EP1364351B1 - Method and device for detecting fires based on image analysis - Google Patents
Method and device for detecting fires based on image analysis Download PDFInfo
- 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
- algorithm
- detection
- images
- smoke
- 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.)
- Expired - Lifetime
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000010191 image analysis Methods 0.000 title description 6
- 239000000779 smoke Substances 0.000 claims abstract description 53
- 238000012545 processing Methods 0.000 claims abstract description 31
- 238000004458 analytical method Methods 0.000 claims abstract description 17
- 238000001228 spectrum Methods 0.000 claims abstract 2
- 238000001514 detection method Methods 0.000 claims description 61
- 230000035945 sensitivity Effects 0.000 claims description 14
- 238000012800 visualization Methods 0.000 claims description 7
- 239000003086 colorant Substances 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 230000008034 disappearance Effects 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 2
- 230000002123 temporal effect Effects 0.000 claims description 2
- 230000005855 radiation Effects 0.000 description 6
- 230000008859 change Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 239000003517 fume Substances 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000000295 emission spectrum Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 241001644893 Entandrophragma utile Species 0.000 description 1
- 240000008042 Zea mays Species 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000002238 attenuated effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 230000000135 prohibitive effect Effects 0.000 description 1
- 238000001454 recorded image Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 238000009423 ventilation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation 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
- G08B13/194—Actuation 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
- G08B13/196—Actuation 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
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
-
- 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
Definitions
- 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.
- 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 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.
- 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.
- 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.
- 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:
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- the sensitivity can be modified to adapt the system to its environment.
- 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.
- Figure 5 illustrates two slider buttons to separately adjust the flame detection and the smoke detection.
- 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
- log file a 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.
Abstract
Description
La présente invention concerne un procédé et un dispositif ou un système de détection de feux basé sur l'analyse d'images, en particulier sur l'analyse de séquences d'images animées numériques.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.
Dans le domaine de la surveillance et de la sécurité de sites industriels ou de tronçons de routes ou de tunnels, la vitesse de détection d'incendies constitue un facteur de sécurité prépondérant. En particulier, il est nécessaire de pouvoir détecter un départ d'incendie le plus rapidement possible afin de pouvoir le combattre efficacement et de prendre des mesures pour limiter l'ampleur du sinistre. Pour des raisons de coûts, il est toutefois généralement impossible d'employer une surveillance humaine en continu. Des systèmes de surveillance et de détection automatiques sont donc hautement souhaitables.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.
Différentes systèmes ont déjà été proposés ou commercialisés pour détecter des feux ou des fumées.Different systems have already been proposed or marketed to detect fires or fumes.
La majorité des systèmes utilisés actuellement mettent en oeuvre des capteurs de fumée ponctuels qui doivent attendre que la fumée se propage jusqu'à eux pour avoir une chance de la détecter. Ces capteurs sont inutilisables en extérieur (raffineries, dépôts de containers, etc.), dans les grands locaux dans lesquels la fumées se disperse et met beaucoup de temps à atteindre le capteur (hangar, centrale nucléaire, etc.) ou dans les locaux à fort courant d'air (tunnels, locaux fortement ventilés, etc.). Les capteurs doivnt être suffisament rapprochés et câblés; le coût du câblage d'un grand nombre de capteurs peut toutefois s'avérer prohibitif. Ces solutions sont donc peu appropriées à la surveillance de grands volumes ou de grandes étendues.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.
D'autres systèmes connus sont basés soit sur une mesure de l'augmentation de température dans le local, soit sur la mesure de la quantité de rayonnement UV ou infrarouge reçu. 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.
Les systèmes utilisant l'augmentation de température sont relativement lents (inertie thermique), et ne fonctionnent pas de manière fiable en extérieur ou dans des grands locaux. Les systèmes basés sur la mesure du rayonnement UV fonctionnent dans n'importe quel environnement mais perdent rapidement de leur efficacité lorsque le capteur s'encrasse, sans que cela soit détectable.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.
Les systèmes basés sur la mesure du rayonnement infrarouge fonctionnent dans n'importe quel environnement mais engendrent de fausses détections lorsqu'ils sont en présence d'un objet chaud, ou lorsqu'ils sont exposés au rayonnement solaire.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.
