CN101625789A - Method for monitoring forest fire in real time based on intelligent identification of smoke and fire - Google Patents
Method for monitoring forest fire in real time based on intelligent identification of smoke and fire Download PDFInfo
- Publication number
- CN101625789A CN101625789A CN 200810127874 CN200810127874A CN101625789A CN 101625789 A CN101625789 A CN 101625789A CN 200810127874 CN200810127874 CN 200810127874 CN 200810127874 A CN200810127874 A CN 200810127874A CN 101625789 A CN101625789 A CN 101625789A
- Authority
- CN
- China
- Prior art keywords
- fire
- cloud terrace
- image
- forest
- pyrotechnics
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 12
- 238000000034 method Methods 0.000 title claims abstract description 8
- 239000000779 smoke Substances 0.000 title abstract description 9
- 238000012545 processing Methods 0.000 claims abstract description 9
- 238000004458 analytical method Methods 0.000 claims abstract description 6
- 238000013528 artificial neural network Methods 0.000 claims description 10
- 230000003542 behavioural effect Effects 0.000 claims description 6
- 230000009471 action Effects 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 4
- 230000003068 static effect Effects 0.000 claims description 4
- 230000008676 import Effects 0.000 claims description 3
- 239000000443 aerosol Substances 0.000 claims description 2
- 238000003062 neural network model Methods 0.000 claims description 2
- 238000003672 processing method Methods 0.000 claims description 2
- 230000003595 spectral effect Effects 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 4
- 230000005540 biological transmission Effects 0.000 abstract description 3
- RTAQQCXQSZGOHL-UHFFFAOYSA-N Titanium Chemical compound [Ti] RTAQQCXQSZGOHL-UHFFFAOYSA-N 0.000 abstract 1
- 238000011156 evaluation Methods 0.000 abstract 1
- 238000010191 image analysis Methods 0.000 abstract 1
- 230000007935 neutral effect Effects 0.000 abstract 1
- 235000019504 cigarettes Nutrition 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 230000003750 conditioning effect Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
Images
Classifications
-
- 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 introduces a new method for monitoring forest fire in real time based on digital image processing and the intelligent identification of smoke and fire to accurately detect the forest fire. The method comprises the following steps: performing real-time image analysis on a video frame transmitted by a network camera; selecting that whether fire exists in the field of view and a position and an area where the fire happens, wherein the analysis and the selection are carried out by means of the latest digital image processing technology and the digital image mode identification technology; based on behavior characteristics of the smoke and fire, such as color, color distribution, shape, outline, textures and the like, performing parallel processing; and finally transmitting processing results to a fuzzy neutral network, and obtaining the final evaluation according to the weight of each algorithm. The quick and reliable comprehensive analysis on the smoke and fire greatly reduces the probability of misinformation. Based on the method, aiming at the current situations of forests in different areas, a forest fire protection system independently developed by Beijing Oriental Titan Technology Co., Ltd. can effectively and rationally predict and identify the fire which is to happen or has happened and can timely perform fire-alarm prediction to reduce loss of forest resources through a monitoring management and command center system, a wireless transmission system, a camera and lens system, a tripod head control system and a power system.
Description
Technical field
The present invention monitors forest fire by the Intelligent Recognition of pyrotechnics and reports to the police, and is applicable to forestry fire prevention commanding and decision-making.
