-26 | 武汉纺织大学 | Straw burning detection alarm system based on video information |
| CN111432182A (en) * | 2020-04-29 | 2020-07-17 | 上善智城(苏州)信息科技有限公司 | Safety supervision method and system for oil discharge place of gas station |
| CN115409073A (en) * | 2022-10-31 | 2022-11-29 | 之江实验室 | I/Q signal identification-oriented semi-supervised width learning method and device |
| CN115409073B (en) * | 2022-10-31 | 2023-03-24 | 之江实验室 | I/Q signal identification-oriented semi-supervised width learning method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108777777A (en) | A kind of monitor video crop straw burning method for inspecting based on deep neural network | |
| WO2021142902A1 (en) | Danet-based unmanned aerial vehicle coastline floating garbage inspection system | |
| Long et al. | Safety helmet wearing detection based on deep learning | |
| CN111462451B (en) | Straw burning detection alarm system based on video information | |
| CN111881730A (en) | Wearing detection method for on-site safety helmet of thermal power plant | |
| CN102854192B (en) | Method for detecting apple surface defect based on apple surface defect detecting system | |
| CN105869340B (en) | A kind of fiery point monitoring system of exception based on unmanned plane and monitoring method | |
| CN111401419A (en) | Improved RetinaNet-based employee dressing specification detection method | |
| CN106339657B (en) | Crop straw burning monitoring method based on monitor video, device | |
| CN108038424B (en) | Visual automatic detection method suitable for high-altitude operation | |
| CN103324937A (en) | Method and device for labeling targets | |
| CN113516076A (en) | Improved lightweight YOLO v4 safety protection detection method based on attention mechanism | |
| CN108761237A (en) | Unmanned plane electric inspection process image vital electrical component diagnoses automatically and labeling system | |
| CN104320610A (en) | Intelligent recognition system for small mammals (rats) | |
| CN113850562B (en) | Intelligent side station supervision method and system | |
| CN103279760B (en) | A kind of plant quarantine larva real-time grading method | |
| CN114898238B (en) | Wild animal remote sensing identification method and device | |
| CN113487570A (en) | High-temperature continuous casting billet surface defect detection method based on improved yolov5x network model | |
| CN113935364A (en) | Unmanned aerial vehicle flame detection method and system based on YOLOv4 network | |
| CN207366475U (en) | A kind of relief pattern Online Video detection device | |
| CN111931573A (en) | Helmet detection and early warning method based on YOLO evolution deep learning model | |
| CN205983585U (en) | Join in marriage net transformer system of patrolling and examining, RFID module and handheld piece module | |
| CN108195847A (en) | A kind of relief pattern Online Video detection device and its detection method | |
| CN112861676B (en) | Smoke and fire identification marking method, system, terminal and storage medium | |
| CN107657782A (en) | A kind of condition of a fire Automated visual inspection system for high |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181109 |