Plus récemment, il a été suggéré de détecter des feux à l'aide de méthodes basées sur l'analyse d'images. Beaucoup de sites potentiellement dangereux sont déjà équipés de caméras de surveillance reliées à une centrale d'alarme, et employées par exemple pour détecter des effractions ou des accidents. L'emploi de ces systèmes de surveillance pour détecter également des incendies permet d'économiser la mise en place et la connexion d'un système de capteurs distinct. Des solutions d'analyse automatique d'images, employant les caméras vidéos déjà installées et des logiciels de traitement des signaux vidéo fournis par les caméras, ont aussi été suggérées.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.
La détection de la fumée par l'analyse d'image présente les avantages suivantes par rapport aux solutions utilisant des capteurs ponctuels:
- La caméra peut détecter la fumée et les flammes à distance, avant que celles-ci n'atteignent le capteur, un tel système est donc capable de combler les lacunes des systèmes traditionnels en extérieur ou dans les grands locaux.
- Les image prises par la caméra peuvent non seulement être traitées, mais aussi utilisées pour la visualisation de l'incident par un opérateur. Ceci est utile pour la levée des doutes en cas de fausse détection: la visualisation de l'image ou de la séquence d'images par un humain permet d'éviter de nombreux déplacement inutiles.
- Les image prises permettent aussi de se faire une idée plus précise de l'ampleur de l'incendie, ainsi que du type d'incendie. Il est ainsi possible de préparer immédiatement le bon matériel d'intervention, et de gagner ainsi de précieuses minutes.
- Un encrassement du capteur (caméra) est visible sur l'image, et selon l'invention peut même être détecté automatiquement, contrairement aux capteurs de rayonnement UV qui perdent leur efficacité sans que cela soit détectable.
- Une panne ou un sabotage de la caméra est détectable automatiquement.
- La caméra utilisée pour la détection d'incendie est utilisable simultanément pour des applications de surveillance vidéo classiques, ce qui permet de simplifier le câblage.
- 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.
Des systèmes de détection de feux par analyse d'images vidéo ont déjà été décrits dans l'art antérieur. WO00/23959 décrit un système de détection de fumée, consistant en un équipement de caméra vidéo, une unité de numérisation des signaux vidéo et une unité de traitement des données numériques. La fumée est détectée par des algorithmes de traitement d'image basés sur la comparaison de pixels entre images successives. Les méthodes de comparaison employées visent par exemple à détecter si un changement important est intervenu entre une image et une image de référence, pouvant indiquer l'apparition de fumée mais aussi d'un autre objet dans le champ visuel filmé. Un autre algorithme détecte la convergence de la couleur de plusieurs pixels vers une valeur moyenne, pouvant indiquer une baisse de contraste provoquée par la fumée. Une telle convergence peut aussi indiquer une modification des conditions d'éclairage. Un troisième algorithme mesure des changements dans la netteté des zones de transition, affectée par la fumée mais aussi par les caractéristiques de l'optique qui sont modifiées par exemple lors de zooms ou de changements d'ouverture. Ces procédés sont uniquement adaptés à la détection de fumées, mais pas de flammes dégageant peu ou pas de fumées. Les algorithmes employés sont complexes et nécessitent une puissance de calcul importante.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 décrit une méthode de détection de changement dans une séquence d'image afin de détecter des évènements. La méthode de détection est basée sur la prise d'une image de référence qui contient l'information de l'arrière-plan de la scène enregistrée. L'apparition de nouveaux objets est détectée par des méthodes de seuillage et de groupement de pixels. Les algorithmes employés permettent mal de distinguer entre l'apparition de fumée ou d'un autre objet dans le champ visuel filmé.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 décrit un système de détection de feux de forêts par traitement d'images animées. Pour détecter le feu, un algorithme de détection de fumée est employé. Ce document décrit un procédé de détection des variations temporelles de l'intensité des pixels en basse fréquence (entre 0.3 et 0.1Hz). Le système est donc assez lent à réagir puisque de nombreux cycles de quelques dixièmes de secondes sont nécessaires pour détecter une décorrélation pouvant indiquer la présence de fumée.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 décrit un système de détection de feu de forêt automatique par traitement d'images. Les algorithmes de traitement sont basés sur la détection et l'analyse de mouvements de volutes et de nuages de fumée; ils sont en revanche peu adaptés à la détection de flammes ou de fumées se développant de manière inhabituelle, par exemple sous l'effet de vent ou d'une ventilation. 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.