Background technology
Set up the round-the-clock long-focus video camera of infrared low-light (level) on the sightseeing tower of control point, forest zone, rotation is taken incessantly, and forest map picture is on every side reached Internet video service centre through wireless network; Each control point forest fire situation of Video service center real time monitoring can be logined by Intranet in the control and command center, carry out pyrotechnics and discern automatically by intelligent image processing, forest fires identification alarm software, receive the status information of The Cloud Terrace simultaneously, according to the camera position and other associated information calculation fire alarm target location that obtain, after monitoring fire and further confirming by the operator, command centre sends warning message to the fire-fighting center, and the commander's work of correspondingly putting out a fire to save life and property.Smoke and fire intelligent identification alarm module plays an important role in system
Summary of the invention
The problem to be solved in the present invention is by carrying out data transmission with the place ahead monitoring camera, obtain monitoring image in real time, carry out the realtime graphic analysis by passing the frame of video of coming, get the position and the zone of deciding whether to exist in the ken condition of a fire and condition of a fire generation by web camera.These algorithms are made up of up-to-date Digital Image Processing, digital picture mode identification technology, behavioural characteristic based on flame smog, as: color, color distribution, shape, profile, texture etc., carry out parallel processing, give fuzzy neural network with result transmission at last, according to the weight of each algorithm, draw the final assessment that whether has pyrotechnics to take place, step is as follows:
(1) decoding digital video is gathered the video information that transmits from the monitoring front end, drives by video acquisition and converts video information the image of appointment to, so that carry out the identification of pyrotechnics image;
(2) the The Cloud Terrace code stream is gathered, the The Cloud Terrace code stream is that the serial equipment manager incoming end (RS-232) by the master-control room PC imports into, The Cloud Terrace code stream acquisition module is according to the code stream coding rule of arranging in advance, the action message that The Cloud Terrace is current is resolved, judge the information of the current horizontal rotatio direction of The Cloud Terrace, vertical sense of rotation and prefabricated position;
(3) smoke and fire intelligent image recognition, the pyrotechnics picture recognition module is the key that forest fires identification warning system realizes detection, behavioural characteristic according to flame smog, as: color, color distribution, shape, profile, texture etc., utilize forest background image and fire, the difference of smog image on spectral signature, space geometry feature, utilization image processing method and complicated recognizer are analyzed the forest zone image, judge whether doubtful fiery point is arranged on the image of forest zone;
(4) cradle head control, the user can realize the adjusting of the depth of field, focal length and the aperture of camera lens by the control to The Cloud Terrace, can also obtain the image of different angles by the adjusting up and down of The Cloud Terrace.When fire took place, the forest fires alarm module sent warning message, and the cradle head control module is monitored the action command that sends the locking The Cloud Terrace in system to forest fires simultaneously, thus control The Cloud Terrace fixed range (or fixed point) scanning;
(5) forest fires location, after monitoring pyrotechnics, the system lock The Cloud Terrace by relevant informations such as the orientation of the height of Dang Qian sightseeing tower, The Cloud Terrace, focus of camera, is calculated the position that forest fire takes place according to formula.
Embodiment
A, based on the anticipation algorithm of color
Usually the forest most of the time is in the state of no burning things which may cause a fire disaster, so can be to simply judging earlier from video flowing image intercepting and that be converted to the BMP form.Native system adopts the state based on the algorithm detected image of color: no matter when, because the flame envelope high-temperature part of flame is absolute high temperature, and the brightness of flame itself concentrates on redness mostly, the color of fire always shows as red, so in the algorithm of fire, anticipation that we have at first carried out image: judge promptly whether this image has red information, if there is not red zone, just, so just accelerated recognition efficiency greatly not with carrying out other fiery algorithm.Its algorithm is:
Pi(x,y)∈[R1,R2]
Wherein, (x y) is the rgb value of pending image pixel to Pi, and [R1, R2] is the red threshold values that show as fire of experiment after determining.(x, y) during ∈ [R1, R2], then judging has doubtful burning things which may cause a fire disaster, takes red channel, gives up the color of other two passages, and separately red channel is discerned processing, and should separate [] in the zone from background as Pi.Algorithm to various forest fires behavioural characteristics below then entering is judged.When
The time, then judge and do not have fire cigarette whether occurs so judge this image.
B, based on the algorithm of pyrotechnics color distribution
Flame generally from the flame core to the flame envelope its color should move to redness from white, according to these characteristics, following recognizer has been proposed.From the top left pixel of flame color object, get the connected pixel point successively, communication direction is the bottom right, does not have connected pixel as the bottom right and then takes off connection, until having got.Per three pixels are got the mean value of red proportion, form ordered series of numbers, do first order difference then.The difference ordered series of numbers that obtains at last inputs to the differentiation algorithm, from initial pixel is that starting point is when working as the heavy minimizing trend of red ratio and continuing certain step number, illustrated from red to white mobile trend, in like manner from being that starting point is worked as that red ratio heavily continues to increase and during certain step number, illustrated from red to white mobile trend by pixel.Any situation occurs all, and the account for color distribution just has the flame characteristics.
Calculate red proportion.Formula is as follows:
Wherein, (Pi (x, y)) is P frame (x, the R among RGB y) (Pi (x, y)), G (Pi (x, y)), G (Pi (x, y)) to R.
C, based on the algorithm of pyrotechnics shape recognition:
Circularity characterizes the complexity of body form, and its computing formula is:
μ=L
2/S
Wherein, μ is a circularity, and L is a girth, and S is an area.
