CN107688793A - A kind of outside transformer substation fire automatic monitoring method for early warning - Google Patents
A kind of outside transformer substation fire automatic monitoring method for early warning Download PDFInfo
- Publication number
- CN107688793A CN107688793A CN201710791817.9A CN201710791817A CN107688793A CN 107688793 A CN107688793 A CN 107688793A CN 201710791817 A CN201710791817 A CN 201710791817A CN 107688793 A CN107688793 A CN 107688793A
- Authority
- CN
- China
- Prior art keywords
- flame
- smog
- result
- obtains
- early warning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000012544 monitoring process Methods 0.000 title claims abstract description 15
- 238000000605 extraction Methods 0.000 claims abstract description 10
- 238000005311 autocorrelation function Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims abstract description 5
- 238000006073 displacement reaction Methods 0.000 claims abstract description 4
- 238000001514 detection method Methods 0.000 claims description 26
- 230000008859 change Effects 0.000 claims description 19
- 238000012360 testing method Methods 0.000 claims description 14
- 238000012216 screening Methods 0.000 claims description 12
- 230000003542 behavioural effect Effects 0.000 claims description 9
- 230000037237 body shape Effects 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 230000019771 cognition Effects 0.000 description 2
- 238000009792 diffusion process Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 235000019504 cigarettes Nutrition 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000000541 pulsatile effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- 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
-
- 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
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/10—Actuation by presence of smoke or gases, e.g. automatic alarm devices for analysing flowing fluid materials by the use of optical means
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/12—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
- G08B17/125—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions by using a video camera to detect fire or smoke
Abstract
The invention discloses a kind of outside transformer substation fire automatic monitoring method for early warning, belongs to image identification technical field, including S1, the video frame images to input carry out digital processing, and picture signal is converted into data signal；S2, the data signal to video image carry out feature extraction, obtain the variance of the equal value sequence of auto-correlation function, Di Du, the average of circle sequence and auto-correlation function, five features of displacement of barycenter of suspicious flame region；S3, Classification and Identification will be carried out in five features feeding Bayes classifier of extraction, identify fire disaster flame；S4, flame smog is identified, obtains smog recognition result；S5, with reference to flame identification result and smog recognition result, identify final flame location and alarmed.The present invention, then in conjunction with fire location is identified, improves the accuracy of fire alarm by the way that flame and smog are separately identified.
Description
Technical field
The present invention relates to transforming plant protecting technical field, more particularly to a kind of pre- police of outside transformer substation fire automatic monitoring
Method.
Background technology
In recent years, transformer station's fire incident caused by equipment fault frequently occurs, if do not had in fire early period of origination
Find in time and take effective treatment measures, fire not only can directly burn substantial amounts of electric equipment, and the reparation that has a power failure
Between it is also longer, had a strong impact on the safe for operation of power network.
At present, it is general using pre- based on video image identification fire automatic monitoring in outside transformer substation fire early-warning system
Alert, its principle is：The image of former frame in video code flow and a later frame (pixel) is compared, distinguish " prospect " and
" background ", " prospect " is extracted after filtering background and prospect noise reduction as detection target.Smog in detection target is carried out
Differentiate, often produced before temperature is increased to flare appearance with smog, therefore carried according to the feature of " flame " and " smog "
Algorithm is taken to carry out aspect ratio pair to the on-site supervision video code flow from outside transformer substation, so as to realize in monitored picture
The automatic capture of " flame " and " smog " signal, triggering alarm.
But the current fire automatic monitoring process based on video image identification has a drawback in that：First, video
In the movement velocity of smoke and fire flame be to be determined by the movement velocity of air-flow in environment and the distance of photographed, therefore, cigarette
It is unstable with the motion state of flame in video, easily produce wrong report.Second, the feature of smog is by external environment shadow in video
Sound is larger, and the accuracy rate that fire differentiates is low.
The content of the invention
It is an object of the invention to provide a kind of outside transformer substation fire automatic monitoring method for early warning, to improve fire differentiation
Accuracy rate.
