CN108492517A - A kind of fire monitoring system for building - Google Patents
A kind of fire monitoring system for building Download PDFInfo
- Publication number
- CN108492517A CN108492517A CN201810185574.9A CN201810185574A CN108492517A CN 108492517 A CN108492517 A CN 108492517A CN 201810185574 A CN201810185574 A CN 201810185574A CN 108492517 A CN108492517 A CN 108492517A
- Authority
- CN
- China
- Prior art keywords
- image
- video
- flame
- building
- pixel
- 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
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 19
- 238000001514 detection method Methods 0.000 claims abstract description 26
- 238000000605 extraction Methods 0.000 claims abstract description 7
- 238000000034 method Methods 0.000 claims abstract description 6
- 238000011410 subtraction method Methods 0.000 claims abstract description 6
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 4
- 230000005540 biological transmission Effects 0.000 claims abstract description 3
- 238000005457 optimization Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 206010021703 Indifference Diseases 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000003068 static effect Effects 0.000 claims description 4
- 238000009499 grossing Methods 0.000 claims description 2
- 238000004040 coloring Methods 0.000 claims 1
- 239000000779 smoke Substances 0.000 abstract description 5
- 230000009286 beneficial effect Effects 0.000 abstract 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000034994 death Effects 0.000 description 1
- 231100000517 death Toxicity 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
- 230000004580 weight loss Effects 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
- G08B17/12—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
-
- A—HUMAN NECESSITIES
- A62—LIFE-SAVING; FIRE-FIGHTING
- A62C—FIRE-FIGHTING
- A62C37/00—Control of fire-fighting equipment
Landscapes
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Fire-Detection Mechanisms (AREA)
- Alarm Systems (AREA)
Abstract
A kind of fire monitoring system for building, including video acquisition system, monitoring center and control module, the video acquisition system for acquiring the video image in building in real time, and by the transmission of video images to monitoring center, the monitoring center is used to be filtered the video image received and image carries out flame object image detection according to treated, extraction detects the characteristics of image in obtained flame object image and is identified, whether comprehensive descision is flame, when being determined as flame, the alarm that the control module controls in building immediately is alarmed and watering device is enabled to carry out fire extinguishing water.Beneficial effects of the present invention are：Smog pixel determining method in conjunction with background subtraction method and based on color characteristic carries out smoke target image zooming-out to the video image collected, improves the accuracy of smoke target image zooming-out, lays a good foundation for subsequent image feature extraction and identification.
Description
Technical field
The invention is related to gloomy building safety monitoring field, and in particular to a kind of fire monitoring system for building.
Background technology
With being on the increase for Chinese population and going from strength to strength for Developing Urbanization, centralized house has become city
The trend of city's development causes fire to take place frequently, fire since people lack security against fire consciousness and the presence of some combustible materials
It has become incidence height, endanger big, weight losses disaster.For fire, people start to turn to actively from passive fire extinguishing of putting out a fire to save life and property
Monitoring prevent, largely reduce the injures and deaths of personnel and the loss of property in this way.
For the deficiency of traditional building fire detection and prevention, the present invention provides a kind of building fire based on image procossing
Monitoring system acquires the video image in building, and the video to collecting by the camera in building in real time
Image carries out flame object detection, target image optimization and target identification work as hair to judge whether fire occurs in building
It is alarmed immediately when calamity of lighting a fire and opens watering device and put out a fire, realize the timely discovery and reply of fire in building.
Invention content
In view of the above-mentioned problems, the present invention is intended to provide a kind of fire monitoring system for building.
The purpose of the invention is achieved through the following technical solutions：
A kind of fire monitoring system for building, including video acquisition system, monitoring center and control module, it is described to regard
Frequency acquisition system for acquiring the video image in building in real time, and by the transmission of video images to monitoring center, the prison
Control center includes image processing module, module of target detection and target identification module, and described image processing module is used for receiving
To video image be filtered, the module of target detection be used for detection process after video image in flame mesh
Mark, the target identification module for extracting the flame characteristic in flame object image and be identified, comprehensive descision whether be
Flame, when being determined as flame, the alarm that the control module controls in building immediately alarmed and enable watering device into
Row fire extinguishing water.