Girth is the boundary length of object, can travel through boundary chain code, can calculate boundary length.Bright spot number by the statistics pel can obtain area.Circularity is got minimum value 4 π to circular object, and complicated more its value of body form is big more.Divided by 4 π, the minimum value that makes circularity is 1 to native system with the circularity value, so that observation.
Circularity is highly effective as the criterion that characterizes the fire disaster flame characteristic, can do early stage judgement, the interference of the shinny object of exclusionary rules (as the sun etc.), thus reduce calculated amount.
D, blending algorithm
(Back2propagation, BP) neural network is discerned neural network model as fire hazard aerosol fog to native system, utilizes fuzzy neural network, with above assessment Macro or mass analysis to flame object behavioral trait with three layers of backpropagation.Judge accurately because above each feature all can not provide strictness separately, and if several assessments are combined and will improve the accuracy of judgement degree greatly; Simultaneously, when several assessments were merged, decision parameter was to be difficult to determine, so consider to utilize fuzzy neural network to realize data fusion.In the whole network, discern the input of neural network as smog with the result of each algorithm of front, utilize neural network to determine the membership function of input, output data, smog identification neural network is carried out analysis and judgement to the input data, identify " forest fires feature " or " non-forest fires feature ", the system that obtains finally exports.When confirming as the fire possibility, send alerting signal, otherwise do not report to the police, and change the image recognition processes of the cigarette of next stage over to greater than certain threshold values (for example 60%).
E, smoke and fire intelligent recognizer
1, algorithm inlet: be the InputPicture (CStringArray﹠amp of CFireWarning class; PicArray) function only need import image file name (three width of cloth images) into and can carry out forest fires identification;
2, the main flow process of algorithm is at the int of CFireWarning class InputPicture (CStringArray﹠amp; Pic) in the function:
A, at first finish the base conditioning of image by the COpenCVDetect class---comprise Static Detection and detection of dynamic;
B, utilize the CFireRecDetect class to finish the feature extraction of image again;
C, utilize neural network to carry out the identification of static forest fires image;
D, in conjunction with the warning of classifying of dynamic and static recognition result.
Description of drawings
Accompanying drawing is a smoke and fire intelligent recognizer basic flow sheet
Claims (4)
1, based on the forest fire method of real-time of Digital Image Processing and identification, its feature includes:
Video acquisition module is gathered the video information that transmits from the monitoring front end, drives by video acquisition and converts video information the image of appointment to, so that carry out the identification of pyrotechnics image;
Decoder module is gathered the video information that transmits from the monitoring front end, drives by video acquisition and converts video information the image of appointment to, so that carry out the identification of pyrotechnics image;
The Cloud Terrace code stream acquisition module, the The Cloud Terrace code stream is that the serial equipment manager incoming end (RS-232) by the master-control room PC imports into, The Cloud Terrace code stream acquisition module is according to the code stream coding rule of arranging in advance, the action message that The Cloud Terrace is current is resolved, judge the information of the current horizontal rotatio direction of The Cloud Terrace, vertical sense of rotation and prefabricated position;
The cradle head control module, the user can realize the adjusting of the depth of field, focal length and the aperture of camera lens by the control to The Cloud Terrace, can also obtain the image of different angles by the adjusting up and down of The Cloud Terrace.When fire took place, the forest fires alarm module sent warning message, and the cradle head control module sends the action command of locking The Cloud Terrace to the forest fires monitoring subsystem simultaneously, thereby controlled The Cloud Terrace fixed range (or fixed point) scanning;
Intelligence pyrotechnics picture recognition module, the pyrotechnics picture recognition module is the key that forest fires identification warning system realizes detection, behavioural characteristic according to flame smog, as: color, color distribution, shape, profile, texture etc., utilize forest background image and fire, the difference of smog image on spectral signature, space geometry feature, utilization image processing method and complicated recognizer are analyzed the forest zone image, judge whether doubtful fiery point is arranged on the image of forest zone;
The forest fires locating module, monitor pyrotechnics after, the system lock The Cloud Terrace by relevant informations such as the orientation of the height of Dang Qian sightseeing tower, The Cloud Terrace, focus of camera, is calculated the position that forest fire takes place according to formula.
2, cradle head control according to claim 1 is characterized in that: The Cloud Terrace control panel conveniently, carry out upper and lower, left and right, cruise The Cloud Terrace, control operations such as aperture, brightness regulation.
