AU2004202851A1 - Method and Device for Detecting Flames - Google Patents

Method and Device for Detecting Flames Download PDF

Info

Publication number
AU2004202851A1
AU2004202851A1 AU2004202851A AU2004202851A AU2004202851A1 AU 2004202851 A1 AU2004202851 A1 AU 2004202851A1 AU 2004202851 A AU2004202851 A AU 2004202851A AU 2004202851 A AU2004202851 A AU 2004202851A AU 2004202851 A1 AU2004202851 A1 AU 2004202851A1
Authority
AU
Australia
Prior art keywords
images
image
flame
pixels
determined
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
Application number
AU2004202851A
Other versions
AU2004202851B2 (en
Inventor
Giuseppe Marbach
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Siemens AG
Original Assignee
Siemens Building Technologies AG
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Siemens Building Technologies AG filed Critical Siemens Building Technologies AG
Publication of AU2004202851A1 publication Critical patent/AU2004202851A1/en
Application granted granted Critical
Publication of AU2004202851B2 publication Critical patent/AU2004202851B2/en
Assigned to SIEMENS AKTIENGESELLSCHAFT reassignment SIEMENS AKTIENGESELLSCHAFT Request for Assignment Assignors: SIEMENS BUILDING TECHNOLOGIES AG
Ceased legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B17/00Fire alarms; Alarms responsive to explosion
    • G08B17/12Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B17/00Fire alarms; Alarms responsive to explosion
    • G08B17/12Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
    • G08B17/125Actuation 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

A flame detection procedure (2) analyses a video (1) image (3) for bright spots and moving areas using a weighted accumulation matrix (4) constructed from the differences between successive images with low intensity and so dark moving objects filtered (5) out to leave small areas of interest for integration (6) and flame presence probability (7) estimation (8). Includes INDEPENDENT CLAIMs for equipment using the procedure.

