EP1364351B1 - Method and device for detecting fires based on image analysis - Google Patents

Method and device for detecting fires based on image analysis Download PDF

Info

Publication number
EP1364351B1
EP1364351B1 EP02711747A EP02711747A EP1364351B1 EP 1364351 B1 EP1364351 B1 EP 1364351B1 EP 02711747 A EP02711747 A EP 02711747A EP 02711747 A EP02711747 A EP 02711747A EP 1364351 B1 EP1364351 B1 EP 1364351B1
Authority
EP
European Patent Office
Prior art keywords
image
method according
algorithm
detection
images
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.)
Not-in-force
Application number
EP02711747A
Other languages
German (de)
French (fr)
Other versions
EP1364351A1 (en
EP1364351B8 (en
Inventor
Didier Rizzotti
Nikolaus c/o Patents & Technology Survey SCHIBLI
Werner Straumann
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.)
Securiton AG
Original Assignee
Securiton AG
Fastcom Tech SA
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
Priority to CH340012001 priority Critical
Priority to CH3402001 priority
Application filed by Securiton AG, Fastcom Tech SA filed Critical Securiton AG
Priority to PCT/CH2002/000118 priority patent/WO2002069292A1/en
Publication of EP1364351A1 publication Critical patent/EP1364351A1/en
Publication of EP1364351B1 publication Critical patent/EP1364351B1/en
Application granted granted Critical
Publication of EP1364351B8 publication Critical patent/EP1364351B8/en
Application status is Not-in-force legal-status Critical
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B13/00Burglar, theft or intruder alarms
    • G08B13/18Actuation by interference with heat, light or radiation of shorter wavelength; Actuation by intruding sources of heat, light or radiation of shorter wavelength
    • G08B13/189Actuation by interference with heat, light or radiation of shorter wavelength; Actuation by intruding sources of heat, light or radiation of shorter wavelength using passive radiation detection systems
    • G08B13/194Actuation by interference with heat, light or radiation of shorter wavelength; Actuation by intruding sources of heat, light or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
    • G08B13/196Actuation by interference with heat, light or radiation of shorter wavelength; Actuation by intruding sources of heat, light or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
    • G08B13/19602Image analysis to detect motion of the intruder, e.g. by frame subtraction
    • 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 infra-red radiation or of ions
    • G08B17/125Actuation by presence of radiation or particles, e.g. of infra-red radiation or of ions by using a video camera to detect fire or smoke

Abstract

The invention for automatic detection of fires, based flame and/or smoke recognition by analysing a sequence of images. The analysis is based on several image processing algorithms. One algorithm consists in comparing the frequency content of at least an image of said sequence with the frequency content of a reference image so as to detect an attenuation of high frequencies independently of variations on other portions of the spectrum.

Description

The present invention relates to a method and a device or a a fire detection system based on image analysis, in particular on the analysis of digital moving picture sequences.

In the field of surveillance and site security industrial sectors or sections of roads or tunnels, the speed of detection fire is a major safety factor. In particular, he is necessary to be able to detect a fire departure as quickly as possible possible in order to be able to combat it effectively and to take measures to limit the scale of the incident. For reasons of cost, it is however, generally impossible to employ human surveillance in continued. Automatic monitoring and detection systems are therefore highly desirable.

Different systems have already been proposed or marketed to detect fires or fumes.

The majority of systems currently in use implement spot smoke sensors that have to wait for the smoke to spread to them for a chance to detect it. These sensors can not be used outside (refineries, container depots, etc.), in the large premises in which the fumes disperse and puts a lot of time to reach the sensor (hangar, nuclear power station, etc.) or in premises with strong drafts (tunnels, highly ventilated rooms, etc.). The sensors must be sufficiently close together and hardwired; the cost of wiring a large number of sensors can, however, be prohibitive. These solutions are therefore not appropriate for monitoring large volumes or large expanses.

Other known systems are based either on a measurement of the increase in temperature in the room, either on the measure of the amount of UV or infrared radiation received.

Systems using the temperature increase are relatively slow (thermal inertia), and do not work reliable outdoors or in large premises. Systems based on measuring UV radiation work in any environment but rapidly lose their effectiveness when the collector becomes dirty without being detectable.

Systems based on the measurement of infrared radiation operate in any environment but generate false detections when they are in the presence of a hot object, or when are exposed to solar radiation.

More recently, it has been suggested to detect fires with the help of methods based on image analysis. Many potential sites are already equipped with surveillance cameras connected to a central alarm, and used for example to detect break-ins or accidents. The use of these surveillance systems to detect also fires saves the set up and the connection of a separate sensor system. Analysis solutions images, using the video cameras already installed and video signal processing software provided by the cameras, have also been suggested.

Smoke detection by image analysis has the following advantages over solutions using point sensors:

  • The camera can detect smoke and flame remotely before it reaches the sensor, so such a system can fill gaps in traditional systems outdoors or in large premises.
  • The images taken by the camera can not only be processed, but also used for the viewing of the incident by an operator. This is useful for the removal of doubts in case of false detection: the visualization of the image or sequence of images by a human avoids many unnecessary movements.
  • The images taken also help to get a better idea of the magnitude of the fire, as well as the type of fire. It is thus possible to immediately prepare the right intervention equipment, and thus gain valuable minutes.
  • Clogging of the sensor (camera) is visible in the image, and according to the invention can even be detected automatically, unlike UV radiation sensors that lose their effectiveness without being detectable.
  • A breakdown or tampering of the camera is detectable automatically.
  • The camera used for fire detection can be used simultaneously for conventional video surveillance applications, which simplifies wiring.