The advantageous effect of the invention：A kind of fire monitoring system for building is provided, is adopted in real time by camera
Collect the video image of forest, smog pixel determining method in conjunction with background subtraction method and based on color characteristic is to the video that collects
Image carries out smoke target image zooming-out, improves the accuracy of smoke target image zooming-out, improves smoke target image
Quality is laid a good foundation for subsequent image feature extraction and identification.
Description of the drawings
Innovation and creation are described further using attached drawing, but the embodiment in attached drawing does not constitute and appoints to the invention
What is limited, for those of ordinary skill in the art, without creative efforts, can also be according to the following drawings
Obtain other attached drawings.
Fig. 1 is the structural schematic diagram of the present invention.
Reference numeral：
Video acquisition system 1；Monitoring center 2；Control module 3；Image processing module 21；Module of target detection 22；Target
Identification module 23.
Specific implementation mode
The invention will be further described with the following Examples.
Referring to Fig. 1, in a kind of fire monitoring system for building of the present embodiment, including video acquisition system 1, monitoring
The heart 2 and control module 3, the video acquisition system 1 for acquiring the video image in building in real time, and by the video image
It is transmitted to monitoring center 2, the monitoring center 2 includes image processing module 21, module of target detection 22 and target identification module
23, described image processing module 21 for being filtered to the video image received, use by the module of target detection 22
The flame object in video image after detection process, the target identification module 23 is for extracting in flame object image
Flame characteristic is simultaneously identified, and whether comprehensive descision is flame, and when being determined as flame, the control module 3 controls building immediately
Alarm in the world is alarmed and watering device is enabled to carry out fire extinguishing water.
Preferably, the video acquisition system 1 carries out video image acquisition using video camera.
This preferred embodiment provides a kind of building fire monitoring system based on image procossing, is acquired in real time using video camera
Video image in building carries out Preliminary detection, then to detection using background subtraction method to the flame object in video image
To flame object image in pixel analyzed, reject image in nonflame pixel, improve flame object detection
Accuracy lays a good foundation for image characteristics extraction and identification, can effectively judge whether there is fire.
Preferably, described image processing module 21 carries out the video image received using non-local mean filtering algorithm
Denoising is improved the weight calculation in non-local mean filtering algorithm, specially：
In formula, β is the standard deviation of Gaussian kernel, TaIndicate the image-region centered on pixel a, faIndicate pixel a's
Gray value,Indicate image-region TaGray average, TbIndicate the image-region centered on pixel b, fbIndicate pixel
The gray value of b,Indicate image-region TbGray average, r indicate smoothing parameter, the rate of decay of control characteristic function, α, ρ
It is weight coefficient with γ.
This preferred embodiment is filtered video image using non-local mean filtering algorithm, adjacent weighing image
Between domain when the calculating of similitude, Gauss weighted euclidean distance, neighborhood similarity coefficient and the neighborhood ash between neighborhood have been considered
Angle value difference has good filtering performance, and can higher retain the structural information in image.
Preferably, the module of target detection 22 includes background subtraction unit and objective optimization unit, the background subtraction
Unit is used to detect the flame object in the video image collected, and the objective optimization unit is used to reject what detection obtained
The pixel of nonflame in flame object image.
Preferably, the background subtraction unit is used to detect the flame object in the video image collected, uses
Background subtraction method carries out flame object extraction, and context update model b is calculated by following formulan+1(x, y), specially：
In formula, (x, y) movement and (x, y) it is static refer to previous frame background graphics and next frame original image at (x, y)
The gray value of point has indifference, and it is movement to have difference then, and indifference is then static, bn+1(x, y) is in the (n+1)th frame background image
Coordinate is the gray value of the point of (x, y), bn(x, y) is that coordinate is the gray value of the point of (x, y), h in n-th frame background imagen+1
(x, y) is that coordinate is the gray value of the point of (x, y), h from the (n+1)th frame of truncated picture sequence in monitor videon(x, y) is
Coordinate is the gray value of the point of (x, y), b from the n-th frame of truncated picture sequence in monitor videoo(x, y) is image sequence
Coordinate is the gray value of the point of (x, y) in the original background of first width image, and A, B and C are respectively weight coefficient, A+B+C=1.