Les systèmes existant de détection de feu par analyse d'image vidéo sont bien appropriés à la détection de type de feu particuliers dans des environnements bien définis. Une société souhaitant se spécialiser dans la surveillance de feux dans des sites différents doit toutefois acqurérir et se familiariser avec différents logiciels; il n'existe pas à l'heure actuelle de solution suffisament robuste et polyvalente permettant de détecter à l'aide d'un même logiciel des feux très différents.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.
Un but de la présente invention est de proposer un procédé et un dispositif de détection de feu plus fiable, plus rapide et plus polyvalent que les procédés et les systèmes de l'art antérieur.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.
Un autre but est de proposer un procédé et un système de détection de feu pouvant être mis en oeuvre à l'aide d'un système de surveillance vidéo déjà installé sur le site à surveiller.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.
L'invention sera mieux comprise à la lecture de la description
donnée à titre d'exemple et illustrée par les figures qui montrent:
La figure 1 illustre un schéma bloc d'un système de détection
automatique de feu permettant de mettre en oeuvre le procédé de
l'invention. Le système illustré permet d'acquérir des images à partir de
différentes sources, par exemple d'une caméra vidéo PAL ou NTSC 3, d'une
caméra vidéo numérique, d'un support d'enregistrement tel que disque dur
2 ou disque optique ou d'une bande vidéo 1. Les séquences d'images sont
numérisées si nécessaire par un numériseur 4 et transmises à un système de
traitement numérique 6, par exemple un PC industriel, qui exécute les
algorithmes de détection de flammes et de fumées décrits plus bas. Le
numériseur 4 est constitué par exemple par une carte de numérisation des
séquences vidéos venant de la caméra ou du magnétoscope insérée dans le
système de traitement numérique 6. Certains algorithmes peuvent utiliser
une ou des images ou séquences d'images de référence, par exemple une
vue de l'arrière-plan de l'image sans feu, dans une mémoire 5.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
Les résultats des algorithmes de détection peuvent être affichés
localement sur l'écran du système de traitement numérique 6 ou traités par
un système d'interprétation des résultats et de prise de décision 7 apte à
générer des alarmes ou des préalarmes feu ou fumée lorsque certaines
conditions prédéfinies sont remplies. Cette alarme peut être transmise à
une centrale d'alarme 8, à un appareillage 9 générant une alarme
acoustique et/ou à un opérateur par l'intermédiaire d'une interface
graphique 10 sur l'un des systèmes 7 ou 8. La centrale d'alarme gère toutes
les alarmes provenant du système d'interprétation des résultats et de prise
de décision. Le système 7 peut être mis en oeuvre par un ordinateur
industriel proche de la zone surveillée ou par un programme ou ensemble
de programmes exécutés par le système de traitement numérique 6. La
centrale d'alarme peut se trouver à distance et gérer les alarmes provenant
de différents sites sous surveillance. The results of the detection algorithms can be displayed
locally on the screen of the
La figure 2 illustre une variante de système permettant de mettre
en oeuvre l'invention, dans laquelle la plupart des éléments de la figure 1
sont intégrés dans une seule caméra intelligente 3, c'est-à-dire une caméra
intégrant des moyens de traitement numérique d'images. La caméra
intègre une optique 30, un capteur d'image non représenté, par exemple
un capteur à accès aléatoire, et un système d'acquisition d'images et de
traitement numérique 6 pour acquérir les séquences d'images de la caméra
sous une forme numérique et pour exécuter sur ces séquences d'images les
différents algorithmes de détection de flammes et de fumée décrits plus
bas. La caméra intelligente 3 intègre en outre une mémoire 5 pour y
stocker ces algorithmes ainsi qu'une ou plusieurs images ou séquences
d'images de référence employées par ces algorithmes. Un système
d'interprétation des résultats et de prise de décision 7 peut être réalisé par
exemple sous la forme d'un module informatique chargé dans la mémoire 5
et exécuté par le système de traitement numérique 6. La caméra
intelligente 3 peut en outre intégrer un système de gestion d'événements
70 pour gérer les événements détectés par le système 7 et déclencher par
exemple l'envoi d'une alarme ou d'une prélarme. La caméra intelligente 2
peut être connectée au travers d'une interface de communication à un
écran 15 pour visualiser soit les séquences d'images acquises en direct, soit
des images enregistrées correspondant à des événements détectés. La
