CN1576839A - Method and apparatus for the detection of flames - Google Patents
Method and apparatus for the detection of flames Download PDFInfo
- Publication number
- CN1576839A CN1576839A CNA2004100635877A CN200410063587A CN1576839A CN 1576839 A CN1576839 A CN 1576839A CN A2004100635877 A CNA2004100635877 A CN A2004100635877A CN 200410063587 A CN200410063587 A CN 200410063587A CN 1576839 A CN1576839 A CN 1576839A
- Authority
- CN
- China
- Prior art keywords
- image
- flame
- matrix
- mean value
- adds
- 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 9
- 238000000034 method Methods 0.000 title claims description 36
- 230000005855 radiation Effects 0.000 claims abstract description 7
- 238000012544 monitoring process Methods 0.000 claims abstract description 6
- 239000011159 matrix material Substances 0.000 claims description 21
- 230000010354 integration Effects 0.000 claims description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 4
- 238000003909 pattern recognition Methods 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 claims 1
- 238000000605 extraction Methods 0.000 claims 1
- 229920006395 saturated elastomer Polymers 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000004744 fabric Substances 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Fire-Detection Mechanisms (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
- Closed-Circuit Television Systems (AREA)
- Photometry And Measurement Of Optical Pulse Characteristics (AREA)
- Control Of Combustion (AREA)
Abstract
The invention relates to a flame detection in a monitoring area which is achieved by analyzing at least a reference of the radiation appeared in the monitoring area. The video image of the monitoring area is produced and the area with higher light intensity and local flashing shift is sought in the video image, wherein the area and the image part in relation to the following analysis of the flame existence is positioned in the first step. The coordinate of the brightest pixel is sought, and then the concerned image range [ROI] smaller than the original image but containing the brightest pixel is defined, and the image range is analyzed according to the appearance of the flame.
Description
Technical field
The present invention relates to below one, to be called the method and apparatus that carries out flame detection in the monitoring area of Control Room by at least one parameter of analyzing the radiation that in Control Room, occurs.
Background technology
Comprise at least one sensor such as the present known device of describing in United States Patent (USP) Nr.4 866 420 and Nr.4 280 058, this biosensor analysis is handled the scintillation spectrum of radiation, and the radio signal assessment that wherein is in outside definite frequency band is a undesired signal.Just the typical case flicker of flame in low-down hunting of frequency scope as distinguishing the radiation that flame sends and the feature of interference emission.Wave filter by being connected the sensor front under the simplest situation or by be connected the sensor back, frequency-selecting amplifier determines frequency band, wherein obtains for example 5 to 25Hz the free transmission range of determining in both of these case.
Known fire alarm definitely is reliably, but it is a considerable cost element in fire alarm equipment.This is bypassed disregard, also may not get rid of under the situation of flame flicking at the frequency band optimal tuning and disturb and wrong indication,, in free transmission range, exist the random strength of environmental radiation to change because also occur all the time.For example may because the covering or reflect of vibration or the object that slowly moves, because the reflection of water surface sunlight or because flicker or the light source that fluctuates cause so Strength Changes.
Summary of the invention
Will provide a kind of method of flame detection by the present invention, the feature of this method is that very high anti-interference is arranged under the situation of very low expense.
Solve this task thus according to the present invention, promptly produce the video image of Control Room and in this video image, seek high light brightness and zone that winking is moved, wherein the existence that associated picture is partly sought flame is analyzed in this zone, location in first step next.
Feature according to first preferred implementing form of the inventive method is to produce video image and therefrom obtain luminance picture with the frequency of determining.
Feature according to second preferred implementation of the inventive method is, seek the zone that high light brightness and winking are moved by means of the matrix that adds up, from continuous luminance picture to obtain this matrix that adds up the differential image of weighting factor weighting, wherein weighting factor shows, what kind of intensity to add up matrix by being added up to differential image with.
Feature according to the 3rd preferred implementing form of the inventive method is to seek the coordinate of bright pixel by means of the matrix that adds up.