Fire detection systems by video image analysis have already been described in the prior art. WO00 / 23959 discloses a system of smoke detection, consisting of video camera equipment, unit for digitizing video signals and a processing unit for digital data. Smoke is detected by algorithms of image processing based on comparing pixels between images successive. The comparison methods used, for example, aim to detect whether a significant change has occurred between an image and a image of reference, which can indicate the appearance of smoke but also another object in the filmed field of view. Another algorithm detects the convergence of the color of several pixels to an average value, may indicate a decrease in contrast caused by smoke. A Such convergence may also indicate a change in the conditions lighting. A third algorithm measures changes in the sharpness of the transition zones, affected by the smoke but also by the characteristics of the optics that are modified for example during zooms or opening changes. These methods are only suitable for the detection of smoke, but no flames giving off little or no fumes. The algorithms used are complex and require high computing power.

WO97 / 16926 discloses a change detection method in an image sequence to detect events. The method detection is based on taking a reference image that contains the information of the background of the recorded scene. The appearance of new objects is detected by methods of thresholding and grouping of pixels. The algorithms employed make it hard to distinguish between the appearance of smoke or another object in the field visual filmed.

EP0818766 discloses a system for detecting forest fires by animated image processing. To detect fire, an algorithm of smoke detection is used. This document describes a method of detection of temporal variations of the intensity of the pixels in low frequency (between 0.3 and 0.1 Hz). So the system is slow enough to react since many cycles of a few tenths of a second are necessary to detect a decorrelation that may indicate the presence of smoke.

FR-A-2696939 describes a forest fire detection system automatic by image processing. The processing algorithms are based on the detection and analysis of volute and cloud movements smoke; they are, on the other hand, not very suitable for the detection of flames or fumes developing in an unusual way, for example under the effect wind or ventilation.

Existing fire detection systems by image analysis video are well suited to the detection of particular types of fire in well-defined environments. A company wishing to specialize in however, the monitoring of fires in different sites must acquire and familiarize with different software; there is currently no sufficiently robust and versatile solution to detect using the same software very different lights.

An object of the present invention is to propose a method and a Fire detection device more reliable, faster and more versatile than the methods and systems of the prior art.

Another aim is to propose a method and a system of detection of fire which can be implemented using a system of video surveillance already installed on the site to be monitored.

The invention will be better understood on reading the description given by way of example and illustrated by the figures which show:

  • FIG. 1 is a block diagram of an automatic fire detection system making it possible to implement the method of the invention.
  • FIG. 2 is a block diagram of an alternative automatic fire detection system making it possible to implement the method of the invention, in which various elements are integrated in an intelligent video camera.
  • Figure 3 a block diagram of a variant of automatic fire detection system comprising several cameras connected to a computer through a processing unit.
  • FIG. 4 is a diagrammatic representation of a frequency analysis algorithm for images for smoke detection.
  • Figure 5 a representation of slider buttons of a graphical interface for separately adjusting the sensitivity of the detection of flames and smoke.
  • Figure 1 illustrates a block diagram of a detection system automatic fire making it possible to implement the method of the invention. The illustrated system allows you to acquire images from different sources, for example a PAL or NTSC 3 video camera, a digital video camera, recording media such as hard disk 2 or optical disk or video tape 1. The image sequences are scanned if necessary by a digitizer 4 and transmitted to a system of digital processing 6, for example an industrial PC, which executes the Flame and smoke detection algorithms described below. The digitizer 4 is constituted for example by a digitization card of video footage from the camera or VCR inserted into the digital processing system 6. Some algorithms can use one or more images or sequences of reference images, for example a view of the background of the image without fire, in a memory 5.

    The results of the detection algorithms can be displayed locally on the screen of the digital processing system 6 or processed by a system of interpretation of results and decision-making 7 capable of generate alarms or fire or smoke pre-warnings when certain predefined conditions are met. This alarm can be transmitted to a central alarm 8, to an apparatus 9 generating an alarm acoustic and / or to an operator via an interface graph 10 on one of the systems 7 or 8. The control panel manages all alarms from the interpretation system of results and taking of decision. The system 7 can be implemented by a computer near the supervised area or by a program or ensemble of programs executed by the digital processing system. alarm center can be located remotely and manage alarms from different sites under surveillance.

    FIG. 2 illustrates a variant of a system making it possible to the invention, in which most of the elements of FIG. are integrated in a single intelligent camera 3, that is to say a camera integrating digital image processing means. The camera integrates an optical 30, a not shown image sensor, for example a random access sensor, and a system for acquiring images and digital processing 6 to acquire the sequences of images of the camera in a digital form and to execute on these image sequences the different algorithms for detecting flames and smoke described more low. The smart camera 3 also includes a memory 5 for store these algorithms as well as one or more images or sequences reference images used by these algorithms. A system of interpretation of results and decision-making 7 can be achieved by example in the form of a computer module loaded in the memory 5 and executed by the digital processing system 6. The camera Smart 3 can additionally integrate an event management system 70 to handle the events detected by the system 7 and trigger by example sending an alarm or a pre-alarm. The smart camera 2 can be connected through a communication interface to a screen 15 to view either the sequences of images acquired live, or recorded images corresponding to detected events. The camera 3 is also able to communicate its results to a computer 12. A control unit 11 makes it possible to choose areas of interest in the image, to vary the sensitivity of the detection, to program camera movements, etc. The camera 3 therefore constitutes a system complete smart camera able to detect flames and smoke and generate warning signals accordingly.

