CN111354152A - Flame detecting and positioning system - Google Patents

Flame detecting and positioning system Download PDF

Info

Publication number
CN111354152A
CN111354152A CN201811580910.6A CN201811580910A CN111354152A CN 111354152 A CN111354152 A CN 111354152A CN 201811580910 A CN201811580910 A CN 201811580910A CN 111354152 A CN111354152 A CN 111354152A
Authority
CN
China
Prior art keywords
camera
module
alarm
infrared
path
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.)
Pending
Application number
CN201811580910.6A
Other languages
Chinese (zh)
Inventor
孟祥杰
李华锋
刘思庆
廉黎
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.)
Beijing Huahang Radio Measurement Research Institute
Original Assignee
Beijing Huahang Radio Measurement Research Institute
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 Beijing Huahang Radio Measurement Research Institute filed Critical Beijing Huahang Radio Measurement Research Institute
Priority to CN201811580910.6A priority Critical patent/CN111354152A/en
Publication of CN111354152A publication Critical patent/CN111354152A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • 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
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01JMEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J5/00Radiation pyrometry, e.g. infrared or optical thermometry
    • G01J5/0014Radiation pyrometry, e.g. infrared or optical thermometry for sensing the radiation from gases, flames
    • G01J5/0018Flames, plasma or welding

Abstract

A flame detection and positioning system comprises two near infrared cameras and a color/black and white camera; one path is used for monitoring visible light images, and the other path is additionally provided with a near-infrared coating film to form a near-infrared camera; two paths of acquisition modules, wherein one path adopts visible light images of a color/black-and-white camera, and the other path acquires images of a near-infrared coated camera; the signal processing and control module adopts an embedded processor, supports two paths of video image input and supports the connection with a control host through a communication module; the video image transmission to the regional alarm monitoring system is supported by utilizing the network through the communication module; debugging through a debugging interface is supported; when a fire disaster occurs, the alarm signal is transmitted to the area alarm monitoring system through the communication module, alarm display is carried out in the area alarm monitoring system, and fire alarm information is reset. The invention solves the problem that the traditional video monitoring and fire detection are separated and can not be reused.