The feature of the 4th preferred implementing form is, definition comprises bright pixel and compares scope that dwindle, interested with original image range and analyze this image range about the existence of flame.
From appended claims 7 to 10, draw other preferred implementing form according to the inventive method.
The feature according to present device that begins the form of mentioning is a video camera, it has the analyzing and processing level that the image that provided by video camera is provided, wherein the analyzing and processing level has a processor, and it has and is used on the image of video camera scope that location higher light intensities and winking move and the algorithm of analyzing the appropriate section image subsequently about the existence of flame.
In dependent claims 12 to 17, propose claim according to the preferred implementing form of present device.
Along with the application more and more widely of CCTV system and equipment can promptly be settled a video camera in many cases as starting point in Control Room, so for flame detects, a distinctive sensor needn't be installed, this makes expense reduce certainly.By analyzing and processing being limited in the image section that may comprise flame, this can obviously reduce computing power and further reduce expense thus.Also can make that the analyzing and processing of image section is enough anti-interference doughtily as starting point.
Description of drawings
Following basis shows that the block scheme according to flame detection equipment of the present invention elaborates the present invention.
Embodiment
With video camera of reference symbol 1 expression, it provides the continuous videos image for analyzing and processing level 2 by output terminal, and wherein analyzing and processing level 2 can be integrated in the video camera 1 or with this analyzing and processing level and be connected.Analyzing and processing level 2 can be predesignated in the installation site of video camera 1 or directly close on video camera or the analyzing and processing level also can be separated with video camera 1 on the space, wherein exists to communicate to connect in the situation of back in video camera 1 and analyzing and processing level 2.
Analyzing and processing level 2 comprises a processor (not shown), and it has flame that the image that is used for being positioned at video camera 1 finds and the algorithm of next analyzing the respective image part.According to diagram, be called of algorithm and from the continuous videos image that provides by video camera 1, obtain brightness and/or chromatic diagram in first process that image obtains as X
Ij(t) (below be called luminance picture); I and j are the coordinates of each pixel.The frequency of this image is per second 15 width of cloth images at least, and the image size for example is 352 * 288 pixels.Therefore obtain luminance picture, because can be as starting point, promptly flame shows the position of higher brightness and has unique tone in addition.
In a next process that is called pre-service 4, at luminance picture X
Ij(t) seek the flame that the location is found in flame and the corresponding image section in.Realize the location by means of the so-called matrix that adds up, form the matrix that adds up in the following manner:
In first step, determine the maximal value max[X of brightness
IjAnd mean value mean[X (t)]
Ij(t)], therefrom determine luminance threshold q (t), wherein q (t+1)=λ
1Max[X
Ij(t)], if mean[X
Ij(t)]＜λ
1Max[X
IjAnd q (t+1)=λ (t)],
2{ max[X
Ij(t)]-mean[X
Ij(t)] }+mean[X
Ij(t)], in all other situations.λ
1And λ
2Be constant, be between 0 and 1, wherein λ for example
1Equal 0.68, λ
2Equal 0.05.
Determine a weighting factor w who considers flame characteristics by means of these two conditions
Ij(t):
w
Ij(t)=X
Ij(t), if X
Ij(t)＞max[X
Ij(t)]-q (t) and
w
Ij(t)=0, in all other situations.
This shows, therefrom filtering and consider that no longer all brightness are lower than value max [X
Ij(t)]-pixel of q (t), dark target just.As what point out, be dark moving target at once by the filtering target.
Because can be as starting point, promptly flame can be identified as moving of higher light intensities, and continuous images forms differential image so pass through more successively, so that find out so mobile; Because according to weighting factor w
Ij(t) dark target has therefrom been deleted in definition, just when forming differential image therefrom filtering move, it can not be the dark target of flame.Just seek the zone that higher light intensities and winking are moved, this shows, does not for example glimmer, static light source is not judged to be flame, laterally also is not judged to be flame through the lamp of Control Room equally.