caméra 3 est aussi capable de communiquer ses résultats à un ordinateur
12. Une unité de commande 11 permet de choisir des zones d'intérêt dans
l'image, de varier la sensibilité de la détection, de programmer des
mouvements de caméra, etc. La caméra 3 constitue donc un système
complet de caméra intelligente capable de détecter les flammes et la fumée
et de générer des signaux d'alerte en conséquence.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
La figure 3 illustre une autre variante de système permettant de
mettre en oeuvre l'invention, dans laquelle une ou plusieurs caméras vidéo
3 de détection de fumée 13 ou de flammes 14 fournissent des séquences
d'images directement traitées par le système de traitement numérique
d'images 6, par exemple un PC industriel sur le site surveillé. Le système 6
exécute les algorithmes de détection de feu par traitement d'images et
l'interprétation des résultats. Les images traitées et les événement s
détectés sont transmis à un opérateur à distance muni d'un ordinateur 12
intégrant une interface graphique permettant de visualiser les images
vidéo provenant des caméras 3 et d'informer l'opérateur en cas de
détection d'alarme.FIG. 3 illustrates another variant of a system enabling
implement the invention, wherein one or
Afin de permettre de prendre des décisions fiables sur l'état du
site surveillé, c'est-à-dire de réduire le nombre de fausses alarmes ou de
feus non détectés, le système de traitement numérique d'images 6 et le
système d'interprétation des résultats et de prise de décision 7 utilisent
plusieurs algorithmes de traitement d'image distincts et combinés entre
eux. Les algorithmes employés peuvent se baser sur les méthodes suivantes: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
La présence de fumée réduit la netteté des contours des objets
présents dans la scène, ce qui correspond à un filtre de lissage spatial passe-bas.
Les hautes fréquences de l'image 31 sont donc atténuées par la
présence de fumée par rapport à l'image de référence 32 stockée dans la
mémoire 5 et correspondant par exemple à une image de l'arrière-plan sans
fumée ni flammes. Le procédé consiste donc à calculer la transformée
fréquentielle de chaque image 31 ou portion d'image acquise à l'aide d'un
module 33 de transformation de Fourier rapide FFT ou FHT par exemple et
à la comparer à l'aide d'un système de comparaison 35 avec la transformée
fréquentielle de l'image de référence 32 calculée par un module 34.
Lorsque le système de comparaison détecte une atténuation des hautes
fréquences de l'image supérieure à l'atténuation des basses fréquence par
rapport à l'image de référence, un module de décision 36 peut indiquer
une alarmé fumée ou une probabilité d'alarme fumée.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
Cet algorithme peut être utilisé sur toute l'image. Afin de détecter plus nettement et plus rapidement l'apparition de fumée, cet algorithme est de préférence appliqué sur une ou plusieurs sous-portions ou zoes de l'image filmée; une alarme étant déclenchée dès qu'une ou un nombre minimal de zones indiquent une atténuation des hautes fréquences spatiales par rapport à l'image de référence. Il est aussi possible de n'appliquer cet algorithme que sur les portions de l'image sur lesquelles de la fumée est susceptible d'apparaítre ou dans lesquels un autre algorithme a indiqué une probabilité d'événement feu. Enfin, cet algorithme peut soit être appliqué sur une image en nuance de gris ou d'une autre composante, soit séparément sur les différentes composantes d'une image couleur. Selon les couleurs de fumée susceptibles d'apparaítre, il est possible de pondérer différemment les différentes composantes chromatiques. 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.
L'apparition d'un objet dont les contours, la chrominance ou la luminosité oscillent à une fréquence supérieure à 0.5 Hz est un signe de la présence éventuelle de flammes. Ceci peut être détecté à l'aide d'un procédé d'analyse fréquentielle utilisant les images successives d'une séquence d'images. Pour faire cette analyse, l'ordinateur doit disposer de toute une séquence d'images dans sa mémoire et détecter dans le domaine spatialles objets à l'ade d'un aglgorithme de reconaissanc de forme.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.
Cet algorithme peut aussi être mis en oeuvre pour détecter et suivre sur plusieurs images successives des objets dont la forme, la taille et/ou la couleur varient de manière non régulière et selon une fréquence aléatoire. Des méthodes d'identification d'objet et de suivi d'objet peuvent être employées.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.
