CN107025753B - Wide area fire alarm device based on multispectral image analysis - Google Patents

Wide area fire alarm device based on multispectral image analysis Download PDF

Info

Publication number
CN107025753B
CN107025753B CN201710411068.2A CN201710411068A CN107025753B CN 107025753 B CN107025753 B CN 107025753B CN 201710411068 A CN201710411068 A CN 201710411068A CN 107025753 B CN107025753 B CN 107025753B
Authority
CN
China
Prior art keywords
fire
multispectral
vector
alarm
characteristic
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.)
Active
Application number
CN201710411068.2A
Other languages
Chinese (zh)
Other versions
CN107025753A (en
Inventor
朱爱民
康尽善
张丽
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Shipbuilding Hanguang (Tianjin) Information Technology Co.,Ltd.
Original Assignee
TIANJIN HGXIANGYUN INFORMATION TECHNOLOGY Co Ltd
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 TIANJIN HGXIANGYUN INFORMATION TECHNOLOGY Co Ltd filed Critical TIANJIN HGXIANGYUN INFORMATION TECHNOLOGY Co Ltd
Priority to CN201710411068.2A priority Critical patent/CN107025753B/en
Publication of CN107025753A publication Critical patent/CN107025753A/en
Application granted granted Critical
Publication of CN107025753B publication Critical patent/CN107025753B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B17/00Fire alarms; Alarms responsive to explosion
    • G08B17/005Fire alarms; Alarms responsive to explosion for forest fires, e.g. detecting fires spread over a large or outdoors area
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/20Image preprocessing
    • G06V10/28Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/40Extraction of image or video features
    • G06V10/44Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/10Terrestrial scenes
    • G06V20/13Satellite images
    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B17/00Fire alarms; Alarms responsive to explosion
    • G08B17/12Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
    • G08B17/125Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions by using a video camera to detect fire or smoke

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Emergency Management (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Astronomy & Astrophysics (AREA)
  • Remote Sensing (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Fire-Detection Mechanisms (AREA)
  • Radiation Pyrometers (AREA)

Abstract

The wide area fire alarm device based on multispectral image analysis comprehensively utilizes a plurality of spectral image analysis technologies to overcome the defect of fire alarm by a single image analysis method; the invention effectively solves the problems of missing report and false report caused by factors such as burning materials, background illumination, illumination intensity and the like of a visible light analysis method; the invention also solves the problems of missing report and false report caused by inaccurate temperature information in the thermal imaging image because the thermal image analysis method needs to detect the ambient temperature to work.