3, intelligent pyrotechnics image recognition according to claim 1, it is characterized in that: produce with recognition mode static and that dynamically combine, extract pyrotechnics about pyrotechnics features such as color, saturation degree, center of circle degree, out-of-shape, movement locus scramblings, with three layers of backpropagation (Back2propagation, BP) neural network is discerned neural network model as fire hazard aerosol fog, utilize fuzzy neural network, with above assessment Macro or mass analysis to the pyrotechnics behavioral trait.
4, forest fires according to claim 1 are located, it is characterized in that: once intelligent pyrotechnics image recognition detects the condition of a fire, system automatically locks The Cloud Terrace, and calculates the geographic position that the condition of a fire takes place and locate on electronic chart according to the current attitude (The Cloud Terrace horizontal azimuth, the angle of pitch, geographic coordinate) of The Cloud Terrace.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 200810127874 CN101625789A (en) | 2008-07-07 | 2008-07-07 | Method for monitoring forest fire in real time based on intelligent identification of smoke and fire |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 200810127874 CN101625789A (en) | 2008-07-07 | 2008-07-07 | Method for monitoring forest fire in real time based on intelligent identification of smoke and fire |
Publications (1)
Publication Number | Publication Date |
---|---|
CN101625789A true CN101625789A (en) | 2010-01-13 |
Family
ID=41521625
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN 200810127874 Pending CN101625789A (en) | 2008-07-07 | 2008-07-07 | Method for monitoring forest fire in real time based on intelligent identification of smoke and fire |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN101625789A (en) |
Cited By (47)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101872526A (en) * | 2010-06-01 | 2010-10-27 | 重庆市海普软件产业有限公司 | Smoke and fire intelligent identification method based on programmable photographing technology |
CN102497509A (en) * | 2011-12-14 | 2012-06-13 | 哈尔滨工业大学 | Forest fire point disturbance-removing single point positioning device and positioning method based on the same |
CN102609710A (en) * | 2012-02-22 | 2012-07-25 | 武汉大学 | Smoke and fire object segmentation method aiming at smog covering scene in fire disaster image video |
CN102622845A (en) * | 2012-03-31 | 2012-08-01 | 哈尔滨工业大学 | Background interference elimination device and elimination method based on forest flash point de-disturbance point positioning device |
CN103136893A (en) * | 2013-01-24 | 2013-06-05 | 浙江工业大学 | Tunnel fire early-warning controlling method based on multi-sensor data fusion technology and system using the same |
CN103248878A (en) * | 2013-05-23 | 2013-08-14 | 南车株洲电力机车有限公司 | Pattern recognition method, device and system of abnormal situation of fully mechanized coal mining face |
CN103377533A (en) * | 2012-04-21 | 2013-10-30 | 哈尔滨宝亮凯瑞科技发展有限公司 | Smoke and fire detection method for photographing, processing and identifying color images used for forest fire prevention |
CN103456124A (en) * | 2013-03-27 | 2013-12-18 | 北京科实医学图像技术研究所 | Early warning system for forest fires |
CN103630948A (en) * | 2012-08-28 | 2014-03-12 | 鸿升视通(北京)科技有限公司 | Intelligent information fusion image type fire hazard detector and detection information fusion method |
CN103646284A (en) * | 2013-12-27 | 2014-03-19 | 长春工业大学 | Forest fire prediction method based on GRA-BRLMBP algorithm |
WO2014043975A1 (en) * | 2012-09-24 | 2014-03-27 | 天津市亚安科技股份有限公司 | Prewarning locating monitoring device for multidirectional monitoring area |
CN103996045A (en) * | 2014-06-04 | 2014-08-20 | 南京大学 | Multi-feature fused smoke identification method based on videos |
CN104408745A (en) * | 2014-11-18 | 2015-03-11 | 北京航空航天大学 | Real-time smog scene detection method based on video image |
CN104966372A (en) * | 2015-06-09 | 2015-10-07 | 四川汇源光通信有限公司 | Multi-data fusion forest fire intelligent recognition system and method |
