CN108335454A - A kind of fire behavior detection method and device - Google Patents
A kind of fire behavior detection method and device Download PDFInfo
- Publication number
- CN108335454A CN108335454A CN201810034509.6A CN201810034509A CN108335454A CN 108335454 A CN108335454 A CN 108335454A CN 201810034509 A CN201810034509 A CN 201810034509A CN 108335454 A CN108335454 A CN 108335454A
- Authority
- CN
- China
- Prior art keywords
- macro block
- pixel
- gradation data
- value
- ratio
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 89
- 238000000034 method Methods 0.000 claims abstract description 101
- 230000006399 behavior Effects 0.000 claims description 82
- 238000004590 computer program Methods 0.000 claims description 22
- 238000012512 characterization method Methods 0.000 claims description 20
- 241001269238 Data Species 0.000 claims description 15
- 238000005516 engineering process Methods 0.000 abstract description 12
- 230000006870 function Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 11
- 238000001931 thermography Methods 0.000 description 8
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000005855 radiation Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000037237 body shape Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000001066 destructive effect Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003287 optical effect 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
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B29/00—Checking or monitoring of signalling or alarm systems; Prevention or correction of operating errors, e.g. preventing unauthorised operation
- G08B29/18—Prevention or correction of operating errors
- G08B29/185—Signal analysis techniques for reducing or preventing false alarms or for enhancing the reliability of the system
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Computer Security & Cryptography (AREA)
- Fire-Detection Mechanisms (AREA)
- Photometry And Measurement Of Optical Pulse Characteristics (AREA)
Abstract
The invention discloses a kind of fire behavior detection method and device, wherein the method includes：Include the first frame gradation data of target object by thermal infrared imager acquisition, wherein the first frame gradation data includes N number of pixel, and N is the positive integer more than 1；The first frame gradation data is divided into M macro block, determine the fluctuation characteristic of K macro block in the M macro block, wherein each macro block includes at least one pixel that temperature value is more than predetermined threshold value in the K macro block, M is the positive integer more than 1, and K is the positive integer no more than M；If the fluctuation characteristic of the K macro block meets preset condition, determine that the target object is flame.For solving the technical problem relatively low for the fire behavior detection method accuracy of fire of the existing technology, the accuracy of the fire behavior detection method for fire is improved.
Description
Technical field
The present invention relates to fire monitoring and image identifying and processing technical field, more particularly to a kind of fire monitoring method
And device.
Background technology
Fire is one of the Disasters of modern civilization society most destructive power, in order to drop to loss caused by fire
It is minimum, wherein one of most efficient method is exactly early detection, and is put out before sprawling.
Currently, coming frequently with the thermal infrared imager that can export uncorrected data (such as gradation data of 14 bits) with digital signal
Realize the detection and identification to fire behavior, specifically, thermal infrared imager utilizes infrared detector and optical imagery object lens, will connect
It is infrared to obtain in the infrared energy distribution pattern reflection to the temperature-sensitive element of infrared detector of the measured target received
Thermography, this thermography are corresponding with the heat distribution field of body surface.Generally, thermal infrared imager is exactly to say that object is sent out
Invisible infrared energy be changed into visible thermal image.Different colours above thermal image represent the not equality of temperature of testee
Degree.
In the prior art, temperature or gray scale height are often based upon to carry out fire behavior detection, but is carrying out remote fire behavior
When detection, false drop rate is higher.In addition, increasing spy in Color Distribution Features, change rate feature, area sprawling according to fire thermal image
Sign, circularity feature, body shape changes feature various features factor are into comprehensive descision.Although false drop rate reduces, entire mistake
Cheng Bingwei considers the distance that fire occurs, and can not detect the fiery point of distant place very little, increases omission factor.
As it can be seen that the prior art is relatively low in the presence of the fire behavior detection method accuracy for fire.
Invention content
The embodiment of the present invention provides a kind of fire behavior detection method and device, of the existing technology for fire for solving
The relatively low technical problem of fire behavior detection method accuracy, improve the accuracy of the fire behavior detection method for fire.
On the one hand, an embodiment of the present invention provides a kind of fire behavior detection methods, including：
Include the gradation data of target object by thermal infrared imager acquisition, wherein the gradation data includes N number of pixel
Point, N number of pixel correspond to N number of temperature value, and N is the positive integer more than 1；Gradation data is divided into M macro block, M is less than N
Positive integer；
The gradation data is analyzed, determines the fluctuation characteristic of K macro block in the M macro block, wherein the K
A macro maximum temperature value in the block is more than predetermined threshold value, and K is the positive integer less than M；
If the fluctuation characteristic meets preset condition, determine that the target object is flame.
Optionally, in the determination M macro block K macro block fluctuation characteristic, including：
Determine that the fluctuation of the first temperature value in each macro block of the K macro block more than the first preset temperature threshold is special
Sign；And/or
Determine the positional fluctuation of L pixel in each macro block of the K macro block more than the second preset temperature threshold
Feature, wherein second preset temperature threshold is not more than the first preset temperature threshold.
Optionally, the first temperature of the first preset temperature threshold is more than in each macro block of the determination K macro block
The fluctuation characteristic of value, including：
The P frame gradation datas including the first frame gradation data are obtained by the thermal infrared imager, and will be every
Frame gradation data is divided into M macro block, wherein P is the positive integer more than 1；
From determined in the M macro block include in the P frames gradation data be more than the first preset temperature threshold
Macro block determines K macro block altogether；
Determine P of first macro block on the P frames gradation data the first temperature values in the K macro block；
Calculate the standard deviation and mean value of the P the first temperature values, and determine the standard deviation of P first temperature value with
The ratio of mean value；
Based on the P standard deviations of the first temperature value and the ratio of mean value, the fluctuation characteristic of first macro block is determined,
The fluctuation characteristic of the K macro block is obtained altogether.
Optionally, L pixel of the second preset temperature threshold is more than in each macro block of the determination K macro block
Positional fluctuation feature, including：
It determines and is more than the first pixel in L pixel of the second preset temperature threshold in the K macro block in the first macro block
First position and first pixel of the point in the first frame gradation data are obtained by the thermal infrared imager
The second position in the second frame gradation data including target object；
Temperature gap based on the first position and the second position between front and back two frames gradation data, determine described in
The positional fluctuation feature of first pixel obtains the positional fluctuation feature of the L pixel altogether.
Optionally, the method further includes：
If the temperature gap is more than preset temperature difference, determine that first pixel has fluctuation characteristic；
Count the pixel number with fluctuation characteristic in first macro block；
If the pixel number is more than predetermined number, determine that the first sub-goal object of the first macro block characterization is fire
Flame.
Optionally, it is described determine K macro block after, the method further includes：
If the current distance value between the first sub-goal object and the thermal infrared imager of the first macro block characterization is less than
First pre-determined distance value, judges whether the ratio is more than default ratio；
If the ratio is more than the default ratio, and the current distance value is more than the second pre-determined distance value, determines institute
It is flame to state the first sub-goal object, wherein the second pre-determined distance value is less than the first pre-determined distance value.