Description

S&F Ref: 681004
AUSTRALIA
PATENTS ACT 1990 COMPLETE SPECIFICATION FOR A STANDARD PATENT Name and Address of Applicant: Actual Inventor(s): Address for Service: Invention Title: Siemens Building Technologies AG, of Bellerivestrasse 36, 8008, Zirich, Switzerland Giuseppe Marbach Spruson Ferguson St Martins Tower Level 31 Market Street Sydney NSW 2000 (CCN 3710000177) Method and Device for Detecting Flames The following statement is a full description of this invention, including the best method of performing it known to me/us:- 5845c Method and device for detecting flames Description The present invention relates to a method and a device for detecting flames in a monitored zone, referred to hereinafter as monitoring space, by analysis of at least one parameter of a radiation that occurs in the monitoring space.
Previously known devices, as are described for example in US patents No. 4 866 420 and No. 4 280 058, contain at least one sensor which evaluates the flicker frequency spectrum of the radiation, signals lying outside a specific frequency band being assessed as interference signals. The typical flicker of the flames in a very low-frequency oscillation range is thus used as a feature for distinguishing between the radiation emitted by a flame and interference radiation. In the simplest case, the frequency band is defined by filters connected upstream of the sensor, or by frequencyselective amplifiers connected downstream thereof, a specific passband of 5 to 25 Hz, for example, being obtained in both cases.
These known flame detectors have proved to be successful, but they represent a not inconsiderable cost factor in a fire alarm system. Apart from that, even with optimum tuning of the frequency band to the flicker of flames, disturbances and incorrect ~t 'cnt be p~rcluded~C beC~I11aP t haIPpns again and again that random changes in intensity of the ambient radiation lie in the passband. Such changes in intensity may be caused for example by shading or reflections of vibrating or slowly moving objects, by reflections of sunlight on water surfaces or by flickering or fluctuating light sources.
2 The invention, then, is intended to specify a method for detecting flames which is distinguished by high interference immunity in conjunction with low costs.
This object is achieved according to the invention by virtue of the fact that a video image of the monitoring space is generated and zones having high light intensity and local flicker motion are sought in said video image, in which case, in a first step, said zones are localized and the relevant image excerpts are subsequently analyzed with regard to the presence of a flame.
A first preferred embodiment of the method according to the invention is characterized in that the video images are generated with a specific frequency and intensity images are attained therefrom.
A second preferred embodiment of the method according to the invention is characterized in that the search for zones having high light intensity and local flicker motion is effected with the aid of an accumulation matrix, which is obtained from the difference images of successive intensity images, said difference images being weighted with a weighting factor, the weighting factor specifying the extent to which the difference images influence the accumulation matrix.
A third preferred embodiment of the method according to the invention is characterized in that the coordinates of the brightest pixels are sought with the aid of the accumulation matrix.
A fourth preferred embodiment is characterized in that an image region of interest which contains the brightness pixel or pixels and is reduced with respect to the original image is defined and analyzed with regard to the presence of a flame.
3 Further preferred embodiments of the method according to the invention emerge from the dependent claims 7 to The device according to the invention of the type mentioned in the introduction is characterized -by a video camera with an evaluation stage for the images supplied by the camera, the evaluation stage having a processor with an algorithm for the localization of regions having high light intensity and local flicker motion in the images of the camera and the subsequent analysis of the corresponding image excerpts with regard to the presence of a flame.
Preferred embodiments of the device according to the invention are claimed in the dependent claims 12 to 17.