This preferred embodiment carries out target detection by background subtraction method to the video image collected, in context update
In the process, the calculating for introducing original background image and the illumination variation factor increases the accuracy of target detection.
Preferably, the objective optimization unit is used to reject the pixel of nonflame in the flame object image that detection obtains
Point, specially：
Define the index of discrimination f (x, y) of the pixel in flame object image at position coordinates (x, y), then f (x, y)
Calculation formula is：
In formula, r (x, y), g (x, y) and b (x, y) are respectively the pixel value in flame object image at position coordinates (x, y)
Red color component value, green component values and blue color component value；
Flame pixels threshold value k is defined, the index of discrimination f (x, y) obtained by above-mentioned calculating in flame object image to sitting
The pixel at (x, y) is marked into judgement：
This preferred embodiment carries out the pixel in the flame object image of detection gained according to the color characteristic of flame
Analysis, rejects the pixel of nonflame in the flame object image, the precision of flame object detection is increased, to reduce
The calculation amount of subsequent image feature extraction and identification improves the operational efficiency of system.
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than the present invention is protected
The limitation of range is protected, although being explained in detail to the present invention with reference to preferred embodiment, those skilled in the art answer
Work as understanding, technical scheme of the present invention can be modified or replaced equivalently, without departing from the reality of technical solution of the present invention
Matter and range.
Claims (6)
1. a kind of fire monitoring system for building, characterized in that including video acquisition system, monitoring center and control mould
Block, the video acquisition system in real time acquire building in video image, and will the transmission of video images to monitor in
The heart, the monitoring center include image processing module, module of target detection and target identification module, and described image processing module is used
It is filtered in the video image received, the module of target detection is in the video image after detection process
Flame object, the target identification module is for extracting the flame characteristic in flame object image and being identified, comprehensive descision
Whether it is flame, when being determined as flame, the alarm that the control module controls in building immediately is alarmed and enables watering
Device carries out fire extinguishing water.
2. a kind of fire monitoring system for building according to claim 1, characterized in that the video acquisition system
Video image acquisition is carried out using video camera.
3. a kind of fire monitoring system for building according to claim 1, characterized in that described image processing module
Denoising is carried out to the video image received using non-local mean filtering algorithm, in non-local mean filtering algorithm
Weight calculation is improved, specially：
In formula, β is the standard deviation of Gaussian kernel, TaIndicate the image-region centered on pixel a, faIndicate the gray scale of pixel a
Value,Indicate image-region TaGray average, TbIndicate the image-region centered on pixel b, fbIndicate pixel b's
Gray value,Indicate image-region TbGray average, r indicate smoothing parameter, the rate of decay of control characteristic function, α, ρ and
γ is weight coefficient.
4. a kind of fire monitoring system for building according to claim 1, characterized in that the module of target detection
Including background subtraction unit and objective optimization unit, the background subtraction unit is used to detect in the video image collected
Flame object, the objective optimization unit are used to reject the pixel of nonflame in the flame object image that detection obtains.
5. a kind of fire monitoring system for building according to claim 4, characterized in that the background subtraction unit
For detecting the flame object in the video image collected, uses background subtraction method to carry out flame object extraction, pass through
Following formula calculates context update model bn+1(x, y), specially：
In formula, (x, y) movement static with (x, y) refers to the point of previous frame background graphics and next frame original image at (x, y)
Gray value has indifference, and it is movement to have difference then, and indifference is then static, bn+1(x, y) is coordinate in the (n+1)th frame background image
For the gray value of the point of (x, y), bn(x, y) is that coordinate is the gray value of the point of (x, y), h in n-th frame background imagen+1(x,y)
It is that coordinate is the gray value of the point of (x, y), h from the (n+1)th frame of truncated picture sequence in monitor videon(x, y) is from prison
Coordinate is the gray value of the point of (x, y), b in the n-th frame of truncated picture sequence in control videoo(x, y) is the first width of image sequence
Coordinate is the gray value of the point of (x, y) in the original background of image, and A, B and C are respectively weight coefficient, A+B+C=1.