Optionally, the method further includes：
If the ratio is more than the default ratio, and the current distance value is not more than the second pre-determined distance value,
Judge whether the pixel number with fluctuation characteristic is more than predetermined number in first macro block；
If the pixel number is more than the predetermined number, determine that the first sub-goal object is flame.
Optionally, it is described determine K macro block after, the method further includes：
If L pixel in first macro block more than second preset temperature threshold is formed by first area face
Product is more than the first preset area, judges whether the ratio is more than default ratio；
If the ratio is more than the default ratio, and the first area area is less than the second preset area, determines institute
It is flame to state the first sub-goal object, wherein second preset area is more than first preset area.
Optionally, the method further includes：
If the ratio is more than the default ratio, and the first area area is not less than second preset area,
Judge whether the pixel number with fluctuation characteristic is more than predetermined number in first macro block；
If the pixel number is more than the predetermined number, determine that the first sub-goal object is flame.
On the other hand, the embodiment of the present invention additionally provides a kind of fire detection device, including：
Thermal infrared imager, for obtain include target object first frame gradation data, wherein the first frame grey
According to including N number of pixel, N is the positive integer more than 1；
Processor determines K macro block in the M macro block for the first frame gradation data to be divided into M macro block
Fluctuation characteristic, wherein in the K macro block each macro block include temperature value be more than predetermined threshold value at least one pixel, M
For the positive integer more than 1, K is the positive integer no more than M；If the fluctuation characteristic of the K macro block meets preset condition, institute is determined
It is flame to state target object.
Optionally, the processor is used for：
Determine that the fluctuation of the first temperature value in each macro block of the K macro block more than the first preset temperature threshold is special
Sign；And/or
Determine the positional fluctuation of L pixel in each macro block of the K macro block more than the second preset temperature threshold
Feature, wherein second preset temperature threshold is not more than the first preset temperature threshold.
Optionally, when the thermal infrared imager obtains the P frame gradation datas including the first frame gradation data,
The processor is used for：
It will be divided into M macro block per frame gradation data, wherein P is the positive integer more than 1；
From determined in the M macro block include in the P frames gradation data be more than the first preset temperature threshold
Macro block determines K macro block altogether；
Determine P of first macro block on the P frames gradation data the first temperature values in the K macro block；
Calculate the standard deviation and mean value of the P the first temperature values, and determine the standard deviation of P first temperature value with
The ratio of mean value；
Based on the P standard deviations of the first temperature value and the ratio of mean value, the fluctuation characteristic of first macro block is determined,
The fluctuation characteristic of the K macro block is obtained altogether.
Optionally, the processor is used for：
It determines and is more than the first pixel in L pixel of the second preset temperature threshold in the K macro block in the first macro block
First position and first pixel of the point in the first frame gradation data are obtained by the thermal infrared imager
The second position in the second frame gradation data including target object；
Temperature gap based on the first position and the second position between front and back two frames gradation data, determine described in
The positional fluctuation feature of first pixel obtains the positional fluctuation feature of the L pixel altogether.
Optionally, the processor is additionally operable to：
If the temperature gap is more than preset temperature difference, determine that first pixel has fluctuation characteristic；
Count the pixel number with fluctuation characteristic in first macro block；
If the pixel number is more than predetermined number, determine that the first sub-goal object of the first macro block characterization is fire
Flame.
Optionally, it is described determine K macro block after, the processor is additionally operable to：
If the current distance value between the first sub-goal object and the thermal infrared imager of the first macro block characterization is less than
First pre-determined distance value, judges whether the ratio is more than default ratio；
If the ratio is more than the default ratio, and the current distance value is more than the second pre-determined distance value, determines institute
It is flame to state the first sub-goal object, wherein the second pre-determined distance value is less than the first pre-determined distance value.
Optionally, the processor is additionally operable to：
If the ratio is more than the default ratio, and the current distance value is not more than the second pre-determined distance value,
Judge whether the pixel number with fluctuation characteristic is more than predetermined number in first macro block；
If the pixel number is more than the predetermined number, determine that the first sub-goal object is flame.
Optionally, it is described determine K macro block after, the processor is additionally operable to：
If L pixel in first macro block more than second preset temperature threshold is formed by first area face
Product is more than the first preset area, judges whether the ratio is more than default ratio；
If the ratio is more than the default ratio, and the first area area is less than the second preset area, determines institute
It is flame to state the first sub-goal object, wherein second preset area is more than first preset area.
Optionally, the processor is additionally operable to：
If the ratio is more than the default ratio, and the first area area is not less than second preset area,
Judge whether the pixel number with fluctuation characteristic is more than predetermined number in first macro block；
If the pixel number is more than the predetermined number, determine that the first sub-goal object is flame.
On the other hand, the embodiment of the present invention additionally provides a kind of fire detection device, including：
Obtaining unit, for including the first frame gradation data of target object by thermal infrared imager acquisition, wherein described
First frame gradation data includes N number of pixel, and N is the positive integer more than 1；
First determination unit determines K in the M macro block for the first frame gradation data to be divided into M macro block
The fluctuation characteristic of a macro block, wherein each macro block includes at least one picture that temperature value is more than predetermined threshold value in the K macro block
Vegetarian refreshments, M are the positive integer more than 1, and K is the positive integer no more than M；
Second determination unit determines that the target object is fire if the fluctuation characteristic of the K macro block meets preset condition
Flame.
Optionally, first determination unit is used for：
Determine that the fluctuation of the first temperature value in each macro block of the K macro block more than the first preset temperature threshold is special
Sign；And/or
Determine the positional fluctuation of L pixel in each macro block of the K macro block more than the second preset temperature threshold
Feature, wherein second preset temperature threshold is not more than the first preset temperature threshold.
Optionally, first determination unit is used for：
It, will be per frame grey when including the multiframe gradation data of the target object by thermal infrared imager acquisition
According to being divided into M macro block, wherein P is the positive integer more than 1；
From determined in the M macro block include in the P frames gradation data be more than the first preset temperature threshold
Macro block determines K macro block altogether；
Determine P of first macro block on the P frames gradation data the first temperature values in the K macro block；
Calculate the standard deviation and mean value of the P the first temperature values, and determine the standard deviation of P first temperature value with
The ratio of mean value；
Based on the P standard deviations of the first temperature value and the ratio of mean value, the fluctuation characteristic of first macro block is determined,
The fluctuation characteristic of the K macro block is obtained altogether.
Optionally, first determination unit is used for：
It determines and is more than the first pixel in L pixel of the second preset temperature threshold in the K macro block in the first macro block
First position and first pixel of the point in the first frame gradation data are obtained by the thermal infrared imager
The second position in the second frame gradation data including target object；
Temperature gap based on the first position and the second position between front and back two frames gradation data, determine described in
The positional fluctuation feature of first pixel obtains the positional fluctuation feature of the L pixel altogether.