Description

Flame detecting and positioning system
Technical Field
The invention belongs to the field of fire detection and positioning, and particularly relates to a fire detection and positioning system based on a combined sensor and an embedded platform framework.
Background
At present, in the aspect of flame detection, a double-visible-light-camera working system and a visible-light combined infrared temperature measurement multiband composite detection working system are more used for domestic image type fire detectors. The visible light imaging resolution is high, the detail resolution is good, and the advantage of scene imaging is obvious. The method has the disadvantages that when the artificial light source such as lamplight and the like and the flame light source are imaged at the same time, the lamplight interferes with the flame, cannot be distinguished visually, and can only be distinguished from the aspects of light source appearance, shaking frequency and the like through an identification algorithm.
A large number of test results show that: when a fire is burnt, the invisible light radiation of the infrared band (wavelength of 950 nm-2000 nm) of the flame has obvious identification characteristics, and in order to remove an interference light source in fire detection, a filter (usually 1000nm) of a specific band can be additionally arranged in an optical system, so that the difficulty of an image identification algorithm can be effectively reduced. The infrared detector has the defects that when the flame light in a scene can only be imaged, the scene resolution is low, the information is not rich enough, the flame positioning precision is reduced, and meanwhile, the price of the detector in the infrared band is more than three times that of the detector in the visible light band, and is generally more than three times that of the detector in the infrared band.
Disclosure of Invention
Aiming at the problems, the invention provides a flame detection and positioning system, which solves the problem that the traditional video monitoring and fire detection separation can not be reused, and realizes video monitoring and a fire detection and positioning system with high accuracy, high reliability and strong robustness.
A flame detection and positioning system comprises a camera module, an image acquisition module, a hardware module, a debugging interface, a communication module, an area alarm monitoring system and an alarm display and reset device;
the camera module comprises two near infrared cameras and color/black and white cameras with the same performance; one path is used for monitoring visible light images, and the other path is additionally provided with a near-infrared coating film to form a near-infrared camera; the image acquisition module comprises 2 paths of AR0130 acquisition modules, wherein one path of the AR0130 acquisition modules adopts visible light images of a color/black-and-white camera, the other path of the AR0130 acquisition modules collects images of a near-infrared coating camera, h.264 code stream is output by the camera, and the resolution ratio is 1280 x 720; the hardware module comprises a signal processing and control module and an interface I/O module, the signal processing and control module adopts an embedded processor, supports two paths of video image input and supports the connection of a regional alarm monitoring system through a communication module; the video image transmission to the regional alarm monitoring system is supported by utilizing the network through the communication module; debugging through a debugging interface is supported; when a fire disaster occurs, the alarm signal is transmitted to the area alarm monitoring system through the communication module, the alarm display and reset device carries out alarm display and carries out fire alarm information reset.
Furthermore, the wave band of the two color/black-and-white cameras with the same performance is 360-1100 nm, a near-infrared coating film is additionally arranged to form the near-infrared camera, and the light-transmitting wave band is 850-1100 mm.
Further, the LED lamp also comprises a shield, an LED indicator light, a guard plate and an L-shaped bracket; the protection plate is L-shaped, an opening which is matched with the camera module is formed in the protection plate, the protection plate is sleeved on the camera module and fixedly connected with the L-shaped support; the Led pilot lamps divide into 3, fix on the backplate, and the color is green, red, yellow, and green is the circular telegram state and instructs, and red is alarm state and instructs, and yellow is the fault condition.
The invention adopts the film-coated near-infrared filter and the visible light high-definition camera, combines the high-performance embedded platform framework, realizes the flame detection and positioning system design of the combined sensor and the embedded platform framework, solves the problem that the traditional video monitoring and fire detection are separated and can not be reused, and realizes the video monitoring and the fire detection, positioning and alarming with high accuracy, high reliability and strong robustness. The system has high precision, high reliability and strong anti-interference capability, and is suitable for fire monitoring occasions such as tunnels.
Drawings
FIG. 1 is a block diagram of the present invention;
FIG. 2 is a schematic composition of the present invention;
FIG. 3 is a block diagram of the fire detection and location process of the present invention.
Detailed Description
The invention is further described with reference to the accompanying drawings and real-time examples.
A flame detection and location system, as shown in FIG. 1, in this embodiment comprises: the system comprises a near infrared camera, a color/black and white camera, a coated near infrared filter, an image acquisition module, a signal processing and control module, an interface I/O module, a debugging interface, a communication module, an area alarm monitoring system and an alarm display and reset device.
The imaging system adopts two images of a broadband 360-1100 nm color/black and white camera with the same performance, the two images comprise visible light and partial near-infrared bands, one image is used for monitoring the visible light image, the other image is additionally provided with a near-infrared coating to form a near-infrared coating camera, the light transmitting band is 850-1100 mm, the visible light band is prevented from being transmitted, and flame target detection is carried out only by using the near-infrared band generated by flame.
The image acquisition module selects 2 paths of AR0130 acquisition modules and comprises cameras, wherein one path of the image acquisition module adopts visible light images, and the other path of the image acquisition module acquires images of the near-infrared coating camera. The output of the camera is h.264 code stream, and the resolution is 1280 × 720.