For differential image Q
Ij(t) be suitable for:
Q
ij(t)＝|X
ij(t)-X
ij(t-1)|w
ij(t)
From differential image Q
Ij(t) determine the matrix A that adds up in
Ij(t):
A
ij(t)＝αA
ij(t-1)+(1-α)Q
ij(t)
α is a constant between 0 and 1, and it shows differential image Q
Ij(t) what kind of intensity to inject the matrix A that adds up with
Ij(t).Equal error image for α=0 matrix that adds up, and do not inject, because A for α=1 differential image
Ij(t) equal A
Ij(t-1).At first therefore, form the matrix that adds up, so that the steady image that acquisition does not have noise and changes in short-term.
As the final step of pre-service 4, seek the pixel [i of mxm. by means of the matrix that adds up
m, j
m] (t), and definition comprises this or these pixel, so-called interested image range ROI, may have flame in this scope:
[i
m，j
m](t)＝{(i，j)|?max[A
ij(t)]}
This determine just to provide have winking and move coordinate with the pixel of maximum brightness.Be usually directed to a unique pixel, wherein also can determine the brightest a plurality of pixels, can use multichannel to select for this reason and mainly determine minor increment between each pixel.
In being called 5 the next process analyzed, not in the image of whole initial 352 * 288 pixels, to analyze, but in for example 32 * 32 pixels reduce the interested image range ROI of size, analyze, realize that so at first tangible data reduce.Pixel is reduced to one of percentage.Certain this minimizing also can be lacked, for example reduce to 1/50th, or minimizing is more.
So determine following image information for each interested image range:
Interested image range X
ROI(t) mean flow rate L (t):
L(t)＝[mean?von?X
ij(t)|
ROI]
Interested image range X
ROI(t) chrominance C (t):
C (t)=[C
Ij(t) |
ROINumber] ∈ " heat color degree sector "/R (t), wherein C
Ij(t) be illustrated in time t image X
Ij(t) colourity is to (V
Ij, U
Ij).YUV is the known expression of color space, has the intensity Y on last two the chrominance component U of x axle and y axle and V and the z axle, wherein shows the color saturation of this pixel in the UV plane from the vector length of initial point to a pixel.Heat color degree sector R (t) is the sector region of the color space in the UV plane, and the typical case comprises red gamut of coloration especially in this color space.
Matrix A adds up
ROI(t) number of valid pixel R (t):
R (t)=[A
Ij(t) |
ROINumber＞η
1]; 1≤η
1＜Z (total number of the pixel of Z=image of interest scope ROI), for example η
1=30
Image of interest scope X
ROI(t) saturation degree S (t):
S (t)=[X
Ij(t) |
ROINumber＞η
2].1≤η
2＜Z is η for example
2=5
In order to make this result keep stable, next be called in 6 the process extracted and be implemented in the time integral of analyzing the image information of determining in 5 at one.If in 1 second, carry out integration, then in the PAL form, continue 25 width of cloth images.Just at t
0To t
nTime in to mean flow rate, colourity, valid pixel and saturation coefficient integration and obtain following characteristic:
Average brightness: F
L=L
Frequency averaging value: F
F=F
Amplitude mean value: F
M=M
Flame chroma pixel mean value: F
C=C
Valid pixel mean value: F
R=R
Saturated mean value: F
S=S
For example obtain the mean value of frequency by the pixel counts of mean flow rate L (t).Because the frequency that the flicker of the feature of flame causes is a significant quantity of flame detection, because this frequency is in the narrow range that defines between 1Hz and 10Hz usually.
In the process that next is called pattern-recognition 7, from extracting the characteristic that obtains 6, calculating the probability that has flame.To this for example for each above-mentioned characteristic check, whether mean value be on the threshold value or under, probability correspondingly is set equals 1 or 0.From the probability of all n characteristic, form a general probability then.
Ψ
L=Γ (F
LIf)=1 is F
L＞δ
L
Ψ
L=Γ (F
LIf)=0 is F
L＜δ
L
So formula also is applicable to other characteristic.
