CN107025753A - A kind of wide area fire alarm installation analyzed based on multispectral image - Google Patents
A kind of wide area fire alarm installation analyzed based on multispectral image Download PDFInfo
- Publication number
- CN107025753A CN107025753A CN201710411068.2A CN201710411068A CN107025753A CN 107025753 A CN107025753 A CN 107025753A CN 201710411068 A CN201710411068 A CN 201710411068A CN 107025753 A CN107025753 A CN 107025753A
- Authority
- CN
- China
- Prior art keywords
- pyrotechnics
- fire
- multispectral
- alarm
- priori
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000009434 installation Methods 0.000 title claims abstract description 8
- 238000004458 analytical method Methods 0.000 claims abstract description 18
- 238000001931 thermography Methods 0.000 claims abstract description 17
- 239000000284 extract Substances 0.000 claims description 16
- 230000000007 visual effect Effects 0.000 claims description 15
- 238000000034 method Methods 0.000 claims description 14
- 230000007246 mechanism Effects 0.000 claims description 11
- 238000013507 mapping Methods 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 7
- 238000012544 monitoring process Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 239000000203 mixture Substances 0.000 claims description 6
- 230000000877 morphologic effect Effects 0.000 claims description 6
- 241001269238 Data Species 0.000 claims description 4
- 206010000369 Accident Diseases 0.000 claims description 3
- 238000005498 polishing Methods 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 2
- 238000013459 approach Methods 0.000 abstract description 9
- 238000005286 illumination Methods 0.000 abstract description 8
- 238000001228 spectrum Methods 0.000 abstract description 7
- 238000005516 engineering process Methods 0.000 abstract description 6
- 230000007812 deficiency Effects 0.000 abstract description 4
- 238000001514 detection method Methods 0.000 abstract description 4
- 239000000463 material Substances 0.000 abstract description 4
- 238000010191 image analysis Methods 0.000 abstract description 3
- 238000002474 experimental method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000010422 painting Methods 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 239000002023 wood Substances 0.000 description 1
Classifications
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- 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
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
A kind of wide area fire alarm installation analyzed based on multispectral image of the present invention, integrated use multiple spectrum image analysis technology overcomes the deficiency of single image analytic approach fire alarm;It is of the invention effectively solve the problems, such as that the factors such as the material burnt, background illumination, the intensity of illumination of visible light analysis method cause fail to report, wrong report;The present invention simultaneously also solve thermography analytic approach need detection environment temperature could work, because in graphic images temperature information it is inaccurate and caused by fail to report, report by mistake the problem of.
Description
Technical field
The invention belongs to spectrum analysis field, more particularly to a kind of wide area fire alarm dress analyzed based on multispectral image
Put.
Background technology
Fire alarm in forest either metropolitan area is different from indoor fire alarm, and it needs to detect (monitoring)
Area reaches more than ten even tens square kilometres.Conventional way one kind is to install visible light camera pair in commanding elevation at present
Target area is scanned, and the image scanned is detected into fire using image analysis technology, and (we term it visible ray map analysis
Method) way of this method is " to obtain video image and reference picture ..., carry out first smog and judge in advance ..., it is determined that monitoring
Whether smog generation is had in region;It is determined that having after smog generation ..., then judge whether smog is true smoke;It is defined as true
Whether it is smog caused by fire that smog is determined whether after smog ...;It is defined as smog caused by fire, then further sentences
It whether there is flame in disconnected monitor area, if there is flame in monitor area, it is determined that forest currently has fire." (Shaanxi
A kind of forest fire automatic testing methods of flames of war Industrial Co., Ltd. and system [P] China:CN201611256815.1,
20170426).Another method is to install thermal imaging camera in commanding elevation, is by the temperature information monitoring in analysis diagram picture
No generation fire (we term it thermography analytic approach).The way of this method is " to utilize thermal infrared imager, Video service
Device, transmitting device ..., are provided with the temperature-detecting device being acquired to environment temperature in wood land to be monitored, red
Outer thermal imaging system obtains the ambient temperature value of monitor area by temperature-detecting device.... calculate alarm threshold value ... and (utilize figure
As analytical technology) temperature value ... (if the temperature over-range) alert in computing unit region and upload image ".(mountain
A kind of threshold variable forest fire protection thermal imaging monitoring system [P] China of Dong Shenrong electronics limited company:
CN201620084343.5,2016.11.09)。
All there is respective defect in both approaches:
First, visible light analysis method
This method analysis is visible images, and color, form, texture, area, target are only contained in visible images
The image model characteristic information such as mobile, so for there is the non-fire image such as the cloud of similar features, fog then can not correctly to know
Not, very high fire alarm rate of false alarm can be caused.