As CCTV systems and installations are becoming ever more widespread, it can be assumed that in many cases a video camera will be present in a monitoring space, and so a dedicated sensor does not have to be installed for the flame detection, which undoubtedly means a reduction of costs. A further reduction of costs results from restricting the evaluation to the image excerpts possibly containing a flame, which enables the computer power to be significantly reduced. It can also be assumed that the evaluation of these image excerpts is sufficiently robust toward disturbances.
The invention is explained in more detail below by way of example with reference to a block diagram showing a rip'rv rAinry i-l i for flames.
deice accor~in 471te nra~inCr dttF The reference symbol 1 designates a video camera, which, via an output, supplies video sequences to an evaluation stage 2, in which the evaluation stage 2 may be integrated into the camera 1 or be connected thereto. The evaluation stage 2 may be provided at the location where the camera 1 is installed, or in direct proximity thereto, or it may also be provided spatially 4 remote from the camera 1, there being a communication link between camera 1 and evaluation stage 2 in the latter case.
The evaluation stage 2 contains a processor (not illustrated) having an algorithm for the localization of flames found in the images of the camera 1 and the subsequent analysis of the corresponding image excerpts. In accordance with the illustration, in a first process of the algorithm, designated image obtaining, intensity and/or chrominance images Xij (t) (referred to hereinafter as intensity images) are obtained from the video sequences supplied by the camera 1; i and j are the coordinates of the individual pixels. The frequency of these images is at least images per second, and the image size is 352 by 288 pixels, for example. Intensity images are obtained because it can be assumed that a flame represents a location having a high light intensity and additionally has a characteristic hue.
In a next process, designated preprocessing 4, flames are sought in the intensity images Xij(t) and the flames found are localized in corresponding image excerpts.
This localization is effected with the aid of a socalled accumulation matrix, which is formed in the following manner: In a first step the maximum value max [Xij(t)] and the mean value mean [Xij(t)] of the intensity are determined and a brightness threshold q(t) is determined therefrom, the following holding true: q(t+l) )i max [Xij if mean [Xij X, max [Xij and q(t+l) X 2 {max [Xij(t)] mean mean in all other cases.
X
1 and k 2 are constants lying between 0 and 1, in which case, by way of example, X, is equal to 0.68 and 2 is 5 equal to 0.05.
A weighting factor wij that takes account of the flame properties is determined with the aid of these two conditions: wj Xij(t) if Xij(t) max [Xij and wij(t) 0 in all other cases.
This means that all pixels having an intensity below the value max [Xij(t)] that is to say dark objects, are filtered out and not taken into account any further. As will directly be revealed, the objects filtered out are dark moving objects.
Since it can be assumed that a flame can be identified as motion having high light intensity, a difference image is formed by comparison of successive images in order to find such motion; since dark objects are omitted on account of the definition of the weighting factor wij(t), moving dark objects, which cannot be flames, are thus filtered out during the formation of the difference image. Zones having high light intensity and local flicker motion are thus sought and this means that, by way of example, a stationary light source which does not flicker would not be interpreted as a flame, and nor would a lamp moved transversely through the monitoring space.
The following hold trues for the difference image Qij i Xi t 4-ij. t-l 'I The difference image Qij(t) is then used to determine the accumulation matrix Aij(t): Aij(t) a Aij(t-1) Qij(t) a is a constant between 0 and 1 specifying the extent to which the difference image Qij(t) influences the 6 accumulation matrix Aij(t). For a 0, the accumulation matrix becomes equal to the difference image, and for a 1, the difference image no longer has an influence because Aij is equal to Aij(t-l). The accumulation matrix is primarily formed in order to obtain a smoothed image without noise and momentary changes.
As a final step of preprocessing 4, the pixel or pixels [im, jm[(t) having the highest value is or are sought with the aid of the accumulation matrix and a so-called image region of interest ROI which contains said pixel or pixels and in which a flame might be situated is defined: max [Aij(t)]} This determination thus supplies the coordinates of the pixels having local flicker motion and maximum brightness. Generally, a single pixel will be involved, but it is also possible, of course, to determine a plurality of brightest pixels, for which purpose a multichannel selection may be used and minimum spacings between the individual pixels are preferably defined.