General probability П (t):
П(t)：＝1/N
F∑Ψ
n＝(Ψ
L.W
L+Ψ
F.W
F+Ψ
M.W
M+Ψ
C.W
C+Ψ
R.W
R+Ψ
S.W
S)/N
F
For w
iBe suitable for 0≤w
i≤ 1, determined value w by rule of thumb wherein
iN
FBe w about all i
iWith.
In the process that is called judgement 8, next judge whether trigger warning.This process comprises integration, asks general probability П (t) about consecutive image to upper integral in this integration.Begin this integration zero, and count an increment, and deduct an increment for each П (t)＜κ for each П (t)＞κ (κ is a threshold value).If I (t) represents integrated value, then draw:
I(t＝0)＝0
If П (t)＞κ, then I (t)=I (t-1)+σ
+If (I (t)＞S
+, then saturated is S
+), under all other situations, satisfy I (t)=I (t-1)-σ
-If (I (t)＜S-, then saturated is S-(being generally 0).σ
+And σ
-Be generally equal to+1.
By means of integration I (t) judge whether trigger alarm now:
If I (t)＞β (β is a threshold value) then triggers alarm,
Under all other situations, do not trigger.
Described equipment has such advantage, can employ the video camera of having installed under many applicable cases, does not need to install special flame sensor, and this reduces expense certainly.Because analyzing and processing is limited in the image section that may comprise flame and further reduces expense, this might obviously further reduce the requirement to computing power.Also can make that the analyzing and processing of image section is enough anti-interference doughtily as starting point.
Claims (17)
1. be called the method for carrying out flame detection in the monitoring area of Control Room by at least one parameter of analyzing the radiation that in Control Room, occurs below, it is characterized in that, produce the video image of Control Room and in this video image, seek high light brightness and zone that winking is moved, wherein this zone, location and next have a relevant image section of analyzing and processing in first step for what seek flame.
2. according to the method for claim 1, it is characterized in that generation has the video image of definite frequency and therefrom obtains luminance picture [X
Ij(t)].
3. according to the method for claim 2, it is characterized in that, by means of the matrix [A that adds up
Ij(t)] seek the zone that high light brightness and winking are moved, from continuous luminance picture [X
Ij(t)], to obtain this matrix that adds up in the differential image of weighting factor weighting, wherein weighting factor shows, differential image flows into the matrix [A that adds up with what kind of intensity
Ij(t)].
4. according to the method for claim 3, it is characterized in that, thereby forming differential image and forming the matrix [X that adds up
Ij(t)] thus the time therefrom filtering all have and be in the pixel of predesignating the following brightness of threshold value and all dark targets that move.
5. according to the method for claim 4, it is characterized in that, by means of the matrix [X that adds up
Ij(t)] seek the coordinate of bright pixel.
6. according to the method for claim 5, it is characterized in that definition comprises bright pixel and compares image range that reduce, interested [ROI] with initial image, and analyze this image range for the existence of seeking flame.
7. according to the method for claim 6, it is characterized in that the size of interested image range (ROI) is up to 1/50th of original image size.
8. according to the method for claim 7, it is characterized in that, in interested image range [ROI], determine these image informations, the number [R (t)] and the saturation degree [S (t)] of brightness [L (t)], colourity [C (t)], the valid pixel on definite luminance threshold.
9. according to the method for claim 8, it is characterized in that, about definite time and therefore about the above-mentioned image information of a plurality of image integrations, and determine its mean value, when integration, determine the mean value of frequency [F] and the mean value of amplitude [M], all calculate the probability that has flame for each mean value of these mean values as additional parameter.
10. according to the method for claim 9, it is characterized in that, from the probability of mean value, calculate the general probability that in the image range that reduces [ROI], has flame,, surpassing under the situation of threshold value by integrated value triggering warning about this general probability of a plurality of image integrations.
11. be called the equipment that carries out flame detection in the monitoring area of Control Room by at least one parameter of analyzing the radiation that in Control Room, occurs below, it is characterized in that a video camera [1], it has the analyzing and processing level [2] that the image that provided by video camera [1] is provided, wherein analyzing and processing level [2] has processor, and it has and is used for the scope that moves in the location high light brightness of the image of video camera [1] and winking and next analyzes respective image algorithm partly for the existence of seeking flame.