    FIG. 3 illustrates another variant of a system enabling implement the invention, wherein one or more video cameras 3 smoke detection 13 or flames 14 provide sequences images processed directly by the digital processing system 6, for example an industrial PC on the monitored site. The system 6 executes fire detection algorithms by image processing and the interpretation of the results. Images processed and events detected are transmitted to a remote operator equipped with a computer 12 integrating a graphical interface allowing to visualize the images video from the cameras 3 and to inform the operator in case of alarm detection.

    In order to make reliable decisions about the state of the supervised site, that is to say to reduce the number of false alarms or undetected, the digital image processing system 6 and the interpretation system of results and decision-making 7 use several distinct image processing algorithms and combined them. The algorithms used can be based on the following methods:

    1. Frequency analysis of the current image and the imacle of reference with a comparison of the results.

    The presence of smoke reduces the sharpness of the outlines of objects present in the scene, which corresponds to a low-pass spatial smoothing filter. The high frequencies of the image 31 are thus attenuated by the presence of smoke compared to the reference image 32 stored in the memory 5 and corresponding for example to an image of the background without smoke and no flames. The method therefore consists of calculating the transform frequency of each image 31 or image portion acquired using a fast FFT or FHT Fourier transform module 33 for example and compare it using a comparison system 35 with the transform frequency of the reference image 32 calculated by a module 34. When the comparison system detects high attenuation image frequencies higher than low frequency attenuation by compared to the reference image, a decision module 36 may indicate an alarmed smoke or a probability of smoke alarm.

    This algorithm can be used throughout the image. In order to detect more clearly and more quickly the appearance of smoke, this algorithm is preferably applied on one or more sub-portions or zoes of the filmed image; an alarm being triggered as soon as one or minimum number of zones indicate high attenuation spatial frequencies relative to the reference image. It is also possible to apply this algorithm only on the portions of the image on which smoke is likely to appear or in which another algorithm indicated a fire event probability. Finally, this algorithm can either be applied to a grayscale image or another component, ie separately on the different components a color image. Depending on the colors of smoke likely to appear, it is possible to weight differently the different components chromatic.

    2. Frequency analysis between consecutive images for the flame oscillation detection

    The appearance of an object whose contours, chrominance or brightness oscillate at a frequency greater than 0.5 Hz is a sign of the possible presence of flames. This can be detected using a frequency analysis method using the successive images of a sequence of images. To perform this analysis, the computer must have a whole sequence of images in his memory and detect in the domain space objects with the aid of an algorithm of reconaissanc of form.

    This algorithm can also be used to detect and follow on several successive images objects whose shape, size and / or the color vary in a non regular way and according to a frequency random. Object identification and object tracking methods can be to be employed.

    3. Analysis of the information of the color saturation for detect smoke

    When a sequence of color images is available, it is possible to use color information directly as a criterion for presence of smoke. Indeed, the smoke is generally not very colorful (white, black, gray, etc.). An image or a portion of an image becoming less colorful is therefore likely to represent smoke. According to colors of smoke likely to appear, it is possible to take into account of this color.

    Conversely, a portion of the image suddenly becoming more colorful and brighter could represent flames, especially if this portion is at the bottom of the image or below a portion that represent smoke.

    4. Analysis of color temperatures

    When a sequence of color images is available, it is possible to approximate the emission spectrum of an object on each image in measuring green and blue red components, which allows to approximate the temperature of an object. An object with strong light having an emission spectrum corresponding to a hot body with a maximum in the red-yellow can be suspected to be a flame (or the reflection of a flame).

    5. Detection of disappearances of straight segments (lines) in the current image

    The appearance of an object whose contours contain only a few of straight segments is a sign of the possible presence of smoke or of flames. If a comparison is made with the reference image, the disappearance of straight segments can be detected.

    6. Analysis of the differences between the current image and an image of reference for the detection of areas of interest

    By measuring the differences between the current image filmed and a reference image of the same scene, it is possible to detect reliably the appearance of objects that were not present in the image reference. This algorithm makes it possible to identify areas where the probability of occurrence of smoke is greater. Other algorithms Flame or smoke detection can focus on this area. To prevent changes in lights or shadows from being detected as new objects, it is possible to renew the reference image regularly.

    7. Analysis of several image sequences of the same scene from several different shooting angles (stereo analysis)

    When multiple images of the same scene from different views are available, it is possible to use algorithms of stereoscopic vision to evaluate the position, the three-dimensional shape, the volume and distance of objects filmed, for example new objects appearing in relation to a reference image. It is thus possible to distinguish for example between a column of smoke appearing in front of a wall and a shadow or a reflection on this wall. In the open air, this algorithm distinguish between a new cloud and a column of smoke much closer. This algorithm can be used for example for very reliably identify the areas of interest of an image or image sequences on which the other algorithms must focus.