The factors such as material, background illumination, wind-force size, lens focus size, the intensity of illumination of burning can be to above-mentioned pattern
Feature produces significant impact, causes to fail to report greatly very much, reports by mistake.
Two, thermography analytic approach
This method needs to detect environment temperature, to set appropriate alarm threshold value, could obtain the correct two-value on pyrotechnics
Image.Otherwise it can produce and fail to report or report by mistake.It is actually this to require very unrealistic, for tens square kilometres of forest easily,
These environment temperature detection devices are installed at all unworkable for metropolitan area fire alarm.
The temperature information in image is mainly used due to thermography analytic approach, the underground heat meeting under ambient temperature very low environment
Cause wrong report.
For the metropolitan area fire alarm that building stand in great numbers, ground small fire can not heat upper space air, so can not
The early stage condition of a fire is found from commanding elevation.
The content of the invention
It is comprehensive it is a primary object of the present invention to provide a kind of wide area fire alarm installation analyzed based on multispectral image
The deficiency of single image analytic approach fire alarm is overcome with multiple spectrum image analysis technology;The present invention effectively solves visible
What the factors such as the material burnt, background illumination, the intensity of illumination of optical analysis were caused fail to report, wrong report problem;The present invention is simultaneously
Also solve thermography analytic approach need detection environment temperature could work, because in graphic images temperature information it is inaccurate make
Into the problem of failing to report, report by mistake.
To achieve the above object, the technical scheme taken of the present invention is:
A kind of wide area fire alarm installation analyzed based on multispectral image, is comprised the following steps:First according to monitoring
Area of woods or metropolitan area size selection commanding elevation, the selection of commanding elevation should follow and can all include fire supervision object
The principle in the visual field;
High tower using the seeds above all manually built or natural mountain top, metropolitan area fire alarm in forest fire accident alarm
Select the top of highest building in metropolitan area;
By T1, the multispectral signal sensor in the front end such as T2 is arranged on commanding elevation, and completes the mark of pitching and orientation angles
It is fixed;
Interchanger N2 is collected to the yuv data of the visible ray detected and infrared thermal imaging, data transfer by Ethernet
Into fire decision analysis server E3, judged by fire decision analysis server E3 analysis, in the event of fire the condition of a disaster
Alarm signal is then produced, while by the multispectral signal sensor T1 in front end, the azimuth information of the feedback such as T2 sends alarm linkage and watched
Mechanism A4 is taken, alarm linkage servo control mechanism A4 then drives warning lamp warning signal to send sound and light alarm, while driving corresponding fire compartment
Extinguishing device starts fire-fighting work;
Alarm linkage servo control mechanism A4 can also export 4 tunnels normal in addition to the integrated extinguishing device in the driving present invention
The switching value opened and the character string comprising Ti longitudes and latitudes and pitching azimuth information are used for other fire control platforms.
Further, server E3 fire resolution principle is as follows:
Fire determining server E3 receives the YUV numbers that visible light camera is produced in the multispectral signal sensor Ti in front end
According to rear,
Step 1.1.YUV data are converted into RGB data, and then RGB data is converted into HSV data, and then it is empty to extract HSV
Between color characteristic;
The RGB data that step 1.1 is obtained is changed into gray-scale map by step 2.1;
Step 3.1, by gray-scale map binaryzation, is converted into binary map according to priori threshold value;Priori threshold value in this step comes from
In the experimental data of the present inventor;
The binary map that step 4.1 is obtained using step 3.1 extracts the morphological feature of pyrotechnics, including circularity feature, wedge angle
Feature, white area area change;
The binary map that step 5.1 is obtained using step 3.1 extracts the motion feature of pyrotechnics, including center of mass motion feature, jump
Dynamic frequency feature;
Step 1.1, step 4.1, step 5.1 are obtained pyrotechnics characteristic value composition of vector α l by step 6.1;
Step 7.1 calculation procedure 6.1 obtain vectorial α l and pyrotechnics priori features vector β l apart from Dl, if Dl is small
Then think to find doubtful pyrotechnics in visual field in priori threshold value dl and send vector α l to " multispectral characteristic overall merit " step.This
The experimental data of priori features vector β l, priori threshold value dl both from inventor of step pyrotechnics.