To realize object above, the technical solution adopted by the present invention is：A kind of outside transformer substation fire automatic monitoring is provided
Method for early warning, including：
S1, the video frame images to input carry out digital processing, and picture signal is converted into data signal；
S2, the data signal to video image carry out feature extraction, obtain auto-correlation function, the Di Du of suspicious flame region
The equal variance of value sequence, the average of circle sequence and auto-correlation function, five features of displacement of barycenter；
S3, Classification and Identification will be carried out in five features feeding Bayes classifier of extraction, identify fire disaster flame；
S4, flame smog is identified, obtains smog recognition result；
S5, with reference to flame identification result and smog recognition result, identify final flame location and alarmed.
Wherein, step S1 is specifically included：
Video frame images are obtained, and sequential frame image pixel number is indicated with rgb space, obtain first flame zone
Domain the selection result；
Flame contours in preliminary flame region the selection result are identified, seizure obtains the flame for meeting profile, obtains
To postsearch screening result；
Frequency screening is carried out to the flame flame envelope in postsearch screening result using 10Hz as screening conditions, is screened knot three times
Fruit；
Whether uniformly the selection result three times is screened with Energy distribution, the uneven result of Energy distribution is defined as
Flame region.
Wherein, after step s 3, in addition to：
The behavioral characteristics of flame are analyzed, obtain flame identification result, the behavioral characteristics of its Flame include flame
Area change, edge variation, body shape changes, flash rule, layering change and move integrally.
Wherein, it is described that flame smog is identified, smog recognition result is obtained, is specifically included：
Slow moving object in the video frame images is detected, obtains object detection result；
Smog color region in the video frame images is detected, obtains smog color region testing result；
Smog elevated areas in the object detection result is detected, obtains smog elevated areas testing result；
Shade in the object detection result is detected and removed, obtains shadow detection result；
To the object detection result, smog color region testing result, smog elevated areas testing result and shade
Testing result is filtered, weighted sum decision-making treatment, obtains smog recognition result.
Compared with prior art, there is following technique effect in the present invention：Because the feature of smog is in terms of dynamic and static state
There is obvious difference with flame, carry out separating identification by flame and smog in the present invention, pass through multiple features to smog
Extraction, reduces False Rate.Simultaneously because the fire disaster flame of early stage is unstable, at different moments the shape of flame, area and
Radiation intensity etc. is all changing, the present invention by fire (flame and smog) it is dynamic read signature analysis (including：Area change, side
Edge change, body shape changes, flash rule, layering change, move integrally), strengthen and realize the intelligence of fire (flame and smog)
Ability to predict.
Brief description of the drawings
Below in conjunction with the accompanying drawings, the embodiment of the present invention is described in detail：
Fig. 1 is a kind of schematic flow sheet of outside transformer substation fire automatic monitoring method for early warning in the present invention；
Fig. 2 is the flame identification effect diagram in the present invention；
Fig. 3 is the flame flame envelope the selection result schematic diagram in the present invention；
Fig. 4 is the Energy distribution schematic diagram of clothes in the present invention；
Fig. 5 is the Energy distribution schematic diagram of Flame of the present invention.
Embodiment
In order to illustrate further the feature of the present invention, please refer to the following detailed descriptions related to the present invention and accompanying drawing.Institute
Accompanying drawing is only for reference and purposes of discussion, is not used for being any limitation as protection scope of the present invention.
As shown in figure 1, present embodiment discloses a kind of outside transformer substation fire automatic monitoring method for early warning, including following step
Rapid S1 to S5：
S1, the video frame images to input carry out digital processing, and picture signal is converted into data signal；
Specifically, the processing such as interference, noise and difference is removed to picture signal, obtains being adapted to computer to carry out feature
The data signal of extraction.