CN105261030A (en) * | 2015-11-26 | 2016-01-20 | 四川汇源光通信有限公司 | Method and device for detecting flame from infrared video |
CN105336085A (en) * | 2015-09-02 | 2016-02-17 | 华南师范大学 | Remote large-space fire monitoring alarm method based on image processing technology |
CN105788143A (en) * | 2016-05-23 | 2016-07-20 | 北京林业大学 | Forest-fire monitoring method and forest-fire monitoring system |
CN106157518A (en) * | 2015-03-24 | 2016-11-23 | 青岛浩海网络科技股份有限公司 | A kind of forest fire protection far infrared anti-false-alarm system and method |
CN106205077A (en) * | 2016-06-29 | 2016-12-07 | 韦醒妃 | Alarm system of quick discernment |
CN106474646A (en) * | 2015-08-31 | 2017-03-08 | 赵国运 | Fully-automatic intelligent extinguishing device |
CN106650600A (en) * | 2016-10-17 | 2017-05-10 | 东南大学 | Forest smoke and fire detection method based on video image analysis |
CN106845410A (en) * | 2017-01-22 | 2017-06-13 | 西安科技大学 | A kind of flame identification method based on deep learning model |
CN106846699A (en) * | 2017-03-10 | 2017-06-13 | 深圳实现创新科技有限公司 | The accident localization method and system of urban fire control system |
CN107437318A (en) * | 2016-05-25 | 2017-12-05 | 知晓(北京)通信科技有限公司 | A kind of visible ray Intelligent Recognition algorithm |
CN107516398A (en) * | 2017-08-09 | 2017-12-26 | 湖北泰龙互联通信股份有限公司 | A kind of technology of flame detecting and video image linkage |
CN107749067A (en) * | 2017-09-13 | 2018-03-02 | 华侨大学 | Fire hazard smoke detecting method based on kinetic characteristic and convolutional neural networks |
CN107862333A (en) * | 2017-11-06 | 2018-03-30 | 哈尔滨工程大学 | A kind of method of the judgment object combustion zone under complex environment |
CN108154637A (en) * | 2017-12-26 | 2018-06-12 | 大连函量科技发展有限公司 | A kind of forest fire monitoring device with warning function |
CN108334801A (en) * | 2017-01-20 | 2018-07-27 | 杭州海康威视系统技术有限公司 | A kind of method for recognizing fire disaster, device and fire alarm system |
CN108520615A (en) * | 2018-04-20 | 2018-09-11 | 芜湖岭上信息科技有限公司 | A kind of fire identification system and method based on image |
CN108564762A (en) * | 2018-06-11 | 2018-09-21 | 南昌航空大学 | A kind of forest rocket identification intelligent cloud system based on Distributed Calculation |
CN108877136A (en) * | 2017-05-12 | 2018-11-23 | 上海防灾救灾研究所 | A kind of fire alarm system and its method of combination gamma camera and infrared point temperature instrument |
CN109101882A (en) * | 2018-07-09 | 2018-12-28 | 石化盈科信息技术有限责任公司 | A kind of image-recognizing method and system of fire source |
CN109165577A (en) * | 2018-08-07 | 2019-01-08 | 东北大学 | A kind of early stage forest fire detection method based on video image |
CN110005975A (en) * | 2018-10-29 | 2019-07-12 | 永康市道可道科技有限公司 | Intellectualized LED lamps and lanterns based on scene monitoring |
CN110082781A (en) * | 2019-05-20 | 2019-08-02 | 东北大学秦皇岛分校 | Fire source localization method and system based on SLAM technology and image recognition |
CN110812753A (en) * | 2019-09-23 | 2020-02-21 | 重庆特斯联智慧科技股份有限公司 | Artificial intelligent fire extinguishing method with open fire point identification function and fire extinguisher equipment |
CN110827501A (en) * | 2019-10-21 | 2020-02-21 | 四川汇源光通信有限公司 | Fire detection method and device based on 5G communication technology and polarization technology |
CN111145275A (en) * | 2019-12-30 | 2020-05-12 | 重庆市海普软件产业有限公司 | Intelligent automatic control forest fire prevention monitoring system and method |
CN111639620A (en) * | 2020-06-08 | 2020-09-08 | 深圳航天智慧城市系统技术研究院有限公司 | Fire disaster analysis method and system based on visible light image recognition |
CN111951508A (en) * | 2020-07-03 | 2020-11-17 | 北京中安安博文化科技有限公司 | Fire classification method, device, medium and electronic equipment |
CN112216052A (en) * | 2020-11-18 | 2021-01-12 | 北京航天泰坦科技股份有限公司 | Forest fire prevention monitoring and early warning method, device and equipment and storage medium |
CN112257575A (en) * | 2020-10-21 | 2021-01-22 | 中国人民解放军火箭军工程大学 | Fixed point location forest fire positioning method |