12. the equipment according to claim 11 is characterized in that, this algorithm comprises a process that is called Image Acquisition [3] below, obtains luminance picture [X in this process from the video image that produces with definite frequency
Ij(t)].
13. the equipment according to claim 12 is characterized in that, this algorithm comprises a process that is called pre-service [4] below, determines an accumulative total matrix [A in this process
Ij(t)] be used to seek the zone that higher light intensities and winking are moved, from continuous luminance picture [X
Ij(t)], to obtain this matrix that adds up in the differential image of weighting factor weighting, wherein weighting factor shows, differential image flows into the matrix [A that adds up with what kind of intensity
Ij(t)].
14. the equipment according to claim 13 is characterized in that, in pre-service [4] by means of the matrix [A that adds up
Ij(t)] determine the coordinate of bright pixel and determine that comprises bright pixel, compares image range that reduce, interested [ROI] with initial image.
15. equipment according to claim 14, it is characterized in that, this algorithm comprises the process that is called analysis [5] below and is used to analyze interested image range [ROI], in analyzing, this determines these image informations, the number [R (t)] of brightness [L (t)], colourity [C (t)], the valid pixel more than definite luminance threshold and saturation degree [S (t)].
16. equipment according to claim 15, it is characterized in that, this algorithm comprises the process that is called extraction [6] below, in this process about time of determining and therefore about the above-mentioned image information of a plurality of image integrations, and determine the mean value of these image informations, when integration, determine the mean value of frequency [F] and the mean value of amplitude [M], and have the probability of flame for each mean value calculation of these mean values as additional parameter.
17. equipment according to claim 16, it is characterized in that, this algorithm comprises the process of a pattern-recognition [7] and the process of a judgement [8], in these processes, from the probability of mean value, calculate the general probability that has flame in the image range [ROI] that is reducing, about this general probability of a plurality of image integrations, surpassing under the situation of threshold value by integrated value triggering warning.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| EP03015846A EP1496483B1 (en) | 2003-07-11 | 2003-07-11 | Method and apparatus for the detection of flames |
| EP03015846.3 | 2003-07-11 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN1576839A true CN1576839A (en) | 2005-02-09 |
| CN100595583C CN100595583C (en) | 2010-03-24 |
Family
ID=33442787
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN200410063587A Expired - Fee Related CN100595583C (en) | 2003-07-11 | 2004-07-12 | Method and apparatus for the detection of flames |
Country Status (9)
| Country | Link |
|---|---|
| EP (1) | EP1496483B1 (en) |
| KR (1) | KR20050009135A (en) |
| CN (1) | CN100595583C (en) |
| AT (1) | ATE357714T1 (en) |
| AU (1) | AU2004202851B2 (en) |
| DE (1) | DE50306852D1 (en) |
| ES (1) | ES2282550T3 (en) |
| NO (1) | NO330182B1 (en) |
| PL (1) | PL369016A1 (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101128699B (en) * | 2005-02-24 | 2010-12-15 | 阿尔斯托姆科技有限公司 | Intelligent flame scanner and method for determining flame characteristic |
| US7868772B2 (en) | 2006-12-12 | 2011-01-11 | Industrial Technology Research Institute | Flame detecting method and device |
| CN101316371B (en) * | 2007-05-31 | 2012-11-28 | 财团法人工业技术研究院 | Flame detecting method and device |
| CN107064113A (en) * | 2017-06-13 | 2017-08-18 | 华电青岛发电有限公司 | One kind realizes burner coal dust firing quality detecting system and method using optical fiber |