    Multiple image sequences can be generated by example using multiple cameras, using a single camera motorized to change the position or angle of view, to using one or more cameras and a set of mirrors, etc.

    8. Alarms provided by external sensors

    The digital processing system 6 may furthermore be connected to one or more external sensors possibly present and to detect particular events, for example temperature sensors, infrared or ultraviolet radiation, movement, etc. The indications provided by these sensors are transmitted to of acquisition cards in the digital processing system 6 and can be used to confirm the indications provided by the image processing algorithms or to improve the performance of these algorithms. For example, a motion detector can be used to trigger a move or zoom movement optical or digital camera to the area where the movement was product, or to focus the image processing algorithms on image portions corresponding to the area where motion has been detected.

    The results of the different algorithms are combined through a process of interpretation and decision-making of the results executed for example by the system 7 to detect the flames and / or the smoke reliably. This process of interpreting the results can take into account the evolution of the various detection criteria in function of time. For example, a level of detection that grows quickly is more dangerous than a stable detection level.

    As mentioned above, it is possible to improve the performance of the system by segmenting the image into several portions and adapting the detection sensitivity of the different algorithms according to these different portions. Image portions can to pose problems of false alarms (chimneys in a landscape, portion of a wall where car headlights are reflected, etc.) can be desensitized without influencing detection in other parts of the image. It is also possible to make more sensitive parts away from the scene, and less sensitive the closer parts in order to offset the perspective effect. This adaptation can be done manually or automatically.

    According to the invention, the sensitivity can be modified to adapt the system to its environment. In a preferred embodiment, this setting can be done using a single parameter influencing all system algorithms. This parameter can be changed via a slider button on the graphical interface 10, a potentiometer, or by any other adjustment element.

    When the fire detection program is intended to be used in very different environments, for example if the same program is used to detect forest fires in a landscape or fires in a road tunnel, it is desirable to be able to separately the sensitivity of flame detection algorithms and smoke detection algorithms. Figure 5 illustrates two slider buttons to separately adjust the flame detection and the smoke detection.

    The skilled person will understand that it is easily possible, in the scope of the invention, to imagine an advanced configuration mode to separately adjust the sensitivity of each algorithm, the sensitivity applied to each zone or component of colors, etc. It is thus possible to use the same device and a same fire detection program and set it to detect flames or smoke in very different environments, for example example in a road or rail tunnel, outdoors, in sheds, etc.

    The different events that can occur in the system are presented by the graphical interface 10 to the operator in order of urgency. The graphical interface thus displays for example at the top of the list the alarms flame and smoke starting with the most recent alarm, then the pre-warnings flame and smoke starting here also by the pre-alarm the most recent, other events or alarms possibly detected being displayed at the bottom of the list. These other events can understand, for example, camera failures, dirty cameras, indications of insufficient brightness of the scene to be monitored, or external events detected by unrepresented sensors, such as stalling fire extinguishers, door openings, etc. A visual message, preferably a "pop-up" window indicating the type of alarm detected and opening in a graphical interface 10, and a sound beep are preference generated when detecting an alarm

    These different events can be stored in a file ("log file") in the processing system 6, in the system 7 or in the computer used by the remote operator and listing all the events occurred. This file is preferably constituted by a XML document also containing images or sequences images related to each event listed, as well as the date of the event. An operator can thus consult the XML file corresponding to the monitoring period and load the images stored, for example remotely, to check the detected alarms and ensure, for example, that the detected alarms match actually to fires.

    The present invention relates to a fire detection method. It also relates to a device specially adapted to implement this process, for example a computer or a smart camera programmed to implement this method, as well as a support for data with a directly loadable computer program in the memory of such a device and comprising portions of code computer hardware constituting means for executing this method.

    Claims (24)