Description

Wide area fire alarm device based on multispectral image analysis
Technical Field
The invention belongs to the field of spectral analysis, and particularly relates to a wide-area fire alarm device based on multispectral image analysis.
Background
Fire alarms in the forest or metropolitan area range differ from indoor fire alarms in that they require detection (monitoring) of up to tens or even tens of square kilometers in area. One of the conventional methods at present is to install a visible light camera at a high-point to scan a target region, and use an image analysis technology to detect a fire by using a scanned image (which is called as a visible light image analysis method). the method comprises the steps of obtaining a video image and a reference image … …, performing smoke pre-judgment … …, and determining whether smoke is generated in a monitored area; after determining that smoke is generated … …, judging whether the smoke is real smoke; determining … … whether the smoke is caused by fire; and if the smoke caused by the fire is determined, further judging whether flames exist in the monitoring area, and if the flames exist in the monitoring area, determining that the fire happens to the forest currently. "(Shanxi Beacon industry Co., Ltd. a forest fire automatic detection method and system [ P ]. China: CN201611256815.1,20170426). Another method is to install a thermal imaging camera at the elevation point and monitor whether a fire occurs by analyzing the temperature information in the image (we refer to as thermography analysis). The method comprises the steps of utilizing a thermal infrared imager, a video server and a transmission device … …, arranging a temperature detection device for collecting the ambient temperature in the forest area to be monitored, and acquiring the ambient temperature value of the monitored area by the thermal infrared imager through the temperature detection device. … … calculates alarm threshold … … (using image analysis techniques) calculates temperature value … … for the cell area (if the temperature is out of limit) sends alarm information and uploads an image ". (Shandong Shenrong electronic products, Inc. A forest fire prevention thermal imaging monitoring system with variable thresholds [ P ]. China: CN201620084343.5,2016.11.09).
Both of these methods have their own drawbacks:
one, visible light analysis method
The method analyzes a visible light image, and the visible light image only contains image mode characteristic information such as color, form, texture, area, target movement and the like, so that non-fire images such as clouds, fog and the like with similar characteristics cannot be correctly identified, and a high fire alarm false alarm rate is caused.
Factors such as burning material, background illumination, wind power, lens focal length, illumination intensity and the like can have great influence on the mode characteristics, so that great report omission and false report are caused.
Second, thermographic analysis
This method requires the detection of the ambient temperature to set the proper alarm threshold in order to obtain the correct binary image about the fire. Otherwise, false or missing reports will occur. In fact, the requirement is not practical, and the installation of the environment temperature detection devices is not feasible for forest and metropolitan area fire alarms which move many tens of square kilometers.
Since thermography mainly uses temperature information in the image, heat may cause false alarms in environments with very low background temperatures.
For city fire alarm in building forests, the ground fire cannot heat the air in the high-rise space, so that the early fire cannot be found from the high-rise point.
Disclosure of Invention
The invention mainly aims to provide a wide-area fire alarm device based on multispectral image analysis, which overcomes the defect of fire alarm by a single image analysis method by comprehensively using a plurality of spectral image analysis technologies; the invention effectively solves the problems of missing report and false report caused by factors such as burning materials, background illumination, illumination intensity and the like of a visible light analysis method; the invention also solves the problems of missing report and false report caused by inaccurate temperature information in the thermal imaging image because the thermal image analysis method needs to detect the ambient temperature to work.
In order to achieve the purpose, the invention adopts the technical scheme that:
a wide area fire alarm device based on multispectral image analysis comprises the following steps: firstly, selecting a height control point according to the size of a forest area or a metropolitan area to be monitored, wherein the height control point is selected according to the principle that all fire monitoring objects can be brought into the visual field;
in the forest fire alarm, a high tower or a natural mountain top which is higher than all tree species is artificially constructed, and the top end of the highest building in a metropolitan area is selected for the metropolitan area fire alarm;
mounting multispectral signal detectors at the front ends of T1, T2 and the like on a height control point, and completing the calibration of pitch and azimuth angles;
the switch N2 collects detected visible light and infrared thermal imaging YUV data through Ethernet, the data are transmitted to a fire judgment analysis server E3, the analysis and the judgment of the fire judgment analysis server E3 are carried out, if a fire disaster occurs, an alarm signal is generated, meanwhile, the direction information fed back by front-end multispectral signal detectors T1, T2 and the like is sent to an alarm linkage servo mechanism A4, the alarm linkage servo mechanism A4 drives an alarm lamp to send out sound and light alarm, and simultaneously drives the fire extinguishing devices of corresponding fire protection subareas to start fire extinguishing work;
the alarm linkage servo mechanism A4 can output 4-way normally open switching value and character string containing Ti longitude and latitude and pitching azimuth information for other fire-fighting platforms except driving the integrated fire extinguishing device in the invention.
Further, the fire determination principle of the server E3 is as follows:
after the fire determination server E3 receives YUV data generated by the visible light camera in the front-end multispectral signal detector Ti,
step 1.1, converting YUV data into RGB data, further converting the RGB data into HSV data, and further extracting color features of HSV space;
step 2.1, converting the RGB data obtained in the step 1.1 into a gray-scale image;
step 3.1, binarizing the gray level image according to the prior threshold value, and converting the gray level image into a binary image; the prior threshold value in the step is from experimental data of the inventor;
step 4.1, extracting morphological characteristics of the firework, including circularity characteristics, sharp corner characteristics and white area changes, by using the binary image obtained in the step 3.1;
step 5.1, extracting the motion characteristics of the firework, including the centroid motion characteristic and the jumping frequency characteristic, by using the binary image obtained in the step 3.1;
step 6.1, obtaining a vector α l of the smoke and fire characteristic values obtained in the step 1.1, the step 4.1 and the step 5.1;
step 7.1 calculates the distance Dl between the vector α l obtained in step 6.1 and the prior eigenvector β l of the smoke and fire, considers that suspected smoke and fire are found in the field of view if Dl is less than the prior threshold Dl and sends vector α l to the "multispectral feature comprehensive evaluation" step the prior eigenvector β l of the smoke and fire of this step, the prior threshold Dl being derived from the experimental data of the inventor.
Meanwhile, the fire determination server E3 also receives YUV data of the thermal imaging camera in the front-end multispectral signal detector Ti, and the server E3 synchronously performs the following steps:
step 1.2, extracting Y channel data of YUV data;
2.2, selecting a threshold according to the temperature and gray mapping spectrum, and binarizing the image obtained in the step 1.2 to obtain a binary image;
3.2, extracting morphological characteristics of the fireworks by using the binary image obtained in the step 2.2, wherein the morphological characteristics comprise circularity characteristics, sharp corner characteristics and white area changes;
step 4.2, extracting the motion characteristics of the firework, including the centroid motion characteristic and the jumping frequency characteristic, by using the binary image obtained in the step 2.2;
step 5.2, forming a vector α r by the firework characteristic values obtained in the step 3.2 and the step 4.2;
step 6.2, calculating the distance Dr between the vector α r obtained in the step 5.2 and the prior characteristic vector β r of the firework, and if Dr is smaller than a prior threshold Dr, considering that the suspected firework is found in the field of view and sending the vector α r to the step of multispectral characteristic comprehensive evaluation, wherein the prior characteristic vector β r of the firework in the step is the prior threshold Dr which is obtained from experimental data of the inventor;
step 7, comprehensively evaluating multispectral characteristics, namely synthesizing α l and α r into a new vector α, wherein α r has no color characteristic component in the step, and in order to be synthesized with α l, the color characteristic components of α r are supplemented and all set to be 0, calculating the distance D between a vector α and a multispectral priori characteristic vector β of fireworks, and if D is smaller than a priori threshold D, the fireworks are found in a field of view, and in the step, the priori characteristic vector β of the fireworks and the priori threshold D are all from experimental data of the inventor;
and 8, if smoke and fire appear in the view field, generating an alarm signal, and packaging and sending the azimuth information fed back by the front-end multispectral signal detector Ti to an alarm linkage servo mechanism A4.
Further, the foreground of the binary image mentioned in the algorithm is set to be white.
Compared with the prior art, the invention has the following beneficial effects: the method does not need to install a temperature detection device in the forest or the metropolitan area, comprehensively uses a visible light image analysis method and an infrared thermal imaging image analysis method, assists and supplements each other, effectively overcomes various defects of a single method, reduces the cost and the construction difficulty of the forest or metropolitan area fire alarm system, and improves the accuracy of fire alarm.
Drawings
FIG. 1 is a pictorial view of a mid-front end multi-spectral signal detector of the present invention;
fig. 2 is a logical block diagram of the present invention.
Fig. 3 is a schematic diagram of fire determination by the fire determination analysis server E3.
In the figure, P1 is a visible light camera; p2 is a thermal imaging camera; p3 is an orientation information feedback turntable.
Detailed Description
In order to make the technical means, the creation characteristics, the achievement purposes and the effects of the invention easy to understand, the invention is further described with the specific embodiments.
In the figure:
example (b): firstly, the height control point is selected according to the forest area or the metropolitan area range to be monitored, and the height control point is selected according to the principle that all fire monitoring objects can be brought into the visual field. In forest fire alarm, high tower or natural mountain top higher than all kinds of trees is used, and city fire alarm selects the top of the highest building in city. And (3) mounting the front multispectral signal detectors such as T1 and T2 on a height control point, and completing the calibration of the pitch angle and the azimuth angle. The switch N2 collects detected visible light and infrared thermal imaging YUV data through the Ethernet, the data are transmitted to a fire judgment analysis server E3, the analysis and the judgment are carried out through a fire judgment analysis server E3, if a fire disaster occurs, an alarm signal is generated, meanwhile, the direction information fed back by front-end multispectral signal detectors T1, T2 and the like is sent to an alarm linkage servo mechanism A4, the alarm linkage servo mechanism A4 drives an alarm lamp to send out sound and light alarm, and meanwhile, the fire extinguishing device of the corresponding fire protection subarea is driven to start fire extinguishing work. The alarm linkage servo mechanism A4 can output 4-way normally open switching value and character string containing Ti longitude and latitude and pitching azimuth information for other fire-fighting platforms except driving the integrated fire extinguishing device in the invention.