S2, the data signal to video image carry out feature extraction, obtain auto-correlation function, the Di Du of suspicious flame region
The equal variance of value sequence, the average of circle sequence and auto-correlation function, five features of displacement of barycenter；
S3, Classification and Identification will be carried out in five features feeding Bayes classifier of extraction, identify fire disaster flame；
S4, flame smog is identified, obtains smog recognition result；
S5, with reference to flame identification result and smog recognition result, identify final flame location and alarmed.
It should be noted that due to the feature of smog it is either static or it is dynamic, itself and flame have significantly
It is different.Therefore the present embodiment separately handles smog with flame identification, improves the accuracy of smog and flame identification.Pass through prison
The automatic capture of " flame " and " smog " signal in picture is controlled, triggering alarm is carried out, also improves the accuracy of fire alarm.
Further, step S1 is specifically included：
Video frame images are obtained, and sequential frame image pixel number is indicated with rgb space, obtain first flame zone
Domain the selection result；
As long as it should be noted that using meeting R in RGB image in the present embodiment>=G and G>B color can be seen
Work is the principle of flame, in two field picture flame carry out Preliminary detection, exclude most unlikely be flame object.
Flame contours in preliminary flame region the selection result are identified, seizure obtains the flame for meeting profile, obtains
To postsearch screening result；
It should be noted that the profile of flame is also the key character for identifying, flame from burning point from level to level to
External diffusion, more to outer layer its local shape can edge degree it is bigger, and be continuous.2- (a) in Fig. 2 illustrates a combustion
Burn the flame model of point, it is made up of three layers of flame contours, for the flame in Fig. 2-(b) by the model catch to obtain Fig. 2-
(c) result.
The flame identification method used in the present embodiment includes but is not limited to based on flame contours of the barycenter away from pulsatile characteristics
Recognizer etc..
Frequency screening is carried out to the flame flame envelope in postsearch screening result using 10Hz as screening conditions, is screened knot three times
Fruit；
It should be noted that flame is dynamic jump, or perhaps mobile change.The motion of the flame envelope part of flame
Certain frequency be present, as shown in Figure 3 in from the point of view of the flame flame envelope part that marks, these pixels are experiencing flame and without fire
The switching of flame two states, it is 10Hz that the frequency of this switching, which passes through measuring and calculating,.Therefore, can be with by catching this 10Hz feature
Whether further confirm that has the presence of flame.
Whether uniformly the selection result three times is screened with Energy distribution, the uneven result of Energy distribution is defined as
Flame region.
It should be noted that the motion of flame has energy variation, the physical change of burning and chemical change cause
The unbalanced distribution of flame energy, this point can be as the features for distinguishing flame and other color similar movement objects.It is such as red
The region energy change such as Fig. 4 marked on color clothes by dark border, it is seen that the Energy distribution of clothes is uniformly (to be shown as equal
One grey, without bright dark change).In contrast, the energy variation of flame just seems very uneven such as Fig. 5, sees bright to see
Aobvious bright dark change.
By using two field picture pixel value, rgb space, flame contours, flame flame envelope frequency and energy in the present embodiment
The screening conditions such as distribution situation are screened to the flame in two field picture, drastically increase the accuracy of flame identification.
Further, outside transformer substation fire automatic monitoring method for early warning disclosed in the present embodiment, after step s 3, also
Comprise the following steps S3`：
S3`, the behavioral characteristics to flame are analyzed, and obtain flame identification result, and the behavioral characteristics of its Flame include
The area change of flame, edge variation, body shape changes, flash rule, layering change and move integrally.
It should be noted that fire disaster flame is unstable, the shape of flame, area and radiation intensity etc. be all at different moments
Changing, in the present embodiment to the area change of flame, edge variation, body shape changes, flash rule, layering change and overall
The behavioral characteristics such as mobile are analyzed, it is possible to achieve the good anticipation of fire.
Further, it is to the recognition principle of smog in the present embodiment：
The contrast change of pixel goes to judge the presence or absence of smog, obtains the preliminary recognition result of smog；
The preliminary recognition result of smog is screened according to the behavioral characteristics of smog, identify smog, wherein smog
Behavioral characteristics include：The dynamic diffusion of smog, the border change switching frequency of smog are 3Hz, the profile of smog is clear picture
It is continuous and is nonrigid etc. with is obscured the boundary of picture and the motion of smog by smog.