CN112291536A (en) * | 2020-12-26 | 2021-01-29 | 深圳应急者安全技术有限公司 | Fire fighting identification method and fire fighting system |
CN112516505A (en) * | 2020-10-31 | 2021-03-19 | 泰州程顺制冷设备有限公司 | Real-time fire-fighting water consumption scheduling system |
CN113609885A (en) * | 2020-06-22 | 2021-11-05 | 王英婷 | Adaptive cabin door switch control system and method |
CN115138013A (en) * | 2022-06-14 | 2022-10-04 | 安徽工程大学 | Fire point identification injection system of intelligent fire fighting truck |
-
2008
- 2008-07-07 CN CN 200810127874 patent/CN101625789A/en active Pending
Cited By (62)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101872526B (en) * | 2010-06-01 | 2012-04-18 | 重庆市海普软件产业有限公司 | Smoke and fire intelligent identification method based on programmable photographing technology |
CN101872526A (en) * | 2010-06-01 | 2010-10-27 | 重庆市海普软件产业有限公司 | Smoke and fire intelligent identification method based on programmable photographing technology |
CN102497509A (en) * | 2011-12-14 | 2012-06-13 | 哈尔滨工业大学 | Forest fire point disturbance-removing single point positioning device and positioning method based on the same |
CN102609710A (en) * | 2012-02-22 | 2012-07-25 | 武汉大学 | Smoke and fire object segmentation method aiming at smog covering scene in fire disaster image video |
CN102609710B (en) * | 2012-02-22 | 2013-07-24 | 武汉大学 | Smoke and fire object segmentation method aiming at smog covering scene in fire disaster image video |
CN102622845A (en) * | 2012-03-31 | 2012-08-01 | 哈尔滨工业大学 | Background interference elimination device and elimination method based on forest flash point de-disturbance point positioning device |
CN103377533B (en) * | 2012-04-21 | 2015-10-28 | 鲍鹏飞 | For the fire-smoke detection method of the coloured image ingest process identification of forest fire protection |
CN103377533A (en) * | 2012-04-21 | 2013-10-30 | 哈尔滨宝亮凯瑞科技发展有限公司 | Smoke and fire detection method for photographing, processing and identifying color images used for forest fire prevention |
CN103630948B (en) * | 2012-08-28 | 2016-08-17 | 鸿升视通(北京)科技有限公司 | Intelligent information fusion image-type fire detector and detection information fusion method |
CN103630948A (en) * | 2012-08-28 | 2014-03-12 | 鸿升视通(北京)科技有限公司 | Intelligent information fusion image type fire hazard detector and detection information fusion method |
WO2014043975A1 (en) * | 2012-09-24 | 2014-03-27 | 天津市亚安科技股份有限公司 | Prewarning locating monitoring device for multidirectional monitoring area |
CN103136893A (en) * | 2013-01-24 | 2013-06-05 | 浙江工业大学 | Tunnel fire early-warning controlling method based on multi-sensor data fusion technology and system using the same |
CN103136893B (en) * | 2013-01-24 | 2015-03-04 | 浙江工业大学 | Tunnel fire early-warning controlling method based on multi-sensor data fusion technology and system using the same |
CN103456124A (en) * | 2013-03-27 | 2013-12-18 | 北京科实医学图像技术研究所 | Early warning system for forest fires |
CN103248878A (en) * | 2013-05-23 | 2013-08-14 | 南车株洲电力机车有限公司 | Pattern recognition method, device and system of abnormal situation of fully mechanized coal mining face |
CN103248878B (en) * | 2013-05-23 | 2016-03-09 | 南车株洲电力机车有限公司 | A kind of mode identification method, equipment and system of fully-mechanized mining working unusual condition |
CN103646284A (en) * | 2013-12-27 | 2014-03-19 | 长春工业大学 | Forest fire prediction method based on GRA-BRLMBP algorithm |
CN103996045A (en) * | 2014-06-04 | 2014-08-20 | 南京大学 | Multi-feature fused smoke identification method based on videos |
CN103996045B (en) * | 2014-06-04 | 2017-06-06 | 南京大学 | A kind of smog recognition methods of the various features fusion based on video |
CN104408745A (en) * | 2014-11-18 | 2015-03-11 | 北京航空航天大学 | Real-time smog scene detection method based on video image |
CN106157518A (en) * | 2015-03-24 | 2016-11-23 | 青岛浩海网络科技股份有限公司 | A kind of forest fire protection far infrared anti-false-alarm system and method |