The fire determination principle of E3 is as follows:
after the fire determination server E3 receives YUV data generated by the visible light camera in the front-end multispectral signal detector Ti,
step 1.1, converting YUV data into RGB data, further converting the RGB data into HSV data, and further extracting color features of HSV space.
And 2.1, converting the RGB data obtained in the step 1.1 into a gray-scale image.
Step 3.1 binarization of the grey scale image according to prior threshold value, and conversion into binary image
The a priori thresholds in this step are derived from the inventors' implementation data.
And 4.1, extracting morphological characteristics of the fireworks by using the binary image obtained in the step 3.1, wherein the morphological characteristics comprise a circularity characteristic, a sharp angle characteristic and a white area change.
And 5.1, extracting the motion characteristics of the fireworks by using the binary image obtained in the step 3.1, wherein the motion characteristics comprise a mass center motion characteristic and a jumping frequency characteristic.
Step 6.1 the vector α l is composed of the pyrotechnic characteristic values obtained in step 1.1, step 4.1 and step 5.1.
Step 7.1 calculates the distance Dl between the vector α l obtained in step 6.1 and the prior eigenvector β l of the smoke and fire, considers that a suspected smoke and fire is found in the field of view if Dl is less than the prior threshold Dl and sends vector α l to the "multispectral feature comprehensive evaluation" step the prior eigenvector β l of the smoke and fire of this step, the prior threshold Dl all coming from the inventors' experiments.
Meanwhile, the fire determination server E3 also receives YUV data of the thermal imaging camera in the front-end multispectral signal detector Ti, and E3 performs the following steps in synchronization:
and step 1.2, extracting Y-channel data of the YUV data.
2.2, selecting a threshold according to the temperature and gray mapping spectrum, and binarizing the image obtained in the step 1.2 to obtain a binary image;
the temperature and gray scale mapping spectra in this step were derived from the inventors' experiments. The mapping spectrum solves the defect that a thermography analysis method needs to measure background temperature, the gray scale corresponding to smoke and fire temperature can be directly selected from the mapping spectrum without measuring environmental temperature when a binary threshold value of a gray scale image is selected, and the temperature of non-fire heat sources such as people, animals, automobiles and the like is also in the mapping spectrum and can be directly avoided when the binary threshold value of the gray scale image is selected, so the problem of the interference source shielding method for forest fire prevention can be directly solved by utilizing the mapping spectrum.
And 3.2, extracting morphological characteristics of the fireworks by using the binary image obtained in the step 2.2, wherein the morphological characteristics comprise circularity characteristics, sharp corner characteristics and white area changes.
And 4.2, extracting the motion characteristics of the fireworks by using the binary image obtained in the step 2.2, wherein the motion characteristics comprise the mass center motion characteristic and the jumping frequency characteristic.
Step 5.2 the vectors α r are formed by the smoke and fire characteristic values obtained in step 3.2 and step 4.2.
Step 6.2 calculates the distance Dr between the vector α r obtained in step 5.2 and the prior eigenvector β r of the smoke and fire, if Dr is less than the prior threshold Dr, the suspected smoke and fire is considered to be found in the field of view and the vector α r is sent to the step of "multispectral characteristic comprehensive evaluation", the prior eigenvector β r of the smoke and fire in the step, and the prior threshold Dr is from the experiment of the inventor.
Step 7 multispectral feature synthesis evaluation α l and α r are synthesized into a new vector α. in this step α r has no color feature components, and we complement α r color feature components and set all 0's in order to be synthesized with α l.
The method shields the influence of burning materials, background illumination and illumination intensity factors on firework characteristics, realizes the function of verifying the firework characteristics of the visible light image by the firework characteristics of the thermal imaging image, and improves the recognition rate of fireworks.
Distance D between vector α and multispectral a priori eigenvector β of fireworks is calculated, and fireworks are considered to be found in the field of view if D is smaller than a priori threshold D, the a priori eigenvector β of fireworks and the a priori threshold D are all from experimental data of the inventor.
And 8, if smoke and fire appear in the view field, generating an alarm signal, and packaging and sending the azimuth information fed back by the front-end multispectral signal detector Ti to an alarm linkage servo mechanism A4.
The foreground of the binary image mentioned in the algorithm is set to be white.
The temperature and the gray scale spectrum used by the invention have the temperature of 28 ℃, the wavelength of 9.96678E-06M and the gray scale of 9044; the temperature is 29 ℃, the wavelength is 9.93377E-06, and the gray scale is 9367; the temperature is 30 ℃, the wavelength is 9.90099E-06, and the gray scale is 9690; the temperature was 31 deg.C, the wavelength was 9.86842E-06, the gray scale was 10013 … …, the temperature was 726 deg.C, the wavelength was 3.003E-06, and the gray scale was 234498.
The foregoing shows and describes the general principles and broad features of the present invention and advantages thereof. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.