Optionally, second determination unit is used for：
If the temperature gap is more than preset temperature difference, determine that first pixel has fluctuation characteristic；
Count the pixel number with fluctuation characteristic in first macro block；
If the pixel number is more than predetermined number, determine that the first sub-goal object of the first macro block characterization is fire
Flame.
Optionally, it is described determine K macro block after, described device further includes：
First judging unit, if working as between the first sub-goal object and the thermal infrared imager of first macro block characterization
Front distance value is less than the first pre-determined distance value, judges whether the ratio is more than default ratio；
Third determination unit, if the ratio is more than the default ratio, and the current distance value is more than second and presets
Distance value determines that the first sub-goal object is flame, wherein the second pre-determined distance value be less than described first it is default away from
From value.
Optionally, described device further includes：
Second judgment unit, if the ratio is more than the default ratio, and the current distance value is no more than described the
Two pre-determined distance values judge whether the pixel number with fluctuation characteristic is more than predetermined number in first macro block；
4th determination unit determines the first sub-goal object if the pixel number is more than the predetermined number
For flame.
Optionally, it is described determine K macro block after, described device further includes：
Third judging unit, if being more than L pixel institute shape of second preset temperature threshold in first macro block
At first area area be more than the first preset area, judge whether the ratio is more than default ratio；
5th determination unit, if the ratio is more than the default ratio, and the first area area is less than second in advance
If area, determine that the first sub-goal object is flame, wherein second preset area is more than the described first default face
Product.
Optionally, described device further includes：
4th judging unit, if the ratio is more than the default ratio, and the first area area is not less than described
Second preset area judges whether the pixel number with fluctuation characteristic is more than predetermined number in first macro block；
6th determination unit determines the first sub-goal object if the pixel number is more than the predetermined number
For flame.
On the other hand, an embodiment of the present invention provides a kind of terminal, the terminal includes processor, and the processor is used for
The step of fire behavior detection method as described above being realized when executing the computer program stored in memory.
On the other hand, an embodiment of the present invention provides a kind of readable storage medium storing program for executing, are stored thereon with computer program, described
The step of fire behavior detection method as described above is realized when computer program is executed by processor.
Said one in the embodiment of the present invention or multiple technical solutions at least have following one or more technology effects
Fruit：
Include the first frame gray scale of target object by thermal infrared imager acquisition in the technical solution of the embodiment of the present invention
Data, wherein the first frame gradation data includes N number of pixel, and N is the positive integer more than 1；By the first frame grey
According to M macro block is divided into, the fluctuation characteristic of K macro block in the M macro block is determined, wherein each macro block in the K macro block
It is more than at least one pixel of predetermined threshold value including temperature value, M is the positive integer more than 1, and K is the positive integer no more than M；If
The fluctuation characteristic of the K macro block meets preset condition, determines that the target object is flame.That is, by including
The fluctuation characteristic of local macro block in the gradation data of target object is detected, and then determines whether the target object is fire
Flame further comes in conjunction with the fluctuation characteristic of local macro block comprehensive while realizing on the whole to fire behavior progress Preliminary detection
Judgement is closed, to solve the technical problem relatively low for the fire behavior detection method accuracy of fire of the existing technology, is carried
The accuracy of the high fire behavior detection method for fire.
Description of the drawings
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, embodiment will be described below
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description be only the present invention some
Embodiment.
Fig. 1 is a kind of method flow diagram of the fire behavior detection method provided in the embodiment of the present invention one；
Fig. 2 is step in step S102 in a kind of fire behavior detection method for providing in the embodiment of the present invention one：Determine the M
The method flow diagram of the first realization method of the fluctuation characteristic of K macro block in a macro block；
Fig. 3 is step in step S102 in a kind of fire behavior detection method for providing in the embodiment of the present invention one：Determine the M
The method flow diagram of second of realization method of the fluctuation characteristic of K macro block in a macro block；
Fig. 4 is to be determined using second of realization method in a kind of fire behavior detection method provided in the embodiment of the present invention one
Method flow diagram in the M macro block after the fluctuation characteristic of K macro block；
Fig. 5 be in the embodiment of the present invention one in a kind of fire behavior detection method for providing in step S202 step：Determine K
Method flow diagram after a macro block；
Fig. 6 is a kind of another method flow diagram of the fire behavior detection method provided in the embodiment of the present invention one；
Fig. 7 is based on target object in a kind of fire behavior detection method provided in the embodiment of the present invention one apart from infrared thermal imagery
The flow chart that fire behavior is detected when instrument distance；
Fig. 8 is a kind of fire behavior detection method for providing step in step S202 in the embodiment of the present invention one：Determine K
Method flow diagram after macro block；
Fig. 9 is a kind of another method flow diagram of the fire behavior detection method provided in the embodiment of the present invention one；
Figure 10 is the region area based on target object in a kind of fire behavior detection method provided in the embodiment of the present invention one
The flow chart that fire behavior is detected；
Figure 11 is a kind of structural schematic diagram of the fire detection device provided in the embodiment of the present invention two；
Figure 12 is a kind of structural schematic diagram of the fire detection device provided in the embodiment of the present invention three.
Specific implementation mode
The embodiment of the present invention provides a kind of fire behavior detection method and device, of the existing technology for fire for solving
The relatively low technical problem of fire behavior detection method accuracy, improve the accuracy of the fire behavior detection method for fire.
In order to solve the above technical problems, general thought is as follows for technical solution in the embodiment of the present invention：
A kind of fire behavior detection method, including：
It include the first frame gradation data of target object by thermal infrared imager acquisition, wherein the first frame grey
According to including N number of pixel, N is the positive integer more than 1；
The first frame gradation data is divided into M macro block, determines the fluctuation characteristic of K macro block in the M macro block,
Wherein, each macro block includes at least one pixel of the temperature value more than predetermined threshold value in the K macro block, and M is just more than 1
Integer, K are the positive integer no more than M；
If the fluctuation characteristic of the K macro block meets preset condition, determine that the target object is flame.
Include the first frame gray scale of target object by thermal infrared imager acquisition in the technical solution of the embodiment of the present invention
Data, wherein the first frame gradation data includes N number of pixel, and N is the positive integer more than 1；By the first frame grey
According to M macro block is divided into, the fluctuation characteristic of K macro block in the M macro block is determined, wherein each macro block in the K macro block
It is more than at least one pixel of predetermined threshold value including temperature value, M is the positive integer more than 1, and K is the positive integer no more than M；If
The fluctuation characteristic of the K macro block meets preset condition, determines that the target object is flame.That is, by including
The fluctuation characteristic of local macro block in the gradation data of target object is detected, and then determines whether the target object is fire
Flame further comes in conjunction with the fluctuation characteristic of local macro block comprehensive while realizing on the whole to fire behavior progress Preliminary detection
Judgement is closed, to solve the technical problem relatively low for the fire behavior detection method accuracy of fire of the existing technology, is carried
The accuracy of the high fire behavior detection method for fire.
