CN109637066A - A kind of building intelligent the monitoring system of fire protection and method - Google Patents
A kind of building intelligent the monitoring system of fire protection and method Download PDFInfo
- Publication number
- CN109637066A CN109637066A CN201811518961.6A CN201811518961A CN109637066A CN 109637066 A CN109637066 A CN 109637066A CN 201811518961 A CN201811518961 A CN 201811518961A CN 109637066 A CN109637066 A CN 109637066A
- Authority
- CN
- China
- Prior art keywords
- module
- fire
- information
- image
- life
- 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
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000012544 monitoring process Methods 0.000 title claims abstract description 17
- 238000001514 detection method Methods 0.000 claims abstract description 38
- 238000004458 analytical method Methods 0.000 claims abstract description 6
- 230000007547 defect Effects 0.000 claims description 22
- 238000001914 filtration Methods 0.000 claims description 13
- 239000003517 fume Substances 0.000 claims description 10
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 8
- 239000002341 toxic gas Substances 0.000 claims description 7
- 239000007789 gas Substances 0.000 claims description 6
- 206010013654 Drug abuse Diseases 0.000 claims description 5
- 239000000779 smoke Substances 0.000 claims description 5
- 208000011117 substance-related disease Diseases 0.000 claims description 5
- 238000007599 discharging Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 230000003213 activating effect Effects 0.000 claims description 2
- 239000003034 coal gas Substances 0.000 claims 1
- 238000012502 risk assessment Methods 0.000 abstract description 8
- 238000007689 inspection Methods 0.000 abstract description 6
- 238000003012 network analysis Methods 0.000 abstract description 5
- 238000002922 simulated annealing Methods 0.000 abstract description 3
- 230000000007 visual effect Effects 0.000 abstract description 3
- 230000008859 change Effects 0.000 description 9
- 230000006870 function Effects 0.000 description 7
- 238000012806 monitoring device Methods 0.000 description 6
- 238000011161 development Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000002146 bilateral effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 229940079593 drug Drugs 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 230000002068 genetic effect Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 239000003643 water by type Substances 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005538 encapsulation Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000009970 fire resistant effect Effects 0.000 description 1
- 239000003063 flame retardant Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000005507 spraying Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000002699 waste material 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
-
- A—HUMAN NECESSITIES
- A62—LIFE-SAVING; FIRE-FIGHTING
- A62C—FIRE-FIGHTING
- A62C37/00—Control of fire-fighting equipment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- 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)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Probability & Statistics with Applications (AREA)
- Public Health (AREA)
- Multimedia (AREA)
- Alarm Systems (AREA)
- Fire Alarms (AREA)
Abstract
The invention belongs to fire protection warning technical fields, a kind of building intelligent the monitoring system of fire protection and method are disclosed, the building intelligent the monitoring system of fire protection includes: fire detection module, life detection module, alarm module, photographing module, central control module, cutting module, evacuation module, emergency fire fighting module, elevator forced landing module, access door detection module, fire Safety Assessment module, display module.Access door detection module of the present invention without keeping a public place clean and Security Personnel etc. makes an inspection tour, reduces human cost, and improve the monitoring efficiency for monitoring passageway for fire apparatus door state according to the automatic state of monitoring passageway for fire apparatus door in real time of visual identification algorithm；Meanwhile by fire Safety Assessment module using simulated annealing as search strategy, Bayesian network optimum structure is found；In Bayesian Estimation method, by updated Bayesian network analysis tool, analysis obtains security risk assessment result.
Description
Technical field
The invention belongs to fire protection warning technical field more particularly to a kind of building intelligent the monitoring system of fire protection and sides
Method.