At the same time, fire determining server E3 also receives the thermal imaging shooting in the multispectral signal sensor Ti in front end
The yuv data of machine, server E3 synchronously carries out the work of following steps:
Step 1.2 extracts the Y channel datas of yuv data;
Step 2.2 composes selected threshold according to temperature and grey scale mapping, and the image binaryzation that step 1.2 is obtained obtains two
Value figure;
The binary map that step 3.2 is obtained using step 2.2 extracts the morphological feature of pyrotechnics, including circularity feature, wedge angle
Feature, white area area change;
The binary map that step 4.2 is obtained using step 2.2 extracts the motion feature of pyrotechnics, including center of mass motion feature, jump
Dynamic frequency feature;
Step 3.2, step 4.2 are obtained pyrotechnics characteristic value composition of vector α r by step 5.2;
Step 6.2 calculation procedure 5.2 obtain vectorial α r and pyrotechnics priori features vector β r apart from Dr, if Dr is small
Then think to find doubtful pyrotechnics in visual field in priori threshold value dr and send vector α r to " multispectral characteristic overall merit " step.This
The experimental data of priori features vector β r, priori threshold value dr both from inventor of step pyrotechnics;
Step 7. multispectral characteristic overall merit.α l and α r are synthesized into a new vectorial α;α r do not have face in this step
Color characteristic component, in order to be able to be synthesized with α l, our polishing α r color characteristic component is simultaneously all set to 0;Calculate vector α and pyrotechnics
Multispectral priori features vector β apart from D, discovery pyrotechnics visual field in is thought if D is less than priori threshold value d;This step pyrotechnics
The experimental data of priori features vector β, priori threshold value d both from inventor;
If step 8. pyrotechnics occurs in visual field, alarm signal is produced, while the multispectral signal sensor Ti in front end is anti-
The azimuth information of feedback is transmitted together gives alarm linkage servo control mechanism A4.
Further, the binary map that this algorithm is referred to sets prospect to be white.
Compared with prior art, the present invention has the advantages that:Without installing temperature detection in forest or metropolitan area
Device, the analysis of integrated use visible images and infrared thermal imaging image analytical method, assist a ruler in governing a country mutually, complement each other, effectively solve
A variety of deficiencies of single method, reduce forest or metropolitan area fire alarm system cost and difficulty of construction, improve fire report
Alert accuracy rate.
Brief description of the drawings
Fig. 1 is the multispectral signal sensor pictorial diagram in middle front end of the invention;
Fig. 2 is building-block of logic of the present invention.
Fig. 3 is fire decision analysis server E3 fire resolution principle figures.
In figure, P1 is visible light camera;P2 is thermal imaging camera;P3 is azimuth information feedback turntable.
Embodiment
To be easy to understand the technical means, the inventive features, the objects and the advantages of the present invention, with reference to
Embodiment, is expanded on further the present invention.
In figure:
Embodiment:Commanding elevation is selected according to the area of woods of monitoring or metropolitan area size first, the selection of commanding elevation should
Following can all include fire supervision object the principle in the visual field.It is general in forest fire accident alarm to use being higher than for manually building
The top of highest building in the high tower of all seeds or natural mountain top, metropolitan area fire alarm selection metropolitan area.By T1, the front end such as T2
Multispectral signal sensor is arranged on commanding elevation, and completes pitching and the demarcation of orientation angles.By Ethernet by interchanger
N2 collects the yuv data of the visible ray detected and infrared thermal imaging, and data transfer is led into fire decision analysis server E3
The analysis for crossing fire decision analysis server E3 judges, alarm signal is then produced in the event of fire the condition of a disaster, while front end is more
The azimuth information of the feedbacks such as spectral signal detector T1, T2 sends alarm linkage servo control mechanism A4, alarm linkage servo control mechanism A4
Then driving warning lamp warning signal sends sound and light alarm, while driving the extinguishing device of corresponding fire compartment to start fire-fighting work.Alarm connection
Dynamic servo control mechanism A4 can also export the normally opened switching value in 4 tunnels and bag in addition to the integrated extinguishing device in the driving present invention
The character string of longitude and latitude containing Ti and pitching azimuth information is used for other fire control platforms.
E3 fire resolution principle is as follows:
Fire determining server E3 receives the YUV numbers that visible light camera is produced in the multispectral signal sensor Ti in front end
According to rear,
Step 1.1YUV data are converted into RGB data, and then RGB data is converted into HSV data, and then it is empty to extract HSV
Between color characteristic.