In the next process, designated analysis 5, firstly a significant reduction of the data is effected in that the analysis is not effected in the entire original image of 352 by 288 pixels, but rather in the image region of interest ROI having a reduced size of 32 by 32 pixels, for example. This results in a reduction to a hundredth. This reduction may, of course, also be lower, for example to a fiftieth, or else significantly greater The following image information items are then determined for each image region of interest: Mean brightness L(t) of the image region of interest XRoi(t): L(t) [mean of Xij(t) IROI] Chrominance C(t) of the image region of interest 7 XROI C(t) [number of Cij(t) IRo] c "fire chroma sector" where Cij designates the chrominance pair (Vij, Uij) of the image Xij(t) at the time t. YUV is a known representation of the color space, with two color components U and V on the x and y axis, respectively, and the intensity Y on the z axis, the length of the vector from the zero point to a pixel in the UV plane specifies the color saturation of this pixel. The fire chroma sector R(t) is a sector of the color space in the UV plane, in the color range typical of a flame, which, in particular, contains the color red.
Number of active pixels R(t) of the accumulation matrix AROI(t) R(t) [Number of Aij(t) IRoI 1i]; 1 ri Z (Z total number of pixels of the image region of interest ROI) for example ri Degree of saturation S(t) of the image region of interest XRO S(t) [number of Xij(t) IROI T1 2 1 2 Z for example 12 In order that the result remains stable, a time integration of the image information items determined during the analysis 5 is subsequently effected in a process designated extraction 6. If the integration is carried out for example over 1 second, it extends over 25 images in the PAL format. Thus, the mean brightness, the chrominance, the active pixels and the degree of saturaton are integrated over time t from t to n and the following properties are obtained: Mean value of brightness: FL =L Mean value of frequency: FF F Mean value of amplitude: FM M Mean value of fire chroma pixels: Fc C Mean value of active pixels: FR R 8- Mean value of saturation: Fs S The mean value of the frequency is obtained for example by counting the pixels having the mean brightness L(t).
The frequency caused by the characteristic flicker of a flame is an important quantity for the detection of a flame because it lies in a defined narrow range of generally between 1 Hz and 10 Hz.
In the subsequent process designated pattern recognition 7, the properties obtained during the extraction 6 are used to calculate the probability that a flame is present. In this case, an examination is effected for example for each of the above properties to determine whether the mean value lies above or below a threshold value and the probability is correspondingly set equal to one or equal to zero. An overall probability is then formed from the probabilities of all n properties.
TL F(FL) 1, if FL 8L TL F(FL) 0, if FL 8L and so on for the other properties.
Overall probability H(t): 1/NF Z n (T.WL TF.WF TM.WM C.-Wc TR.WR s.Ws)/NF (lw, w. w cWR +R Sws)/NF F n for wi, it holds true that 0 wi 1, the values wi being determined empirically. Np is the sum of wi over all i.
In the process designated decision 8, as to whether an alarm is triggered is subsequently taken. This process contains an integration during which the overall probability 17(t) is integrated upward over successive images. The integration starts at zero and counts an 9 increment thereto for each 17(t) K (K is a threshold) and subtracts an increment for each 17(t) K. If I(t) designates the value of the integral, the following holds true: I(t 0) 0 If 1(t) K then I(t) I(t-l) o+ (saturated toward if I(t) S+ in all other cases I(t) I(t-1) C_ holds true (saturated towards S_ (usually if I(t) S_) T+ and are generally equal to +1.
The decision as to whether an alarm is triggered is then taken with the aid of the integral I(t): If I(t) P (P is a threshold), an alarm is triggered, in all other cases no alarm is triggered.
The device described has the advantage that, in many applications, it is possible to recourse to already installed video cameras and an installation of special flame sensors is not necessary, which undoubtedly means a reduction of costs. A further reduction of costs results from restricting the evaluation to the image excerpts possibly containing a flame, which enables the computer power to be significantly reduced. It can also be assumed that the evaluation of the said image excerpts is sufficiently robust with respect to disturbances.