6. a kind of fire monitoring system for building according to claim 5, characterized in that the objective optimization unit
Pixel for rejecting nonflame in the flame object image that detection obtains, specially：
Define the index of discrimination f (x, y) of the pixel in flame object image at position coordinates (x, y), the then calculating of f (x, y)
Formula is：
In formula, r (x, y), g (x, y) and b (x, y) are respectively the red of the pixel value in flame object image at position coordinates (x, y)
Colouring component value, green component values and blue color component value；
Define flame pixels threshold value k, index of discrimination f (x, y) obtained by above-mentioned calculating to coordinate in flame object image (x,
Y) pixel at place is into judgement：
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810185574.9A CN108492517A (en) | 2018-03-06 | 2018-03-06 | A kind of fire monitoring system for building |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810185574.9A CN108492517A (en) | 2018-03-06 | 2018-03-06 | A kind of fire monitoring system for building |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108492517A true CN108492517A (en) | 2018-09-04 |
Family
ID=63341764
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810185574.9A Pending CN108492517A (en) | 2018-03-06 | 2018-03-06 | A kind of fire monitoring system for building |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108492517A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109466362A (en) * | 2018-12-07 | 2019-03-15 | 中能易电新能源技术有限公司 | Charging pile safety monitoring system |
| CN110674799A (en) * | 2019-11-15 | 2020-01-10 | 南昌木本医疗科技有限公司 | Plant extraction parameter setting system based on image processing |
| CN111489317A (en) * | 2020-05-12 | 2020-08-04 | 江西天境精藏科技有限公司 | Intelligent cinerary casket storage system |
| CN112200877A (en) * | 2020-04-02 | 2021-01-08 | 吉安诺惠诚莘科技有限公司 | Car fills electric pile monitored control system based on artificial intelligence |
| CN116453029A (en) * | 2023-06-16 | 2023-07-18 | 济南东庆软件技术有限公司 | Building fire environment detection method based on image data |
| CN116630843A (en) * | 2023-04-13 | 2023-08-22 | 安徽中科数智信息科技有限公司 | Fire prevention supervision and management method and system for fire rescue |
| CN117152906A (en) * | 2023-11-01 | 2023-12-01 | 福建阿古电务数据科技有限公司 | Video image fire alarm system based on artificial intelligence |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102368345A (en) * | 2010-06-28 | 2012-03-07 | 东芝电梯株式会社 | Elevator remote monitoring system |
| CN102685929A (en) * | 2011-03-14 | 2012-09-19 | 淮阴工学院 | Intelligent video fire detection Internet of things system |
| CN202713510U (en) * | 2012-05-30 | 2013-01-30 | 李少斌 | 4g video monitoring system |
| CN103377534A (en) * | 2012-04-20 | 2013-10-30 | 苏州启山电器技术开发事务所(普通合伙) | Building fire alarm system |
| CN104463869A (en) * | 2014-12-05 | 2015-03-25 | 西安交通大学 | Video flame image composite recognition method |
| CN104464162A (en) * | 2014-12-02 | 2015-03-25 | 苏州立瓷电子技术有限公司 | Building fire protection linkage system |
-
2018
- 2018-03-06 CN CN201810185574.9A patent/CN108492517A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102368345A (en) * | 2010-06-28 | 2012-03-07 | 东芝电梯株式会社 | Elevator remote monitoring system |
| CN102685929A (en) * | 2011-03-14 | 2012-09-19 | 淮阴工学院 | Intelligent video fire detection Internet of things system |
| CN103377534A (en) * | 2012-04-20 | 2013-10-30 | 苏州启山电器技术开发事务所(普通合伙) | Building fire alarm system |
| CN202713510U (en) * | 2012-05-30 | 2013-01-30 | 李少斌 | 4g video monitoring system |
| CN104464162A (en) * | 2014-12-02 | 2015-03-25 | 苏州立瓷电子技术有限公司 | Building fire protection linkage system |
| CN104463869A (en) * | 2014-12-05 | 2015-03-25 | 西安交通大学 | Video flame image composite recognition method |
Non-Patent Citations (1)
| Title |
|---|
| 《中国优秀硕士学位论文全文数据库 信息科技辑》: "基于视频图像的火灾检测方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109466362A (en) * | 2018-12-07 | 2019-03-15 | 中能易电新能源技术有限公司 | Charging pile safety monitoring system |
| CN110674799B (en) * | 2019-11-15 | 2022-04-05 | 南昌木本医疗科技有限公司 | Plant extraction parameter setting system based on image processing |