The terms "and/or", only a kind of incidence relation of description affiliated partner, indicates that there may be three kinds of passes
System, for example, A and/or B, can indicate：Individualism A exists simultaneously A and B, these three situations of individualism B.In addition, herein
Middle character "/", in the case where not illustrating, it is a kind of relationship of "or" to typically represent forward-backward correlation object.
The terms " first " and " second " are for distinguishing different objects, not for description particular order.In addition,
Term " comprising " and their any deformations, it is intended that cover non-exclusive protection.Such as contain series of steps or list
The step of process, method, system, product or the equipment of member are not limited to list or unit, but further include optionally not having
The step of listing or unit, or further include optionally for the intrinsic other steps of these processes, method, product or equipment or
Unit.
Fire behavior detection method in the embodiment of the present invention can be applied to video camera, and the video camera refers at least with red
The video camera of outer camera function.It is mentioned here that at least to have the function of that infrared photography refers to that the video camera can at least carry out infrared
Image Acquisition, such as infrared image acquisition can only be carried out, or infrared image acquisition can also be carried out simultaneously and can
Light-exposed Image Acquisition.Video camera in the embodiment of the present invention can be monocular thermal imaging camera, or can be binocular (all the way
Thermal imaging, all the way visible light) video camera, or can also be multi-lens camera (at least thermal imaging all the way), in addition, for such as
The video camera in the prior art that can only carry out visible light shooting, can be when needing to implement the scheme in the embodiment of the present invention
This can will install a simple thermal imaging sensor additional on light video camera.
In addition, the video camera in the embodiment of the present invention can be the device for supporting temp sensing function, it can also be and do not support to survey
The device of temperature function, for example, the temperature of target object in the present invention can also with the gray scale of the target object respective pixel come
Instead of.Certainly, those skilled in the art can select function possessed by the video camera according to actual needs, herein just not
It has been illustrated one by one.
In order to better understand the above technical scheme, below by attached drawing and specific embodiment to technical solution of the present invention
It is described in detail, it should be understood that the specific features in the embodiment of the present invention and embodiment are to the detailed of technical solution of the present invention
Thin explanation, rather than to the restriction of technical solution of the present invention, in the absence of conflict, the embodiment of the present invention and embodiment
In technical characteristic can be combined with each other.
Embodiment one
Referring to FIG. 1, the embodiment of the present invention one provides a kind of fire behavior detection method, including：
S101：It include the first frame gradation data of target object by thermal infrared imager acquisition, wherein the first frame ash
Degrees of data includes N number of pixel, and N is the positive integer more than 1；
S102：The first frame gradation data is divided into M macro block, determines the fluctuation of K macro block in the M macro block
Feature, wherein in the K macro block each macro block include temperature value be more than predetermined threshold value at least one pixel, M be more than
1 positive integer, K are the positive integer no more than M；
S103：If the fluctuation characteristic of the K macro block meets preset condition, determine that the target object is flame.
Step S101 to step S103's the specific implementation process is as follows：
First, include the first frame gradation data of target object by thermal infrared imager acquisition, that is to say, that user's control
The thermal infrared imager is acquired the current scene including the target object, and then it includes the target object to obtain
First frame gradation data, wherein the gradation data includes N number of pixel, and N number of pixel corresponds to N number of temperature value, and N is
Positive integer more than 1.Wherein, the first frame gradation data is not converted into the gray level image after 8 bits, infrared thermal imagery instead of
The gray scale of target object radiation energy magnitude, the usually data of 14 bits described in the original representative of instrument output.It is being embodied
In the process, can by the thermal infrared imager collected original thermal infrared images be known as Raw image datas.It is general and
Speech, the Raw data of thermal infrared images are all the gradation datas of 14 bits, i.e., indicate that each pixel receives with the gray scale of 14 bits
Heat radiation energy, the gradation datas of 14 bits can have 214A gray value, you can with by different temperature with 0~16383
This 16384 gray value weighs the heat radiation energy of target object.According to the law of thermodynamics it is found that the temperature of object is higher,
The infra-red heat energy of radiation is higher, accordingly it is also possible to say, the temperature of target object is higher, the gray value in corresponding infrared image
It is bigger.
In specific implementation process, wait for the gradation data of 14 bits handling the data rear for 8 bits with thermal image shape
Formula is shown, is checked for user, and certainly, the gradation data can also be that those skilled in the art are set according to actual needs
The data of meter, just differ one has been illustrated herein.
Then, the first frame gray scale is divided into M macro block, determines that the fluctuation of K macro block in the M macro block is special
Sign, wherein each macro block includes at least one pixel that temperature value is more than predetermined threshold value in the K macro block, and M is more than 1
Positive integer, K is positive integer no more than M；Wherein, the predetermined threshold value can be specifically those skilled in the art according to difference
Heat source temperature profile set by temperature threshold, for example, 1000 DEG C.The target pair acquired by the thermal infrared imager
As being possible to different, the pixel number in corresponding the obtained first frame gradation data included by each macro block also may be used
Can be different, can also be 3000 pixels for example, can be 2000 pixels.In addition, to the first frame gradation data
In temperature value be more than the fluctuation characteristic of local macro block of the predetermined threshold value and be detected, for example, by the first frame
M macro block described in gradation data includes that the fluctuation characteristic of K macro block of pixel of the temperature value more than 1000 DEG C is examined
It surveys, the fluctuation characteristic of each macro block includes the fluctuation characteristic of corresponding maximum temperature value in the K macro block, and high temperature pixel (is set
A fixed preset temperature threshold, if pixel corresponding temperature value is more than the preset temperature threshold, then the pixel is high temperature pixel, on the contrary
For low temperature pixel) positional fluctuation feature.In addition, the first frame gradation data is divided into M macro block, for example, will include
The gradation data of 640x512 pixel is divided into 1280 macro blocks, the technology of this field according to the macroblock size of 16x16
The first frame gradation data can be divided into different number of macro block by personnel according to actual needs, and just differ a citing herein
It illustrates.
It is then detected that whether the fluctuation characteristic of the K macro block meets preset condition, for example, highest in the K macro block
Whether the fluctuating range of temperature value is more than a default fluctuating range, for another example, the fluctuation frequency of maximum temperature value in the K macro block
Whether rate is more than a default vibration frequency, and for another example, whether the vibration frequency of the K macro block high temperature pixel position
More than default vibration frequency, etc., certainly, those skilled in the art can design the default item according to actual needs
Part, just differ one has been illustrated herein.
Further, if the fluctuation characteristic of the K macro block meets preset condition, it is determined that the target object is fire
Flame.If for example, the vibration frequency of the K macro maximum temperature values in the block is more than a default vibration frequency, it is determined that the mesh
Mark object is flame, can further export the warning information for the fire behavior, prompt related personnel the flame is carried out and
When handle.
In embodiments of the present invention, step in step S102：The fluctuation characteristic for determining K macro block in the M macro block, can
There are following three kinds of realization methods, but it is not limited only to following three kinds of realization methods.