Claims (16)

1. A method for detecting flames in a monitored zone, referred to hereinafter as monitoring space, by analysis of at least one parameter of a radiation that occurs in the monitoring space, characterized in that a video image of the monitoring space is generated and zones having high light intensity and local flicker motion are sought in said video image, in which case, in a first step, said zones are localized and the relevant image excerpts are subsequently analyzed with regard to the presence of a flame.
2. The method as claimed in claim i, characterized in that the video images are generated with a specific frequency and intensity images [Xij(t)] are attained therefrom.
3. The method as claimed in claim 2, characterized in that the search for zones having high light intensity and local flicker motion is effected with the aid of an accumulation matrix [Aij(t)I, which is obtained from the difference images of successive intensity images said difference images being weighted with a weighting factor, the weighting factor specifying the extent to which the difference images influence the accumulation matrix [Aij(t) I.
4. The method as claimed in claim 3, characterized in that all pixels having a brightness that lies below a predetermined threshold and thus all moving, dark difference images and thus of the accumulation matrix [Aij(t)]. The method as claimed in claim 4, characterized in that the coordinates of the brightest pixels are sought with the aid of the accumulation matrix [Aij(t)]. 11
6. The method as claimed in claim 5, characterized in that an image region of interest [ROI] which contains the brightest pixel or pixels and is reduced with respect to the original image is defined and analyzed with regard to the presence of a flame.
7. The method as claimed in claim 6, characterized in that the size of the image region of interest (ROI) amounts at most to one fiftieth of the size of the original image.
8. The method as claimed in claim 7, characterized in that the image information items of brightness chrominance number of active pixels above a specific intensity threshold, and the saturation are determined in the image region of interest [ROI]
9. The method as claimed in claim 8, characterized in that said image information items are integrated over a specific time and thus over a plurality of images and their mean value is determined in that the mean value of the frequency and the mean value of the amplitude are determined as additional parameters during the integration, and in that the probability for the presence of a flame is calculated for each of said mean values. The method as claimed in claim 9, characterized in that the probabilities of the mean values are used to calculate an overall probability for the presence of a flame in the reduced image region [ROI], in that said overall probability is integrated over a plurality of images, and in that an alarm is triggered when a threshold is exceeded by the integrated value.
11. A device for detecting flames in a monitored zone, referred to hereinafter as monitoring space, by analysis of at least one parameter of a radiation that 12 occurs in the monitoring space, characterized by a video camera with an evaluation stage for the images supplied by the camera the evaluation stage having a processor with an algorithm for the localization of regions having high light intensity and local flicker motion in the images of the camera [1] and the subsequent analysis of the corresponding image excerpts with regard to the presence of a flame.
12. The device as claimed in claim 11, characterized in that the algorithm contains a process, referred to below as image obtaining during which intensity images [Xij(t)] are obtained from the video images generated with a specific frequency.
13. The device as claimed in claim 12, characterized in that the algorithm contains a process, referred to below as preprocessing during which an accumulation matrix [Aij(t)] is determined for the search for zones having high light intensity and local flicker motion, said accumulation matrix being obtained from the difference images of successive intensity images said difference images being weighted with a weighting factor, the weighting factor specifying the extent to which the difference images influence the accumulation matrix [Aij(t)]
14. The device as claimed in claim 13, characterized in that, during the preprocessing with the aid of the accumulation matrix the coordinates of the brightest pixels are determined and an image region of interest (ROI) which contains the brightest pixel or pixels and is reduced with respect to the original image is defined. The device as claimed in claim 14, characterized in that the algorithm contains a process, referred to below as analysis for the analysis of the image region of interest [ROI] during which analysis the 13 image information items of brightness chrominance number of active pixels above a specific intensity threshold, and the saturation are determined.
16. The device as claimed in claim 15, characterized in that the algorithm contains a process, referred to below as extraction during which said image information items are integrated over a specific time and thus over a plurality of images and the mean values of the image information items are determined, in that the mean value of the frequency and the mean value of the amplitude are determined as additional parameters during the integration, and in that the probability for the presence of a flame is calculated for each of said mean values.
17. The device as claimed in claim 16, characterized in that the algorithm contains a process of pattern recognition and a process of decision during which the probabilities of the mean values are used to calculate an overall probability for the presence of a flame in the reduced image region [ROI] and said overall probability is integrated over a plurality of images and an alarm is triggered in the event of a threshold being exceeded by the integrated value. -14-
18. A method for detecting flame in a monitored zone substantially as described herein with reference to the accompanying drawings.
19. A device for detecting flames in a monitored zone substantially as described herein with reference to the accompanying drawings. Dated 25 June, 2004 Siemens Building Technologies AG Patent Attorneys for the Applicant/Nominated Person SPRUSON FERGUSON
AU2004202851A 2003-07-11 2004-06-25 Method and Device for Detecting Flames Ceased AU2004202851B2 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
EP03015846.3 2003-07-11
EP03015846A EP1496483B1 (en) 2003-07-11 2003-07-11 Method and apparatus for the detection of flames