Further, it is above-mentioned that flame smog is identified, smog recognition result is obtained, is specifically comprised the following steps：
Slow moving object in the video frame images is detected, obtains object detection result；
Smog color region in the video frame images is detected, obtains smog color region testing result；
Smog elevated areas in the object detection result is detected, obtains smog elevated areas testing result；
Shade in the object detection result is detected and removed, obtains shadow detection result；
To the object detection result, smog color region testing result, smog elevated areas testing result and shade
Testing result is filtered, weighted sum decision-making treatment, obtains smog recognition result.
It should be noted that slow moving object segmentation, the detection of smog color region, the detection of smog elevated areas and shade
The processes such as detection are all that the presence situation of pyrotechnics is separately monitored in the visual range of camera.Finally use adaptive subalgorithm
Filtered, weighted sum decision-making, obtain final smog recognition result.
Wherein, slow moving object segmentation, the detection of smog color region, the detection of smog elevated areas and shadow Detection is first
Beginning weights are obtained by actual fire video, and when initially setting up, error amount is defined as each detection process composition value and artificial cognition
Signals between excessive difference.
Further, the fire early-warning system in the present embodiment is the intelligence system that man-machine interaction and self study are combined,
When early warning system sends early warning, also need to send request to artificial cognition to confirm whether to send alarm of fire, this mode makes
The actual use personnel of the system take part in the process of study.
It should be noted that algorithm in the present embodiment can resident service device program, the video code flow uploaded to each road
Flame identification and intellectual analysis are carried out, can be also implanted into all kinds of intelligent network cameras, carries out front end recognition, reduces video and passes
Defeated bandwidth pressure.
The foregoing is only presently preferred embodiments of the present invention, be not intended to limit the invention, it is all the present invention spirit and
Within principle, any modification, equivalent substitution and improvements made etc., it should be included in the scope of the protection.
Claims (4)
- A kind of 1. outside transformer substation fire automatic monitoring method for early warning, it is characterised in that including：S1, the video frame images to input carry out digital processing, and picture signal is converted into data signal；S2, the data signal to video image carry out feature extraction, obtain auto-correlation function, the Di Du averages of suspicious flame region Five features of displacement of the variance of sequence, the average of circle sequence and auto-correlation function, barycenter；S3, Classification and Identification will be carried out in five features feeding Bayes classifier of extraction, identify fire disaster flame；S4, flame smog is identified, obtains smog recognition result；S5, with reference to flame identification result and smog recognition result, identify final flame location and alarmed.
- 2. outside transformer substation fire automatic monitoring method for early warning as claimed in claim 1, it is characterised in that described step S1 Specifically include：Video frame images are obtained, and sequential frame image pixel number is indicated with rgb space, obtain first flame region sieve Select result；Flame contours in preliminary flame region the selection result are identified, seizure obtains the flame for meeting profile, obtains two Secondary the selection result；Frequency screening is carried out to the flame flame envelope in postsearch screening result using 10Hz as screening conditions, obtains the selection result three times；Whether uniformly the selection result three times is screened with Energy distribution, the uneven result of Energy distribution is defined as flame Region.
- 3. outside transformer substation fire automatic monitoring method for early warning as claimed in claim 2, it is characterised in that in described step After S3, in addition to：The behavioral characteristics of flame are analyzed, obtain flame identification result, the behavioral characteristics of its Flame include the face of flame Product change, edge variation, body shape changes, flash rule, layering change and move integrally.