    1. Automatic fire detection method, based on the recognition of flames and/or smoke from the analysis of a sequence of images, the analysis being based on several image processing algorithms,
         characterized in that one algorithm consists in comparing the frequency content of at least one image (31) of said sequence with the frequency content of a reference image (32) so as to detect an attenuation of the high frequencies independently of the variations on the other portions of the image's spatial spectrum.
    2. Method according to claim 1, wherein the detection sensitivity of at least one of said algorithms can be adjusted through a graphical interface (10) independently of the system's global sensitivity.
    3. Method according to one of the claims 1 or 2, wherein said comparison is performed only in one or several portions of said image (31).
    4. Method according to claim 3, wherein said image (31) is divided into several zones, said comparison being performed between at least one zone of said reference image (32) and at least one comparable zone of at least one image (31) of said sequence.
    5. Method according to one of the claims 1 to 4, wherein the frequency content of at least two chromatic components of said images of said sequence and of said reference image are calculated and used separately for said comparison.
    6. Method according to one of the claims 1 to 5, wherein at least one said image processing algorithm is a smoke detection algorithm by measuring the saturation of colours in at least one portion of said images.
    7. Method according to one of the claims 1 to 6, wherein at least one said image processing algorithm is an algorithm for detecting the disappearance of straight segments in at least one portion of said images (31).
    8. Method according to one of the claims 1 to 7, wherein at least one said image processing algorithm is an algorithm for detecting flames (14).
    9. Method according to claim 8, wherein one said flame detection algorithm consists in analyzing the variations between consecutive images in order to detect objects whose outline oscillate with a frequency greater than 0.5 Hz.
    10. Method according to claim 8, wherein one said flame detection algorithm consists in identifying objects whose shape and colour vary in a non-regular manner.
    11. Method according to claim 8, wherein one said flame detection algorithm consists in evaluating the colour temperatures in at least a portion of said images in order to detect the presence of flames.
    12. Method according to one of the claims 1 to 11, wherein at least one said image processing algorithm uses several image sequences representing the same view at different angles.
    13. Method according to claim 12, wherein said algorithm using several image sequences allows information on the distance, the shape and/or the volume of the flames and of the smoke to be supplied.
    14. Method according to one of the preceding claims, wherein at least one said image processing algorithm is an algorithm allowing the presence of a new object in a portion of the image to be detected.
    15. Method according to claim 14, wherein at least one flame or smoke detection algorithm is used in order to analyze in more detail the portion of the image where a new object has appeared.
    16. Method according to any of the claims 1 to 15, wherein the temporal evolution of the results supplied by at least one of said algorithms is taken into account in the flame or smoke detection.
    17. Method according to any of the claims 1 to 16, implemented by means of at least one video camera (3) and a video digitization device (4) connected to a computer (6) in order to perform all the detection algorithms, and equipped with visualization means (10, 15, 12) for a human operator.
    18. Method according to any of the claims 1 to 16, implemented by a digital camera (3) integrating the optic (30), the image sensor, the image digitization device, the processor (6) for executing all the detection algorithms and the detection results communication interface and/or visualization means for a human operator.
    19. Method according to any of the claims 1 to 18, comprising a step of adjusting the sensitivity by means of an adjusting element allowing the flame detection sensitivity and the smoke detection sensitivity to be selected independently.
    20. Method according to any of the claims 1 to 18, comprising a step of adjusting the sensitivity by means of an adjusting element allowing the detection sensitivity at each algorithm to be chosen independently from a plurality of used algorithms.
    21. Device for processing digital images (6; 3) adapted to receive sequences of digital images coming from at least one video camera (3) and comprising a computer program capable of executing the method of one of the preceding claims.
    22. Device according to the preceding claim, comprising visualization means (10, 15, 12) for a human operator allowing said sequences of digital images to be visualized.
    23. Device according to the preceding claim, comprising alarm-generating means for generating an alarm displayed on said visualization means as soon as a fire has been detected, and means allowing a human operator to confirm or invalidate the presence of fire by visualizing said images.
    24. Data carrier comprising a computer program directly loadable in the memory of a digital processing device and comprising computer code portions constituting means for executing the method of one of the claims 1 to 20.
    EP02711747A 2001-02-26 2002-02-26 Method and device for detecting fires based on image analysis Not-in-force EP1364351B8 (en)

    Priority Applications (3)

    Application Number Priority Date Filing Date Title
    CH340012001 2001-02-26
    CH3402001 2001-02-26
    PCT/CH2002/000118 WO2002069292A1 (en) 2001-02-26 2002-02-26 Method and device for detecting fires based on image analysis

    Publications (3)

    Publication Number Publication Date
    EP1364351A1 EP1364351A1 (en) 2003-11-26
    EP1364351B1 true EP1364351B1 (en) 2005-06-29
    EP1364351B8 EP1364351B8 (en) 2006-05-03

    Family

    ID=4505312

    Family Applications (1)

    Application Number Title Priority Date Filing Date
    EP02711747A Not-in-force EP1364351B8 (en) 2001-02-26 2002-02-26 Method and device for detecting fires based on image analysis

    Country Status (5)

    Country Link
    US (1) US6937743B2 (en)
    EP (1) EP1364351B8 (en)
    AT (1) AT298912T (en)
    ES (1) ES2243699T3 (en)
    WO (1) WO2002069292A1 (en)

    Families Citing this family (47)