Background technique
With the raising of people's quality of life.Fitting-up is gradually superior, and electrical equipment increases, high-rise and Super High
Masses' gathering place scale such as the increase of building and shopping mall supermarket expands rapidly, and the importance of security against fire is more and more prominent
Out.With the development and maturation of INTELLIGENT BUILDING TECHNIQUE.More and more novel buildings use intelligent fire-pretection system.It is by two
Divide and constitute, a part is automatic fire alarm system, i.e. perception and cental system, like the face and brain of people；Another part
It is linkage extinguishing system, that is, system is executed, like the four limbs of people.In this way, intelligent fire-pretection system can find the fire of building in time
Hidden danger takes corresponding measure.It saves in time.The fire that will likely be bred disaster was eliminated at fire-retardant phase or initial stage.Prevent disaster from expanding
Greatly.Intelligent fire-pretection system has Initial Stage of Fire auto-alarm function, and is attached to and leads directly on the alarm at fire-fighting center
Phone, self-extinguishing control cabinet, public-fire alarm address system of fire department etc..Once fire occurs, intelligent fire-pretection system can be immediately
Alarm signal is issued on the fire-alarm of one's respective area, while alarm signal is issued on the warning device at fire-fighting center, and show
Position or the area code of fire occurs, administrative staff are connected to alert and start fire alarm broadcast immediately, and establishment officer's safe escape opens
Dynamic Fire lift；Alarm linkage signal drives the work of self-extinguishing control cabinet, closes fire resistant doorsets with bashing domain, and in fire
Disaster area domain automatic spraying water or extinguishing chemical fire extinguishing；Start fire pump and automatic fume exhauster.However, existing building intelligent fire-fighting report
The open and-shut mode of fire exit door can only be maked an inspection tour by Security Personnel and be checked in alert control system, be easy to appear missing inspection, checked not
It in time, unmanned situations such as checking at night, cannot 24 hours comprehensive guarantee safety；Meanwhile existing security risk assessment mode,
Including the security risk assessment mode calculated according to basic statistical, micro-judgment and big number, real-time is poor, accuracy compared with
It is low, it is thus impossible to meet the security risk assessment demand of existing fire system.
In conclusion problem of the existing technology is:
In existing building intelligent the monitoring system of fire protection the open and-shut mode of fire exit door can only be maked an inspection tour by Security Personnel into
Row checks, be easy to appear missing inspection, check not in time, unmanned situations such as checking at night, cannot 24 hours comprehensive guarantee safety；Together
When, existing security risk assessment mode, the security risk including being calculated according to basic statistical, micro-judgment and big number is commented
Estimate mode, real-time is poor, and accuracy is lower, it is thus impossible to meet the security risk assessment demand of existing fire system.
The clarity for acquiring the image of scene of fire in the prior art is insufficient, is unfavorable for the accurate true of scene of fire situation
Acquisition；Acquisition life-information cannot be accurately obtained in the prior art, extends detection time, waste valuable rescue time；It is existing
The image and data information for being unfavorable for scene of fire in technology not can guarantee the accurate acquisition of collected fire condition at showing,
It is unfavorable for the development of salvaging.
Summary of the invention
In view of the problems of the existing technology, the present invention provides a kind of building intelligent the monitoring system of fire protection and sides
Method.
The invention is realized in this way a kind of building intelligent fire protection warning control method, the building intelligent fire protection warning
Control method the following steps are included:
Step 1 detects Fires Occurred information using fire detector；It is adopted by using the data based on GA-SVR
The life detectors of set algorithm detect life-information；
Step 2 is alarmed by manual pull station or phone；It is acquired by the image pick-up device of specific two-sided filter
Scene of fire；
Step 3 electrically activates UPS, and cutting gas piping by cutting circuitry cuts exchange；By open closed-circuit television,
Fire broadcast, fire information carry out evacuation personnel；By starting water valve watering, and by discharging fume, drug abuse system discharged fume, inhaled
Receive poison gas；Utilize electric life controller control elevator forced landing to bottom；
Step 4 detects channel door state according to the image information of acquisition；Using Safety Evaluation Software to fire-fighting
Safety is assessed；Finally using without make an uproar display display acquisition fire condition, life-information, monitor video data believe
Breath.
Further, the image pick-up device for passing through specific two-sided filter in the step 1, acquires the image of scene of fire, specifically
Are as follows:
Image filtering can be represented by the formula:
Wherein: I (x, y) is the clear image after filtering out noise, and n (i, j) is the noisy acoustic image for needing to be filtered, Ω
It is the neighborhood of pixel, w (i, j) is power of the filter at point (i, j)；wpIt is a standard volume, indicates:
The space length of weight w (i, j) and pixel is linearly related, and the nearlyr correlation of distance is bigger, and weight is also bigger, filter
Wave kernel function is defined as follows:
Wherein σkIt is Gaussian function standard deviation.
Further, the fire condition without display display acquisition of making an uproar, life-information, monitor video are utilized in the step 4
Data information, quantized value L passes through the average gray difference value with normal background is defined as:
Wherein: ISB is normal background, i.e., the normal LCD image num shot under the conditions of same Image Acquisition is the ash of statistics
Spend non-zero pixels number；It is lossless to refer to that defect image does not lose Mura defects information after reconstructed background inhibits, generally from obtaining
Mura defects region area A evaluated:
Wherein: s (x, y) is the area of unit pixel；D representative meets the pixel domain that difference in defect area is not 0；Pass through
The average contrast of Define defects and background defines the data quantity C:
C=(| LM-LB|)/LB；
Wherein: LM is the average brightness of defect area in original image, and LB is to correspond to defect area in the background image rebuild
The average brightness at place；By the way that each quantized value is answered in the ideal situation known to analysis mode are as follows: L=0, A=AMura, C → ∞；Due to reality
Border reconstruction process will receive the interference of various factors, and there are errors compared to ideal value for each quantized value obtained at this time, therefore are directed to
The calculated L of certain Background Rebuilding Method is smaller, A and C more defecate it can be assumed that the background masses that this method is rebuild are higher.
Another object of the present invention is to provide a kind of building intelligence for realizing the building intelligent fire protection warning control method
Energy the monitoring system of fire protection, the building intelligent the monitoring system of fire protection include:
Fire detection module is connect with central control module, for detecting Fires Occurred letter by fire detector
Breath；
Life detection module, connect with central control module, for detecting life-information by life detectors；
Alarm module is connect with central control module, for being alarmed by manual pull station or phone；
Photographing module is connect with central control module, for acquiring scene of fire by image pick-up device；
Central control module, with fire detection module, life detection module, alarm module, photographing module, cutting module,
Module, emergency fire fighting module, elevator forced landing module, access door detection module, fire Safety Assessment module, display module is evacuated to connect
It connects, is worked normally for controlling modules by single-chip microcontroller；
Module is cut off, is connect with central control module, for electrically activating UPS, and cutting by cutting circuitry cuts exchange
Gas piping；
Module is evacuated, connect with central control module, is dredged for opening closed-circuit television, fire broadcast, fire information
Dissipate personnel；
Emergency fire fighting module, connect with central control module, waters for starting water valve, and pass through smoke evacuation, drug abuse system
It discharged fume, absorb poison gas；
Elevator forced landing module, connect with central control module, controls elevator forced landing to bottom for passing through electric life controller；
Access door detection module, connect with central control module, for the image information by acquisition to channel door state
It is detected；
Fire Safety Assessment module, connect with central control module, for by Safety Evaluation Software to security against fire into
Row assessment；
Display module is connect with central control module, is believed for the fire condition by display display acquisition, life
The data information of breath, monitor video.
Another object of the present invention is to provide a kind of Information Numbers using the building intelligent fire protection warning control method
According to processing terminal.
Advantages of the present invention and good effect are as follows: access door detection module of the present invention is automatically real according to visual identification algorithm
When the state of monitoring passageway for fire apparatus door reduce human cost, and improve prison without keeping a public place clean and Security Personnel etc. makes an inspection tour
Control the monitoring efficiency of passageway for fire apparatus door state；Certainly, in the present invention, which can be a frame image, be also possible to one section
Image including multiple images frame, single frames comparison can be accelerated to detect speed, and Detection accuracy can be improved in multiframe comparison；Together
When, by fire Safety Assessment module by fire-fighting system initial data collected, using fire-fighting data filter and fire-fighting number
The mode combined according to wrapper searches for optimal spy using Fisher criterion and classifier performance function as characteristic evaluating standard
Levy subset；Then, with optimal feature subset and empirical data, training generates original Bayesian network analysis tool.Meanwhile with
Simulated annealing is search strategy, finds Bayesian network optimum structure；In Bayesian Estimation method, Bayesian network is estimated
Node condition probability parameter value, to realize that the iteration of bayesian network structure and parameter updates；Finally, being acquired with a new round
Initial data, search for its optimal feature subset, and by after its discretization, by updated Bayesian network analysis tool,
Analysis obtains security risk assessment result.
The present invention passes through the image pick-up device of specific two-sided filter, it is ensured that the clarity of the image of scene of fire is acquired,
And have the function of smoothly protecting side, be conducive to the accurate true acquisition of scene of fire situation；The present invention is by using based on GA-
The life detectors of the data gathering algorithm of SVR detect life-information, improve the accuracy rate of acquisition life-information, effectively reduce letter
The traffic between node is ceased, the consumption of gross energy is reduced, improves speed of detection, strives for more quality time for life；This hair
The data informations such as bright fire condition, life-information, monitor video using without display display acquisition of making an uproar, have without display of making an uproar
Noise reduction, lossless, enhancing effect, the image and data information for being conducive to scene of fire guarantee collected fire condition at showing
Accurate acquisition, be conducive to the development of salvaging.
Detailed description of the invention
Fig. 1 is building intelligent fire protection warning control method flow chart provided in an embodiment of the present invention.
Fig. 2 is building intelligent the monitoring system of fire protection structural schematic diagram provided in an embodiment of the present invention；
In figure: 1, fire detection module；2, life detection module；3, alarm module；4, photographing module；5, center control mould
Block；6, module is cut off；7, module is evacuated；8, emergency fire fighting module；9, elevator forced landing module；10, access door detection module；11,
Fire Safety Assessment module；12, display module.
Specific embodiment
In order to further understand the content, features and effects of the present invention, the following examples are hereby given, and cooperate attached drawing
Detailed description are as follows.
Structure of the invention is explained in detail with reference to the accompanying drawing.
As shown in Figure 1, building intelligent fire protection warning control method provided by the invention specifically includes the following steps:
S101: Fires Occurred information is detected using fire detector；By using the data acquisition based on GA-SVR
The life detectors of algorithm detect life-information；
S102: it is alarmed by manual pull station or phone；Fire is acquired by the image pick-up device of specific two-sided filter
Calamity scene；
S103: UPS, and cutting gas piping are electrically activated by cutting circuitry cuts exchange；By opening closed-circuit television, disappearing
Anti- broadcast, fire information carry out evacuation personnel；By starting water valve watering, and by discharging fume, drug abuse system discharged fume, absorbed
Poison gas；Utilize electric life controller control elevator forced landing to bottom；
S104: channel door state is detected according to the image information of acquisition；Fire-fighting is pacified using Safety Evaluation Software
It is assessed entirely；Finally utilize the data informations such as fire condition, life-information, the monitor video that acquisition is shown without display of making an uproar.
In step S101, the image pick-up device provided in an embodiment of the present invention by specific two-sided filter, it is ensured that acquisition
The clarity of the image of scene of fire, and have the function of smoothly protecting side, be conducive to the accurate true acquisition of scene of fire situation,
Specific algorithm are as follows:
Image filtering can be represented by the formula:
Wherein: I (x, y) is the clear image after filtering out noise, and n (i, j) is the noisy acoustic image for needing to be filtered, Ω
It is the neighborhood of pixel, w (i, j) is power of the filter at point (i, j)；wpIt is a standard volume, can indicates:
So, for gaussian filtering, the space length of weight w (i, j) and pixel is linearly related, the nearlyr correlation of distance
Property it is bigger, weight is also bigger, filtering kernel function can be defined as follows:
Wherein σkIt is Gaussian function standard deviation；
Gaussian filtering only focuses on the space length of pixel and has ignored the variation (change of image grayscale) of pixel value, filters out
Also smooth edge while noise；Bilateral filtering increases one on the basis of weight above and measures pixel value variation
Power, calculation formula such as formula:
The weight w of bilateral filtering is wk(i, j) and whThe product of (i, j), at image border pixel value variation greatly, wh(i, j)
Value is smaller, so that w also becomes smaller, filter action of the filter in edge is reduced, to maintain side while filtering
Edge.
In step S101, the life provided in an embodiment of the present invention by using the data gathering algorithm based on GA-SVR is visited
It surveys device and detects life-information, improve the accuracy rate of acquisition life-information, effectively reduce the traffic between information node, reduce total
The consumption of energy improves speed of detection, strives for more quality time for life；The specific steps of GA-SVR algorithm are as follows:
(1) evolutionary generation t=0 is initialized；
(2) initial information p (t) is generated at random, the size of life group is set, and real coding shape is passed through to parameter C, σ, ε
At life-information individual；
(3) to the living individual training SVR in p (t), and individual adaptation degree functional value F (t) is calculated；
(4) if the corresponding F (t) of living individual in p (t) meets required precision or reaches the number of iterations of setting, turn
To step 7)；
(5) otherwise, t=t+1；
(6) confirmation message operation is executed, life-information is generated and determines, then go to step 3)；
(7) the weak parameter C of optimal life-information, insensitive coefficient ε, the strong parameter σ of life-information are provided, and by life
Information, which is trained, obtains optimal SVR model.
It is provided in an embodiment of the present invention to believe using without the make an uproar fire condition of display display acquisition, life in step S104
The data informations such as breath, monitor video, without display of making an uproar with noise reduction, lossless, enhancing effect is conducive to the image of scene of fire
And data information guarantees the accurate acquisition of collected fire condition, is conducive to the development of salvaging at showing；Refer to weight without making an uproar
The background built cannot introduce new noise jamming, and quantized value L passes through the average gray difference value with normal background is defined as:
Wherein: ISB is normal background, i.e., the normal LCD image shot under the conditions of same Image Acquisition；Num is statistics
Gray scale non-zero pixels number；It is lossless to refer to that defect image does not lose Mura defects information after reconstructed background inhibits, generally from
Mura defects region area A out is evaluated:
Wherein: s (x, y) is the area of unit pixel；D representative meets the pixel domain that difference in defect area is not 0；And increase
It is strong then refer to that the Mura defects after background inhibits are more obvious, it is visual higher, then it can pass through the flat of Define defects and background
Equal contrast defines the data quantity C:
C=(| LM-LB|)/LB
Wherein: LM is the average brightness of defect area in original image, and LB is to correspond to defect area in the background image rebuild
The average brightness at place；By the way that each quantized value is answered in the ideal situation known to analysis mode are as follows: L=0, A=AMura, C → ∞；Due to reality
Border reconstruction process will receive the interference of various factors, and there are errors compared to ideal value for each quantized value obtained at this time, therefore are directed to
The calculated L of certain Background Rebuilding Method is smaller, A and C more defecate it can be assumed that the background masses that this method is rebuild are higher.
As shown in Fig. 2, building intelligent the monitoring system of fire protection provided by the invention includes: fire detection module 1, life
Detecting module 2, alarm module 3, photographing module 4, central control module 5, cutting module 6, evacuation module 7, emergency fire fighting module
8, elevator forced landing module 9, access door detection module 10, fire Safety Assessment module 11, display module 12.
Fire detection module 1 is connect with central control module 5, for detecting Fires Occurred by fire detector
Information；
Life detection module 2 is connect with central control module 5, for detecting life-information by life detectors；
Alarm module 3 is connect with central control module 5, for being alarmed by manual pull station or phone；
Photographing module 4 is connect with central control module 5, for acquiring scene of fire by image pick-up device；
Central control module 5, with fire detection module 1, life detection module 2, alarm module 3, photographing module 4, cutting
Module 6, evacuation module 7, emergency fire fighting module 8, elevator forced landing module 9, access door detection module 10, fire Safety Assessment module
11, display module 12 connects, and works normally for controlling modules by single-chip microcontroller；
Module 6 is cut off, is connect with central control module 5, electrically activates UPS for exchanging by cutting circuitry cuts, and cut
Disconnected gas piping；
Module 7 is evacuated, is connect with central control module 5, is carried out for opening closed-circuit television, fire broadcast, fire information
Evacuation personnel；
Emergency fire fighting module 8, connect with central control module 5, waters for starting water valve, and passes through smoke evacuation, system of taking drugs
System is discharged fume, absorbs poison gas；
Elevator forced landing module 9, connect with central control module 5, for controlling elevator forced landing on earth by electric life controller
Layer；
Access door detection module 10 is connect with central control module 5, for the image information by acquisition to channel gate-shaped
State is detected；
Fire Safety Assessment module 11 is connect with central control module 5, for passing through Safety Evaluation Software to security against fire
It is assessed；
Display module 12 is connect with central control module 5, for the fire condition by display display acquisition, life
The data informations such as information, monitor video.
10 detection method of access door detection module provided by the invention is as follows:
(1) the template image frame saved under the collected passageway for fire apparatus door normal condition of monitoring device is preset；
(2) the realtime graphic frame of the collected passageway for fire apparatus door of crawl monitoring device, by realtime graphic frame and template image
Frame compares, and calculates the change rate of picture frame；
(3) it if change rate is more than preset threshold, alarms.
The realtime graphic frame of crawl monitoring device provided by the invention collected passageway for fire apparatus door, by realtime graphic frame and
Template image frame compares, and in the step of calculating the change rate of picture frame:
The realtime graphic frame for grabbing the collected passageway for fire apparatus door of monitoring device, by the picture of each pixel of realtime graphic frame
The pixel value of plain value and each pixel of template image frame compares, and calculates the change rate of pixel value.
The realtime graphic frame of the collected passageway for fire apparatus door of crawl monitoring device provided by the invention, by realtime graphic frame
The pixel value of pixel value and template image frame compares, and the step of calculating the change rate of pixel value includes:
The pixel value of the pixel value of realtime graphic frame and template image frame is compared one by one；
Calculate the absolute difference of the pixel value of every group of respective pixel；
According to the absolute difference of the pixel value of every group of respective pixel, the change rate of picture frame is calculated.
The absolute difference of pixel value provided by the invention according to every group of respective pixel calculates the change rate packet of picture frame
It includes:
Pixel by absolute difference less than 15 is set as 0；
Statistics absolute difference is not 0 number of pixels, is divided by obtain the change rate of picture frame with total number of pixels.
Template image frame provided by the invention includes at least the first lightness environment template image frame and the second lightness environment mould
Plate picture frame, the first lightness environment template image frame and the second lightness environment template image frame are based on different lightness environment
The normal condition picture frame of acquisition；
The step of default template image frame saved under the collected passageway for fire apparatus door normal condition of monitoring device, wraps
It includes: acquiring and judge imaging environment brightness in real time, select corresponding lightness environment template image frame as template image frame.
11 appraisal procedure of fire Safety Assessment module provided by the invention is as follows:
Step 1: with the fire-fighting system hydraulic pressure real value of collection site, vibration real value, temperature real value, liquid level real value
And system real-time parameter is as initial data, and carries out acquiring in real time to it and transmission；
Step 2: the fire-fighting data filter using Fisher criterion as characteristic evaluating standard is established, by fire-fighting collected
System initial data carries out feature ordering according to the size of weight；
Step 3: establishing the fire-fighting data encapsulation of the fitness evaluation standard using classifier performance function as genetic algorithm
Device, using fire-fighting system initial data feature ordering as a result, instructing the initialization of Population in Genetic Algorithms, to find optimal characteristics
Subset；
Step 4: the optimal feature subset and empirical data searched using step 3, training generate original Bayesian network
Network analysis tool.Meanwhile using simulated annealing as search strategy, Bayesian network optimum structure is found；Estimated using Bayes
Meter method estimates the node condition probability parameter value of Bayesian network, to realize the iteration of bayesian network structure and parameter
It updates；
Step 5: its optimal feature subset being searched for the initial data of new round acquisition, and by after its discretization, by more
Bayesian network analysis tool after new, analysis obtain security risk assessment result.
Step 1 provided by the invention the following steps are included:
Receive the running state parameter and real-time parameter value of all live underlying devices of the fire-fighting system；
By preconfigured transport protocol, real-time Transmission is carried out to initial data using bus structures.
The working principle of the invention:
When the invention works, believe firstly, detecting Fires Occurred using fire detector by fire detection module 1
Breath；Life-information is detected using life detectors by life detection module 2；Manual pull station is utilized by alarm module 3
Or phone is alarmed；Scene of fire is acquired using image pick-up device by photographing module 4；Secondly, the scheduling cutting of central control module 5
Module 6 electrically activates UPS, and cutting gas piping using cutting circuitry cuts exchange；By evacuation module 7 open closed-circuit television,
Fire broadcast, fire information carry out evacuation personnel；Start water valve watering by emergency fire fighting module 8, and passes through smoke evacuation, system of taking drugs
System is discharged fume, absorbs poison gas；Elevator forced landing is controlled to bottom using electric life controller by elevator forced landing module 9；By logical
Sect detection module 10 detects channel door state according to the image information of acquisition；Then, pass through fire Safety Assessment mould
Block 11 assesses security against fire using Safety Evaluation Software；Finally, fire of the display module 12 using display display acquisition
The data informations such as the condition of a disaster condition, life-information, monitor video.
The above is only the preferred embodiments of the present invention, and is not intended to limit the present invention in any form,
Any simple modification made to the above embodiment according to the technical essence of the invention, equivalent variations and modification, belong to
In the range of technical solution of the present invention.
Claims (5)
1. a kind of building intelligent fire protection warning control method, which is characterized in that the building intelligent fire protection warning control method packet
Include following steps:
Step 1 detects Fires Occurred information using fire detector；It acquires and calculates by using the data based on GA-SVR
The life detectors of method detect life-information；
Step 2 is alarmed by manual pull station or phone；Fire is acquired by the image pick-up device of specific two-sided filter
Scene；
Step 3 electrically activates UPS, and cutting gas piping by cutting circuitry cuts exchange；By opening closed-circuit television, fire-fighting
Broadcast, fire information carry out evacuation personnel；By starting water valve watering, and by discharging fume, drug abuse system discharged fume, absorbs poison
Gas；Utilize electric life controller control elevator forced landing to bottom；
Step 4 detects channel door state according to the image information of acquisition；Using Safety Evaluation Software to security against fire
It is assessed；Finally using without make an uproar display display acquisition fire condition, life-information, monitor video data information.
2. building intelligent fire protection warning control method as described in claim 1, which is characterized in that pass through tool in the step 1
The image pick-up device of body two-sided filter acquires the image of scene of fire, specifically:
Image filtering can be represented by the formula:
Wherein: I (x, y) is the clear image after filtering out noise, and n (i, j) is the noisy acoustic image for needing to be filtered, and Ω is picture
The neighborhood of element, w (i, j) is power of the filter at point (i, j)；wpIt is a standard volume, indicates:
The space length of weight w (i, j) and pixel is linearly related, and the nearlyr correlation of distance is bigger, and weight is also bigger, filtering core
Function is defined as follows:
Wherein σkIt is Gaussian function standard deviation.
3. building intelligent fire protection warning control method as described in claim 1, which is characterized in that utilize nothing in the step 4
Display of making an uproar display acquisition fire condition, life-information, monitor video data information, quantized value L by with normal background
Average gray difference value is defined as:
Wherein: ISB is normal background, i.e., the normal LCD image num shot under the conditions of same Image Acquisition is that the gray scale of statistics is non-
Zero number of pixels；It is lossless refer to after reconstructed background inhibits that defect image does not lose Mura defects information, generally from obtaining
Mura defects region area A is evaluated:
Wherein: s (x, y) is the area of unit pixel；D representative meets the pixel domain that difference in defect area is not 0；Pass through definition
The average contrast of defect and background defines the data quantity C:
C=(| LM-LB|)/LB；
Wherein: LM is the average brightness of defect area in original image, and LB is corresponded at defect area in the background image rebuild
Average brightness；By the way that each quantized value is answered in the ideal situation known to analysis mode are as follows: L=0, A=AMura, C → ∞；Due to practical weight
The process of building will receive the interference of various factors, and there are errors compared to ideal value for each quantized value obtained at this time, therefore are directed to certain
The calculated L of Background Rebuilding Method is smaller, A and C more defecate it can be assumed that the background masses that this method is rebuild are higher.
4. a kind of building intelligent fire protection warning control system for realizing building intelligent fire protection warning control method described in claim 1
System, which is characterized in that the building intelligent the monitoring system of fire protection includes:
Fire detection module is connect with central control module, for detecting Fires Occurred information by fire detector；
Life detection module, connect with central control module, for detecting life-information by life detectors；
Alarm module is connect with central control module, for being alarmed by manual pull station or phone；
Photographing module is connect with central control module, for acquiring scene of fire by image pick-up device；
Central control module, with fire detection module, life detection module, alarm module, photographing module, cutting module, evacuation
Module, emergency fire fighting module, elevator forced landing module, access door detection module, fire Safety Assessment module, display module connection,
It is worked normally for controlling modules by single-chip microcontroller；
Module is cut off, is connect with central control module, for electrically activating UPS, and cutting coal gas by cutting circuitry cuts exchange
Pipeline；
Module is evacuated, is connect with central control module, carries out evacuation people for opening closed-circuit television, fire broadcast, fire information
Member；
Emergency fire fighting module, connect with central control module, carries out for starting water valve watering, and by smoke evacuation, drug abuse system
Smoke evacuation absorbs poison gas；
Elevator forced landing module, connect with central control module, controls elevator forced landing to bottom for passing through electric life controller；
Access door detection module, connect with central control module, carries out for the image information by acquisition to channel door state
Detection；
Fire Safety Assessment module, connect with central control module, for being commented by Safety Evaluation Software security against fire
Estimate；
Display module is connect with central control module, for the fire condition by display display acquisition, life-information, prison
Control the data information of video.
5. a kind of information data using building intelligent fire protection warning control method described in claims 1 to 3 any one is handled
Terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811518961.6A CN109637066A (en) | 2018-12-12 | 2018-12-12 | A kind of building intelligent the monitoring system of fire protection and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811518961.6A CN109637066A (en) | 2018-12-12 | 2018-12-12 | A kind of building intelligent the monitoring system of fire protection and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109637066A true CN109637066A (en) | 2019-04-16 |
Family
ID=66073331
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811518961.6A Pending CN109637066A (en) | 2018-12-12 | 2018-12-12 | A kind of building intelligent the monitoring system of fire protection and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109637066A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111882815A (en) * | 2020-07-30 | 2020-11-03 | 吉林建筑大学 | Intelligent security and fire protection integrated method and system |
| CN111888675A (en) * | 2020-07-24 | 2020-11-06 | 王娟 | Automatic fire-fighting air cushion control platform and method |
| CN112057773A (en) * | 2020-09-08 | 2020-12-11 | 河南银苑电子有限公司 | Large-space intelligent fire extinguishing system and construction method thereof |
| 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 |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104464163A (en) * | 2014-12-02 | 2015-03-25 | 苏州立瓷电子技术有限公司 | Building fire protection linkage method |
| CN104657947A (en) * | 2015-02-06 | 2015-05-27 | 哈尔滨工业大学深圳研究生院 | Noise reducing method for basic group image |
| CN205692310U (en) * | 2016-06-06 | 2016-11-16 | 武汉网信机电工程股份有限公司 | A kind of intelligent building fire automatization alarm device |
-
2018
- 2018-12-12 CN CN201811518961.6A patent/CN109637066A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104464163A (en) * | 2014-12-02 | 2015-03-25 | 苏州立瓷电子技术有限公司 | Building fire protection linkage method |
| CN104657947A (en) * | 2015-02-06 | 2015-05-27 | 哈尔滨工业大学深圳研究生院 | Noise reducing method for basic group image |
| CN205692310U (en) * | 2016-06-06 | 2016-11-16 | 武汉网信机电工程股份有限公司 | A kind of intelligent building fire automatization alarm device |
Non-Patent Citations (1)
| Title |
|---|
| 谢瑞，李钢，张仁斌: "液晶显示器斑痕缺陷高质量背景建模" * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111888675A (en) * | 2020-07-24 | 2020-11-06 | 王娟 | Automatic fire-fighting air cushion control platform and method |
| CN111888675B (en) * | 2020-07-24 | 2021-10-26 | 深圳市丰用实业集团有限公司 | Automatic fire-fighting air cushion control platform and method |
| CN111882815A (en) * | 2020-07-30 | 2020-11-03 | 吉林建筑大学 | Intelligent security and fire protection integrated method and system |
| CN112057773A (en) * | 2020-09-08 | 2020-12-11 | 河南银苑电子有限公司 | Large-space intelligent fire extinguishing system and construction method thereof |
| 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 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109637066A (en) | A kind of building intelligent the monitoring system of fire protection and method | |
| CN106241533B (en) | Elevator occupant's comprehensive safety intelligent control method based on machine vision | |
| CN105046682B (en) | A kind of video frequency monitoring method based on local computing | |
| CN110135266A (en) | A kind of dual camera electrical fire preventing control method and system based on deep learning | |
| CN107911653A (en) | The module of intelligent video monitoring in institute, system, method and storage medium | |
| CN101188745B (en) | Intelligent drowning video monitoring system and method for natatorium | |
| CN105484798B (en) | Underground floods alarm method based on temperature and humidity and image monitoring | |
| CN109102684A (en) | Wisdom fire-fighting system and its working method | |
| CN103957387B (en) | A kind of security protection channel sundries detection method and detection system | |
| CN103839373A (en) | Sudden abnormal event intelligent identification alarm device and system | |
| CN105347127A (en) | Monitoring system and monitoring method for abnormal condition in elevator car | |
| KR102396888B1 (en) | Real-time smart fire fighting sensing and monitoring system | |
| CN105569733B (en) | Underground coal mine driving face floods alarm method based on image | |
| CN107403158A (en) | A kind of personnel video frequency identifying method on duty and intelligent subscriber information carrying means | |
| CN110517441A (en) | Based on the frame-embedded smog of deep learning and flame video alarming system and method | |
| CN109460744A (en) | A kind of video monitoring system based on deep learning | |
| CN109657626A (en) | A kind of analysis method by procedure identification human body behavior | |
| CN109395302A (en) | A kind of intelligent extinguisher management system | |
| CN106817560A (en) | It is a kind of to distributed terminal display device real-time monitoring system and monitoring method | |
| CN109785574B (en) | Fire detection method based on deep learning | |
| CN208847389U (en) | Liquefied ammonia equipment monitoring system for the monitoring of industrial accident hidden danger | |
| CN112653870B (en) | Abnormal behavior early warning system based on big data | |
| CN116976832A (en) | Intelligent fire-fighting centralized unified supervision platform based on AI, big data and Internet of things | |
| WO2021022427A1 (en) | Community stray-animal monitoring system and monitoring method | |
| CN115049988A (en) | Edge calculation method and device for power distribution network monitoring and prejudging |
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 |
Application publication date: 20190416 |