- 4. outside transformer substation fire automatic monitoring method for early warning as claimed in claim 3, it is characterised in that described step S4, specifically include：Slow moving object in the video frame images is detected, obtains object detection result；Smog color region in the video frame images is detected, obtains smog color region testing result；Smog elevated areas in the object detection result is detected, obtains smog elevated areas testing result；Shade in the object detection result is detected and removed, obtains shadow detection result；To the object detection result, smog color region testing result, smog elevated areas testing result and shadow Detection As a result filtered, weighted sum decision-making treatment, obtain smog recognition result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710791817.9A CN107688793A (en) | 2017-09-05 | 2017-09-05 | A kind of outside transformer substation fire automatic monitoring method for early warning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710791817.9A CN107688793A (en) | 2017-09-05 | 2017-09-05 | A kind of outside transformer substation fire automatic monitoring method for early warning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107688793A true CN107688793A (en) | 2018-02-13 |
Family
ID=61155993
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710791817.9A Pending CN107688793A (en) | 2017-09-05 | 2017-09-05 | A kind of outside transformer substation fire automatic monitoring method for early warning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107688793A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108363992A (en) * | 2018-03-15 | 2018-08-03 | 南京邮电大学 | A kind of fire behavior method for early warning monitoring video image smog based on machine learning |
| CN108564760A (en) * | 2018-06-06 | 2018-09-21 | 广西防城港核电有限公司 | Fire detection device under nuclear power station extreme environmental conditions and detection method |
| CN108682105A (en) * | 2018-05-29 | 2018-10-19 | 贵州电网有限责任公司 | One kind is based on multispectral transmission line forest fire exploration prior-warning device and method for early warning |
| CN111325940A (en) * | 2020-02-26 | 2020-06-23 | 国网陕西省电力公司电力科学研究院 | Transformer substation fire-fighting intelligent linkage method and system based on fuzzy theory |
| CN111460973A (en) * | 2020-03-30 | 2020-07-28 | 国网山西省电力公司电力科学研究院 | Smoke and fire signal detection and image visualization automatic identification method |
| CN113205659A (en) * | 2021-03-19 | 2021-08-03 | 武汉特斯联智能工程有限公司 | Fire disaster identification method and system based on artificial intelligence |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101441771A (en) * | 2008-12-19 | 2009-05-27 | 中国科学技术大学 | Video fire hazard smoke detecting method based on color saturation degree and movement mode |
| KR100948568B1 (en) * | 2008-04-04 | 2010-03-18 | 계명대학교 산학협력단 | Fire detection apparatus and method using Bayesian Networks |
| CN104715559A (en) * | 2015-03-06 | 2015-06-17 | 温州大学 | Smoke detection and fire alarm method based on trajectory identification |
| CN106897720A (en) * | 2017-01-11 | 2017-06-27 | 济南中维世纪科技有限公司 | A kind of firework detecting method and device based on video analysis |
| CN107067412A (en) * | 2017-04-01 | 2017-08-18 | 江苏移动信息系统集成有限公司 | A kind of video flame smog detection method of Multi-information acquisition |
-
2017
- 2017-09-05 CN CN201710791817.9A patent/CN107688793A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100948568B1 (en) * | 2008-04-04 | 2010-03-18 | 계명대학교 산학협력단 | Fire detection apparatus and method using Bayesian Networks |
| CN101441771A (en) * | 2008-12-19 | 2009-05-27 | 中国科学技术大学 | Video fire hazard smoke detecting method based on color saturation degree and movement mode |
| CN104715559A (en) * | 2015-03-06 | 2015-06-17 | 温州大学 | Smoke detection and fire alarm method based on trajectory identification |
| CN106897720A (en) * | 2017-01-11 | 2017-06-27 | 济南中维世纪科技有限公司 | A kind of firework detecting method and device based on video analysis |
| CN107067412A (en) * | 2017-04-01 | 2017-08-18 | 江苏移动信息系统集成有限公司 | A kind of video flame smog detection method of Multi-information acquisition |