    * Cited by examiner, † Cited by third party
    Publication number Priority date Publication date Assignee Title
    DE10011411C2 (en) * 2000-03-09 2003-08-14 Bosch Gmbh Robert Imaging fire detector
    AT335958T (en) * 2002-09-24 2006-09-15 Pilz Gmbh & Co Kg Method and device for protecting a hazardous area
    US7729511B2 (en) 2002-09-24 2010-06-01 Pilz Gmbh & Co. Kg Method and device for safeguarding a hazardous area
    US7154400B2 (en) * 2003-06-27 2006-12-26 The United States Of America As Represented By The Secretary Of The Navy Fire detection method
    DE602004019244D1 (en) * 2003-11-07 2009-03-12 Axonx L L C Smoke detection method and device
    US7764844B2 (en) * 2004-09-10 2010-07-27 Eastman Kodak Company Determining sharpness predictors for a digital image
    DE102004056958B3 (en) * 2004-11-22 2006-08-10 IQ wireless GmbH, Entwicklungsgesellschaft für Systeme und Technologien der Telekommunikation Surveillance of territories for detection of forest and wildfires
    US7574039B2 (en) * 2005-03-24 2009-08-11 Honeywell International Inc. Video based fire detection system
    US7685341B2 (en) 2005-05-06 2010-03-23 Fotonation Vision Limited Remote control apparatus for consumer electronic appliances
    US7694048B2 (en) * 2005-05-06 2010-04-06 Fotonation Vision Limited Remote control apparatus for printer appliances
    US7747596B2 (en) * 2005-06-17 2010-06-29 Fotonation Vision Ltd. Server device, user interface appliance, and media processing network
    US7792970B2 (en) * 2005-06-17 2010-09-07 Fotonation Vision Limited Method for establishing a paired connection between media devices
    GB2428472A (en) * 2005-07-18 2007-01-31 Sony Uk Ltd Smoke detection by processing video images
    GB2428473A (en) * 2005-07-18 2007-01-31 Sony Uk Ltd Fire detection by processing video images
    US7769204B2 (en) * 2006-02-13 2010-08-03 George Privalov Smoke detection method and apparatus
    US7495767B2 (en) 2006-04-20 2009-02-24 United States Of America As Represented By The Secretary Of The Army Digital optical method (DOM™) and system for determining opacity
    US20090115915A1 (en) * 2006-08-09 2009-05-07 Fotonation Vision Limited Camera Based Feedback Loop Calibration of a Projection Device
    CN101395643B (en) * 2006-09-25 2011-12-14 西门子公司 Using a camera to detect smoke
    US20080137906A1 (en) * 2006-12-12 2008-06-12 Industrial Technology Research Institute Smoke Detecting Method And Device
    US20080136934A1 (en) * 2006-12-12 2008-06-12 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
    CA2675705A1 (en) * 2007-01-16 2008-07-24 Utc Fire & Security Corporation System and method for video based fire detection
    US8138927B2 (en) * 2007-03-22 2012-03-20 Honeywell International Inc. Flare characterization and control system
    US7872584B2 (en) * 2007-04-09 2011-01-18 Honeywell International Inc. Analyzing smoke or other emissions with pattern recognition
    DE102007062281A1 (en) * 2007-12-21 2009-06-25 Bayer Materialscience Ag Method and device for checking the risk of fire of a material
    US7786877B2 (en) * 2008-06-20 2010-08-31 Billy Hou Multi-wavelength video image fire detecting system
    WO2010060407A1 (en) 2008-11-03 2010-06-03 IQ Wireless Entwicklungsges. für Systeme und Technologien der Telekommunikation mbH Method and device for the nighttime r4ecgnition of fires and differentiation from artificial light sources
    TWI377511B (en) * 2008-12-05 2012-11-21 Ind Tech Res Inst Flame detecting method and system
    US8941734B2 (en) 2009-07-23 2015-01-27 International Electronic Machines Corp. Area monitoring for detection of leaks and/or flames
    GB2472646A (en) * 2009-08-14 2011-02-16 Alan Frederick Boyd CCTV system arranged to detect the characteristics of a fire
    US8497904B2 (en) * 2009-08-27 2013-07-30 Honeywell International Inc. System and method of target based smoke detection
    WO2011032117A1 (en) * 2009-09-13 2011-03-17 Delacom Detection Systems, Llc Method and system for wildfire detection using a visible range camera
    US20110304728A1 (en) * 2010-06-11 2011-12-15 Owrutsky Jeffrey C Video-Enhanced Optical Detector
    JP2012118698A (en) * 2010-11-30 2012-06-21 Fuji Heavy Ind Ltd Image processing system
    JP2013206328A (en) * 2012-03-29 2013-10-07 Fuji Heavy Ind Ltd Object detection device
    EP2859540A4 (en) * 2012-06-08 2016-01-06 Xtralis Technologies Ltd Multi-mode detection
    DE102012213125A1 (en) * 2012-07-26 2014-01-30 Robert Bosch Gmbh Fire control system
    US9202145B2 (en) * 2012-11-30 2015-12-01 Safety Management Services, Inc. System and method of determining material reaction or sensitivity using high-speed video frames
    US9654742B2 (en) * 2012-11-30 2017-05-16 Safety Management Services, Inc. System and method of automatically determining material reaction or sensitivity using images
    DE102013017395B3 (en) 2013-10-19 2014-12-11 IQ Wireless Entwicklungsges. für Systeme und Technologien der Telekommunikation mbH Method and device for automated early forest fire detection by means of optical detection of clouds of smoke
    US9613432B2 (en) 2014-01-29 2017-04-04 Stmicroelectronics S.R.L. Fire detection system and method employing digital images processing
    CN104469312B (en) * 2014-12-12 2019-01-04 成都栖林测控科技有限责任公司 A kind of fire detecting arrangement and its detection method of view-based access control model
    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
    CN105590401B (en) * 2015-12-15 2019-08-20 天维尔信息科技股份有限公司 Early warning interlock method and system based on video image
    NO342011B1 (en) * 2016-06-16 2018-03-12 Roxel Aanestad As Tunnel monitoring system and method of operation
    JP2017168117A (en) * 2017-04-28 2017-09-21 ホーチキ株式会社 Fire detection device and fire detection method
    DE102018112479B3 (en) * 2018-05-24 2019-10-02 Universität Kassel Method and device for determining spatial information of a gaseous structure

    Family Cites Families (18)