The signal processing and control module adopts an embedded processor, selects a DM8127 series platform of Texas instruments company, supports two paths of video image input, and supports the connection of an area alarm monitoring system through a communication module; supporting the transmission of video images by a communication module through a network; and debugging through a debugging interface is supported. When a fire disaster occurs, the alarm signal is transmitted to the area alarm monitoring system through the communication module, the alarm display and reset device carries out alarm display and carries out fire alarm information reset.
A flame detection and positioning system, the concrete shape and connection relation of which are shown in figure 2, comprises a shield 1, an LED indicator light 2, a guard plate 3, a camera module 4, a hardware module 5 and an L-shaped bracket 6; the hardware module 5 comprises a signal processing and control module and an interface I/O module; the camera module 4 comprises a near infrared camera and a color/black and white camera; the L-shaped support 6 is fixed in a cuboid cavity of the shield 1 through six fastening screws, the hardware module 5 is fixed on the L-shaped support 6, an opening which is adaptive to the shape of the camera module 4 is arranged on the front end face of the L-shaped support 6, the camera module 4 is fixed on the front end face of the L-shaped support 6 through a flange, the guard plate 3 is L-shaped, an opening which is adaptive to the camera module 4 is arranged on the guard plate 3, and the guard plate 3 is sleeved on the camera module 4 and fixedly connected with the L-shaped support 6; the Led indicating lamps 2 are divided into 3, are fixed on the guard plate 3, and are green, red and yellow in color, wherein the green indicates the power-on state, the red indicates the alarm state, and the yellow indicates the fault state.
A method of flame detection and localization, as shown in fig. 3, comprising the steps of:
s1, initializing system hardware and software, uploading a real-time visible light video image to an area alarm monitoring system for monitoring, and then acquiring a frame of visible light image and a frame of near-infrared image by a control module.
And S2, detecting by fusing the image acquired by the near-infrared camera with the visible light image, and if a suspected fire is found in the near-infrared image, extracting color characteristic information of flame from the corresponding visible light image, and jointly fusing to judge whether the fire occurs. :
s2.1, after a fire candidate area is detected in one frame of near-infrared image, the area (R) of flame is extracted from the visible light imagek) Aspect RatiokSimilar to roundness CkArea change rate GkInformation, and comprehensively judging when area (R)k) Take a value of [ area (R)k)th_min,area(Rk)th_max]In between, area (R)k)th_minArea (R) as a minimum threshold for flame areak)th_maxAspect Ratio being the maximum threshold for the flame areakTake value in [ Ratioth_min,Ratioth_max]Ratio ofth_minFor a set aspect Ratio minimum threshold, Ratioth_maxAnd judging the flame target as the maximum threshold value of the set length-width ratio, and judging the flame target as the interference area if the range is exceeded.
S2.2 calculating the circularity characteristic C of the flamek
The shape of the early flame is extremely irregular, most of the fixed interference sources, such as cigarette ends, incandescent lamps and the like, have regular outlines, and the circularity is a characteristic quantity for calculating the shape complexity of an object or an area and is defined as follows
Figure BDA0001917895820000041
C in formula (1)k、Ak、PkRespectively, the circularity, area and perimeter of the kth suspected flame target, and N is the number of suspected flame targets. The closer the suspected flame target shape is to a circle, CkThe larger and conversely the more complex the shape CkThe smaller, CkIs between 0 and 1. Thus, a threshold value C is set0When C is presentk>C0When the suspected flame target contour is more regular, the suspected flame target contour is regarded as a non-flame target; otherwise, Ck<C0And when the suspected flame target is irregular in contour, the suspected flame target conforms to other characteristics of the flame, and the target is judged to be the flame.
S2.3 calculating area growth rate feature Gk
Calculating the area of the suspected flame target extracted from the images at adjacent moments, calculating the ratio of the areas, and using the area growth rate G of the suspected flame targetkAs a criterion. G can be calculated by using equation (2)k
Figure BDA0001917895820000042
In the formula (2), RkThe kth suspected flame target area, area (R)k)t、area(Rk)t0T, t respectively0The area of the suspected flame target area at the moment. Setting a threshold value G0When G isk>G0When the suspected flame target is in a high-intensity state, the suspected flame target is considered to be a flame target; otherwise, Gk<G0And judging that the target is not the flame if the area of the suspected flame target is not changed violently and the suspected flame target does not accord with other characteristics of the flame.
S3, if the fire is judged to be a fire in S2.1, S2.2 and S2.3, alarming, sending fire alarm information to an area alarm monitoring system, and identifying flame information in the visible light video image by using a rectangular frame;
s4, after reporting information, waiting for a reset signal of the regional alarm monitoring system, and after receiving the signal, removing alarm information and removing a rectangular mark window of the visible light video image; and if the fire is not found, continuously processing a new frame of image and sending the real-time visible light video to the area alarm monitoring system all the time.
The invention adopts a coated near-infrared filter and a visible light high-definition camera to realize a combined sensor, acquires images of monitoring videos through the coated near-infrared camera and the visible light camera, comprehensively utilizes the characteristics of flames in a near-infrared wave band and a visible light wave band to detect fire, adopts a communication module to transmit detection results to an area alarm monitoring system, and utilizes an Ethernet module to transmit video images to the area alarm monitoring system. The method combines a digital image intelligent analysis technology, a combined sensor construction technology and an embedded platform development technology. Video monitoring and image fire alarm and positioning are realized, and the effect is ideal through practical verification.