Non-Patent Citations (5)
| Title |
|---|
| HONG JIN 等: "A FIRE AND FLAME DETECTING METHOD BASED ON VIDEO", 《PROCEEDINGS OF THE EIGHTH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS》 * |
| 何舟 等: "基于视频监控的烟雾检测算法", 《电脑知识》 * |
| 刘昕雨: "基于视频特征的火灾火焰识别算法", 《中国优秀硕士论文全文数据库（信息科技辑）》 * |
| 武桂林 等: "基于图像处理的森林烟火检测系统", 《计算机技术与发展》 * |
| 麻仓龙: "火焰检测技术", 《百度学术》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108363992A (en) * | 2018-03-15 | 2018-08-03 | 南京邮电大学 | A kind of fire behavior method for early warning monitoring video image smog based on machine learning |
| CN108363992B (en) * | 2018-03-15 | 2021-12-14 | 南京钜力智能制造技术研究院有限公司 | Fire early warning method for monitoring video image smoke based on machine learning |
| CN108682105A (en) * | 2018-05-29 | 2018-10-19 | 贵州电网有限责任公司 | One kind is based on multispectral transmission line forest fire exploration prior-warning device and method for early warning |
| CN108682105B (en) * | 2018-05-29 | 2019-11-05 | 贵州电网有限责任公司 | One kind is based on multispectral transmission line forest fire exploration prior-warning device and method for early warning |
| CN108564760A (en) * | 2018-06-06 | 2018-09-21 | 广西防城港核电有限公司 | Fire detection device under nuclear power station extreme environmental conditions and detection method |
| CN111325940A (en) * | 2020-02-26 | 2020-06-23 | 国网陕西省电力公司电力科学研究院 | Transformer substation fire-fighting intelligent linkage method and system based on fuzzy theory |
| CN111325940B (en) * | 2020-02-26 | 2021-09-14 | 国网陕西省电力公司电力科学研究院 | Transformer substation fire-fighting intelligent linkage method and system based on fuzzy theory |
| CN111460973A (en) * | 2020-03-30 | 2020-07-28 | 国网山西省电力公司电力科学研究院 | Smoke and fire signal detection and image visualization automatic identification method |
| CN113205659A (en) * | 2021-03-19 | 2021-08-03 | 武汉特斯联智能工程有限公司 | Fire disaster identification method and system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107688793A (en) | A kind of outside transformer substation fire automatic monitoring method for early warning | |
| CN106600888B (en) | Automatic forest fire detection method and system | |
| CN104123544B (en) | Anomaly detection method and system based on video analysis | |
| CN104599427B (en) | A kind of intelligent image type fire alarm system for vcehicular tunnel | |
| JP2018101416A (en) | Fire monitoring system | |
| CN109637068A (en) | Intelligent pyrotechnics identifying system | |
| CN108389359B (en) | Deep learning-based urban fire alarm method | |
| US20140177946A1 (en) | Human detection apparatus and method | |
| CN112069975A (en) | Comprehensive flame detection method based on ultraviolet, infrared and vision | |
| KR100918436B1 (en) | Fire detection system and method basedon visual data | |
| CN107944359A (en) | Flame detecting method based on video | |
| CN106228709B (en) | A kind of wisdom gold eyeball identifies that one adds paper money alarm method and device | |
| CN107679471A (en) | Indoor occupant sky hilllock detection method based on video monitoring platform | |
| CN108038867A (en) | Fire defector and localization method based on multiple features fusion and stereoscopic vision | |
| CN107085714A (en) | A kind of forest fire detection method based on video | |
| CN109377713A (en) | A kind of fire alarm method and system | |
| CN111951250B (en) | Fire detection method based on image | |
| CN109034038B (en) | Fire identification device based on multi-feature fusion | |
| EP2000998B1 (en) | Flame detecting method and device | |
| CN113963301A (en) | Space-time feature fused video fire and smoke detection method and system | |
| Khondaker et al. | Computer vision-based early fire detection using enhanced chromatic segmentation and optical flow analysis technique. | |
| CN108830161A (en) | Smog recognition methods based on video stream data | |
| CN113657250A (en) | Flame detection method and system based on monitoring video | |
| CN107729811B (en) | Night flame detection method based on scene modeling | |
| JP5286113B2 (en) | Smoke detector |
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: 20180213 |