The RGB data that step 1.1 is obtained is changed into gray-scale map by step 2.1.
Step 3.1, by gray-scale map binaryzation, is converted into binary map according to priori threshold value
What the priori threshold value in this step came from the present inventor realizes data.
The binary map that step 4.1 is obtained using step 3.1 extracts the morphological feature of pyrotechnics, including circularity feature, wedge angle
Feature, white area area change.
The binary map that step 5.1 is obtained using step 3.1 extracts the motion feature of pyrotechnics, including center of mass motion feature, jump
Dynamic frequency feature.
Step 1.1, step 4.1, step 5.1 are obtained pyrotechnics characteristic value composition of vector α l by step 6.1.
Step 7.1 calculation procedure 6.1 obtain vectorial α l and pyrotechnics priori features vector β l apart from Dl, if Dl is small
Then think to find doubtful pyrotechnics in visual field in priori threshold value dl and send vector α l to " multispectral characteristic overall merit " step.This
The experiment of priori features vector β l, priori threshold value dl both from inventor of step pyrotechnics.
At the same time, fire determining server E3 also receives the thermal imaging shooting in the multispectral signal sensor Ti in front end
The yuv data of machine, E3 synchronously carries out the work of following steps:
Step 1.2 extracts the Y channel datas of yuv data.
Step 2.2 composes selected threshold according to temperature and grey scale mapping, and the image binaryzation that step 1.2 is obtained obtains two
Value figure;
Temperature in this step composes the experiment for coming from the present inventor with grey scale mapping.(temperature and painting that grey scale mapping is composed
System is with using the novelty and creative concentrated reflection for being the present invention.Mapping spectrum, which solves thermography analytic approach, needs measurement
The deficiency of ambient temperature.When choosing Binary Sketch of Grey Scale Image threshold value, pyrotechnics temperature correspondence can be directly selected from mapping spectrum
Gray scale, without measuring environment temperature.Due to the non-burning hot source such as people, animal, automobile temperature also this mapping spectrum in, choose
Their gray value can be directly avoided during Binary Sketch of Grey Scale Image threshold value, so can directly solve " one using this mapping spectrum
Plant the interference source screen method for forest fire protection " problem encountered.
The binary map that step 3.2 is obtained using step 2.2 extracts the morphological feature of pyrotechnics, including circularity feature, wedge angle
Feature, white area area change.
The binary map that step 4.2 is obtained using step 2.2 extracts the motion feature of pyrotechnics, including center of mass motion feature, jump
Dynamic frequency feature.
Step 3.2, step 4.2 are obtained pyrotechnics characteristic value composition of vector α r by step 5.2.
Step 6.2 calculation procedure 5.2 obtain vectorial α r and pyrotechnics priori features vector β r apart from Dr, if Dr is small
Then think to find doubtful pyrotechnics in visual field in priori threshold value dr and send vector α r to " multispectral characteristic overall merit " step.This
The experiment of priori features vector β r, priori threshold value dr both from inventor of step pyrotechnics.
Step 7 multispectral characteristic overall merit.α l and α r are synthesized into a new vectorial α.α r do not have face in this step
Color characteristic component, in order to be able to be synthesized with α l, our polishing α r color characteristic component is simultaneously all set to 0.
The method shields the influence of the material due to burning, background illumination, intensity of illumination factor to pyrotechnics feature, realizes
The function of the pyrotechnics feature of visible ray figure is confirmed by the pyrotechnics feature of thermograph, the discrimination of pyrotechnics is improved.
Calculate vector α and pyrotechnics multispectral priori features vector β apart from D, if D less than thinking if priori threshold value d
Pyrotechnics is found in visual field.The experimental data of priori features vector β, priori threshold value d both from inventor of this step pyrotechnics.
If step 8 pyrotechnics occurs in visual field, alarm signal is produced, while the multispectral signal sensor Ti in front end is fed back
Azimuth information transmit give alarm linkage servo control mechanism A4 together.
Wherein, the binary map that this algorithm is referred to sets prospect to be white.
Temperature used in the present invention and Gray Spectrum are that temperature is 28 DEG C, and wavelength is 9.96678E-06M, and gray scale is 9044;
Temperature is 29 DEG C, and wavelength is 9.93377E-06, and gray scale is 9367;Temperature is 30 DEG C, and wavelength is 9.90099E-06, and gray scale is
9690;Temperature is 31 DEG C, and wavelength is 9.86842E-06, and temperature that gray scale is 10013 ... is 726 DEG C, and wavelength is 3.003E-06,
Gray scale is 234498.
