CN110009866A - A kind of method of video detection temperature anomaly - Google Patents
A kind of method of video detection temperature anomaly Download PDFInfo
- Publication number
- CN110009866A CN110009866A CN201910265482.6A CN201910265482A CN110009866A CN 110009866 A CN110009866 A CN 110009866A CN 201910265482 A CN201910265482 A CN 201910265482A CN 110009866 A CN110009866 A CN 110009866A
- Authority
- CN
- China
- Prior art keywords
- refraction
- temperature anomaly
- oscillating quantity
- video detection
- flow vector
- 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 51
- 238000001514 detection method Methods 0.000 title claims abstract description 23
- 238000004364 calculation method Methods 0.000 claims abstract description 8
- 238000001914 filtration Methods 0.000 claims abstract description 5
- 239000012530 fluid Substances 0.000 claims description 28
- 230000003287 optical effect Effects 0.000 claims description 16
- 230000007423 decrease Effects 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 claims description 3
- 239000004744 fabric Substances 0.000 claims 1
- 230000033001 locomotion Effects 0.000 abstract description 13
- 230000002159 abnormal effect Effects 0.000 abstract description 5
- 230000035945 sensitivity Effects 0.000 abstract description 3
- 238000003384 imaging method Methods 0.000 description 6
- 238000012544 monitoring process Methods 0.000 description 5
- 239000000126 substance Substances 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000691 measurement method Methods 0.000 description 2
- 238000000917 particle-image velocimetry Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000010894 electron beam technology Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 239000000049 pigment Substances 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 239000002356 single layer Substances 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000017105 transposition Effects 0.000 description 1
- 238000000827 velocimetry Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000007794 visualization technique Methods 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
- G08B17/10—Actuation by presence of smoke or gases, e.g. automatic alarm devices for analysing flowing fluid materials by the use of optical means
- G08B17/11—Actuation by presence of smoke or gases, e.g. automatic alarm devices for analysing flowing fluid materials by the use of optical means using an ionisation chamber for detecting smoke or gas
-
- 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
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Fire-Detection Mechanisms (AREA)
- Radiation Pyrometers (AREA)
- Photometry And Measurement Of Optical Pulse Characteristics (AREA)
Abstract
A kind of method of video detection temperature anomaly, comprising the following steps: step 1: input under normal circumstances with the video that is shot under unknown situation, and the pretreatment such as make gaussian filtering；Step 2: calculating separately oscillating quantity to two kinds of situations；Step 3: matching the refraction stream in the case of oscillating quantity calculates separately two kinds；Step 4: using the method for nonparametric probability respectively to the refraction Flow Field Calculation probability density function under normal and unknown situation；Step 5: the method for using Bayesian Decision calculates the refraction stream at each point as abnormal probability.The method that the present invention detects temperature reduces the lag of time of fire alarming, using fire with respect to the feature of early stage, alarm can be just generated before there is smog and open fire, high sensitivity, it can be identified as exception immediately when occurring with distinguishing refraction flow vector under normal circumstances, and Local treatment is used, is adjusted according to the motion feature of point each in scene and differentiates exceptional condition, feasibility is high and application field is extensive.
Description
Technical field
The present invention relates to Video security monitoring technology field, especially a kind of method of video detection temperature anomaly.
Background technique
Currently used fire detection method can be divided into physical sensors detection method and video monitoring detection method.Object
Sensor detecting method such as smoke alarm is managed, needs that police could be issued when smokescope reaches a certain level in closed room
Report.Video monitoring detection method utilizes vision computing technique, is issued by fire characteristics such as video detection smog or flame colors
Alarm.For above-mentioned two classes method when issuing smog alarm or catch fire and alarming, the time for leaving fire fighter's processing for is considerably less.
Before combustibles are on fire, temperature is gradually increasing, and then combustibles start to generate smog, when temperature reaches combustibles combustion
When point, combustibles will appear open fire.When combustibles temperature rises, above local air temperature rise with it, part is empty
Temperature degree, which constantly changes, causes the regional air refractive index constantly to change, when light passes through the local air of variations in refractive index,
Its direction of propagation is swung, and occurs the random dancing of regional area pixel in monitor video picture.
Refractive fluid detection can be divided into two major classes with visualization method: foreign substance or injection energy are mixed in flow field
The display methods and optics of amount show measurement method.The former foreign substance and energy includes pigment, electron beam, glow discharge
Deng embodying the movement of fluid, referred to as Particle Image Velocimetry (Particle Image by the movement of these substances
Velocimetry,PIV).This method needs that experiment condition is manually set, and is not suitable for real-time natural scene monitoring.Optics
Display methods includes the technologies such as schlieren interference, such as streak photograph amplifies Refractive fluid to light by the optical path of accurate calibration
Deviation for another example in background schlieren method (Background Oriented Schlieren, BOS), exists by one without fluid
When influence of the reference picture comparative fluid to background.The shortcomings that optics display methods is the instrument for needing close adjustment, difficult
To be placed in actual scene.For this problem, occur some improved methods in computer vision field, pass through video camera
It is measured to substitute complicated optical sensor, if S. pricks Mick, Y. Yi Zhake's " estimates turbulent flow from turbulent flow degraded image sequence
Method in intensity ", O. glass Rett, " degraded using video camera from optical turbulence and swing perception Tangential Wind " etc. of J. sand than drawing.
Basic thought using video camera measurement fluid is, when being imaged in a fluid, since light is across non-uniform
Random deviation occurs for medium, finally generates small swing in the picture, therefore can detect background in static scene
Movement.When there are when heat source temperature exception, it is uneven that temperature raising will lead to local index distribution in scene, it is equivalent to shape
At a partial fluid, the essence for detecting heat source temperature exception is to generate in image when detecting through partial fluid imaging
Background motion.Common method for testing motion includes feature point tracking, optical flow method etc., however light is propagated in Refractive fluid
When can generate it is fuzzy etc. degrade, generate luminance fluctuation in the picture, disagreed with " the constant hypothesis of brightness " of optical flow method.One kind has
The reduction luminance fluctuation of effect is brightness to be mapped to another feature space, such as use Xue on the method that motion detection influences
Eigentransformation method described in " fluid flow rate and depth measurement method that swing based on refraction " of its sail etc.: brightness is calculated
The oscillating quantity that changing features generate in the picture obtains representing the refraction flow vector of fluid motion by matching oscillating quantity.In order to
Reduce sensor noise caused by erroneous judgement, calculate refraction flow vector, need to just design it is a kind of using monitor video detect heat source temperature
Spend abnormal method.
Summary of the invention
It is realized it is an object of the invention to overcome the deficiencies of the prior art and provide a kind of using ordinary video monitoring camera
, the method sounded an alarm by the Refractive fluid generated when detection heat source temperature exception.
The present invention solves its technical problem and adopts the following technical solutions to achieve:
A kind of method of video detection temperature anomaly, comprising the following steps:
Step 1: input is under normal circumstances with the video that shoots under unknown situation, whether unknown input includes temperature anomaly
Image sequence I (x, y, t), carry out gaussian filtering noise is smoothly pre-processed, if introducing artificial light source when shooting
It also needs to eliminate Hz noise using bandstop filter；
Step 2: optical flow method calculates the oscillating quantity v (x, y, t) in image；
Step 3: the oscillating quantity between adjacent two frame of matching obtains refraction flow vector u (x, y, t)；
It is screened step 4: being flowed to calculated refraction according to the statistical property of optical turbulence；
Step 5: the refraction stream region for meeting fluid behaviour is labeled as temperature anomaly region, to temperature anomaly area
The refraction flow vector in domain is shown using Munsell (Munsell) color graph code.
Preferably, optical flow method calculation formula in the second step are as follows:
Preferably, oscillating quantity conservation is utilized in the third step, the refraction flow vector u calculated by matching oscillating quantity
(x, y, t) are as follows:
Preferably, in the 4th step in adjacent several frames, to the oscillating quantity degree of bias value at each point
Skewness and kurtosis value kurtosis are respectively as follows:
It is approximately equal to 0, kurtosis for meeting the degree of bias and is approximately equal to the sky that 3 point further verifies refraction flow vector to connected region
Between be distributed, connected region is equally divided into three parts along the vertical direction, calculate separately each section refraction flow vector size mean value,
It is can determine that if meeting production decline law as temperature anomaly region.
Preferably, the method for the video detection temperature anomaly in the specific implementation needed for equipment be common
Xiaoyi2 household monitor camera, the physical parameter of the Xiaoyi2 household monitor camera are as follows: valid pixel 1080
(H) × 720 (V), frame per second 25fps, camera lens specification are F2.0 large aperture, 130 ° of wide-angles.
The advantages and positive effects of the present invention are:
The present invention detects the method for temperature compared with the method for existing fire preventing, reduces the lag of time of fire alarming,
Using fire with respect to the feature of early stage, alarm, high sensitivity, when appearance can be just generated before there is smog and open fire
Exception can be identified as when with distinguishing refraction flow vector under normal circumstances immediately, and uses Local treatment, according to scene
In the motion feature adjustment of each point differentiate abnormal condition, feasibility is high and application field is extensive, and succeeded field indoors
Testing result has been obtained in scape, it can be in the application such as further genralrlization to forest fire protection, no supervision warehouse.
Detailed description of the invention
Fig. 1 is the flow diagram of video detection temperature anomaly of the invention；
Fig. 2 is the schematic diagram of refraction stream geometrical model of the invention.
Specific embodiment
The embodiment of the present invention is further described below in conjunction with attached drawing:
As illustrated in fig. 1 and 2, a kind of method and step of video detection temperature anomaly of the present invention is as follows:
Step 1: input under normal circumstances with the video that is shot under unknown situation, and pretreatment, the input such as make gaussian filtering
It is unknown whether include temperature anomaly image sequence I (x, y, t), carry out gaussian filtering noise is smoothly pre-processed, if
Artificial light source is introduced when shooting also needs to eliminate Hz noise using bandstop filter；
Step 2: calculating separately oscillating quantity to two kinds of situations, is calculated using optical flow method and swings measure feature v (x, y, t):
Step 3: the refraction stream in the case of matching oscillating quantity calculates separately two kinds is put using oscillating quantity conservation by matching
Momentum calculates refraction flow vector u (x, y, t):
Step 4: using the method for nonparametric probability respectively to the refraction Flow Field Calculation under normal and unknown situation
Probability density function calculates skewness and kurtosis to the oscillating quantity at each point in adjacent several frames:
It is approximately equal to 0, kurtosis for meeting the degree of bias and is approximately equal to the sky that 3 point further verifies refraction flow vector to connected region
Between be distributed, connected region is equally divided into three parts along the vertical direction, calculate separately each section refraction flow vector size mean value,
It is can determine that if meeting production decline law as temperature anomaly region；
Step 5: the method for using Bayesian Decision calculates the refraction stream at each point as abnormal probability, will meet
The refraction stream region of fluid behaviour is labeled as temperature anomaly region, uses to the refraction flow vector in temperature anomaly region
Munsell color graph code is shown.
In addition, the offset that background generates when above-mentioned refraction stream calculation is by being imaged in Refractive fluid is finally inversed by fluid
The method of motion information.Due to being usually used in influence of the optical flow method of detection movement by luminance fluctuation, stream calculation is reflected by brightness
Feature is transformed into other feature spaces.
Assuming that there are the Refractive fluid of a single layer, imaging geometries such as institute in attached drawing 2 between video camera and background
Show.Assuming that reflecting the shape and temperature-resistant, the movement of only irregular little refraction body of field in [t, t+ Δ t] time interval
Lead to the change for reflecting field.Assuming that being x in the position of t moment imaging plane certain pointt, the position of corresponding flow surface is x't,
The corresponding position in background is x "t.The depth of these planes is respectively z, z' and z ".The center of camera is denoted as o.Enable αtWith α 't
Respectively light and the angle from image center to imaging surface between background.
As fluid is from tiMoment (solid line position) moves to ti+ time Δt (dotted line position), some point in background
It is moved to another position from a position on imaging plane, produces the oscillating quantity v (t being observed thati).It " swings
Amount conservation " concept be, if a fluid in very short space-time window at the uniform velocity to move, the corresponding swing in successive frame
Feature is also mobile with fluid.We use t in attached drawing 21And t2The oscillating quantity at moment proves oscillating quantity conservation.
Work as αtWhen very little:
tanαt≈αt=(xt-oj)/z=(x 't-oj)/z′ (1)
Can be approximately single order plus item by refraction angle according to Snell law:
α′t=αt+Δαt (2)
The geometrical relationship for recycling refraction angle part, projects to the point in background are as follows:
x″t=x 't+(z″-z′)(αt+Δαt) (3)
Due to x 't+Δt-x′tThe relationship for meeting similar triangles with the oscillating quantity on imaging surface, by proving x 't+Δt-x′t
For constant, that is, constant hypothesis of provable oscillating quantity.
Utilize the conservation of (3):
x′t+Δt+(z″-z′)(αt+Δt+Δαt+Δt)=x 't+(z″-z′)(αt+Δαt)
Transposition:
x′t+Δt-x′t=-(z "-z ') (αt+Δt-αt)-(z″-z′)(Δαt+Δt-Δαt) (4)
According to formula (1):
(5) are substituted into (4) and are transplanted, can be released
As it is assumed that plus item is only related with fluid local surfaces property, it is all unrelated with incidence angle or visual field, therefore formula (6) is said
Bright x 't+Δt-x′tFor constant, i.e. " oscillating quantity is constant " establishment.By in matching oscillating quantity substitution optical flow method when reflecting stream calculation
Refraction stream is calculated with brightness.
Refraction stream statistics specificity analysis is should to can't detect depositing for refraction stream in the Region Theory of not temperature anomaly
However due to being influenced by sensor noise and the limitation of optimization method, even if can the region of heat source is not present
The vector of interference is calculated, these interference will cause false alarm.Mistake caused by noise differentiates that we are by light in order to prevent
The priori knowledge for learning turbulent flow screens calculated refraction flow vector.Refraction stream should meet simultaneously optical turbulence space and
Time statistical property, wherein the former mainly meets Richardson grades of string methods, the latter mainly verify refraction flow vector level and
Whether vertical component size meets Gaussian Profile at any time.
Refractive fluid caused by temperature anomaly is considered as the turbulent flow formed that is vortexed by different scale, therefore can use
Richardson grades of string methods analyze the spatial statistics characteristic of fluid.The thought of Richardson grades of strings is inside turbulent flow
There are different size of vortex and energy transmission, large eddy absorbs energy from the external world and transfers energy to small vortex, final complete
It is complete to dissipate.The fluid generated for heat source, it is assumed that the fluid at heat source is large eddy, then with far from heat source eddy size
Successively decrease, energy is also by transmitting and dissipating with far from heat source closest to heat source.According to the characteristic, in the connected region of refraction stream
Interior, the average value that should meet in the refraction flow vector amplitude close to heat source part is greater than far from heat source part refraction flow vector amplitude
Average value.
Offset in the research and emulation of optical turbulence, when people usually assume that and experimental verification turbulent flow is imaged in image
Amount meets Gaussian random field, which can be used for verifying the time statistical property of fluid.Since refraction flows the parameter of itself not
Know, is difficult model and Gaussian Profile by fitting using mean value and variance and compares.In this regard, the height of Gaussian Profile can be used
Rank square characteristic, i.e., the statistical property that the Gaussian Profile degree of bias is 0, kurtosis is 3, to calculated with adjacent several frames at each point
Oscillating quantity calculates the statistic of skewness and kurtosis and compares in Gaussian Profile, extracts effective folding jet area.
The present invention detects the method for temperature compared with the method for existing fire preventing, reduces the lag of time of fire alarming,
Using fire with respect to the feature of early stage, alarm, high sensitivity, when appearance can be just generated before there is smog and open fire
Exception can be identified as when with distinguishing refraction flow vector under normal circumstances immediately, and uses Local treatment, according to scene
In the motion feature adjustment of each point differentiate abnormal condition, feasibility is high and application field is extensive, and succeeded field indoors
Testing result has been obtained in scape, it can be in the application such as further genralrlization to forest fire protection, no supervision warehouse.
It is emphasized that embodiment of the present invention be it is illustrative, without being restrictive, therefore the present invention is simultaneously
It is not limited to embodiment described in specific embodiment, it is all to be obtained according to the technique and scheme of the present invention by those skilled in the art
Other embodiments, also belong to the scope of protection of the invention.
Claims (5)
1. a kind of method of video detection temperature anomaly, which comprises the following steps:
Step 1: input under normal circumstances with the video that is shot under unknown situation, unknown input whether include temperature anomaly figure
As sequence I (x, y, t), carries out gaussian filtering and noise is smoothly pre-processed, if introducing artificial light source when shooting also needs
Hz noise is eliminated using bandstop filter；
Step 2: optical flow method calculates the oscillating quantity v (x, y, t) in image；
Step 3: the oscillating quantity between adjacent two frame of matching obtains refraction flow vector u (x, y, t)；
It is screened step 4: being flowed to calculated refraction according to the statistical property of optical turbulence；
Step 5: the refraction stream region for meeting fluid behaviour is labeled as temperature anomaly region, to temperature anomaly region
Refraction flow vector is shown using Munsell (Munsell) color graph code.
2. a kind of method of video detection temperature anomaly according to claim 1, it is characterised in that: in the second step
Optical flow method calculation formula are as follows:
3. a kind of method of video detection temperature anomaly according to claim 1, it is characterised in that: in the third step
Using oscillating quantity conservation, the refraction flow vector u (x, y, t) calculated by matching oscillating quantity are as follows:
4. a kind of method of video detection temperature anomaly according to claim 1, it is characterised in that: in the 4th step
In adjacent several frames, the oscillating quantity degree of bias value skewness and kurtosis value kurtosis at each point are respectively as follows:
It is approximately equal to 0, kurtosis for meeting the degree of bias and is approximately equal to the space minute that 3 point further verifies refraction flow vector to connected region
Connected region is equally divided into three parts by cloth along the vertical direction, calculates separately the mean value of each section refraction flow vector size, if full
Sufficient production decline law then can determine that as temperature anomaly region.
5. a kind of method of video detection temperature anomaly according to claim 1, it is characterised in that: the video detection
The method of temperature anomaly in the specific implementation needed for equipment be common Xiaoyi2 household monitor camera, it is described
The physical parameter of Xiaoyi2 household monitor camera are as follows: valid pixel is 1080 (H) × 720 (V), frame per second 25fps, camera lens
Specification is F2.0 large aperture, 130 ° of wide-angles.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910265482.6A CN110009866A (en) | 2019-04-03 | 2019-04-03 | A kind of method of video detection temperature anomaly |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910265482.6A CN110009866A (en) | 2019-04-03 | 2019-04-03 | A kind of method of video detection temperature anomaly |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110009866A true CN110009866A (en) | 2019-07-12 |
Family
ID=67169636
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910265482.6A Pending CN110009866A (en) | 2019-04-03 | 2019-04-03 | A kind of method of video detection temperature anomaly |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110009866A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1677444A (en) * | 2005-02-01 | 2005-10-05 | 珠海金山软件股份有限公司 | Realp-time 3-D image processing device |
| CN101339602A (en) * | 2008-07-15 | 2009-01-07 | 中国科学技术大学 | Video frequency fire hazard aerosol fog image recognition method based on light stream method |
| CN101413887A (en) * | 2007-05-29 | 2009-04-22 | 中国科学院安徽光学精密机械研究所 | Instrument for measuring refractive index fluctuation of optical fiber atmospheric turbulence |
| CN103267969A (en) * | 2013-04-25 | 2013-08-28 | 中国科学院安徽光学精密机械研究所 | Method for measuring atmospheric optical turbulent current profile based on imaging laser radar of laser light beam |
| CN103413321A (en) * | 2013-07-16 | 2013-11-27 | 南京师范大学 | Crowd behavior model analysis and abnormal behavior detection method under geographical environment |
| US20150016690A1 (en) * | 2013-05-15 | 2015-01-15 | Massachusetts Institute Of Technology | Methods and apparatus for refractive flow measurement |
| CN107274432A (en) * | 2017-06-10 | 2017-10-20 | 北京航空航天大学 | A kind of common scene intelligent video monitoring method of view-based access control model conspicuousness and depth own coding |
| CN108197586A (en) * | 2017-12-12 | 2018-06-22 | 北京深醒科技有限公司 | Recognition algorithms and device |
| US20180246137A1 (en) * | 2017-02-28 | 2018-08-30 | King Abdullah University Of Science And Technology | Rainbow Particle Imaging Velocimetry for Dense 3D Fluid Velocity Imaging |
-
2019
- 2019-04-03 CN CN201910265482.6A patent/CN110009866A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1677444A (en) * | 2005-02-01 | 2005-10-05 | 珠海金山软件股份有限公司 | Realp-time 3-D image processing device |
| CN101413887A (en) * | 2007-05-29 | 2009-04-22 | 中国科学院安徽光学精密机械研究所 | Instrument for measuring refractive index fluctuation of optical fiber atmospheric turbulence |
| CN101339602A (en) * | 2008-07-15 | 2009-01-07 | 中国科学技术大学 | Video frequency fire hazard aerosol fog image recognition method based on light stream method |
| CN103267969A (en) * | 2013-04-25 | 2013-08-28 | 中国科学院安徽光学精密机械研究所 | Method for measuring atmospheric optical turbulent current profile based on imaging laser radar of laser light beam |
| US20150016690A1 (en) * | 2013-05-15 | 2015-01-15 | Massachusetts Institute Of Technology | Methods and apparatus for refractive flow measurement |
| CN103413321A (en) * | 2013-07-16 | 2013-11-27 | 南京师范大学 | Crowd behavior model analysis and abnormal behavior detection method under geographical environment |
| US20180246137A1 (en) * | 2017-02-28 | 2018-08-30 | King Abdullah University Of Science And Technology | Rainbow Particle Imaging Velocimetry for Dense 3D Fluid Velocity Imaging |
| CN107274432A (en) * | 2017-06-10 | 2017-10-20 | 北京航空航天大学 | A kind of common scene intelligent video monitoring method of view-based access control model conspicuousness and depth own coding |
| CN108197586A (en) * | 2017-12-12 | 2018-06-22 | 北京深醒科技有限公司 | Recognition algorithms and device |
Non-Patent Citations (1)
| Title |
|---|
| LINYAN CUI 等: "Modified anisotropic turbulence refractive-index fluctuations spectral model and its application in moderate-to-strong anisotropic turbulence", 《JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Garg et al. | Vision and rain | |
| CN100538757C (en) | Fire-disaster monitoring device based on omnibearing vision sensor | |
| CN106845443B (en) | Video flame detection method based on multi-feature fusion | |
| CN105512667B (en) | Infrared and visible light video image fusion recognition fire method | |
| CN103761826B (en) | The recognition methods of a kind of thermal imaging video two mirror forest fires recognition system | |
| CN100459704C (en) | Intelligent tunnel safety monitoring apparatus based on omnibearing computer vision | |
| CN104935893B (en) | Monitor method and apparatus | |
| CN110135269A (en) | A kind of fire image detection method based on blend color model and neural network | |
| US20070097372A1 (en) | Particle detection apparatus and particle detection method used therefor | |
| CN105336085A (en) | Remote large-space fire monitoring alarm method based on image processing technology | |
| JP2007509327A (en) | Improved particle monitoring system and method | |
| JP2008519965A (en) | Particle detector, system and method | |
| CN102298816B (en) | Fire early warning method for marine engine room based on multi-source fusion | |
| CN109598700A (en) | Using the incipient fire detection method of convolutional neural networks | |
| CN107750326A (en) | Detect the presence of liquid in high pressure gas pipeline road | |
| CN114386493A (en) | Fire detection method, system, device and medium based on flame vision virtualization | |
| CN110009863A (en) | A kind of vertical double light path smoke detection labyrinth and its detection method | |
| Widmann | Phase Doppler interferometry measurements in water sprays produced by residential fire sprinklers | |
| CN109001217A (en) | A kind of detection method and detection device of phone housing defect | |
| Patterson et al. | The relation between visibility and the size-number distribution of airborne soil particles | |
| Cauteruccio et al. | Wind tunnel validation of a particle tracking model to evaluate the wind‐induced bias of precipitation measurements | |
| CN108519495A (en) | A kind of device and method for measuring turbomachine interior flow field speed | |
| Lee et al. | A wind tunnel study of natural ventilation for multi–span greenhouse scale models using two–dimensional particle image velocimetry (PIV) | |
| CN110009866A (en) | A kind of method of video detection temperature anomaly | |
| CN104297176A (en) | Device, system and method for monitoring visibility of channel segments of Yangtze River in mountainous area in all-weather manner |
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: 20190712 |
|
| RJ01 | Rejection of invention patent application after publication |