Claims (2)

1. A wide area fire alarm device based on multispectral image analysis is characterized in that: the method comprises the following steps: firstly, selecting a height control point according to the size of a forest area or a metropolitan area to be monitored, wherein the height control point is selected according to the principle that all fire monitoring objects can be brought into the visual field;
in the forest fire alarm, a high tower or a natural mountain top which is higher than all tree species is artificially constructed, and the top end of the highest building in a metropolitan area is selected for the metropolitan area fire alarm;
mounting a front-end multispectral signal detector Ti (i is 1,2 and 3 …) on a height control point, and completing the calibration of a pitch angle and an azimuth angle;
the switch N2 collects detected visible light and infrared thermal imaging YUV data and transmits the YUV data to a fire judgment and analysis server E3 through the Ethernet, the fire judgment and analysis server E3 performs analysis and judgment, if a fire disaster occurs, the fire judgment and analysis server E3 generates an alarm signal and sends azimuth information fed back by a front-end multispectral signal detector Ti to an alarm linkage servo mechanism A4, the alarm linkage servo mechanism A4 drives an alarm lamp to give out sound and light alarm, and meanwhile drives a fire extinguishing device of a corresponding fire protection subarea to start fire extinguishing work;
the alarm linkage servo mechanism A4 drives the integrated fire extinguishing device and also outputs 4-way normally open switching values and character strings containing longitude and latitude and pitching azimuth information of a front-end multispectral signal detector Ti for other fire fighting platforms to use;
the fire determination principle of the server E3 is as follows:
after the fire disaster judgment and analysis server E3 receives the YUV data generated by the visible light camera in the front multispectral signal detector Ti,
step 1.1, converting YUV data into RGB data, further converting the RGB data into HSV data, and further extracting color features of HSV space;
step 2.1, converting the RGB data obtained in the step 1.1 into a gray-scale image;
step 3.1, binarizing the gray level image according to the prior threshold value, and converting the gray level image into a binary image;
step 4.1, extracting morphological characteristics of the firework, including circularity characteristics, sharp corner characteristics and white area changes, by using the binary image obtained in the step 3.1;
step 5.1, extracting the motion characteristics of the firework, including the centroid motion characteristic and the jumping frequency characteristic, by using the binary image obtained in the step 3.1;
step 6.1, obtaining a vector α l of the smoke and fire characteristic values obtained in the step 1.1, the step 4.1 and the step 5.1;
step 7.1, calculating the distance Dl between the vector α l obtained in the step 6.1 and the prior feature vector β l of the firework, and if Dl is smaller than a prior threshold Dl, determining that suspected firework is found in the field of view and sending the vector α l to the step of multispectral feature comprehensive evaluation;
meanwhile, the fire disaster determination and analysis server E3 also receives YUV data of the thermal imaging camera in the front-end multispectral signal detector Ti, and the fire disaster determination and analysis server E3 synchronously performs the following steps:
step 1.2, extracting Y channel data of YUV data;
2.2, selecting a threshold according to the temperature and gray mapping spectrum, and binarizing the image obtained in the step 1.2 to obtain a binary image;
3.2, extracting morphological characteristics of the fireworks by using the binary image obtained in the step 2.2, wherein the morphological characteristics comprise circularity characteristics, sharp corner characteristics and white area changes;
step 4.2, extracting the motion characteristics of the firework, including the centroid motion characteristic and the jumping frequency characteristic, by using the binary image obtained in the step 2.2;
step 5.2, forming a vector α r by the firework characteristic values obtained in the step 3.2 and the step 4.2;
step 6.2, calculating the distance Dr between the vector α r obtained in the step 5.2 and the prior characteristic vector β r of the smoke and fire, and if Dr is smaller than the prior threshold Dr, considering that suspected smoke and fire is found in the field of view and sending the vector α r to the step of multispectral characteristic comprehensive evaluation;
step 7, multispectral feature comprehensive evaluation, wherein α l and α r are synthesized into a new vector α, in the step, α r has no color feature component, in order to be synthesized with α l, the color feature components of α r are supplemented and all set to be 0, the distance D between a vector α and a multispectral priori feature vector β of fireworks is calculated, and if the D is smaller than a priori threshold D, the fireworks are found in a field of view;
and 8, if smoke and fire appear in the view field, generating an alarm signal, and packaging and sending the azimuth information fed back by the front-end multispectral signal detector Ti to an alarm linkage servo mechanism A4.
2. The wide-area fire alarm device based on multispectral image analysis as claimed in claim 1, wherein: the foreground of the binary image extracted by the algorithm is set to be white.
CN201710411068.2A 2017-06-05 2017-06-05 Wide area fire alarm device based on multispectral image analysis Active CN107025753B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710411068.2A CN107025753B (en) 2017-06-05 2017-06-05 Wide area fire alarm device based on multispectral image analysis