The general principle and principal character and advantages of the present invention of the present invention has been shown and described above.The technology of the industry
Personnel are it should be appreciated that the present invention is not limited to the above embodiments, and the simply explanation described in above-described embodiment and specification is originally
The principle of invention, without departing from the spirit and scope of the present invention, various changes and modifications of the present invention are possible, these changes
Change and improvement all fall within the protetion scope of the claimed invention.The claimed scope of the invention by appended claims and its
Equivalent thereof.
Claims (3)
1. a kind of wide area fire alarm installation analyzed based on multispectral image, it is characterised in that:Comprise the following steps:Root first
Commanding elevation is selected according to the area of woods or metropolitan area size of monitoring, the selection of commanding elevation should be followed can be by fire supervision object
All include the principle in the visual field;
High tower using the seeds above all manually built or natural mountain top, the selection of metropolitan area fire alarm in forest fire accident alarm
The top of highest building in metropolitan area;
By T1, the multispectral signal sensor in the front end such as T2 is arranged on commanding elevation, and completes pitching and the demarcation of orientation angles;
Interchanger N2 is collected to the yuv data of the visible ray detected and infrared thermal imaging, data transfer to fire by Ethernet
In calamity decision analysis server E3, judged by fire decision analysis server E3 analysis, then produced in the event of fire the condition of a disaster
Raw alarm signal, while by the multispectral signal sensor T1 in front end, the azimuth information of the feedback such as T2 sends alarm linkage servo
Structure A4, alarm linkage servo control mechanism A4 then drives warning lamp warning signal to send sound and light alarm, while driving the fire extinguishing of corresponding fire compartment
Device starts fire-fighting work;
Alarm linkage servo control mechanism A4 can also export 4 tunnels normally opened in addition to the integrated extinguishing device in the driving present invention
Switching value and character string comprising Ti longitudes and latitudes and pitching azimuth information are used for other fire control platforms.
2. a kind of wide area fire alarm installation analyzed based on multispectral image according to claim 1, it is characterised in that:
Server E3 fire resolution principle is as follows:
Fire determining server E3 receives the yuv data that visible light camera is produced in the multispectral signal sensor Ti in front end
Afterwards,
Step 1.1.YUV data are converted into RGB data, and then RGB data is converted into HSV data, and then extract HSV space
Color characteristic;
The RGB data that step 1.1 is obtained is changed into gray-scale map by step 2.1;
Step 3.1, by gray-scale map binaryzation, is converted into binary map according to priori threshold value;Priori threshold value in this step comes from this
The experimental data of inventor;
The binary map that step 4.1 is obtained using step 3.1 extracts the morphological feature of pyrotechnics, including circularity feature, Sharp features,
White area area change;
The binary map that step 5.1 is obtained using step 3.1 extracts the motion feature of pyrotechnics, including center of mass motion feature, bounce frequency
Rate feature;
Step 1.1, step 4.1, step 5.1 are obtained pyrotechnics characteristic value composition of vector α l by step 6.1;
Vectorial α l that step 7.1 calculation procedure 6.1 the is obtained and priori features vector β l of pyrotechnics apart from Dl, if Dl is less than elder generation
Threshold value dl is tested then to think to find doubtful pyrotechnics in visual field and send vector α l to " multispectral characteristic overall merit " step.This step
Priori features vector the β l, priori threshold value d of pyrotechnicslBoth from the experimental data of inventor.