The first realization method
The first realization method is specially：It determines and is more than the first preset temperature threshold in each macro block of the K macro block
The first temperature value fluctuation characteristic.Specifically, the specific implementation process of the first realization method is as shown in Fig. 2, include：
S201：The P frame gradation datas including the first frame gradation data are obtained by the thermal infrared imager, and
It will be divided into M macro block per frame gradation data, wherein P is the positive integer more than 1；
S202：From being determined in the M macro block in the P frames gradation data including being more than the first preset temperature threshold
The macro block of value determines K macro block altogether；
S203：Determine P of first macro block in P frame data the first temperature values in the K macro block；
S204：The standard deviation and mean value of the P the first temperature values are calculated, and determines the mark of P first temperature value
The ratio of quasi- difference and mean value；
S205：Based on the P standard deviations of the first temperature value and the ratio of mean value, the fluctuation of first macro block is determined
Feature obtains the fluctuation characteristic of the K macro block altogether.
In specific implementation process, step S201 to step S205's the specific implementation process is as follows：
First, the P frame gradation datas including the first frame gradation data are obtained by the thermal infrared imager, and
It will be divided into M macro block per frame gradation data, that is to say, that multiframe gradation data is obtained by the thermal infrared imager；For example,
Include a frame gradation data of the target object in the acquisition of the first moment, then each 0.01 second one frame of acquisition includes the mesh
The gradation data of object is marked, acquisition altogether obtains the 10 frame gradation datas including the target object, and will be per frame grey
According to being divided into M macro block.Then, from being determined in the M macro block in the P frames gradation data including being more than first in advance
If the macro block of temperature threshold determines K macro block altogether.For example, being 10, M 6 in P, divides and compile in the first frame gradation data
Number for a~f totally six macro blocks, wherein number is a and the macro block of b includes more than described first in 10 frame gradation datas
The pixel of preset temperature threshold, it is determined that the macro block that the K macro block gone out is the macro block that number is a and number is b.
Then, it is determined that go out P of first macro block on P frame gradation datas the first temperature values in the K macro block, for example,
Determine the maximum temperature value for numbering the macro block for being a in every frame gradation data of 10 frame gradation datas.For another example, determine that number is
Maximum temperature value of the macro block of b in every frame gradation data of 10 frame gradation datas, just differ one has been illustrated herein.Having
In body implementation process, the maximum temperature value is not less than first temperature value.
Then, the standard deviation and mean value of the P the first temperature values are calculated, and determines the mark of p first temperature value
The ratio of quasi- difference and mean value.Still by taking above-mentioned example as an example, determining number the macro block for being a on 10 frame gradation datas 10 are most
The mean value and standard deviation of high temperature value, then, it is determined that numbering 10 maximum temperature values of the macro block for being a on 10 frame gradation datas
Standard deviation and mean value ratio；Then, based on the P standard deviations of the first temperature value and the ratio of mean value, determine described in
The fluctuation characteristic of first macro block.That is, determining the fluctuation characteristic of the described first macro maximum temperature value in the block.Wherein,
The fluctuating range of bigger characterization first temperature value of the ratio is bigger, instead, the smaller characterization of the first ratio described the
The fluctuating range of one temperature value is smaller.For example, the mean value of the maximum temperature value obtained in the first macro block is 1000 DEG C, standard deviation is
2 DEG C, ratio 1/500 is less than set 1/40, shows that the maximum temperature value fluctuating range in the macro block is smaller.Based on true
The same inventive concept of the fluctuation characteristic of the fixed K macro first macro blocks in the block, finally obtains the K macro block
Fluctuation characteristic no longer details in specific determination process.
It is in embodiments of the present invention, fixed by using maximum temperature value of the flame in some region,
With this feature of certain fluctuating range, and then for distinguishing flame and common high temp objects, to improve for compared with
The accuracy of big flare detection.
Second of realization method
Second of realization method be specially：It determines and is more than the second preset temperature threshold in each macro block of the K macro block
L pixel positional fluctuation feature, wherein second preset temperature threshold be not more than the first preset temperature threshold.Tool
For body, the specific implementation process of second of realization method is as shown in figure 3, include：
S301：It determines in the K macro block and is more than first in L pixel of the second preset temperature threshold in the first macro block
First position and first pixel of the pixel in the first frame gradation data are passing through the thermal infrared imager
Obtain the second position in the second frame gradation data for including target object；
S302：Temperature gap based on the first position and the second position between front and back two frames gradation data, really
The positional fluctuation feature of fixed first pixel, obtains the positional fluctuation feature of the L pixel altogether.
In specific implementation process, step S301 to step S302's the specific implementation process is as follows：
First, it determines in the K macro block and is more than first in L pixel of the second preset temperature threshold in the first macro block
First position and first pixel of the pixel in the first frame gradation data are passing through the thermal infrared imager
Obtain the second position in the second frame gradation data for including target object.Wherein, to the determination process of the K macro block with the
A kind of realization method, details are not described herein again.In addition, in specific implementation process, it can be macro to the K in the block each
Macro block carries out binaryzation, therefrom determines macro high temperature pixel in the block.For example, being with the K macro first macro blocks in the block
Example illustrates the specific implementation process of second of realization method, first, determines and is more than the second preset temperature in first macro block
L pixel of threshold value further determines each pixel position after determining to meet L pixel of condition
The fluctuation characteristic at place.For example, carrying out binaryzation to first macro block, determine to include more than described from first macro block
L pixel of the second preset temperature threshold.Then, by taking any one pixel in the L pixel as an example, for example,
By taking the first pixel in the L pixel as an example, first, determine first pixel in the first frame gradation data
In first position and first pixel obtained by the thermal infrared imager including target object the second frame it is grey
The second position in degrees of data, for example, determining position of first pixel in front and back two frames gradation data.
Then, the temperature gap based on the first position and the second position between front and back two frames gradation data, really
The positional fluctuation feature of fixed first pixel.In specific implementation process, described in the determination L pixel
The same inventive concept of the positional fluctuation feature of first pixel finally obtains the positional fluctuation feature of the L pixel,
It is no longer detailed in specific determination process.In addition, in specific implementation process, second preset temperature threshold can be this
Field technology personnel set temperature threshold according to actual needs, for example, 3000 DEG C, etc..Specifically, from by described
In the pixel of the every frame gradation data for the multiframe gradation data including the target object that thermal infrared imager obtains, determine
More than position of the pixel of the second preset temperature threshold in every frame gradation data.Further, it is based on being more than described second
Temperature gap of the position of the pixel of preset temperature threshold between front and back two frames gradation data determines that the fluctuation of each position is special
Sign.For example, coordinate points (0,0) position in the gradation data of the first frame of thermal infrared imager acquisition where a pixels
Place is the high temperature value more than second preset temperature threshold, and the coordinate points (0,0) in the second subsequent frame gradation data
It is the low temperature value less than second preset temperature threshold at position, shows that the shape of the target object at the position occurs
Fluctuation.It, will be described in determination by the multiframe gradation data that continuous acquisition includes the target object in specific implementation process
The fluctuation of target object global shape.Due to the mobility of air, flame profile can be fluctuated constantly, and this point is different from common high
The high temperature sources such as warm object and the sun.By being detected to the shape fluctuation of the target object, can further increase
For the accuracy of fire behavior detection, rate of false alarm is reduced.
In embodiments of the present invention, special in the positional fluctuation for determining the L pixel using second of realization method
After sign, in order to further increase the accuracy for being directed to fire behavior detection, still by taking the detection of the fire behavior of first macro block as an example, it please join
Fig. 4 is examined, the method further includes：
S401：If the temperature gap is more than preset temperature difference, determine that first pixel has fluctuation characteristic；
S402：Count the pixel number with fluctuation characteristic in first macro block；
S403：If the pixel number is more than predetermined number, the first sub-goal pair of the first macro block characterization is determined
As for flame.
In specific implementation process, step S401 to step S403's the specific implementation process is as follows：
First, if the temperature gap of the first position and the second position between front and back two frames gradation data is more than in advance
If temperature gap, it is determined that first pixel has fluctuation characteristic.For example, the temperature gap is 5000 DEG C, it is described pre-
If temperature gap is 2000 DEG C.Certainly, it is poor the preset temperature can be arranged according to actual needs by those skilled in the art
The concrete numerical value of value, just differ one has been illustrated herein.
Then, the pixel number with fluctuation characteristic in first macro block is counted, it is specifically, macro from described first
The pixel number with fluctuation characteristic is determined in the L pixel of block.Further, the pixel number is detected
Whether predetermined number is more than, if the pixel number is more than the predetermined number, it is meant that, the institute of the first macro block characterization
The shape fluctuation characteristic for stating the first sub-goal object is obvious, it is determined that the first sub-goal object of the first macro block characterization
For flame.For example, the pixel number is 100, the predetermined number is 200, then illustrates exist in first macro block
Fire behavior.Certainly, those skilled in the art can design the concrete numerical value of the predetermined number according to actual needs, herein
Differ and one has been illustrated.
The third realization method
The third realization method is the combination of the first realization method and second of realization method, specially：Determine the K
More than the fluctuation characteristic of the first temperature value of the first preset temperature threshold in each macro block of a macro block；And determine the K
More than the positional fluctuation feature of L pixel of the second preset temperature threshold in each macro block of macro block, wherein described second is pre-
If temperature threshold is not more than the first preset temperature threshold.Finally in conjunction with the fluctuation characteristic of first temperature value and the L picture
The positional fluctuation feature of vegetarian refreshments, determines the fluctuation characteristic of each macro block.For example, for the inspection of the larger flame under closer distance
It surveys, it is higher in the flame temperature values measured, and after the fluctuating range of temperature value is also larger, can also further detect the fire
Whether the shape fluctuation of flame meets condition, to further improve the accuracy for being directed to fire behavior detection, reduces rate of false alarm.Than
Such as, the flame of alcolhol burner is detected for the thermal infrared imager is used, although to meet temperature value higher for its feature, and
Temperature value fluctuating range is larger, if unbonded shape fluctuates to judge, it is easy to the flame of alcolhol burner is just mistaken for fire,
Therefore, the present invention further judges that the accuracy detected for short distance fire behavior can be improved in conjunction with shape fluctuation.Due to
Detailed cohesive process between the two will be described in detail in following schemes, be just no longer described in detail one by one herein.
In embodiments of the present invention, when the device detected for fire behavior includes the camera for whole scene ranging, in order to
The accuracy for further improving fire behavior detection method, the step in step S202：After determining K macro block, figure is please referred to
5, the method further includes：
S501：If the current distance value between the first sub-goal object and the thermal infrared imager of the first macro block characterization
Less than the first pre-determined distance value, judge whether the ratio is more than default ratio；
S502：If the ratio is more than the default ratio, and the current distance value is more than the second pre-determined distance value, really
The fixed first sub-goal object is flame, wherein the second pre-determined distance value is less than the first pre-determined distance value.
In specific implementation process, step S501 to step S502's the specific implementation process is as follows：
First, if first macro block characterization the first sub-goal object and the thermal infrared imager between current distance value
When not less than the first pre-determined distance value, for example, the current distance value is 5km, the first pre-determined distance value is 3km, is shown
The first sub-goal object is long-range detection target, once detect that the maximum temperature value in the macro block is more than described first
Preset temperature threshold then shows that the first sub-goal object is flame, there is fire behavior.
If the current distance is less than the first pre-determined distance value, for example, the current distance value is 1km, described the
One pre-determined distance value be 3km, detect the maximum temperature value in first macro block be more than first preset temperature threshold it
Afterwards, further, judge whether the fluctuation characteristic (for example, fluctuating range or vibration frequency) of the maximum temperature value meets item
Part.Specifically, for a high temperature dot, it can be used as doubtful burning things which may cause a fire disaster, do not alarmed temporarily.If it is flame, slightly greatly
Some temperature value fluctuation characteristic is just had, further, the fluctuation characteristic of combination temperature value judges, specifically, judges institute
It states whether the ratio of the standard deviation of maximum temperature value and mean value in the first macro block is more than default ratio, is preset if the ratio is more than
Ratio, and the current distance value is more than the second pre-determined distance value less than the first pre-determined distance value, determines described first
Sub-goal object is flame, for example, the current distance value is 1km, the first pre-determined distance value is 3km, and described second is pre-
If distance value is 100m, show that the first sub-goal object is middle distance measurement target, the highest in first macro block
When the fluctuation characteristic of temperature value meets ratio more than default this condition of ratio, then further by the first sub-goal object
It is determined as flame, you can fire behavior is alarmed.In addition, in embodiments of the present invention, those skilled in the art can be according to actually making
The first pre-determined distance value and the second pre-determined distance value are set with situation, and just differ one has been illustrated herein.
In embodiments of the present invention, in order to further increase the accuracy of fire behavior detection, referring to FIG. 6, the method is also
Including：
S601：If the ratio is more than the default ratio, and the current distance value it is default no more than described second away from
From value, judge whether the pixel number with fluctuation characteristic is more than predetermined number in first macro block；
S602：If the pixel number is more than the predetermined number, determine that the first sub-goal object is flame.
Step S601 to step S602's the specific implementation process is as follows：
First, if the ratio of the standard deviation of maximum temperature value and mean value is more than default ratio, and institute in first macro block
It states current distance and is not more than the second pre-determined distance value, that is to say, that when carrying out the detection of short distance fire behavior, further tie
The positional fluctuation feature of L pixel position in first macro block more than second preset temperature threshold is closed to examine
It surveys.For example, the current distance value is 50m, the first pre-determined distance value is 3km, and the second pre-determined distance value is 100m,
Further, judge whether the pixel number with fluctuation characteristic is more than predetermined number in first macro block.If the picture
Vegetarian refreshments number is more than the predetermined number, shows that first macro block has high temperature location of pixels fluctuation characteristic, determines described the
One sub-goal object is flame.For specific determination process, it has been described in detail above-mentioned, has not just repeated one by one herein.In addition,
In order to further improve the accuracy of fire behavior detection, if first macro block persistently meets high temperature location of pixels fluctuation characteristic
Frame number is more than a default frame number, then shows that the fluctuating range of first macro block is more than the described first default fluctuating range, into one
Step determines that the first sub-goal object is flame.
In embodiments of the present invention, it due to, to the detection of fire behavior, being easy to cause to report by mistake under short distance, further combines
The fluctuation characteristic of pixel position judges, can further improve the accuracy for fire behavior detection, specifically sentence
Disconnected process does not just repeat one by one herein due to having detailed in above process.
In addition, in embodiments of the present invention, in order to further increase the performance of the corresponding device of fire behavior detection, root
It can automatically select different fluctuation characteristics apart from situation apart from the thermal infrared imager according to the target object and come to fire behavior
It is detected.Fluctuation characteristic and the distance of detectable distance are combined together, to improve fire behavior detection algorithm just
True rate.For example, when to carrying out fire behavior detection at a distance, it only need to be to the maximum temperature of local macro block in the first frame gradation data
Whether value is judged more than the predetermined threshold value, once detect the highest temperature of local macro block in the first frame gradation data
Angle value is more than the predetermined threshold value, that is, is determined as there is fire behavior, you can output alarm.For another example, centering distance carries out fire behavior
When detection, the maximum temperature value of local macro block is more than the predetermined threshold value in detecting the first frame gradation data, need to be into
Whether the fluctuation characteristic that one step detects the maximum temperature value in the macro block meets the preset condition, only when meeting, just will
The corresponding sub-goal object of the macro block is determined as there is fire behavior, then exports alarm.For another example, fire behavior detection is carried out to short distance
When, it need to detect whether the maximum temperature value of local macro block in the first frame gradation data is more than the predetermined threshold value, if greatly
In whether the fluctuation characteristic for further detecting the maximum temperature value in the macro block meets the preset condition, if satisfied, needing again
Further detect whether the pixel number with fluctuation characteristic in the first macro block is more than predetermined number, if more than then should
The corresponding sub-goal object of macro block is determined as there is fire behavior, then exports alarm.
In embodiments of the present invention, when being illustrated in figure 7 based on the target object apart from the thermal infrared imager distance
To the flow chart that fire behavior is detected, specific processing procedure has been described in detail in above process, and details are not described herein again.
In embodiments of the present invention, when the device detected for fire behavior does not have range measurement, in order to further carry
The accuracy of high fire behavior detection method, the step in step S202：After determining K macro block, referring to FIG. 8, the side
Method further includes：
S701：If L pixel in first macro block more than second preset temperature threshold is formed by first
Region area is more than the first preset area, judges whether the ratio is more than default ratio；
S702：If the ratio is more than the default ratio, and the first area area is less than the second preset area, really
The fixed first sub-goal object is flame, wherein second preset area is more than first preset area.
In specific implementation process, step S701 to step S702's the specific implementation process is as follows：
First, it detects and is more than L pixel of second preset temperature threshold in first macro block and is formed by the
Whether one region area is more than the first preset area, wherein first preset area is those skilled in the art according to design
Need set empirical value.
If the L pixel, which is formed by the first area area, is less than first preset area, for example, described
First area area is that 5 pixels are formed by region area, and first preset area is that 10 pixels are formed by
Region area shows that the corresponding first sub-goal object of first macro block is long-range detection target, once it detects
Maximum temperature value in the macro block is more than first preset temperature threshold, then shows that the first sub-goal object is flame,
There is fire behavior.
If the first area area is more than first preset area, need further, to judge in first macro block
Whether the standard deviation of maximum temperature value and the ratio of mean value are more than default ratio, if the ratio is more than the default ratio, and
The first area area is less than the second preset area, determines that the first sub-goal object is flame, wherein described second is pre-
If area is more than first preset area.For example, first area area, which is 20 pixels, is formed by region area, it is described
First preset area is that 10 pixels are formed by region area, and second preset area is that 30 pixels are formed by
Region area, being less than second preset area in the first area area, (second preset area is more than described first
Preset area, that is to say, that the first area area is more than first preset area, and is less than the described second default face
Product) when, show that the first sub-goal object is middle distance measurement target, need to further detect in first macro block most
Whether the fluctuation characteristic of high temperature value meets ratio and is more than default this condition of ratio, the maximum temperature in first macro block
When the fluctuation characteristic of value meets ratio more than default this condition of ratio, then further the first sub-goal object is determined
For flame, you can fire behavior is alarmed.In addition, in embodiments of the present invention, those skilled in the art can be according to actual use feelings
First preset area and second preset area is arranged in condition, and herein just differing one has been illustrated.
In embodiments of the present invention, in order to further improve the accuracy of fire behavior detection method, referring to FIG. 9, described
Method further includes：
S801：If the ratio is more than the default ratio, and the first area area is default not less than described second
Area judges whether the pixel number with fluctuation characteristic is more than predetermined number in first macro block；
S802：If the pixel number is more than the predetermined number, determine that the first sub-goal object is flame.
In specific implementation process, step S801 to step S802's the specific implementation process is as follows：
First, if the ratio of the standard deviation of maximum temperature value and mean value is more than default ratio, and institute in first macro block
It states first area area and is not less than second preset area, that is to say, that carrying out short distance fire behavior detection.It is being embodied
It needs in the process further in place in conjunction with the L pixel institute for being more than second preset temperature threshold in first macro block
The positional fluctuation feature set detects.For example, the first area area, which is 40 pixels, is formed by region area, it is described
First preset area is that 10 pixels are formed by region area, and second preset area is that 30 pixels are formed by
Region area, further, judging to be more than in L pixel of second preset temperature threshold in first macro block has
Whether the pixel number of fluctuation characteristic is more than predetermined number.If the pixel number is more than the predetermined number, institute is determined
It is flame to state the first sub-goal object.For specific determination process, it has been described in detail above-mentioned, has not just repeated one by one herein.
In addition, in order to further improve the accuracy of fire behavior detection, if first macro block persistently meets the fluctuation of high temperature location of pixels
The frame number of feature is more than a default frame number, then shows that first fluctuating range is more than the described first default fluctuating range, into one
Step determines that the first sub-goal object is flame.
In embodiments of the present invention, it due to, to the detection of fire behavior, being easy to cause to report by mistake under short distance, further combines
The fluctuation characteristic of pixel position judges, can further improve the accuracy for fire behavior detection, specifically sentence
Disconnected process does not just repeat one by one herein due to having detailed in above process.
In embodiments of the present invention, as shown in Figure 10 for the region area based on the target object different situations come pair
The flow chart that fire behavior is detected, specific processing procedure have been described in detail in above process, are not just repeating herein.