| CN110674799A (en) * | 2019-11-15 | 2020-01-10 | 南昌木本医疗科技有限公司 | Plant extraction parameter setting system based on image processing |
| CN112200877B (en) * | 2020-04-02 | 2022-08-23 | 吉安诺惠诚莘科技有限公司 | Car fills electric pile monitored control system based on artificial intelligence |
| CN112200877A (en) * | 2020-04-02 | 2021-01-08 | 吉安诺惠诚莘科技有限公司 | Car fills electric pile monitored control system based on artificial intelligence |
| CN111489317B (en) * | 2020-05-12 | 2021-09-14 | 江西天境精藏科技有限公司 | Intelligent cinerary casket storage system |
| CN111489317A (en) * | 2020-05-12 | 2020-08-04 | 江西天境精藏科技有限公司 | Intelligent cinerary casket storage system |
| CN116630843A (en) * | 2023-04-13 | 2023-08-22 | 安徽中科数智信息科技有限公司 | Fire prevention supervision and management method and system for fire rescue |
| CN116630843B (en) * | 2023-04-13 | 2024-05-17 | 安徽中科数智信息科技有限公司 | Fire prevention supervision and management method and system for fire rescue |
| CN116453029A (en) * | 2023-06-16 | 2023-07-18 | 济南东庆软件技术有限公司 | Building fire environment detection method based on image data |
| CN116453029B (en) * | 2023-06-16 | 2023-08-29 | 济南东庆软件技术有限公司 | Building fire environment detection method based on image data |
| CN117152906A (en) * | 2023-11-01 | 2023-12-01 | 福建阿古电务数据科技有限公司 | Video image fire alarm system based on artificial intelligence |
| CN117152906B (en) * | 2023-11-01 | 2024-01-23 | 福建阿古电务数据科技有限公司 | Video image fire alarm system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108492517A (en) | A kind of fire monitoring system for building | |
| CN106600888B (en) | Automatic forest fire detection method and system | |
| WO2020078229A1 (en) | Target object identification method and apparatus, storage medium and electronic apparatus | |
| CN110569772B (en) | Method for detecting state of personnel in swimming pool | |
| CN106295551A (en) | A kind of personal security cap wear condition real-time detection method based on video analysis | |
| CN108470424A (en) | A kind of forest safety monitoring system based on characteristics of image | |
| CN103761529B (en) | A kind of naked light detection method and system based on multicolour model and rectangular characteristic | |
| CN109377703A (en) | A kind of forest fireproofing early warning system and its method based on machine vision | |
| CN105979210A (en) | Pedestrian identification system based on multi-ball multi-gun camera array | |
| CN109635758A (en) | Wisdom building site detection method is dressed based on the high altitude operation personnel safety band of video | |
| CN109118548A (en) | A kind of comprehensive intelligent water quality recognition methods | |
| CN104091354A (en) | Fire detection method based on video images and fire detection device thereof | |
| CN108038867A (en) | Fire defector and localization method based on multiple features fusion and stereoscopic vision | |
| CN114842397B (en) | Real-time old man falling detection method based on anomaly detection | |
| CN107301375A (en) | A kind of video image smog detection method based on dense optical flow | |
| CN107437318A (en) | A kind of visible ray Intelligent Recognition algorithm | |
| CN109190475A (en) | A kind of recognition of face network and pedestrian identify network cooperating training method again | |
| CN109741565B (en) | Coal mine fire disaster recognition system and method | |
| CN109409289A (en) | A kind of electric operating safety supervision robot security job identifying method and system | |
| CN106686377A (en) | Algorithm for determining video key area based on deep neural network | |
| WO2020249054A1 (en) | Living body detection method and system for human face by using two long-baseline cameras | |
| CN106845410A (en) | A kind of flame identification method based on deep learning model | |
| CN107688793A (en) | A kind of outside transformer substation fire automatic monitoring method for early warning | |
| CN109754411A (en) | Building pivot frame larceny detection method and system are climbed based on optical flow method target following | |
| CN207233038U (en) | Face is called the roll and number 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180904 |