Lorsqu'une séquence d'images couleurs est disponible, il est possible d'utiliser directement l'information couleur comme critère de présence de fumée. En effet, la fumée est généralement peu colorée (blanche, noire, grise, etc.). Une image ou une portion d'image devenant moins colorée est donc susceptible de représenter de la fumée. Selon les couleurs de fumée susceptibles d'apparaítre, il est possible de tenir compte de cette couleur.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.
Inversement, une portion d'image devenant soudain plus colorée et plus lumineuse pourrait représenter des flammes, à fortiori si cette portion se trouve en bas de l'image ou en sous une portion pouvant représenter de la fumée. 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.
Lorsqu'une séquence d'images couleurs est disponible, il est possible d'approximer le spectre d'émission d'un objet sur chaque image en mesurant les composantes rouges vertes et bleues, ce qui permet d'approximer la température d'un objet. Un objet à forte luminosité ayant un spectre d'émission correspondant à un corps chaud avec un maxima dans les rouge-jaune peut être suspecté d'être une flamme (ou le reflet d'une flamme).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).
L'apparition d'un objet dont les contours ne contiennent que peu de segments de droites est un signe de la présence éventuelle de fumée ou de flammes. Si une comparaison est faite avec l'image de référence, la disparition de segments droits peut être détectée.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.
En mesurant les différences entre l'image actuelle filmée et une image de référence de la même scène, il est possible de détecter de manière fiable l'apparition d'objets qui n'étaient pas présents dans l'image de référence. Cet algorithme permet d'identifier des zones où la probabilité d'apparition de fumée est plus grande. Les autres algorithmes de détection de flamme ou de fumée peuvent se concentrer sur cette zone. Pour éviter que les changements de lumières ou des ombres soient détectés comme nouveaux objets, il est possible de renouveler l'image de référence régulièrement. 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.
Lorsque plusieurs images de la même scène depuis différents points de vue sont disponibles, il est possible d'utiliser des algorithmes de vision stéréoscopique pour évaluer la position, la forme tridimensionnelle, le volume et la distance d'objets filmés, par exemple de nouveaux objets apparaissant par rapport à une image de référence. Il est ainsi possible de distinguer par exemple entre une colonne de fumée apparaissant devant un mur et une ombre ou un reflet sur ce mur. En plein air, cet algorithme permet de distinguer entre un nouveau nuage et une colonne de fumée beaucoup plus proche. Cet algorithme peut être utilisé par exemple pour identifier de manière très fiable les zones d'intérêt d'une image ou d'une séquence d'image sur lesquels les autres algorithmes doivent se concentrer.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.
Les séquences d'images multiples peuvent être générées par exemple à l'aide de plusieurs caméras, à l'aide d'une seule caméra motorisée permettant de changer la positon ou l'angle de prise de vue, à l'aide d'une ou plusieurs caméras et d'un jeu de miroirs, etc.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.
Le système de traitement numérique 6 peut en outre être
connecté à un ou plusieurs capteurs externes éventuellement présents et
permettant de détecter des événements particuliers, par exemple des
capteurs de température, de rayonnement infrarouge ou ultraviolet, de
mouvement, etc. Les indications fournies par ces capteurs sont transmises à
de cartes d'acquisition dans le sysème de traitement numérique 6 et
peuvent être utilisées pour confirmer les indications fournies par les
algorithmes de traitement d'image ou pour améliorer les performances de
ces algorithmes. Par exemple, un détecteur de mouvements peut être
utilisé pour déclencher un déplacement ou un mouvement de zoom
optique ou numérique d'une caméra vers la zone où le mouvement s'est
produit, ou pour concentrer les algorithmes de traitement d'image sur les
portions d'image correspondant à la zone où le mouvement a été détecté. The
Les résultats des différents algorithmes sont combinés entre eux
par un processus d'interprétation et de prise de décision des résultats
exécutés par exemple par le système 7 afin de détecter les flammes et/ou la
fumée de manière fiable. Ce processus d'interprétation des résultats peut
prendre en compte l'évolution des différents critères de détection en
fonction du temps. Par exemple, un niveau de détection qui grandit
rapidement est plus dangereux qu'un niveau de détection stable.The results of the different algorithms are combined
through a process of interpretation and decision-making of the results
executed for example by the
Comme mentionné plus haut, il est possible d'améliorer sensiblement les performances du système en segmentant l'image en plusieurs portions et en adaptant la sensibilité de détection des différents algorithmes selon ces différentes portions. Les portions d'image pouvant poser des problèmes de fausses alarmes (cheminées dans un paysage, portion d'un mur où les phares de voiture se reflètent, etc.) peuvent ainsi être désensibilisées sans influencer la détection dans les autres parties de l'image. Il est également possible de rendre plus sensible les parties les plus éloignées de la scène, et moins sensibles les parties plus proches afin de compenser l'effet de perspective. Cette adaptation peut se faire manuellement ou automatiquement.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.
Selon l'invention, la sensibilité peut être modifiée pour adapter le système à son environnement. Dans un mode de réalisation préférentiel, ce réglage peut se faire à l'aide d'un paramètre unique influençant tous les algorithmes du système. Ce paramètre peut être modifié par l'intermédiaire d'un bouton glisseur sur l'interface graphique 10, d'un potentiomètre, ou par n'importe quel autre élément de réglage.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.
Lorsque le programme de détection de feu est destiné à être utilisé dans des environnements très différents, par exemple si le même programme est employé pour détecter des feux de forêts dans un paysage ou des incendies dans un tunnel routier, il est souhaitable de pouvoir régler séparément la sensibilité des algorithmes de détection de flamme et des algorithmes de détection de fumée. La figure 5 illustre deux boutons-glisseurs permettant de régler séparément la détection de flammes et la détection de fumée. 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.
L'homme du métier comprendra qu'il est aisément possible, dans le cadre de l'invention, d'imaginer un mode de paramétrage avancé permettant de régler séparément la sensibilité de chaque algorithme, la sensibilité appliquée sur chaque zone ou sur chaque composante de couleurs, etc. Il est ainsi possible d'employer un même dispositif et un même programme de détection de feux et de le paramétrer pour détecter des flammes ou de la fumée dans des environnements très différents, par exemple dans un tunnel routier ou ferroviaire, à l'extérieur, dans des hangars, etc.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.
Les différents événements pouvant survenir dans le systèmes sont présentés par l'interface graphique 10 à l'opérateur par ordre d'urgence. L'interface graphique affiche ainsi par exemple en tête de liste les alarmes flamme et fumée en commençant par l'alarme la plus récente, puis les préalarmes flamme et fumée en commençant ici aussi par la préalarme la plus récente, les autres événements ou alarmes éventuellement détectés étant affichés en queue de liste. Ces autres événements peuvent comprendre par exemple des pannes de caméra, des caméras encrassées, des indications de luminosité insuffisante de la scène à surveiller, ou des événements externes détectés par des capteurs non représentés, tel que décrochage des extincteurs, ouvertures de portes, etc. Un message visuel, de préférence une fenêtre "pop-up" indiquant le type d'alarme détectée et s'ouvrant dans une interface graphique 10, et un beep sonore sont de préférence générés lors de la détection d'une alarmeThe 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
Ces différents événements peuvent être stockés dans un fichier
("log file") dans le système de traitement 6, dans le système 7 ou dans
l'ordinateur employé par l'opérateur distant et répertoriant tous les
événements survenus. Ce fichier est de préférence constitué par un
document XML contenant également des images ou des séquences
d'images liées à chaque événement répertorié, ainsi que la date de
l'événement. Un opérateur peut ainsi consulter le fichier XML
correspondant à la période de surveillance et charger les images
enregistrées, par exemple à distance, pour vérifier les alarmes détectées et
s'assurer par exemple que les alarmes détectées correspondent
effectivement à des incendies.These different events can be stored in a file
("log file") in the
La présente invention concerne un procédé de détection de feu. Elle concerne également un dispositif spécialement adapté pour mettre en oeuvre ce procédé, par exemple un ordinateur ou une caméra intelligente programmés pour mettre en oeuvre ce procédé, ainsi qu'un support de données comportant un programme d'ordinateur directement chargeable dans la mémoire d'un tel dispositif et comprenant des portions de code informatique constituant des moyens pour exécuter ce procédé.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)
- 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. - 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.
- 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).
- 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.
- 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.
- 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.
- 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).
- 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).
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CH3402001 | 2001-02-26 | ||
| CH340012001 | 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 Expired - Lifetime 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) | ATE298912T1 (en) |
| ES (1) | ES2243699T3 (en) |
| WO (1) | WO2002069292A1 (en) |
Families Citing this family (54)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE10011411C2 (en) * | 2000-03-09 | 2003-08-14 | Bosch Gmbh Robert | Imaging fire detector |
| JP4405468B2 (en) * | 2002-09-24 | 2010-01-27 | ピルツ ゲーエムベーハー アンド コー．カーゲー | Method and apparatus for protecting hazardous areas |
| US7729511B2 (en) | 2002-09-24 | 2010-06-01 | Pilz Gmbh & Co. Kg | Method and device for safeguarding a hazardous area |
| US7685341B2 (en) * | 2005-05-06 | 2010-03-23 | Fotonation Vision Limited | Remote control apparatus for consumer electronic appliances |
| US7792970B2 (en) | 2005-06-17 | 2010-09-07 | Fotonation Vision Limited | Method for establishing a paired connection between media devices |
| US7747596B2 (en) * | 2005-06-17 | 2010-06-29 | Fotonation Vision Ltd. | Server device, user interface appliance, and media processing network |
| US7154400B2 (en) * | 2003-06-27 | 2006-12-26 | The United States Of America As Represented By The Secretary Of The Navy | Fire detection method |
| WO2005045775A1 (en) * | 2003-11-07 | 2005-05-19 | Axonx, L.L.C. | Smoke detection method and apparatus |
| 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 |
| US7694048B2 (en) * | 2005-05-06 | 2010-04-06 | Fotonation Vision Limited | Remote control apparatus for printer appliances |
| GB2428473A (en) * | 2005-07-18 | 2007-01-31 | Sony Uk Ltd | Fire detection by processing video images |
| GB2428472A (en) * | 2005-07-18 | 2007-01-31 | Sony Uk Ltd | Smoke 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 |
| KR20090086898A (en) * | 2006-09-25 | 2009-08-14 | 지멘스 슈바이츠 악티엔게젤샤프트 | Detection of smoke with a video camera |
| US20080137906A1 (en) * | 2006-12-12 | 2008-06-12 | Industrial Technology Research Institute | Smoke Detecting Method And Device |
| US7868772B2 (en) * | 2006-12-12 | 2011-01-11 | Industrial Technology Research Institute | Flame detecting method and device |
| US20080136934A1 (en) * | 2006-12-12 | 2008-06-12 | Industrial Technology Research Institute | Flame Detecting Method And Device |
| WO2008088325A1 (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 |
| 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 |
| 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 |
| EP2476098A1 (en) * | 2009-09-13 | 2012-07-18 | 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 |
| AU2013271365B2 (en) * | 2012-06-08 | 2017-02-02 | Garrett Thermal Systems Limited | 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 |
| WO2018079400A1 (en) * | 2016-10-24 | 2018-05-03 | ホーチキ株式会社 | Fire monitoring system |
| CN106997461B (en) | 2017-03-28 | 2019-09-17 | 浙江大华技术股份有限公司 | A kind of firework detecting method and device |
| 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 |
| CN111639620B (en) * | 2020-06-08 | 2023-11-10 | 深圳航天智慧城市***技术研究院有限公司 | Fire analysis method and system based on visible light image recognition |
| US11908195B2 (en) | 2020-12-01 | 2024-02-20 | Devon Energy Corporation | Systems, methods, and computer program products for object detection and analysis of an image |
| WO2022204153A1 (en) * | 2021-03-22 | 2022-09-29 | Angarak, Inc. | Image based tracking system |
| WO2023288209A1 (en) * | 2021-07-14 | 2023-01-19 | Sensormatic Electronics, LLC | Systems and methods for parsing sensor data to provide contextual data for a security event |
| CN114225264A (en) * | 2021-12-29 | 2022-03-25 | 合肥水泥研究设计院有限公司 | Power station fire extinguishing system |
Family Cites Families (18)
| 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 |
| GB2257598B (en) * | 1991-07-12 | 1994-11-30 | Hochiki Co | Surveillance monitor system using image processing |
| FR2696939B1 (en) | 1992-10-16 | 1995-01-06 | Bertin & Cie | Method and device for rapid automatic detection 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 THE AUTOMATIC DETECTION OF FIRES, ESPECIALLY FOREST FIRES |
| FR2775534B1 (en) * | 1998-02-27 | 2000-09-15 | D Aviat Latecoere Soc Ind | DEVICE FOR MONITORING AN ENCLOSURE, ESPECIALLY 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 |
| AU3201101A (en) * | 2000-02-07 | 2001-08-14 | Intelligent Security Limited | 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 |
| BR0209543A (en) * | 2001-05-11 | 2005-04-26 | Detector Electronics | Flame detection and fire detection method and apparatus |
-
2002
- 2002-02-26 ES ES02711747T patent/ES2243699T3/en not_active Expired - Lifetime
- 2002-02-26 EP EP02711747A patent/EP1364351B8/en not_active Expired - Lifetime
- 2002-02-26 WO PCT/CH2002/000118 patent/WO2002069292A1/en not_active Application Discontinuation
- 2002-02-26 AT AT02711747T patent/ATE298912T1/en active
-
2003
- 2003-08-25 US US10/647,109 patent/US6937743B2/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| EP1364351A1 (en) | 2003-11-26 |
| US6937743B2 (en) | 2005-08-30 |
| WO2002069292A8 (en) | 2003-11-13 |
| WO2002069292A1 (en) | 2002-09-06 |
| US20040175040A1 (en) | 2004-09-09 |
| EP1364351B8 (en) | 2006-05-03 |
| ATE298912T1 (en) | 2005-07-15 |
| ES2243699T3 (en) | 2005-12-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP1364351B1 (en) | Method and device for detecting fires based on image analysis | |
| US20190244504A1 (en) | Fire monitoring system | |
| US20030038877A1 (en) | Imaging fire detector | |
| CN109191761A (en) | A kind of method for recognizing fire disaster based on flame multiple features fusion | |
| JP2008537450A (en) | Video-based human verification system and method | |
| Seckiner et al. | Forensic image analysis–CCTV distortion and artefacts | |
| JP5042177B2 (en) | Image sensor | |
| EP0818766B1 (en) | Method for automatic detection of fires, particularly of forest fires | |
| EP4165546A1 (en) | Method for automatic protection of an object, a person or a piece of information or visual work from a risk of undesired observation | |
| JP5393086B2 (en) | Image sensor | |
| EP0577491B1 (en) | Process and device for monitoring a three-dimensional scene using imagery sensors | |
| CN112347874A (en) | Fire detection method, device, equipment and storage medium | |
| KR20210077600A (en) | Close object detection for monitoring cameras | |
| KR20070028812A (en) | Method and apparatus for monitoring forest fire using images photographed by camera device | |
| JPH09293185A (en) | Object detection device/method and object monitoring system | |
| JP7224328B2 (en) | Thermal camera health monitoring | |
| KR102439548B1 (en) | Power plant monitoring system and method | |
| US11087615B2 (en) | Video/sensor based system for protecting artwork against touch incidents | |
| Patil et al. | Integrating Artificial Intelligence with Camera Systems for Automated Surveillance and Analysis | |
| Dheyab et al. | Using the City's Surveillance Cameras to Create a Visual Sensor Network to Detect Fires | |
| Stipaničev | Intelligent Forest Fire Monitoring System–from idea to realization | |
| WO2018152630A1 (en) | Systems and methods for monitoring playback of recorded content | |
| FR2847042A1 (en) | Interactive terminal for use in opticians to permit automatic calculation of ophthalmic parameters has a camera behind an unsilvered mirror and various command buttons for controlling the terminal in response to stimuli | |
| JPH03267893A (en) | Picture monitoring device | |
| EP2329474A1 (en) | Scene surveillance method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
| 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 |
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 | Party data changed (applicant data changed or 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 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: FASTCOM TECHNOLOGY S.A. Owner name: SECURITON AG |
|
| GRAP | Despatch of communication of intention to grant a patent |
Free format text: ORIGINAL CODE: EPIDOSNIGR1 |
|
| GRAS | Grant fee paid |
Free format text: ORIGINAL CODE: EPIDOSNIGR3 |
|
| GRAA | (expected) grant |
Free format text: ORIGINAL CODE: 0009210 |
|
| 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 |
|
| NLV1 | Nl: lapsed or annulled due to failure to fulfill the requirements of art. 29p and 29m of the patents act | ||
| 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 |
|
| 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 |
|
| PLBE | No opposition filed within time limit |
Free format text: ORIGINAL CODE: 0009261 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT |
|
| 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 via postgrant information 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 via postgrant information 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 via postgrant information 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 |