    * Cited by examiner, † Cited by third party
    Publication number Priority date Publication date Assignee Title
    US4614968A (en) * 1982-02-16 1986-09-30 American District Telegraph Company Contrast smoke detector
    US5153722A (en) * 1991-01-14 1992-10-06 Donmar Ltd. Fire detection system
    US5237308A (en) * 1991-02-18 1993-08-17 Fujitsu Limited Supervisory system using visible ray or infrared ray
    US5289275A (en) * 1991-07-12 1994-02-22 Hochiki Kabushiki Kaisha Surveillance monitor system using image processing for monitoring fires and thefts
    FR2696939B1 (en) 1992-10-16 1995-01-06 Bertin & Cie Method and rapid automatic detection device of forest fires.
    US6037976A (en) 1995-10-31 2000-03-14 Sarnoff Corporation Method and apparatus for determining ambient conditions from an image sequence, such as fog, haze or shadows
    US5625342A (en) * 1995-11-06 1997-04-29 The United States Of America As Represented By The Administrator Of The National Aeronautics And Space Administration Plural-wavelength flame detector that discriminates between direct and reflected radiation
    US5937077A (en) * 1996-04-25 1999-08-10 General Monitors, Incorporated Imaging flame detection system
    FR2750870B1 (en) * 1996-07-12 1999-06-04 T2M Automation Method for automatic detection of fires, including forest fires
    FR2775534B1 (en) * 1998-02-27 2000-09-15 D Aviat Latecoere Soc Ind Monitoring device of an enclosure, including the hold of an aircraft
    US6529132B2 (en) * 1998-02-27 2003-03-04 Societe Industrielle D'avation Latecoere Device for monitoring an enclosure, in particular the hold of an aircraft
    GB9822956D0 (en) 1998-10-20 1998-12-16 Vsd Limited Smoke detection
    AT340395T (en) * 2000-02-07 2006-10-15 Vsd Ltd Smoke and flame detection
    DE10011411C2 (en) * 2000-03-09 2003-08-14 Bosch Gmbh Robert Imaging fire detector
    US6184792B1 (en) * 2000-04-19 2001-02-06 George Privalov Early fire detection method and apparatus
    US6597799B1 (en) * 2000-06-19 2003-07-22 Scientech, Inc. Optical digital environment compliance system
    JP4111660B2 (en) * 2000-07-18 2008-07-02 富士通株式会社 Fire detection equipment
    RU2003133287A (en) * 2001-05-11 2005-05-27 Детектор Электроникс Корпорэйшн (Us) Method and device for flame detection by forming flame images

    Also Published As

    Publication number Publication date
    EP1364351A1 (en) 2003-11-26
    US6937743B2 (en) 2005-08-30
    EP1364351B8 (en) 2006-05-03
    AT298912T (en) 2005-07-15
    WO2002069292A8 (en) 2003-11-13
    WO2002069292A1 (en) 2002-09-06
    ES2243699T3 (en) 2005-12-01
    US20040175040A1 (en) 2004-09-09

    Similar Documents

    Publication Publication Date Title
    KR100948572B1 (en) Method and apparatus for inhibiting projection of selected areas of a projected image
    US7801328B2 (en) Methods for defining, detecting, analyzing, indexing and retrieving events using video image processing
    DE60317396T2 (en) A composite camera system, a zoom camera image display control method, a zoom camera control method, a control program and a computer readable recording medium
    US5151945A (en) Determination of ambient light level changes in visual images
    CA2883638C (en) Particle detector, system and method
    US4999614A (en) Monitoring system using infrared image processing
    JP2004515944A (en) Method and apparatus for selecting an optimal video frame to transmit to a remote station for CCTV-based residential security monitoring
    JP2008537380A (en) Intelligent camera selection and target tracking
    EP2284814A1 (en) Systems and methods for night time surveillance
    US8300890B1 (en) Person/object image and screening
    US8908034B2 (en) Surveillance systems and methods to monitor, recognize, track objects and unusual activities in real time within user defined boundaries in an area
    US6097429A (en) Site control unit for video security system
    ES2656490T3 (en) Security system, home surveillance, office using micro drones and IP cameras
    US6989745B1 (en) Sensor device for use in surveillance system
    JP4702598B2 (en) Monitoring system, monitoring apparatus and method, recording medium, and program
    CA2179801C (en) Security sensor arrangement with overlapping fields of view
    EP1275094B1 (en) Early fire detection method and apparatus
    US5153722A (en) Fire detection system
    US7167575B1 (en) Video safety detector with projected pattern
    US7342489B1 (en) Surveillance system control unit
    JP4966012B2 (en) System and method for searching for changes in surveillance video
    EP2196967B1 (en) Methods and apparatus for adaptively streaming video data based on a triggering event
    US20030038877A1 (en) Imaging fire detector
    EP0939387B1 (en) Room supervision device
    US5980123A (en) System and method for detecting an intruder

    Legal Events

    Date Code Title Description
    17P Request for examination filed

    Effective date: 20030904

    AK Designated contracting states

    Kind code of ref document: A1

    Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LI LU MC NL PT SE TR

    AX Request for extension of the european patent to:

    Extension state: AL LT LV MK RO SI

    RIN1 Information on inventor provided before grant (corrected)

    Inventor name: STRAUMANN, WERNER

    Inventor name: RIZZOTTI, DIDIER

    Inventor name: SCHIBLI, NIKOLAUS

    RAP1 Rights of an application transferred

    Owner name: SECURITON AG

    RIN1 Information on inventor provided before grant (corrected)

    Inventor name: SCHIBLI, NIKOLAUS,C/O PATENTS & TECHNOLOGY SUR

    Inventor name: RIZZOTTI, DIDIER

    Inventor name: STRAUMANN, WERNER

    RAP1 Rights of an application transferred

    Owner name: FASTCOM TECHNOLOGY S.A.