Claims (3)

1. A flame detection and positioning system comprises a camera module (4), an image acquisition module, a hardware module (5), a debugging interface, a communication module, an area alarm monitoring system and an alarm display and reset device; the camera module (4) comprises a near infrared camera and a color/black and white camera with the same performance; one path is used for monitoring visible light images, and the other path is additionally provided with a near-infrared coating film to form a near-infrared camera; the image acquisition module comprises 2 paths of AR0130 acquisition modules, wherein one path of the AR0130 acquisition modules adopts visible light images of a color/black-and-white camera, the other path of the AR0130 acquisition modules collects images of a near-infrared coating camera, h.264 code stream is output by the camera, and the resolution ratio is 1280 x 720; the hardware module (5) comprises a signal processing and control module and an interface I/O module, the signal processing and control module adopts an embedded processor, supports two paths of video image input and supports the connection of a regional alarm monitoring system through a communication module; the video image transmission to the regional alarm monitoring system is supported by utilizing the network through the communication module; debugging through a debugging interface is supported; when a fire disaster occurs, the alarm signal is transmitted to the area alarm monitoring system through the communication module, the alarm display and reset device carries out alarm display and carries out fire alarm information reset.
2. The flame detection and positioning system of claim 1, wherein the two color/black-and-white cameras with the same performance have a wavelength of 360nm to 1100nm, and are provided with near-infrared coating films to form a near-infrared camera, and the light transmission wavelength band is 850 mm to 1100 mm.
3. The flame detection and localization system of claim 1, further comprising a shroud (1), an Led indicator light (2), a shield plate (3), an L-bracket (6); the L-shaped support (6) is fixed in a cuboid cavity of the protective cover (1), the hardware module (5) is fixed on the L-shaped support (6), an opening adaptive to the shape of the camera module (4) is arranged on the front end face of the L-shaped support (6), the camera module (4) is fixed on the front end face of the L-shaped support (6), the protective plate (3) is L-shaped, an opening adaptive to the camera module (4) is arranged on the protective plate, and the protective plate (3) is sleeved on the camera module (4) and fixedly connected with the L-shaped support (6); the Led indicating lamps (2) are divided into 3 parts and fixed on the guard plate (3), the colors are green, red and yellow, the green part is used for indicating the power-on state, the red part is used for indicating the alarm state, and the yellow part is used for indicating the fault state.
CN201811580910.6A 2018-12-24 2018-12-24 Flame detecting and positioning system Pending CN111354152A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811580910.6A CN111354152A (en) 2018-12-24 2018-12-24 Flame detecting and positioning system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811580910.6A CN111354152A (en) 2018-12-24 2018-12-24 Flame detecting and positioning system

Publications (1)

Publication Number Publication Date
CN111354152A true CN111354152A (en) 2020-06-30

Family

ID=71195468

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811580910.6A Pending CN111354152A (en) 2018-12-24 2018-12-24 Flame detecting and positioning system

Country Status (1)

Country Link
CN (1) CN111354152A (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111986437A (en) * 2020-07-02 2020-11-24 湖南翰坤实业有限公司 Fire source detection and positioning method and system
CN111985489A (en) * 2020-09-01 2020-11-24 安徽炬视科技有限公司 Night light and flame classification discrimination algorithm combining target tracking and motion analysis
CN112129414A (en) * 2020-09-22 2020-12-25 苏州热工研究院有限公司 Multispectral image type fire detector
CN112699970A (en) * 2021-02-26 2021-04-23 江苏昂内斯电力科技股份有限公司 Multi-feature information fused flame detection system and method thereof
CN113160513A (en) * 2021-04-19 2021-07-23 杭州舜程科技有限公司 Flame detection device based on multisensor
CN116913033A (en) * 2023-05-29 2023-10-20 东莞市众可智能科技有限公司 Fire big data remote detection and early warning system

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0458938A1 (en) * 1989-12-20 1991-12-04 Selenia Ind Elettroniche Fire fighting system mainly conceived to safeguard forests.
DE20022869U1 (en) * 2000-09-08 2002-06-06 Sirena Sicherheitssysteme Proj Fire detection system for detecting visible and hidden sources of fire
CN101339687A (en) * 2008-08-15 2009-01-07 南京视威电子有限公司 Integral network intelligence safety monitoring alarming method and device
CN101609589A (en) * 2008-06-17 2009-12-23 侯荣琴 Multi-frequency image fire detection system
CN203722695U (en) * 2013-12-10 2014-07-16 广州供电局有限公司 Double-vision holder camera
CN107123227A (en) * 2017-07-06 2017-09-01 合肥科大立安安全技术股份有限公司 A kind of embedded image flame detector and its recognition methods based on two waveband
CN208227139U (en) * 2018-03-23 2018-12-11 广州广电运通金融电子股份有限公司 Binocular camera and picture pick-up device