| CN111141504A (en) * | 2019-12-25 | 2020-05-12 | Oppo（重庆）智能科技有限公司 | Fire-break detection method and device and computer readable storage medium |
| CN113436406A (en) * | 2021-08-25 | 2021-09-24 | 广州乐盈信息科技股份有限公司 | Sound-light alarm system |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20060041555A (en) * | 2004-11-09 | 2006-05-12 | 한국서부발전 주식회사 | System and method for detecting and alarming a fire of thermal power plants |
| KR100680114B1 (en) * | 2005-05-12 | 2007-02-07 | (주)에이치엠씨 | Device, method and recording medium of robust fire detecting using color of image |
| EP2000998B1 (en) * | 2007-05-31 | 2013-01-02 | Industrial Technology Research Institute | Flame detecting method and device |
| DE112009003247A5 (en) * | 2008-11-03 | 2012-05-03 | IQ Wireless Entwicklungsges. für Systeme und Technologien der Telekommunikation mbH | METHOD AND DEVICE FOR THE NOMINANT DETECTION OF FIRE AND DISTINCTION OF ARTIFICIAL LIGHT SOURCES |
| CN101441712B (en) * | 2008-12-25 | 2013-03-27 | 北京中星微电子有限公司 | Flame video recognition method and fire hazard monitoring method and system |
| CN101847304B (en) * | 2009-12-04 | 2012-05-23 | 四川川大智胜软件股份有限公司 | Image-based method of finding flames with large-space intelligent fire-fighting system |
| CN102645246B (en) * | 2011-02-17 | 2014-04-23 | 中国石油化工股份有限公司 | Method for real-time measurement of torch flow rate of torch discharge system based on torch videos |
| CN103776056B (en) * | 2012-10-25 | 2016-04-20 | 宁波立诚电子制造有限公司 | A kind of lighter detection method and device thereof |
| CN111583610B (en) * | 2020-04-30 | 2021-07-16 | 深圳市前海用电物联网科技有限公司 | Fire-fighting linkage control method and system of causal model |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB9216811D0 (en) * | 1992-08-07 | 1992-09-23 | Graviner Ltd Kidde | Flame detection methods and apparatus |
| WO2001057819A2 (en) * | 2000-02-07 | 2001-08-09 | Vsd Limited | Smoke and flame detection |
| WO2002054364A2 (en) * | 2000-12-28 | 2002-07-11 | Siemens Building Technologies Ag | Video smoke detection system |
| BR0209543A (en) * | 2001-05-11 | 2005-04-26 | Detector Electronics | Flame detection and fire detection method and apparatus |
-
2003
- 2003-07-11 AT AT03015846T patent/ATE357714T1/en not_active IP Right Cessation
- 2003-07-11 EP EP03015846A patent/EP1496483B1/en not_active Expired - Lifetime
- 2003-07-11 DE DE50306852T patent/DE50306852D1/en not_active Expired - Lifetime
- 2003-07-11 ES ES03015846T patent/ES2282550T3/en not_active Expired - Lifetime
-
2004
- 2004-06-25 AU AU2004202851A patent/AU2004202851B2/en not_active Ceased
- 2004-06-30 KR KR1020040050227A patent/KR20050009135A/en not_active Application Discontinuation
- 2004-07-09 NO NO20042948A patent/NO330182B1/en not_active IP Right Cessation
- 2004-07-09 PL PL04369016A patent/PL369016A1/en not_active Application Discontinuation
- 2004-07-12 CN CN200410063587A patent/CN100595583C/en not_active Expired - Fee Related
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101128699B (en) * | 2005-02-24 | 2010-12-15 | 阿尔斯托姆科技有限公司 | Intelligent flame scanner and method for determining flame characteristic |
| US7868772B2 (en) | 2006-12-12 | 2011-01-11 | Industrial Technology Research Institute | Flame detecting method and device |
| CN101316371B (en) * | 2007-05-31 | 2012-11-28 | 财团法人工业技术研究院 | Flame detecting method and device |
| CN107064113A (en) * | 2017-06-13 | 2017-08-18 | 华电青岛发电有限公司 | One kind realizes burner coal dust firing quality detecting system and method using optical fiber |
| CN111141504A (en) * | 2019-12-25 | 2020-05-12 | Oppo（重庆）智能科技有限公司 | Fire-break detection method and device and computer readable storage medium |
| CN113436406A (en) * | 2021-08-25 | 2021-09-24 | 广州乐盈信息科技股份有限公司 | Sound-light alarm system |
Also Published As
| Publication number | Publication date |
|---|---|
| ES2282550T3 (en) | 2007-10-16 |
| AU2004202851B2 (en) | 2008-08-28 |
| ATE357714T1 (en) | 2007-04-15 |
| PL369016A1 (en) | 2005-01-24 |
| NO20042948L (en) | 2005-01-12 |
| EP1496483B1 (en) | 2007-03-21 |
| DE50306852D1 (en) | 2007-05-03 |