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710411068.2A CN107025753B (en) 2017-06-05 2017-06-05 Wide area fire alarm device based on multispectral image analysis

Publications (2)

Publication Number Publication Date
CN107025753A CN107025753A (en) 2017-08-08
CN107025753B true CN107025753B (en) 2020-02-04

Family

ID=59529588

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710411068.2A Active CN107025753B (en) 2017-06-05 2017-06-05 Wide area fire alarm device based on multispectral image analysis

Country Status (1)

Country Link
CN (1) CN107025753B (en)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107577997A (en) * 2017-08-21 2018-01-12 国家电网公司 The discrimination method that mountain fire is invaded in a kind of electric transmission line channel
CN108922098A (en) * 2018-05-04 2018-11-30 国网山西省电力公司电力科学研究院 A kind of forest fire monitoring system and method based on infrared guidance and radar detection
CN108898782B (en) * 2018-07-20 2020-12-11 湖北烽火平安智能消防科技有限公司 Smoke detection method and system for infrared image temperature information identification for tunnel fire prevention
CN110135266A (en) * 2019-04-17 2019-08-16 浙江理工大学 A kind of dual camera electrical fire preventing control method and system based on deep learning
CN111111049A (en) * 2019-12-19 2020-05-08 重庆特斯联智慧科技股份有限公司 Intelligent Internet of things fire fighting device and method
CN113076797B (en) * 2021-02-24 2022-01-18 江苏濠汉信息技术有限公司 Charging station electric vehicle fire alarm method and system based on intelligent video identification
DE102021116957A1 (en) 2021-07-01 2023-01-05 IQ Technologies for Earth and Space GmbH Method and device for the automated early detection of wildfires by means of optical detection of smoke events