At the same time, fire determining server E3 also receives the thermal imaging camera in the multispectral signal sensor Ti in front end
Yuv data, server E3 synchronously carries out the work of following steps:
Step 1.2 extracts the Y channel datas of yuv data;
Step 2.2 composes selected threshold according to temperature and grey scale mapping, and the image binaryzation that step 1.2 is obtained obtains binary map;
The binary map that step 3.2 is obtained using step 2.2 extracts the morphological feature of pyrotechnics, including circularity feature, Sharp features,
White area area change;
The binary map that step 4.2 is obtained using step 2.2 extracts the motion feature of pyrotechnics, including center of mass motion feature, bounce frequency
Rate feature;
Step 3.2, step 4.2 are obtained pyrotechnics characteristic value composition of vector α r by step 5.2;
Vectorial α r that step 6.2 calculation procedure 5.2 the is obtained and priori features vector β r of pyrotechnics apart from Dr, if Dr is less than elder generation
Threshold value dr is tested then to think to find doubtful pyrotechnics in visual field and send vector α r to " multispectral characteristic overall merit " step.This step
The experimental data of priori features vector β r, priori threshold value dr both from inventor of pyrotechnics;
Step 7. multispectral characteristic overall merit.α l and α r are synthesized into a new vectorial α;α r do not have color special in this step
Component is levied, in order to be able to be synthesized with α l, our polishing α r color characteristic component is simultaneously all set to 0;Calculate the light more of vector α and pyrotechnics
Compose priori features vector β apart from D, discovery pyrotechnics in visual field is thought if D is less than priori threshold value d;The elder generation of this step pyrotechnics
Test characteristic vector β, experimental datas of the priori threshold value d both from inventor;
If step 8. pyrotechnics occurs in visual field, alarm signal is produced, while the multispectral signal sensor Ti in front end is fed back
Azimuth information is transmitted together gives alarm linkage servo control mechanism A4.
3. a kind of wide area fire alarm installation analyzed based on multispectral image according to claim 2, it is characterised in that:
The binary map that this algorithm is extracted sets prospect to be white.
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 true CN107025753A (en) | 2017-08-08 |
CN107025753B 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) |
Cited By (7)
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 |
CN108898782A (en) * | 2018-07-20 | 2018-11-27 | 武汉理工光科股份有限公司 | The smoke detection method and system that infrared image temperature information for tunnel fire proofing identifies |
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 |
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 |
CN113076797A (en) * | 2021-02-24 | 2021-07-06 | 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)
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 |
-
2017
- 2017-06-05 CN CN201710411068.2A patent/CN107025753B/en active Active
Patent Citations (5)
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 |
Cited By (7)
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 |
CN108898782A (en) * | 2018-07-20 | 2018-11-27 | 武汉理工光科股份有限公司 | The smoke detection method and system that infrared image temperature information for tunnel fire proofing identifies |
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 |
CN113076797A (en) * | 2021-02-24 | 2021-07-06 | 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 |
Also Published As
Publication number | Publication date |
---|---|
CN107025753B (en) | 2020-02-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107025753A (en) | A kind of wide area fire alarm installation analyzed based on multispectral image | |
CN106646651A (en) | Fire point detection method | |
CN100538757C (en) | Fire-disaster monitoring device based on omnibearing vision sensor | |
AU2012221159B2 (en) | A surveillance system and a method for detecting a foreign object, debris, or damage in an airfield | |
CN104751593B (en) | Method and system for fire detection, warning, positioning and extinguishing | |
CN103400463B (en) | A kind of forest fires localization method based on two dimensional image and device | |
CN105575034B (en) | A kind of two waveband forest fire protection intelligent monitoring software image processing analysis method | |
US20130135470A1 (en) | System and method for detecting adverse atmospheric conditions ahead of an aircraft | |
CN104732700B (en) | Based on the fire alarm system taken photo by plane in the air | |
CN110491066A (en) | Forest fire protection monitoring and warning system based on infrared thermal imaging | |
CN101577033A (en) | Multiband infrared image-type fire detecting system and fire alarm system thereof | |
CN108205862A (en) | Transmission line forest fire guard system | |
CN101334924A (en) | Fire hazard probe system and its fire hazard detection method | |
CN102112867A (en) | Particle detection | |
CN101650866A (en) | Fire detecting system applied to unmanned helicopter and fire detecting method thereof | |
CN108682105B (en) | One kind is based on multispectral transmission line forest fire exploration prior-warning device and method for early warning | |
CN108389359A (en) | A kind of Urban Fires alarm method based on deep learning | |
CN104634784B (en) | atmospheric visibility monitoring method and device | |
CN203338502U (en) | IOT (Internet of Things) monitoring and early-warning command system for forest fire prevention and ecological prevention | |
CN113393486A (en) | Abnormal event monitoring method, intelligent monitoring terminal and system | |
CN102928083A (en) | Forest fireproofing infrared thermometer and temperature measurement method thereof | |
Turner et al. | Geotechnical characterization of underground mine excavations from UAV-captured photogrammetric & thermal imagery | |
CN111539264A (en) | Ship flame detection positioning system and detection positioning method | |
CN209708270U (en) | A kind of forest fire prevention and control monitoring system convenient for safeguarding | |
KR20070115412A (en) | Fire alarm system for recording image and method of fire alarm thereof |
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 |