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0458938A1 (en) * 1989-12-20 1991-12-04 Selenia Ind Elettroniche Fire fighting system mainly conceived to safeguard forests.
DE20022869U1 (en) * 2000-09-08 2002-06-06 Sirena Sicherheitssysteme Proj Fire detection system for detecting visible and hidden sources of fire
CN101609589A (en) * 2008-06-17 2009-12-23 侯荣琴 Multi-frequency image fire detection system
CN101339687A (en) * 2008-08-15 2009-01-07 南京视威电子有限公司 Integral network intelligence safety monitoring alarming method and device
CN203722695U (en) * 2013-12-10 2014-07-16 广州供电局有限公司 Double-vision holder camera
CN107123227A (en) * 2017-07-06 2017-09-01 合肥科大立安安全技术股份有限公司 A kind of embedded image flame detector and its recognition methods based on two waveband
CN208227139U (en) * 2018-03-23 2018-12-11 广州广电运通金融电子股份有限公司 Binocular camera and picture pick-up device

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111986437A (en) * 2020-07-02 2020-11-24 湖南翰坤实业有限公司 Fire source detection and positioning method and system
CN111985489A (en) * 2020-09-01 2020-11-24 安徽炬视科技有限公司 Night light and flame classification discrimination algorithm combining target tracking and motion analysis
CN111985489B (en) * 2020-09-01 2024-04-02 安徽炬视科技有限公司 Night lamplight and flame classification discrimination algorithm combining target tracking and motion analysis
CN112129414A (en) * 2020-09-22 2020-12-25 苏州热工研究院有限公司 Multispectral image type fire detector
CN112699970A (en) * 2021-02-26 2021-04-23 江苏昂内斯电力科技股份有限公司 Multi-feature information fused flame detection system and method thereof
CN113160513A (en) * 2021-04-19 2021-07-23 杭州舜程科技有限公司 Flame detection device based on multisensor
CN116913033A (en) * 2023-05-29 2023-10-20 东莞市众可智能科技有限公司 Fire big data remote detection and early warning system
CN116913033B (en) * 2023-05-29 2024-04-05 深圳市兴安消防工程有限公司 Fire big data remote detection and early warning system

Similar Documents

Publication Publication Date Title
CN111354152A (en) Flame detecting and positioning system
CN105512667B (en) Infrared and visible light video image fusion recognition fire method
CN101458865B (en) Fire disaster probe system and method
US7786877B2 (en) Multi-wavelength video image fire detecting system
EP3407034B1 (en) Intelligent flame detection device and method using infrared thermography
CN106657802B (en) A kind of rotary-type multispectral camera automatic exposure regulating system and adjusting method
CN104036611A (en) Fire detecting alarm method and detecting alarm apparatus implementing same
EP3080788B1 (en) Flame detection system and method
JP5876347B2 (en) Hydrogen flame visualization apparatus and method
CN109375068B (en) Target identification method and device based on ultraviolet imaging corona detection
CN201259717Y (en) Fire disaster probe system
EP2686667A2 (en) Mwir sensor for flame detection
CN204496642U (en) A kind of dual-band image type fire detecting arrangement
CN105261142A (en) Intelligent fire detecting and extinguishing system for outdoor large space and operation method thereof
CN107123227A (en) A kind of embedded image flame detector and its recognition methods based on two waveband
CN101764999B (en) Sub-camera video capture device
CN111948501B (en) Automatic inspection equipment for power grid operation
CN111739251A (en) Fire source detection and positioning system and method
JPWO2019044898A1 (en) Gas detection system
RU2534937C2 (en) Device and method for flame detection by means of detectors
JPH08305980A (en) Device and method for flame detection
CN109243135A (en) A kind of intelligence fire detection and localization method, apparatus and system
CN209842823U (en) Vertical double-light-path smoke-sensing detection labyrinth
CN100516795C (en) Double spectrum image detector
CN211553084U (en) Double-spectrum thermal imaging human face temperature measurement system

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
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20200630

WD01 Invention patent application deemed withdrawn after publication