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0432680A1 (en) * 1989-12-11 1991-06-19 Fujitsu Limited Monitoring system employing infrared image
CN101673448A (en) * 2009-09-30 2010-03-17 青岛科恩锐通信息技术有限公司 Method and system for detecting forest fire
CN101989373A (en) * 2009-08-04 2011-03-23 中国科学院地理科学与资源研究所 Visible light-thermal infrared based multispectral multi-scale forest fire monitoring method
CN104036611A (en) * 2014-06-24 2014-09-10 北京中恩时代科技有限责任公司 Fire detecting alarm method and detecting alarm apparatus implementing same
CN105046868A (en) * 2015-06-16 2015-11-11 苏州华启智能科技股份有限公司 Fire early warning method based on infrared thermal imager in narrow environment

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0432680A1 (en) * 1989-12-11 1991-06-19 Fujitsu Limited Monitoring system employing infrared image
CN101989373A (en) * 2009-08-04 2011-03-23 中国科学院地理科学与资源研究所 Visible light-thermal infrared based multispectral multi-scale forest fire monitoring method
CN101673448A (en) * 2009-09-30 2010-03-17 青岛科恩锐通信息技术有限公司 Method and system for detecting forest fire
CN104036611A (en) * 2014-06-24 2014-09-10 北京中恩时代科技有限责任公司 Fire detecting alarm method and detecting alarm apparatus implementing same
CN105046868A (en) * 2015-06-16 2015-11-11 苏州华启智能科技股份有限公司 Fire early warning method based on infrared thermal imager in narrow environment

Also Published As

Publication number Publication date
CN107025753A (en) 2017-08-08

Similar Documents

Publication Publication Date Title
CN107025753B (en) Wide area fire alarm device based on multispectral image analysis
KR101353952B1 (en) Method for detecting wildfire smoke using spatiotemporal bag-of-features of smoke and random forest
US10949677B2 (en) Method and system for detecting concealed objects using handheld thermal imager
CN108648400A (en) One kind is based on multispectral transmission line forest fire exploration prior-warning device and method for early warning
CN105575034B (en) A kind of two waveband forest fire protection intelligent monitoring software image processing analysis method
CN108389359B (en) Deep learning-based urban fire alarm method
CN106646651A (en) Fire point detection method
KR101906900B1 (en) Fire detection system using thermovision camera
CN110491066A (en) Forest fire protection monitoring and warning system based on infrared thermal imaging
KR20140127574A (en) Fire detecting system using unmanned aerial vehicle for reducing of fire misinformation
CN108682105B (en) One kind is based on multispectral transmission line forest fire exploration prior-warning device and method for early warning
JP2009201064A (en) Method and apparatus for specifying related region, and method and apparatus for recognizing image
RU2686566C2 (en) Method for detecting and classifying scene events
KR20070028813A (en) Method and system for monitoring forest fire
CN103400463B (en) A kind of forest fires localization method based on two dimensional image and device
KR101224494B1 (en) Video based smoke detection method robust to light conditions
KR20130101873A (en) Monitoring apparatus for forest fire using thermal camera and method thereof
Hossain et al. Wildfire flame and smoke detection using static image features and artificial neural network
Yabuki et al. Development of a cloud detection method from whole-sky color images
KR101679148B1 (en) Detection System of Smoke and Flame using Depth Camera
KR20210040258A (en) A method and apparatus for generating an object classification for an object
KR101366198B1 (en) Image processing method for automatic early smoke signature of forest fire detection based on the gaussian background mixture models and hsl color space analysis
CN102928083A (en) Forest fireproofing infrared thermometer and temperature measurement method thereof
Mazur-Milecka et al. Smart city and fire detection using thermal imaging
CN106166356B (en) Three-in-one fire positioning method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
CP03 Change of name, title or address

Address after: Building 501, Building 5, Huijin Plaza, No. 35 West Fifth Road, Tianjin Pilot Free Trade Zone (Airport Economic Zone), Binhai New Area, Tianjin, 300308

Patentee after: China Shipbuilding Hanguang (Tianjin) Information Technology Co.,Ltd.

Address before: No.501, building 5, Huijin Plaza, 35 West Fifth Road, Airport Economic Zone, Binhai New Area, Tianjin

Patentee before: TIANJIN HGXIANGYUN INFORMATION TECHNOLOGY Co.,Ltd.

CP03 Change of name, title or address