Publications (2)

Publication Number Publication Date
AU2004202851A1 true AU2004202851A1 (en) 2005-01-27
AU2004202851B2 AU2004202851B2 (en) 2008-08-28

Family

ID=33442787

Family Applications (1)

Application Number Title Priority Date Filing Date
AU2004202851A Ceased AU2004202851B2 (en) 2003-07-11 2004-06-25 Method and Device for Detecting 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 (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2000998A3 (en) * 2007-05-31 2010-07-28 Industrial Technology Research Institute Flame detecting method and device
US7868772B2 (en) 2006-12-12 2011-01-11 Industrial Technology Research Institute Flame detecting method and device

Families Citing this family (13)

* Cited by examiner, † Cited by third party
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
US7289032B2 (en) * 2005-02-24 2007-10-30 Alstom Technology Ltd Intelligent flame scanner
KR100680114B1 (en) * 2005-05-12 2007-02-07 (주)에이치엠씨 Device, method and recording medium of robust fire detecting using color of image
CN101316371B (en) * 2007-05-31 2012-11-28 财团法人工业技术研究院 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
CN107064113B (en) * 2017-06-13 2020-02-11 华电青岛发电有限公司 System and method for detecting pulverized coal combustion quality of burner by using optical fiber
CN111141504B (en) * 2019-12-25 2022-04-15 Oppo(重庆)智能科技有限公司 Fire-break detection method and device and computer readable storage medium
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
CN113436406B (en) * 2021-08-25 2021-11-12 广州乐盈信息科技股份有限公司 Sound-light alarm system

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB9216811D0 (en) * 1992-08-07 1992-09-23 Graviner Ltd Kidde Flame detection methods and apparatus
EP1256105B1 (en) * 2000-02-07 2006-09-20 VSD Limited Smoke and flame detection
EP1346330B1 (en) * 2000-12-28 2013-05-15 Siemens Aktiengesellschaft Video smoke detection system
BR0209543A (en) * 2001-05-11 2005-04-26 Detector Electronics Flame detection and fire detection method and apparatus

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7868772B2 (en) 2006-12-12 2011-01-11 Industrial Technology Research Institute Flame detecting method and device
EP2000998A3 (en) * 2007-05-31 2010-07-28 Industrial Technology Research Institute Flame detecting method and device

Also Published As

Publication number Publication date
NO330182B1 (en) 2011-02-28
NO20042948D0 (en) 2004-07-09
NO20042948L (en) 2005-01-12
CN100595583C (en) 2010-03-24
AU2004202851B2 (en) 2008-08-28
EP1496483A1 (en) 2005-01-12
CN1576839A (en) 2005-02-09
KR20050009135A (en) 2005-01-24
ATE357714T1 (en) 2007-04-15
EP1496483B1 (en) 2007-03-21
PL369016A1 (en) 2005-01-24
ES2282550T3 (en) 2007-10-16
DE50306852D1 (en) 2007-05-03

Similar Documents

Publication Publication Date Title
AU2004202851B2 (en) Method and Device for Detecting Flames
US7805002B2 (en) Smoke detection method and apparatus
US6696958B2 (en) Method of detecting a fire by IR image processing
Dedeoglu et al. Real-time fire and flame detection in video
Celik Fast and efficient method for fire detection using image processing
US5937092A (en) Rejection of light intrusion false alarms in a video security system
US9047515B2 (en) Method and system for wildfire detection using a visible range camera
US9245187B1 (en) System and method for robust motion detection
KR100922784B1 (en) Image base fire sensing method and system of crime prevention and disaster prevention applying method thereof
US20040080618A1 (en) Smart camera system
CN107944359A (en) Flame detecting method based on video
Günay et al. Video based wildfire detection at night
Pritam et al. Detection of fire using image processing techniques with LUV color space
JP4653207B2 (en) Smoke detector
JP4542929B2 (en) Image signal processing device
US11336869B2 (en) Motion detection methods and motion sensors capable of more accurately detecting true motion event
CN109034038B (en) Fire identification device based on multi-feature fusion
CA2704037A1 (en) Method for detecting a target
JPH0844874A (en) Image change detector
CN113936252A (en) Battery car intelligent management system and method based on video monitoring
CN113989732A (en) Real-time monitoring method, system, equipment and readable medium based on deep learning
CN107346421B (en) Video smoke detection method based on color invariance
JP2005252479A (en) Surveillance camera block detector
JP3933453B2 (en) Image processing apparatus and moving body monitoring apparatus
JPS62147888A (en) Picture monitoring system

Legal Events

Date Code Title Description
FGA Letters patent sealed or granted (standard patent)
PC Assignment registered

Owner name: SIEMENS AKTIENGESELLSCHAFT

Free format text: FORMER OWNER WAS: SIEMENS BUILDING TECHNOLOGIES AG

MK14 Patent ceased section 143(a) (annual fees not paid) or expired