| AU2004202851A1 (en) | 2005-01-27 |
| KR20050009135A (en) | 2005-01-24 |
| NO330182B1 (en) | 2011-02-28 |
| NO20042948D0 (en) | 2004-07-09 |
| CN100595583C (en) | 2010-03-24 |
| EP1496483A1 (en) | 2005-01-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN1576839A (en) | Method and apparatus for the detection of flames | |
| US11700457B2 (en) | Flicker mitigation via image signal processing | |
| US7215795B2 (en) | Intruding object detecting method and intruding object monitoring apparatus employing the method | |
| US9047515B2 (en) | Method and system for wildfire detection using a visible range camera | |
| Engel et al. | A low-complexity vision-based system for real-time traffic monitoring | |
| CN107944359A (en) | Flame detecting method based on video | |
| US8019157B2 (en) | Method of vehicle segmentation and counting for nighttime video frames | |
| CN114143940B (en) | Tunnel illumination control method, device, equipment and storage medium | |
| CN1190759C (en) | Video Smoke detection system | |
| US10326969B2 (en) | Vehicle vision system with reduction of temporal noise in images | |
| CN101764922B (en) | Method and device for adaptive generation of luminance threshold | |
| TWI502964B (en) | Detecting method of abnormality of image capturing by camera | |
| CN114779838A (en) | Vehicle-mounted camera angle intelligent regulation control system | |
| KR101044903B1 (en) | Fire detecting method using hidden markov models in video surveillance and monitoring system | |
| CN107346421B (en) | Video smoke detection method based on color invariance | |
| CN111460964A (en) | Moving target detection method under low-illumination condition of radio and television transmission machine room | |
| US20040114054A1 (en) | Method of detecting a significant change of scene | |
| CN113902694A (en) | Target detection method based on dynamic and static combination | |
| AU2002232008A1 (en) | Method of detecting a significant change of scene | |
| CN115690402A (en) | OCC image recognition decoding method based on gradient corner comprehensive detection | |
| CN113066077B (en) | Flame detection method and device | |
| CN111639638B (en) | System and method for identifying transparent flat plate | |
| US20160364618A1 (en) | Nocturnal vehicle counting method based on mixed particle filter | |
| Bales | Illumination compensation in video surveillance analysis | |
| Conte et al. | Evaluation and improvements of a real-time background subtraction method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| ASS | Succession or assignment of patent right |
Owner name: SWITZERLAND SIEMENS CO., LTD. Free format text: FORMER OWNER: SIEMENS CONSTRUCTION TECHNOLOGY GMBH Effective date: 20050408 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20050408 Address after: Zurich Applicant after: Siemens Schweiz AG Address before: Zurich Applicant before: Siemens Building Technologies AG |
|
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 1071930 Country of ref document: HK |
|
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| ASS | Succession or assignment of patent right |
Owner name: SIEMENS AG Free format text: FORMER OWNER: SWITZERLAND SIEMENS CO., LTD. Effective date: 20090605 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20090605 Address after: Munich, Germany Applicant after: Siemens AG Address before: Zurich Applicant before: Siemens Schweiz AG |
|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: WD Ref document number: 1071930 Country of ref document: HK |
|
| ASS | Succession or assignment of patent right |
Owner name: SIEMENS AG Free format text: FORMER OWNER: SIEMENS AKTIENGESELLSCHAFT Effective date: 20150416 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20150416 Address after: Zurich Patentee after: Siemens Schweiz AG Address before: Munich, Germany Patentee before: Siemens AG |
|
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20100324 Termination date: 20170712 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |