WO2019048603A1 - Détection précoce automatique de fumée, de suie et d'incendie au moyen d'un modèle de terrain en 3d - Google Patents

Détection précoce automatique de fumée, de suie et d'incendie au moyen d'un modèle de terrain en 3d Download PDF

Info

Publication number
WO2019048603A1
WO2019048603A1 PCT/EP2018/074117 EP2018074117W WO2019048603A1 WO 2019048603 A1 WO2019048603 A1 WO 2019048603A1 EP 2018074117 W EP2018074117 W EP 2018074117W WO 2019048603 A1 WO2019048603 A1 WO 2019048603A1
Authority
WO
WIPO (PCT)
Prior art keywords
smoke
sensor
color
terrain
fire
Prior art date
Application number
PCT/EP2018/074117
Other languages
German (de)
English (en)
Inventor
Hans M. WELTERT
Original Assignee
Fcm Dienstleistungs Ag
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Fcm Dienstleistungs Ag filed Critical Fcm Dienstleistungs Ag
Publication of WO2019048603A1 publication Critical patent/WO2019048603A1/fr

Links

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B17/00—Fire alarms; Alarms responsive to explosion
    • G08B17/12—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
    • G08B17/125—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions by using a video camera to detect fire or smoke
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B17/00—Fire alarms; Alarms responsive to explosion
    • G08B17/005—Fire alarms; Alarms responsive to explosion for forest fires, e.g. detecting fires spread over a large or outdoors area
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data

Definitions

  • the present invention relates to a method and a system for automatic early detection of events such as smoke, soot and / or fire with increased detection reliability and exact location of a fire and their use.
  • Forest fires devastate large areas of forest every year worldwide. Not infrequently, cultivated land and even humans, farm animals and their buildings are affected, which leads to major economic and ecological damage. Therefore, great efforts are made to limit forest fires as quickly as possible and possibly completely prevent. It has been shown that the probability of extinguishing the fire quickly and thus preventing a major fire is much higher if the forest fire can be fought within the first 20 minutes after the outbreak of the fire. This requires a very quick fire detection to have enough time to alert the firefighters and start firefighting on the spot.
  • EP 984 413 A2 describes an apparatus and a method for automatic forest fire detection by means of an optical recording device rotatably mounted on a platform, an electronic evaluation unit and a transmitter or local alarm transmitter comprising a plurality of method steps.
  • a reference picture of a scene is taken, the horizon determined, the reference picture normalized, the picture area under the horizon determined, a non-linear filtering performed and the resulting reference picture stored.
  • at least one current picture is taken, a picture matching of the current picture with the reference picture is made and the picture normalized.
  • the current image is then compared with the reference image, a binarized differential image is generated, a cluster algorithm applied, probabilities for evaluating the clusters found and then triggered an alarm if the smoke probability for at least one cluster exceeds the predetermined threshold.
  • the reliability of the evaluation can be increased.
  • the error rate - and thus the triggered error alarms - is particularly due to moving objects such as Animals, vehicles or trees moving in the wind relatively high. Accordingly, the recognition security is poor and does not meet modern standards.
  • DE 10 2009 020 709 A1 describes a method for monitoring and analyzing territories by means of a georeferenced multiplatform system, which is equipped with at least one optical black / white or color sensor and at least one further sensor and thus used for a multiplicity of different monitoring systems can.
  • the number of generated messages should be continuously optimized during operation, whereby influence of an operator is necessary.
  • the monitoring is not automated and not in real time.
  • a database comparison is mandatory in order to arrive at the effect to be achieved.
  • WO-A-97/35433 discloses a system with a viewing unit and a ground station.
  • the viewing unit is mounted on an aircraft, an unmanned aerial vehicle or a fire watch tower and includes a temperature sensitive sensor, such as an IR sensor, for measuring the hot areas.
  • a temperature sensitive sensor such as an IR sensor
  • real-time infrared (IR) images of a fire are combined with digital images of the area at an earlier time.
  • the two types of images are registered, with the IR images superimposed on the digital images.
  • This provides firefighters with information about the types of objects such as houses, Trees, roads, etc. provided, which lie on the way of the fire.
  • the system refers to the detection of high temperatures and thus to existing fires and not to the early detection of fires, where often only smoke or soot can be observed.
  • US-A-2015/332571 discloses a method of detecting extreme temperature events comprising collecting raw data with a high resolution sensor and identifying one or more changing data point values in the raw data by comparing the data to an established background model; identifying, in the collected raw data, that the one or more changing data point values have reached a certain threshold indicating, with a high degree of likelihood, that an extreme temperature event has occurred and, as a result, triggering an alarm indicating that an extreme temperature event has occurred is.
  • the method may identify identifying a sudden extreme increase in one or more data points exceeding a threshold indicative of a high degree of likelihood that an extreme temperature event has occurred in the raw collected data.
  • the method includes issuing a warning indicating that an extreme temperature event has occurred.
  • the disclosed technology is designed to detect extreme temperature events, it is suitable for the detection of larger fires, but not for the early detection of smoke and / or soot, which are an indication of fires in the early stadium. Also, fires in the forest are often not detected for a long time because the heat source is obscured by the forest environment. In addition, neither an electronic pixel color channel mixing unit nor a record for a smoke color optimized pixel area is disclosed or needed.
  • DE-B-10 2016 000 661 describes a device for an optical sensor solution for automated early forest fire detection with a detector unit arranged on a mast comprising an optical sensor, a processor unit and a device for position determination, for example a GPS receiver.
  • the location device is intended to allow precise and permanent detection of the 3D location coordinates of the optical sensor, to link the forest fire detection with spatial information to the location of the optical sensor and cartographic systems and to locate the fires to be detected accurately by position and orientation to perform the optical sensor.
  • the spatial position of the optical sensor can be made by entering a known spatial position from map data. Thus, only the location of the sensor is detected by means of cartographic data, but not the terrain to be observed. Also, GIS records are not mentioned.
  • DE-B-10 2013 017 395 discloses a method for automated early forest fire detection by means of optical sensors and computer-aided image processing for automatic smoke detection.
  • smoke clouds are detected using the method steps i) generating images by means of at least one digital color camera and transmitting the images to a digital data processing medium and ii) defining membership functions in a fuzzy logic system to the classes "smoke", "forest” and " dark area »by evaluating a plurality of test images recorded by the color image camera or test sequences with respect to a saturation value (S) of the image pixels.
  • S saturation value
  • the obtained color information of the RGB space for each pixel is converted by means of suitable functional transformation, for example into an HSV space with color value H, saturation S and bright value H.
  • the resulting color images are then analyzed for smoke detection using fuzzy logic.
  • fuzzy logic is based on fuzzy sets, which are not defined as conventionally by objects that are elements of sets, but by their degree of belonging to that set. For this purpose membership functions are used, which assign each element a numerical value as degree of affiliation.
  • a disadvantage of all proposed methods and systems is that they can not or only insufficiently recognize the required automatic early detection of events such as smoke, soot and fire with a very high probability of detection and a small number of false alarms.
  • the object of the present invention to obtain a fast, automatic and accurate location of a fire, even in very hilly areas with many mountains and valleys. It should also be possible to localize a fire on the - viewed from a sensor unit - back of hills and mountains. In addition, areas should also be defined and recognized, in which fires are permitted. In addition, the invention should provide in a preferred embodiment, a method by which the detection reliability in the automatic forest fire detection in the early stages - and thus in particular of smoke, soot and / or fire - even for large distances of 10 km or more significantly increased and the error rate the triggered error alarms can be greatly reduced.
  • smoke, soot and / or fire should be detectable in the very early stages of an emerging forest fire, even if it does there are no signs visible to the human eye.
  • smoke, soot and / or fire for example, can be distinguished from passing swarms of birds and / or clouds, but also from non-combustible places such as rocks, roads and / or waters with a very low number of false alarms.
  • the complex task could surprisingly be solved with a method for automatic early detection with increased recognition reliability and accurate location of events such as smoke, soot and / or fire by means of a sensor unit (2) comprising at least one lens (4) and at least one sensor (5) and a data processing unit (3), wherein the
  • the sensor (5) is georeferenced, and thus the height, the coordinate position and the inclination and azimuth angle of the sensor (5) for the respective surveillance sector is determined exactly
  • the pixels of the sensor (5) of a first raw data set of a first exposure period (U) are assigned to the respective monitoring sector of the terrain by means of suitable algorithms taking into account the inclination and azimuth angles of the sensor (5) and thus the pixels of the sensor (5) are calibrated , thereby obtaining a 2D terrain calibrated raw record of the surveillance sector
  • the 2D terrain calibrated raw dataset of the surveillance sector is compared with a 3D GIS terrain dataset of the same terrain by means of suitable algorithms, whereby a calibrated 3D terrain model (3D-GM) is obtained in which the pixels of the Correlate sensors (5) with the area of the 3D GIS terrain data set visible from the location of the sensor (5), as well as iv) monitoring of the surveillance sector by means of the sensor unit (2) and analysis of the raw data sets measured by means of the sensor unit (2) by means of a data analysis DA.
  • 3D-GM calibrated 3D terrain model
  • a system (1) for automatic early detection with increased recognition reliability and precise localization of events such as smoke, soot and / or fire comprising a sensor unit (2) comprising a sensor unit (2), a data processing unit (3) and an electronic pixel color channel mixing unit (6) for processing the raw data sets obtained from the sensor (5), wherein preferably each color channel can be mixed in separately, wherein the sensor unit (2)
  • At least one sensor (5) At least one sensor (5), wherein at least one sensor (5) a
  • Color sensor (5-1) represents, and
  • optical filter different from an NIR and / or IR filter
  • a calibrated 3D terrain model (3D-GM) is stored on the data processing unit (3) of the landscape sector to be monitored, the 3D terrain model (3D-GM) being obtained by offsetting the 2D terrain calibrated raw data set of the surveillance sector with a 3D GIS terrain data set with appropriate control points of the same site.
  • inventive method and the inventive system (1) for automatic early detection of events such as smoke, soot, fire and / or fires such as forest fires; for the reduction of false alarms, especially in forest fire detection systems operating from non-combustible locations such as rocks, roads and / or waters, and / or non-combustible events such as cloud shadows, Clouds of dust, bird swarming, air pollution as well as driving and / or flying objects may result; to increase the detection reliability of events; for the exact location of the events; and for geological monitoring of geologically critical regions, in particular at risk of rock and / or ice breakage, a rockfall and / or a landslide claimed.
  • the process according to the invention, the system according to the invention and the use according to the invention offer many advantages. It is thus possible to automatically generate 3D terrain models of very large areas and with a terrain depth of 40 km and more - even in very hilly areas with many mountains and valleys. This surprisingly allows the localization of fires quickly and with very high accuracy of, for example, 10 m or less even in hilly terrain - This is true even if a fire in an area not visible to the sensor unit as in valleys and / or on the back of hills and Bergen, for example, by knowing the wind speed at the location in question and offset data sets, the distance to the event can be calculated.
  • the use of the 3D terrain model also makes it possible to define areas in the terrain and to recognize where fires are permitted.
  • the data analysis DA preferably used in the method according to the invention allows the automatic early detection of events such as smoke, soot and / or fire with increased recognition reliability. There is no need for a so-called "density" of the event, ie the event need not be visible to the human eye and can nevertheless be detected. This allows a much earlier detection than in other known systems, which is a significant advantage for firefighting. Also, surprisingly, smoke, soot and fire can be detected more automatically and without the intervention of a person in the early stages compared to conventional systems with greater likelihood and low error rate both during the day, at night and in difficult light conditions - and up to distances of 40 km or more!
  • an "earlier / now" comparison can be derived and terrain changes, such as rock falls or debris flows, become visible.
  • the 3D terrain model extends only to a distant and visible from the camera area.
  • Generating a 3D terrain model for real-time subsequent image or pixel analysis for use in a method of automatic early detection of fires with increased detection safety of events such as smoke, soot and / or fire, and triggering an alarm in the event of an event neither mentioned nor suggested.
  • data sets in the pixel range DSos, DSi-s, DS2-S, DSn-s and DSo-c can be analyzed and even evaluate data sets, although the human eye is no visible indication of smoke, soot and / or fire, the sensitivity of the system surprisingly increases significantly.
  • the inventive method and the inventive system (1) are used for automatic early detection of events such as smoke, soot and / or fire with increased detection reliability and exact location of a fire.
  • early detection means the detection of smoke, soot and / or fire at such an early stage, in which the human eye can still see no smoke, soot and / or fire.
  • the method according to the invention is carried out by means of at least one sensor unit (2), a data processing unit (3) and optionally - particularly preferably an electronic pixel color channel mixing unit (6).
  • the sensor unit (2) comprises at least one objective (4) and at least one sensor (5). All components can be arranged together in one unit or in spatially different locations.
  • the data processing unit (3) can be arranged separately from the sensor unit (2), wherein data can be exchanged between the sensor unit (2) and the data processing unit (3).
  • one part of the data processing unit (3) may be arranged at the sensor unit (2) and another part of the data processing unit (3) at another location.
  • the electronic pixel color channel mixing unit (6) is preferably located at the sensor unit (2) and / or at the data processing unit (3), since data sets obtained in the sensor unit (2) by exposure of the sensor (5), to the electronic pixel color channel mixing unit (6) and on to the data processing unit (3).
  • the sensor (5) of the sensor unit (2) is georeferenced, and thus the height, the coordinate position and the inclination and azimuth angle of the sensor (5) for the respective surveillance sector are determined exactly and typically in the data processing unit (3) stored.
  • step ii) the pixels of the sensor (5) of a first raw data set of a first exposure period (U) are assigned to the respective surveillance sector of the terrain by means of suitable algorithms taking into account the inclination and azimuth angles of the sensor (5) Sensors (5) are calibrated. As a result, a 2D terrain-calibrated raw data record of the surveillance sector is obtained, which is optionally stored in the data processing unit (3).
  • the 2D terrain calibrated raw data record of the surveillance sector is compared with a 3D GIS terrain data set of the same terrain by means of suitable algorithms, whereby a calibrated 3D terrain model (3D-GM) is obtained in which the pixels of the sensor (5) correlate with the area of the 3D GIS terrain data set visible from the location of the sensor (5).
  • the calibrated 3D terrain model (3D-GM) is optionally stored in the data processing unit (3).
  • Suitable 3D GIS terrain records, also called GIS data are typically in digital form. They are usually known and commercially available from the landscape sectors to be monitored, the data format of the GIS data playing a minor role as long as they can be processed further.
  • GIS stands for "geoinformation system”.
  • the surveillance sector is monitored by means of sensor unit (2) and the raw data records measured by means of the sensor unit (2) are analyzed by means of a data analysis DA.
  • the calibrated 3D Terrain Model (3D-GM) adds altitude information to the 2D terrain calibrated raw dataset. As a result, information is also obtained that a hill train can be present and consequently also an area behind the hill train, which is not seen by the sensor unit (2).
  • the data analysis DA used in the method according to the invention is suitable for the early detection of fire sources.
  • the data analysis DA takes place with the pixels obtained by the sensor (5) and thus the raw data sets.
  • the data of the sensor contents i. the photodiodes present in the sensor (5) are used before they are changed, for example, by means of an electronic pixel color channel mixing unit (6).
  • this does not require a "density" of the event for the detection of smoke, soot and / or fire.
  • the event need not be visible to the human eye and still be detected, allowing much earlier detection.
  • steps i) to iv) can be carried out in the listed or in another order.
  • no comparison with an external database is necessary and the data evaluation in the data processing unit (3) is preferably carried out in real time, ie in a few seconds or less.
  • an alarm is triggered, and no database synchronization is necessary.
  • an alarm can be triggered.
  • a coordinate network is calculated over the surveillance sector and the individual coordinate areas of the surveillance sector thus obtained are assigned to the individual pixels or pixel areas of the sensor (5).
  • the coordinate areas of the surveillance sector and / or the number of pixels of the sensor (5) are advantageously chosen so that the individual coordinate areas of the surveillance sector does not exceed an area of 100 ⁇ 100 m, in particular an area of 30 ⁇ 30 m.
  • the area represents a two-dimensional area of a cartographic map. This creates a 3D terrain model (3D-GM) with information of the GIS data as well as of cartographic data.
  • flammable objects such as forest or trees - and thus leaves of trees, as well as non-combustible objects such as buildings, roads, water, rocks, traffic, snow and / or glaciers are detected. If an indication of smoke, soot and / or fire comes from a non-flammable object, this indicates a false alarm and can be further investigated or ignored. In addition, information about the areas will be located behind a hill range or a mountain range.
  • for clearing and calibrating the 3D terrain model (3D-GM) in the 2D terrain calibrated raw data set and selected in the 3D GIS terrain data set per surveillance sector at least 4, preferably at least 6, identical, precisely defined control points.
  • control points of the 2D terrain calibrated raw dataset are matched with the control points of the 3D GIS terrain dataset by means of suitable algorithms when calculating the 3D terrain model (3D-GM).
  • control points objects and buildings such as buildings, roads, transmission towers, wells, summit crosses, free-standing trees and / or prominent rocks are preferably selected.
  • the clearing and calibration of the 3D terrain model (3D-GM) with control points significantly increases the agreement with the data set created by the sensor (5).
  • detection algorithms are preferably used, in particular by means of the detection algorithms A, B and / or C, and / or machine learning by means of suitable calculation models, in particular the calculation models A, B and / or C used.
  • detection algorithms are preferably used, in particular by means of the detection algorithms A, B and / or C, and / or machine learning by means of suitable calculation models, in particular the calculation models A, B and / or C used.
  • suitable calculation models in particular the calculation models A, B and / or C used.
  • the detection algorithm A is a contrast detection algorithm and / or a brightness detection algorithm
  • the detection algorithm B is a color detection algorithm, and / or
  • the detection algorithm C is a contrast detection algorithm
  • Brightness detection algorithm a smoke detection dynamic dynamics detection algorithm, an expansion detection algorithm for analyzing the propagation of smoke and / or soot, and / or a structure detection algorithm for analyzing the structure and direction of the smoke and / or soot , wherein the detection algorithm C preferably the data sets DSi-s, DS2-S and DSn-s interdependent, ie interactive, analyzed.
  • the machine learning and analysis calculation model includes
  • Detection algorithm A at least one calculation model A for the smoke color-optimized area and for checking the presence of smoke, soot and / or fire,
  • - Detection algorithm B at least one calculation model B for the color range and for checking the presence of non-combustible objects and / or events, such as clouds, shadows, forest, trees and / or leaves, buildings, roads, bodies of water, snow and / or glaciers, rocks and / or traffic, and / or
  • Detection algorithm C at least one calculation model C for
  • Weather data geography and / or the smoke character, such as the movement, expansion and / or structure of the smoke.
  • the method according to the invention comprises a color sensor (5-1) as sensor (5), the data analysis DA comprising the following steps:
  • the sensor (5) is exposed for at least one exposure period (U) by a landscape sector to be monitored, calculating a data set for at least one smoke color-optimized pixel area (DSo-s) per exposure period (Lo) and the obtained data set DSo-s analyzing the presence of smoke, soot and / or fire with at least one detection algorithm A,
  • DSo-c and / or the Smoke Optimized Area (DSo-s) record shows signs of smoke, soot and / or fire (Fo-c ?, Fo-s?),
  • Landscape sector, or a section thereof, during at least two other, staggered, exposure periods (Li, l_2, L n ) expose and the resulting raw data sets to records for the
  • Smoke color-optimized pixel region (DSO s, DSi s, DS2 S, DS n - s) and / or the data set with color information in the pixel area (DSo-c) an image visible to the human eye (P) is calculated.
  • the terms "data for at least one smoke color-optimized pixel area (DSo-s)" and “record DSo-s” all records DSo-s, DSi-s, DS2-S, DS n -s and DSO s, which arise before, during and after the analysis with at least one of the detection algorithms.
  • the data sets for the smoke color-optimized pixel area are preferably created with an electronic pixel-color channel mixing unit (6) and the data processing unit (3) and optionally in the data processing unit (3) stored.
  • DSo-s smoke color-optimized pixel area
  • the DSo-s, DSi-s, DS2-S, DSn-s datasets also include certain color components, such as blue and / or red, although sometimes only from gray tones or - after transformation into a visible image - from a black and white Picture is the speech.
  • the color information of the observed land sector is included. This can, for example, fluttering leaves of a tree - which was identified as a possible smoke, soot and / or fire in the Smoke Optimized Area (DSo-s) record - identified as a false alarm.
  • the method continues with step i).
  • At least two further time-shifted data sets for the smoke color-optimized pixel region (DSi s, DS2 S, DS n -s) is created and the inclusion of at least one detection algorithm A for the presence of smoke, soot and / or fire are analyzed, temporally offset information of the same landscape sector, or a section thereof, provided.
  • the time data sets are put in the presence of smoke, soot and / or fire analyzed (calc (t)).
  • the corresponding data sets (DSi-s, DS2s, DSn-s) change as a function of time. And the difference between the staggered DSi-s, DS2-S, DS n -s records of a rock face glistening in the sun is quite different than smoke, soot, and / or fire. Comparing pixels of different data sets and checking whether the previous conclusion, ie whether there is an indication of the presence of smoke, soot and / or fire, is correct according to the invention is called plausibility check.
  • An exemplary plausibility check comprises comparing pixels from at least one data record - in particular at least one raw data record - with color information (DSo-c), ie a data record for at least one color image, with data records - in particular raw data records - for at least one smoke color. optimized area (DSo-s), ie a data set suitable for generating so-called black-and-white images.
  • This plausibility check preferably takes place in the data processing unit (3) and in real time and using algorithms. It allows a large reduction of misdetections, which leads to a significant decrease of false alarms.
  • the sensor (5) with the at least two further time-shifted exposure periods (Li, l_2, L n ) is exposed at least once each at a time interval of at least 1 second, preferably at least 2 seconds.
  • the time interval of the exposures is generally sufficient for 10 seconds or less, in particular 5 seconds or less.
  • the thus obtained raw data sets are calculated on a data set for the smoke color-optimized range (DSi s, DS2 S, DS n -s), and preferably analyzed with the involvement of at least one A detection algorithm. Due to the temporal spacing of the images, important conclusions can be drawn about the dynamics of the area to be observed. Because two data sets of smoke, soot and / or fire with said time interval are not identical - this in contrast to records of grayish rock.
  • weather data may include current weather data, such as solar radiation, temperature, wind direction, wind force, humidity, soil moisture, precipitation and / or lightning; and / or accumulated weather data of the last days or weeks, such as in particular temperature, humidity, soil moisture and / or precipitation are used.
  • the weather data are preferably weather data from the landscape sector to be monitored, ie surveillance sector, or an adjacent one Area are.
  • Suitable weather data can be retrieved online at weather stations, for example.
  • the inclusion of weather data (WD) further reduces the number of false alarms. After a long period of rain and / or heavy rain, it is unlikely that a fire will break out. In case of doubt, the possible source of fire can be further monitored by collecting and evaluating further data.
  • the use of weather data - in particular of local weather data - in the method according to the invention is particularly helpful for locating a fire source when it is in an area not visible to the sensor unit, such as in valleys and / or on the back of hills and mountains.
  • DSo-s, DSi-s, DS2-S, DSn-s and the data set with color information in the pixel area (DSo-c) light with the wavelengths of at least 350 to 1 100 nm, preferably at least 400 to 1000 nm, is used, and / or
  • the data records for the smoke color-optimized pixel regions are obtained by the during the exposure periods (Lo, Li, L2, L n) of the sensor (5) the obtained raw data records with color pixels on the basis of electronic pixel color channel mixing unit (6) in records Rauchmaschine- optimized pixel regions (DSO s, DSi s, DS2 S, DS n-s) to be converted by the intensity reinforced at least one color channel, and the intensity of at least two
  • Color channels is reduced to represent the resulting mixed colors of the smoke color-optimized pixel areas as gray tone-like colors, preferably the intensity of a color channel at least twice the intensity of the two Has color channels that have the lowest intensity. In other words, if, for example, the three RGB color channels are used, the color channels are changed such that one of the RGB color channels has at least twice the intensity of the other two color channels-measured individually.
  • the Sensor Unit (2) With the sensor unit (2) of the method according to the invention and the system (1) according to the invention, light from the landscape sector to be monitored is passed through the objective (4) onto the sensor (5), where it is moved into the sensor (5). contained photodiodes collected in records and optionally stored.
  • the sensor unit (2) comprises at least one objective (4) and at least one sensor (5), wherein at least one sensor (5) is a color sensor (5-1) and possibly another sensor (5) is a black-and-white sensor, with which data sets in the gray area, and thus in the smoke color-optimized pixel area, are obtained.
  • the black-and-white sensor 5-2) preferably has an upstream filter, in particular an upstream spectral filter.
  • the lens (4) and the sensor (5) are typically arranged so that incident light through the lens (4) hits the sensor (5).
  • the sensor unit (2) comprises a diaphragm (7), wherein the diaphragm (7) before and / or after the lens (4) - in relation to the incident light and the sensor (5) - can be arranged.
  • Suitable diaphragms (7) are known to the person skilled in the art and are commercially available.
  • the exposure time is advantageously controlled by suitable electronic control of the exposure time of the sensor (5).
  • the aperture of the diaphragm (7) in the exposure periods (Lo, Li, L2, L n ) for detecting the raw data sets has a value of f / 4 or smaller, preferably f / 5.6 or smaller, in particular f / 8 or smaller.
  • the aperture can be designed so that it can be varied, or that it is fixed. Through a small aperture, a higher depth of field is achieved, which is beneficial in many cases.
  • the sensor unit (2) advantageously has no filter for wavelengths in the infrared (IR) and / or near-infrared (NIR) range.
  • the sensor unit (2) preferably comprises a lens (4) with diaphragm (7), but without NIR and / or IR filters.
  • the sensor unit (2) typically comprises at least one optical filter different from an NIR and / or IR filter, for example a spectral filter. Suitable filters are known in the art and commercially available.
  • the sensor unit comprises at least one sensor (5), wherein a sensor (5) is a color sensor (5-1) and an optionally further sensor (5) can be a black-and-white sensor.
  • Suitable sensors (5) are the Known and commercially available.
  • Preferred sensors (5) comprise CCD sensors, in particular an at least 2-dimensional CCD sensor, wherein CCD stands for “Charged Coupled Device”, CMOS sensors, CMOS stands for “Complementary Metal-Oxide Semiconductor”, Active Pixel Sensors (APS), line scanner sensors and / or multispectral sensors.
  • sensors (5) with 1000 ⁇ 1000 pixels, preferably with at least 1500 ⁇ 1500 pixels, in particular with at least 2000 ⁇ 2000 pixels, can be used.
  • the data sets obtained in the color sensor (5-1) during the exposure are preferably forwarded in at least 3 different color channels, in particular by means of RGB color channels, from the sensor (5) to the electronic pixel color channel mixing unit (6) and then to the data processing unit (3) ,
  • the records for the smoke color-optimized pixel regions are usually the inclusion of the pixel color channel mixing unit (6), the data processing unit (3 ) and at least one detection algorithm C is calculated.
  • the data sets obtained in the sensor (5), in particular in the color sensor (5-1), by the exposure to light (hv) during the exposure time are suitable for a color image and / or a smoke color optimized image, i. a so-called black and white picture to get.
  • the data sets obtained in the sensor (5) are typically forwarded as raw data to the data processing unit (3), wherein the forwarding preferably takes place first via the electronic pixel color channel mixing unit (6) and then to the data processing unit (3).
  • the data processing unit (3) of the method according to the invention and of the system (1) according to the invention is used for processing the data, in particular for processing the data sets measured at the sensor (5).
  • the data processing unit (3) may comprise one or more data processing units, the latter being able to be arranged at the same location or at different locations.
  • the data processing unit (3) - or a part thereof - can be mounted next to the sensor unit (2) or it can be located at a different location from the sensor unit (2).
  • the data processing unit (3) preferably comprises at least one processor, at least one data communication module, in particular an Internet and / or cable interface, an antenna, a transceiver, a satellite connection and / or a telephone interface, at least one power source, in particular a power supply connection, a battery , a battery, a photovoltaic module, a wind generator and / or a fuel cell.
  • the data communication module is preferably suitable for receiving data, in particular data records, from the sensor unit (2) and / or the electronic pixel color channel mixing unit (6) and possibly sending it back again.
  • Suitable data processing units (3) are known to the person skilled in the art and are commercially available.
  • the electronic pixel color channel mixing unit (6) of the method according to the invention and the system (1) according to the invention receives data, in particular data records, from the sensor unit (2) and forwards them to the data processing unit (3) after processing. It can also receive data from the data processing unit (3) and, if appropriate, forward it to the sensor unit (2), for example the sensor (5).
  • the electronic pixel color channel mixing unit (6) also called color mixing and amplifying unit (6), of the method according to the invention and of the system (1) according to the invention is used in particular for processing the sensor unit (2), preferably the sensor (5). , in particular from the color sensor (5-1), received data sets.
  • the processing is preferably carried out to smoke color-optimized data sets in the pixel region (DSO s, DSi s, DS2 S, DS n -s). These are analyzed with the inclusion of at least one detection algorithm A and by means of the data processing unit (3) for the presence of smoke, soot and / or fire.
  • the electronic pixel color channel mixing unit (6) is advantageously stored as software on a data carrier.
  • the data carrier can form part of the data processing unit (3) and / or a separate chip, which can be arranged, for example, in the sensor unit (2).
  • the electronic pixel color channel mixing unit (6) can preferably receive and / or process separately each color channel of the raw data sets received by the sensor (5) for each color channel.
  • Suitable electronic pixel color channel mixing units (6) are known in the art and commercially available.
  • the system (1) according to the invention is preferably used in the method according to the invention for the automatic early detection of events such as smoke, soot and / or fire with increased recognition reliability and exact localization of a fire source and enables the detection of light of the landscape sector to be monitored, the collection of the data records thereby obtained as well as the electronic processing of the data records to trigger an alarm if necessary.
  • the system (1) comprises the sensor unit (2), the data processing unit (3) and the electronic pixel color channel mixing unit (6) for processing the data sets received from the sensor (5), in particular from the color sensor (5-1) Preferably, each color channel can be added separately.
  • the sensor unit (2) of the system (1) according to the invention comprises
  • At least one sensor (5) is a color sensor (5-1), and
  • a NIR and / or IR filter different optical filter optionally at least one of a NIR and / or IR filter different optical filter.
  • a calibrated 3D terrain model (3D-GM) is stored on the data processing unit (3) of the landscape sector to be monitored, wherein the 3D terrain model (3D-GM) is obtained by offsetting the 2D terrain-calibrated raw data set of the surveillance sector with a 3D GIS terrain data set with appropriate control points of the same terrain.
  • the aperture (7) of the objective (4) has an aperture with a value of f / 4 or smaller, preferably of f / 5.6 or smaller, in particular of f / 8 or smaller,
  • the exposure time is at least 0.2 seconds, preferably at least 0.5 seconds, in particular at least 1 second.
  • the exposure time is usually not more than 10 seconds, especially not more than 5 seconds.
  • the exposure time is preferably controlled electronically, and / or
  • the sensor unit (2) is arranged on a rotatable device, wherein the sensor unit (2) on the rotatable device is preferably rotatable up to 360 °. Due to the rotatable device, the terrain visible by the sensor unit (2) can be monitored up to a distance of about 40 km. In this case, the terrain to be monitored is typically divided by the rotatable device into different landscape sectors to be monitored, which the sensor unit (2) examines in typically defined order for the event to be examined. In this case, a landscape sector advantageously covers an angle of 2 to 30 °, preferably an angle of 5 to 20 °.
  • the inventive method and the inventive system (1) surprisingly find a versatile application.
  • a very particularly preferred use includes the automatic early detection of events such as smoke, soot, fire and / or fires such as forest fires, the reduction of false alarms, especially in forest fire detection systems, from non-combustible locations such as rocks, roads and / or waters, and / or non-combustible events such as cloud shadows, dust clouds, bird swarms, air pollution, and driving and / or Flying objects can originate; increasing the reliability of detection of events; for the exact location of the events; as well as the geological monitoring of geologically critical regions, in particular in case of risk of a rock and / or ice break, a rock fall and / or a landslide.
  • FIG. 1 shows an exemplary embodiment of the sensor unit (2) of the method according to the invention and of the system (1) according to the invention comprising an objective (4), an optional diaphragm (7), a sensor (5), an electronic pixel-color channel mixing unit ( 6) and a data processing unit (3).
  • the data sets can be converted beforehand into images (P) that are visible to the human eye, whereby typically at least one smoke color-optimized pixel area (DSo-s, DSi-s, DS2-S, DSn-s) an image with predominant gray tones, according to the invention also called black and white image, as well as from the record with color information in the pixel area (DSo-c) a color image is generated.
  • the sensor (5) which is a color sensor (5-1), is exposed to light (hv) by a landscape sector to be monitored during at least one exposure period (U).
  • a data set for at least one smoke color-optimized pixel area is calculated by means of the electronic pixel color channel mixing unit (6) and the data processing unit (3) (not shown) and the resulting data set DSo-s.
  • the resulting data set is also shown with DSo-s.
  • a detection algorithm A advantageously a contrast detection algorithm and / or a brightness detection algorithm is used.
  • the next step is to use the raw data set with the Color pixels, or a section of the raw data set - in particular that section which indicates the presence of smoke, soot and / or fire - a record with color information in the pixel area (DSo-c) calculated and with the inclusion of at least one further detection algorithm B analyzed, the resulting data set is also shown with DSo-c.
  • the detection algorithm B a color detection algorithm is preferably used.
  • the calibrated 3D terrain model (3D-GM) is included in the analysis (F3D-GM?).
  • evidence of smoke, soot and / or fire in the middle of a lake or glacier can be excluded.
  • the landscape sector, or a section thereof, ie eligible excerpt - during at least two other, time-shifted, exposure periods (Li, L2, L n ) expose and the resulting raw data sets to data sets for the smoke color optimized area (DSi-s, DS2-S, DSn-s ) and preferably analyzed with the inclusion of at least one detection algorithm A.
  • the thus-obtained and analyzed records Rauchmaschine- optimized range (DSi s, DS2 S, DS n -s) of at least two temporally staggered exposures are described below with inclusion of at least one other detection algorithm analyzes C (calc (t)).
  • the detection algorithm C is preferably a contrast detection algorithm, a brightness detection algorithm, a smoke detection dynamics detection algorithm, an expansion detection algorithm for analyzing smoke propagation and / or soot, and / or a structure detection algorithm for analysis the structure and direction of smoke and / or soot.
  • one or more detection algorithms can be used.
  • the or the detection algorithms C preferably the data sets DSi s, DS2 S and DS n -s in mutual dependence, that is interactively analyzed.
  • data records can optionally current weather data (WD), such as sunlight, temperature, wind direction, wind speed, humidity, soil moisture, precipitation, and / or lightning; and / or accumulated weather data (WD) of the last days or weeks, such as in particular temperature, humidity, soil moisture and / or precipitation are consulted.
  • WD current weather data
  • WD accumulated weather data
  • (calc (t)) of data records can give the operator an optional input for analysis and calculation, for example, interactive adjusting the calculation parameters to the forest fire index at especially increased risk of forest fires.

Landscapes

  • Business, Economics & Management (AREA)
  • Emergency Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Fire-Detection Mechanisms (AREA)
  • Fire Alarms (AREA)

Abstract

La présente invention concerne un procédé de détection précoce automatique avec une plus grande fiabilité de détection et une localisation précise d'événements tels que la présence de fumée, de suie et/ou d'un incendie au moyen d'une unité de détection (2). Selon l'invention, i) le capteur (5) est géoréférencé, ii) les pixels du capteur (5) d'un ensemble de données brutes d'une première période d'exposition (L0) sont associés au secteur de surveillance respectif du terrain au moyen d'algorithmes appropriés en tenant compte des angles d'inclinaison et d'azimut du capteur (5), ce qui permet d'obtenir un ensemble de données brutes, étalonné sur le terrain en 2D, du secteur de surveillance, et iii) l'ensemble de données brutes, étalonné sur le terrain en 2D, du secteur de surveillance est calculé avec un ensemble de données de terrain en 3D-GIS du même terrain au moyen d'algorithmes appropriés, ce qui permet d'obtenir un modèle de terrain étalonné en 3D (3D-GM) dans lequel les pixels du capteur (5) sont en corrélation avec le domaine visible, à partir de l'emplacement du capteur (5), de l'ensemble de données de terrain en 3D-GIS. L'invention concerne également un système de détection précoce automatique d'événements tels que la présence de fumée, de suie et/ou d'un incendie avec une fiabilité de détection améliorée selon le procédé de l'invention, ainsi que l'utilisation du procédé et du système.
PCT/EP2018/074117 2017-09-09 2018-09-07 Détection précoce automatique de fumée, de suie et d'incendie au moyen d'un modèle de terrain en 3d WO2019048603A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
EP17190261 2017-09-09
EP17190261.2 2017-09-09

Publications (1)

Publication Number Publication Date
WO2019048603A1 true WO2019048603A1 (fr) 2019-03-14

Family

ID=59895068

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2018/074117 WO2019048603A1 (fr) 2017-09-09 2018-09-07 Détection précoce automatique de fumée, de suie et d'incendie au moyen d'un modèle de terrain en 3d

Country Status (1)

Country Link
WO (1) WO2019048603A1 (fr)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110933172A (zh) * 2019-11-28 2020-03-27 广州助蜂网络科技有限公司 一种基于云计算的远程监控系统及方法
CN111199623A (zh) * 2020-01-07 2020-05-26 思创数码科技股份有限公司 基于gis的扁平化指挥调度方法和系统
WO2021160749A1 (fr) * 2020-02-11 2021-08-19 Dryad Networks GmbH Procédé de détection précoce d'incendie de forêt et système de détection précoce d'incendie de forêt
CN115410328A (zh) * 2022-10-31 2022-11-29 北京中海兴达建设有限公司 施工工地的火灾预警方法、装置、设备及可读存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO1997035433A1 (fr) 1996-03-17 1997-09-25 Malat Division, Israel Aircraft Industries Ltd. Systeme et procede permettant de realiser la cartographie d'un incendie
EP0984413A2 (fr) 1998-09-01 2000-03-08 Deutsches Zentrum für Luft- und Raumfahrt e.V. Méthode et système de reconnaissance automatique de feux de forêts
DE102009020709A1 (de) 2009-05-11 2010-11-18 Basso, Gertrud Verfahren und Vorrichtung zur Überwachung und Detektion von Zuständen der Luft und Bewuchs in Waldgebieten mit selbstlernenden Analyseverfahren zur Generierung von Alarmwahrscheinlichkeiten
DE102013017395B3 (de) 2013-10-19 2014-12-11 IQ Wireless Entwicklungsges. für Systeme und Technologien der Telekommunikation mbH Verfahren und Vorrichtung zur automatisierten Waldbrandfrüherkennung mittels optischer Detektion von Rauchwolken
US20150332571A1 (en) 2013-04-09 2015-11-19 Thermal Imaging Radar, LLC Fire detection system
DE102016000661B3 (de) 2016-01-22 2017-05-24 IQ-Wireless GmbH Entwicklungsges. für Systeme und Technologien der Telekommunikation Vorrichtung für die Installation einer optischen Sensorlösung zur automatisierten Waldbrandfrüherkennung und Verfahren zu dessen Einrichtung und Kalibrierung

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO1997035433A1 (fr) 1996-03-17 1997-09-25 Malat Division, Israel Aircraft Industries Ltd. Systeme et procede permettant de realiser la cartographie d'un incendie
EP0984413A2 (fr) 1998-09-01 2000-03-08 Deutsches Zentrum für Luft- und Raumfahrt e.V. Méthode et système de reconnaissance automatique de feux de forêts
DE102009020709A1 (de) 2009-05-11 2010-11-18 Basso, Gertrud Verfahren und Vorrichtung zur Überwachung und Detektion von Zuständen der Luft und Bewuchs in Waldgebieten mit selbstlernenden Analyseverfahren zur Generierung von Alarmwahrscheinlichkeiten
US20150332571A1 (en) 2013-04-09 2015-11-19 Thermal Imaging Radar, LLC Fire detection system
DE102013017395B3 (de) 2013-10-19 2014-12-11 IQ Wireless Entwicklungsges. für Systeme und Technologien der Telekommunikation mbH Verfahren und Vorrichtung zur automatisierten Waldbrandfrüherkennung mittels optischer Detektion von Rauchwolken
DE102016000661B3 (de) 2016-01-22 2017-05-24 IQ-Wireless GmbH Entwicklungsges. für Systeme und Technologien der Telekommunikation Vorrichtung für die Installation einer optischen Sensorlösung zur automatisierten Waldbrandfrüherkennung und Verfahren zu dessen Einrichtung und Kalibrierung

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
APPLIED GEOGRAPHY, vol. 63, no. 1015, pages 315 - 325
SCHWEIZ Z FORSTWES 164, vol. 7, 2013, pages 173 - 180

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110933172A (zh) * 2019-11-28 2020-03-27 广州助蜂网络科技有限公司 一种基于云计算的远程监控系统及方法
CN111199623A (zh) * 2020-01-07 2020-05-26 思创数码科技股份有限公司 基于gis的扁平化指挥调度方法和系统
WO2021160749A1 (fr) * 2020-02-11 2021-08-19 Dryad Networks GmbH Procédé de détection précoce d'incendie de forêt et système de détection précoce d'incendie de forêt
EP4104154A1 (fr) * 2020-02-11 2022-12-21 Dryad Networks GmbH Procédé de détection précoce d'incendie de forêt et système de détection précoce d'incendie de forêt
US12047864B2 (en) 2020-02-11 2024-07-23 Dryad Networks GmbH Method for early detection of forest fire and forest fire early detection system
CN115410328A (zh) * 2022-10-31 2022-11-29 北京中海兴达建设有限公司 施工工地的火灾预警方法、装置、设备及可读存储介质

Similar Documents

Publication Publication Date Title
WO2019048604A1 (fr) Détection précoce automatique de fumée, de suie et de feu avec une sécurité de détection améliorée par apprentissage machine
WO2019048603A1 (fr) Détection précoce automatique de fumée, de suie et d'incendie au moyen d'un modèle de terrain en 3d
EP3058556B1 (fr) Procédé et dispositif de détection rapide automatisée d'incendies de forêt au moyen d'une détection optique de nuages de fumée
EP0984413B1 (fr) Méthode et système de reconnaissance automatique de feux de forêts
RU2596246C2 (ru) Система наблюдения и способ обнаружения засорения или повреждения аэродрома посторонними предметами
DE212011100091U1 (de) System zum Detektieren von nachteiligen Atmosphärenbedingungen vor einem Flugzeug
CN103778418A (zh) 一种输电线路杆塔图像监测系统的山火图像识别方法
Mayr et al. Disturbance feedbacks on the height of woody vegetation in a savannah: a multi-plot assessment using an unmanned aerial vehicle (UAV)
CN109218667B (zh) 一种公共场所安全预警系统和方法
KR20160099931A (ko) 재난 위험 및 관심 지역에 대한 재난 예방 및 관리방법
WO2015028294A1 (fr) Installation de surveillance et procédé de visualisation d'une zone surveillée
DE102009020709A1 (de) Verfahren und Vorrichtung zur Überwachung und Detektion von Zuständen der Luft und Bewuchs in Waldgebieten mit selbstlernenden Analyseverfahren zur Generierung von Alarmwahrscheinlichkeiten
WO2019048601A1 (fr) Détection précoce automatique de fumée, de suie et d'incendie avec une sécurité de détection améliorée
DE102012020093A1 (de) Anordnung zur Ortung, Erfassung und Überwachung von Eisbergen sowie Verfahren zur Bestimmung eines von treibenden Eisbergen ausgehenden Gefährdungspotentials für stationäre oder schwimmende Meeresbauwerke
Abdullah et al. Satellite vs. UAVs remote sensing of arid ecosystems: A review with in an ecological perspective
Kinzel et al. Spring census of mid‐continent sandhill cranes using aerial infrared videography
DE102006042318A1 (de) Verfahren zum Betreiben mindestens einer Kamera
Blanks UAS applications
EP3373092B1 (fr) Procédé de localisation d'une défaillance d'un système
EP3236440B1 (fr) Dispositif, systeme et procede de surveillance de pente et/ou de batiment sans marquage
DE102022200996A1 (de) Umgebungsbranddetektionsanordnung zur Überwachung von einem Überwachungsbereich, Verfahren, Computerprogramm und Speichermedium
Adurkar et al. Fire detection using HSV color picker: a review
WO2020038984A1 (fr) Procédé et arrangement pour reconnaître des décharges en couronne d'une installation ayant des moyens d'exploitation
CN102339465A (zh) 一种检测运动物体相互靠近和/或接触的方法和系统
KR102373278B1 (ko) 지상기반 전천 영상자료를 이용한 야간 전운량 산출방법

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18762327

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18762327

Country of ref document: EP

Kind code of ref document: A1