CN104966372A (en) * | 2015-06-09 | 2015-10-07 | 四川汇源光通信有限公司 | Multi-data fusion forest fire intelligent recognition system and method |
CN106474646A (en) * | 2015-08-31 | 2017-03-08 | 赵国运 | Fully-automatic intelligent extinguishing device |
CN105336085A (en) * | 2015-09-02 | 2016-02-17 | 华南师范大学 | Remote large-space fire monitoring alarm method based on image processing technology |
CN105261030A (en) * | 2015-11-26 | 2016-01-20 | 四川汇源光通信有限公司 | Method and device for detecting flame from infrared video |
CN105261030B (en) * | 2015-11-26 | 2019-01-15 | 四川汇源光通信有限公司 | The method and device of flame is detected from infrared video |
CN105788143A (en) * | 2016-05-23 | 2016-07-20 | 北京林业大学 | Forest-fire monitoring method and forest-fire monitoring system |
CN107437318A (en) * | 2016-05-25 | 2017-12-05 | 知晓(北京)通信科技有限公司 | A kind of visible ray Intelligent Recognition algorithm |
CN106205077A (en) * | 2016-06-29 | 2016-12-07 | 韦醒妃 | Alarm system of quick discernment |
CN106205077B (en) * | 2016-06-29 | 2018-07-06 | 南京南工大安全科技有限公司 | A kind of alarm system quickly identified |
CN106650600A (en) * | 2016-10-17 | 2017-05-10 | 东南大学 | Forest smoke and fire detection method based on video image analysis |
CN108334801A (en) * | 2017-01-20 | 2018-07-27 | 杭州海康威视系统技术有限公司 | A kind of method for recognizing fire disaster, device and fire alarm system |
CN106845410A (en) * | 2017-01-22 | 2017-06-13 | 西安科技大学 | A kind of flame identification method based on deep learning model |
CN106845410B (en) * | 2017-01-22 | 2020-08-25 | 西安科技大学 | Flame identification method based on deep learning model |
CN106846699A (en) * | 2017-03-10 | 2017-06-13 | 深圳实现创新科技有限公司 | The accident localization method and system of urban fire control system |
CN108877136A (en) * | 2017-05-12 | 2018-11-23 | 上海防灾救灾研究所 | A kind of fire alarm system and its method of combination gamma camera and infrared point temperature instrument |
CN107516398A (en) * | 2017-08-09 | 2017-12-26 | 湖北泰龙互联通信股份有限公司 | A kind of technology of flame detecting and video image linkage |
CN107749067A (en) * | 2017-09-13 | 2018-03-02 | 华侨大学 | Fire hazard smoke detecting method based on kinetic characteristic and convolutional neural networks |
CN107862333A (en) * | 2017-11-06 | 2018-03-30 | 哈尔滨工程大学 | A kind of method of the judgment object combustion zone under complex environment |
CN108154637A (en) * | 2017-12-26 | 2018-06-12 | 大连函量科技发展有限公司 | A kind of forest fire monitoring device with warning function |
CN108520615B (en) * | 2018-04-20 | 2020-08-25 | 吉林省林业科学研究院 | Fire identification system and method based on image |
CN108520615A (en) * | 2018-04-20 | 2018-09-11 | 芜湖岭上信息科技有限公司 | A kind of fire identification system and method based on image |
CN108564762A (en) * | 2018-06-11 | 2018-09-21 | 南昌航空大学 | A kind of forest rocket identification intelligent cloud system based on Distributed Calculation |
CN109101882A (en) * | 2018-07-09 | 2018-12-28 | 石化盈科信息技术有限责任公司 | A kind of image-recognizing method and system of fire source |
CN109165577A (en) * | 2018-08-07 | 2019-01-08 | 东北大学 | A kind of early stage forest fire detection method based on video image |
CN109165577B (en) * | 2018-08-07 | 2022-03-25 | 东北大学 | Early forest fire detection method based on video image |
CN110005975A (en) * | 2018-10-29 | 2019-07-12 | 永康市道可道科技有限公司 | Intellectualized LED lamps and lanterns based on scene monitoring |
CN110005975B (en) * | 2018-10-29 | 2021-01-26 | 中画高新技术产业发展(重庆)有限公司 | Scene monitoring-based intelligent LED lamp |
CN110082781A (en) * | 2019-05-20 | 2019-08-02 | 东北大学秦皇岛分校 | Fire source localization method and system based on SLAM technology and image recognition |
CN110812753A (en) * | 2019-09-23 | 2020-02-21 | 重庆特斯联智慧科技股份有限公司 | Artificial intelligent fire extinguishing method with open fire point identification function and fire extinguisher equipment |
CN110812753B (en) * | 2019-09-23 | 2021-07-30 | 重庆特斯联智慧科技股份有限公司 | Artificial intelligent fire extinguishing method with open fire point identification function and fire extinguisher equipment |