    Owner name: SECURITON AG

    AK Designated contracting states

    Kind code of ref document: B1

    Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LI LU MC NL PT SE TR

    PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

    Ref country code: FI

    Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

    Effective date: 20050629

    Ref country code: IE

    Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

    Effective date: 20050629

    Ref country code: NL

    Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

    Effective date: 20050629

    Ref country code: TR

    Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

    Effective date: 20050629

    REG Reference to a national code

    Ref country code: GB

    Ref legal event code: FG4D

    Free format text: NOT ENGLISH

    REG Reference to a national code

    Ref country code: CH

    Ref legal event code: EP

    REF Corresponds to:

    Ref document number: 60204855

    Country of ref document: DE

    Date of ref document: 20050804

    Kind code of ref document: P

    REG Reference to a national code

    Ref country code: IE

    Ref legal event code: FG4D

    Free format text: LANGUAGE OF EP DOCUMENT: FRENCH

    PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

    Ref country code: DK

    Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

    Effective date: 20050929

    Ref country code: GR

    Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

    Effective date: 20050929

    Ref country code: SE

    Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

    Effective date: 20050929

    REG Reference to a national code

    Ref country code: CH

    Ref legal event code: NV

    Representative=s name: PATENTS & TECHNOLOGY SURVEYS SA

    GBT Gb: translation of ep patent filed (gb section 77(6)(a)/1977)

    Effective date: 20050917

    REG Reference to a national code

    Ref country code: ES

    Ref legal event code: FG2A

    Ref document number: 2243699

    Country of ref document: ES

    Kind code of ref document: T3

    NLV1 Nl: lapsed or annulled due to failure to fulfill the requirements of art. 29p and 29m of the patents act
    PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

    Ref country code: PT

    Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

    Effective date: 20051207

    REG Reference to a national code

    Ref country code: IE

    Ref legal event code: FD4D

    PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

    Ref country code: MC

    Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

    Effective date: 20060228

    Ref country code: LU

    Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

    Effective date: 20060228

    Ref country code: BE

    Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

    Effective date: 20060228

    26N No opposition filed

    Effective date: 20060330

    BERE Be: lapsed

    Owner name: SECURITON A.G.

    Effective date: 20060228

    Owner name: FASTCOM TECHNOLOGY S.A.

    Effective date: 20060228

    PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

    Ref country code: CY

    Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

    Effective date: 20050629

    REG Reference to a national code

    Ref country code: CH

    Ref legal event code: PFA

    Owner name: SECURITON AG

    Free format text: SECURITON AG#ALPENSTRASSE 20#CH-3052 ZOLLIKOFEN (CH) $ FASTCOM TECHNOLOGY S.A.#BOULEVARD DE GRANCY 19A#1006 LAUSANNE (CH) -TRANSFER TO- SECURITON AG#ALPENSTRASSE 20#CH-3052 ZOLLIKOFEN (CH) $ FASTCOM TECHNOLOGY S.A.#BOULEVARD DE GRANCY 19A#1006 LAUSANNE (CH)

    PGFP Annual fee paid to national office [announced from national office to epo]

    Ref country code: ES

    Payment date: 20140226

    Year of fee payment: 13

    Ref country code: IT

    Payment date: 20140228

    Year of fee payment: 13

    Ref country code: FR

    Payment date: 20140219

    Year of fee payment: 13

    PGFP Annual fee paid to national office [announced from national office to epo]

    Ref country code: DE

    Payment date: 20150219

    Year of fee payment: 14

    Ref country code: CH

    Payment date: 20150218

    Year of fee payment: 14

    PGFP Annual fee paid to national office [announced from national office to epo]

    Ref country code: GB

    Payment date: 20150218

    Year of fee payment: 14

    Ref country code: AT

    Payment date: 20150219

    Year of fee payment: 14

    REG Reference to a national code

    Ref country code: FR

    Ref legal event code: ST

    Effective date: 20151030

    PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

    Ref country code: IT

    Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

    Effective date: 20150226

    PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

    Ref country code: FR

    Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

    Effective date: 20150302

    REG Reference to a national code

    Ref country code: ES

    Ref legal event code: FD2A

    Effective date: 20160329

    PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

    Ref country code: ES

    Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

    Effective date: 20150227

    REG Reference to a national code

    Ref country code: DE

    Ref legal event code: R119

    Ref document number: 60204855

    Country of ref document: DE

    REG Reference to a national code

    Ref country code: CH

    Ref legal event code: PL

    REG Reference to a national code

    Ref country code: AT

    Ref legal event code: MM01

    Ref document number: 298912

    Country of ref document: AT

    Kind code of ref document: T

    Effective date: 20160226

    GBPC Gb: european patent ceased through non-payment of renewal fee

    Effective date: 20160226

    PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

    Ref country code: LI

    Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

    Effective date: 20160229

    Ref country code: CH

    Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

    Effective date: 20160229

    PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

    Ref country code: AT

    Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

    Effective date: 20160226

    PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

    Ref country code: DE

    Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

    Effective date: 20160901

    Ref country code: GB

    Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

    Effective date: 20160226