CN110827501A (en) * | 2019-10-21 | 2020-02-21 | 四川汇源光通信有限公司 | Fire detection method and device based on 5G communication technology and polarization technology |
CN111145275A (en) * | 2019-12-30 | 2020-05-12 | 重庆市海普软件产业有限公司 | Intelligent automatic control forest fire prevention monitoring system and method |
CN111639620A (en) * | 2020-06-08 | 2020-09-08 | 深圳航天智慧城市系统技术研究院有限公司 | Fire disaster analysis method and system based on visible light image recognition |
CN111639620B (en) * | 2020-06-08 | 2023-11-10 | 深圳航天智慧城市系统技术研究院有限公司 | Fire analysis method and system based on visible light image recognition |
CN113609885A (en) * | 2020-06-22 | 2021-11-05 | 王英婷 | Adaptive cabin door switch control system and method |
CN111951508A (en) * | 2020-07-03 | 2020-11-17 | 北京中安安博文化科技有限公司 | Fire classification method, device, medium and electronic equipment |
CN112257575A (en) * | 2020-10-21 | 2021-01-22 | 中国人民解放军火箭军工程大学 | Fixed point location forest fire positioning method |
CN112516505A (en) * | 2020-10-31 | 2021-03-19 | 泰州程顺制冷设备有限公司 | Real-time fire-fighting water consumption scheduling system |
CN112216052A (en) * | 2020-11-18 | 2021-01-12 | 北京航天泰坦科技股份有限公司 | Forest fire prevention monitoring and early warning method, device and equipment and storage medium |
CN112291536A (en) * | 2020-12-26 | 2021-01-29 | 深圳应急者安全技术有限公司 | Fire fighting identification method and fire fighting system |
CN115138013A (en) * | 2022-06-14 | 2022-10-04 | 安徽工程大学 | Fire point identification injection system of intelligent fire fighting truck |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101625789A (en) | Method for monitoring forest fire in real time based on intelligent identification of smoke and fire | |
JP4668978B2 (en) | Flame detection method and apparatus | |
CN102236947B (en) | Flame monitoring method and system based on video camera | |
CN107437318B (en) | Visible light intelligent recognition algorithm | |
CN110837822B (en) | Fire-fighting robot injection curve adjusting method and device based on multi-view vision | |
US9047515B2 (en) | Method and system for wildfire detection using a visible range camera | |
KR101953342B1 (en) | Multi-sensor fire detection method and system | |
CN108389359A (en) | A kind of Urban Fires alarm method based on deep learning | |
CN111686392A (en) | Artificial intelligence fire extinguishing system is surveyed to full scene of vision condition | |
CN112184773A (en) | Helmet wearing detection method and system based on deep learning | |
CN111223263A (en) | Full-automatic comprehensive fire early warning response system | |
CN109741565A (en) | Coal-mine fire identifying system and method | |
CN117037406A (en) | Intelligent monitoring and early warning system for forest fire | |
CN112949536B (en) | Fire alarm method based on cloud platform | |
KR102081577B1 (en) | Intelligence Fire Detecting System Using CCTV | |
CN116206253A (en) | Method and system for detecting and judging site fire behavior based on deep learning | |
CN115393900A (en) | Intelligent construction site safety supervision method and system based on Internet of things | |
CN112861754A (en) | Abnormity processing method and device for electric energy supply station | |
CN116030404A (en) | Artificial intelligence-based construction and safety monitoring method for electronic warning fence of operation area | |
KR101224534B1 (en) | Fire detection device based on image processing with motion detect function | |
CN112215173A (en) | Forest fire monitoring system based on density peak value adaptive clustering | |
CN111502763A (en) | Mine safety dynamic video monitoring management system | |
NL2030149B1 (en) | A method and system for closed-loop automatic control for whole-process intelligent monitoring of fire activity operations | |
CN117422209B (en) | Road construction forest fire prevention monitoring method and system | |
CN116758079B (en) | Harm early warning method based on spark pixels |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
WD01 | Invention patent application deemed withdrawn after publication |
Open date: 20100113 |