Embodiment two
Based on inventive concept same as the embodiment of the present invention one, 1 is please referred to Fig.1, the embodiment of the present invention additionally provides one
Kind fire detection device, including：
Thermal infrared imager 10, for obtain include target object first frame gradation data, wherein the first frame gray scale
Data include N number of pixel, and N is the positive integer more than 1；
Processor 20 determines that K is a macro in the M macro block for the first frame gradation data to be divided into M macro block
The fluctuation characteristic of block, wherein each macro block includes at least one pixel that temperature value is more than predetermined threshold value in the K macro block
Point, M are the positive integer more than 1, and K is the positive integer no more than M；If the fluctuation characteristic of the K macro block meets preset condition, really
The fixed target object is flame.
In embodiments of the present invention, processor 20 is used for：
Determine that the fluctuation of the first temperature value in each macro block of the K macro block more than the first preset temperature threshold is special
Sign；And/or
Determine the positional fluctuation of L pixel in each macro block of the K macro block more than the second preset temperature threshold
Feature, wherein second preset temperature threshold is not more than the first preset temperature threshold.
In embodiments of the present invention, the P frames including the first frame gradation data are obtained in the thermal infrared imager
When gradation data, processor 20 is used for：
It will be divided into M macro block per frame gradation data, wherein P is the positive integer more than 1；
From determined in the M macro block include in the P frames gradation data be more than the first preset temperature threshold
Macro block determines K macro block altogether；
Determine P of first macro block on the P frames gradation data the first temperature values in the K macro block；
Calculate the standard deviation and mean value of the P the first temperature values, and determine the standard deviation of P first temperature value with
The ratio of mean value；
Based on the P standard deviations of the first temperature value and the ratio of mean value, the fluctuation characteristic of first macro block is determined,
The fluctuation characteristic of the K macro block is obtained altogether.
In embodiments of the present invention, processor 20 is used for：
It determines and is more than the first pixel in L pixel of the second preset temperature threshold in the K macro block in the first macro block
First position and first pixel of the point in the first frame gradation data are obtained by the thermal infrared imager
The second position in the second frame gradation data including target object；
Temperature gap based on the first position and the second position between front and back two frames gradation data, determine described in
The positional fluctuation feature of first pixel obtains the positional fluctuation feature of the L pixel altogether.
In embodiments of the present invention, processor 20 is additionally operable to：
If the temperature gap is more than preset temperature difference, determine that first pixel has fluctuation characteristic；
Count the pixel number with fluctuation characteristic in first macro block；
If the pixel number is more than predetermined number, determine that the first sub-goal object of the first macro block characterization is fire
Flame.
In embodiments of the present invention, it is described determine K macro block after, processor 20 is additionally operable to：
If the current distance value between the first sub-goal object and the thermal infrared imager of the first macro block characterization is less than
First pre-determined distance value, judges whether the ratio is more than default ratio；
If the ratio is more than the default ratio, and the current distance value is more than the second pre-determined distance value, determines institute
It is flame to state the first sub-goal object, wherein the second pre-determined distance value is less than the first pre-determined distance value.
In embodiments of the present invention, processor 20 is additionally operable to：
If the ratio is more than the default ratio, and the current distance value is not more than the second pre-determined distance value,
Judge whether the pixel number with fluctuation characteristic is more than predetermined number in first macro block；
If the pixel number is more than the predetermined number, determine that the first sub-goal object is flame.
In embodiments of the present invention, it is described determine K macro block after, processor 20 is additionally operable to：
If L pixel in first macro block more than second preset temperature threshold is formed by first area face
Product is more than the first preset area, judges whether the ratio is more than default ratio；
If the ratio is more than the default ratio, and the first area area is less than the second preset area, determines institute
It is flame to state the first sub-goal object, wherein second preset area is more than first preset area.
In embodiments of the present invention, processor 20 is additionally operable to：
If the ratio is more than the default ratio, and the first area area is not less than second preset area,
Judge whether the pixel number with fluctuation characteristic is more than predetermined number in first macro block；
If the pixel number is more than the predetermined number, determine that the first sub-goal object is flame.
Embodiment three
Based on inventive concept same as the embodiment of the present invention one, 2 are please referred to Fig.1, the embodiment of the present invention additionally provides one
Kind fire detection device, including：
Obtaining unit 30, for including the first frame gradation data of target object by thermal infrared imager acquisition, wherein institute
It includes N number of pixel to state first frame gradation data, and N is the positive integer more than 1；
First determination unit 40 determines the M macro block for the first frame gradation data to be divided into M macro block
The fluctuation characteristic of middle K macro block, wherein each macro block includes at least one of temperature value more than predetermined threshold value in the K macro block
A pixel, M are the positive integer more than 1, and K is the positive integer no more than M；
Second determination unit 50 determines that the target object is if the fluctuation characteristic of the K macro block meets preset condition
Flame.
In embodiments of the present invention, the first determination unit 40 is used for：
Determine that the fluctuation of the first temperature value in each macro block of the K macro block more than the first preset temperature threshold is special
Sign；And/or
Determine the positional fluctuation of L pixel in each macro block of the K macro block more than the second preset temperature threshold
Feature, wherein second preset temperature threshold is not more than the first preset temperature threshold.
In embodiments of the present invention, the first determination unit 40 is used for：
It, will be per frame grey when including the multiframe gradation data of the target object by thermal infrared imager acquisition
According to being divided into M macro block, wherein P is the positive integer more than 1；
From determined in the M macro block include in the P frames gradation data be more than the first preset temperature threshold
Macro block determines K macro block altogether；
Determine P of first macro block on the P frames gradation data the first temperature values in the K macro block；
Calculate the standard deviation and mean value of the P the first temperature values, and determine the standard deviation of P first temperature value with
The ratio of mean value；
Based on the P standard deviations of the first temperature value and the ratio of mean value, the fluctuation characteristic of first macro block is determined,
The fluctuation characteristic of the K macro block is obtained altogether.
In embodiments of the present invention, the first determination unit 40 is used for：
It determines and is more than the first pixel in L pixel of the second preset temperature threshold in the K macro block in the first macro block
First position and first pixel of the point in the first frame gradation data are obtained by the thermal infrared imager
The second position in the second frame gradation data including target object；
Temperature gap based on the first position and the second position between front and back two frames gradation data, determine described in
The positional fluctuation feature of first pixel obtains the positional fluctuation feature of the L pixel altogether.
In embodiments of the present invention, the second determination unit 50 is used for：
If the temperature gap is more than preset temperature difference, determine that first pixel has fluctuation characteristic；
Count the pixel number with fluctuation characteristic in first macro block；
If the pixel number is more than predetermined number, determine that the first sub-goal object of the first macro block characterization is fire
Flame.
In embodiments of the present invention, it is described determine K macro block after, described device further includes：
First judging unit, if working as between the first sub-goal object and the thermal infrared imager of first macro block characterization
Front distance value is less than the first pre-determined distance value, judges whether the ratio is more than default ratio；
Third determination unit, if the ratio is more than the default ratio, and the current distance value is more than second and presets
Distance value determines that the first sub-goal object is flame, wherein the second pre-determined distance value be less than described first it is default away from
From value.
In embodiments of the present invention, described device further includes：
Second judgment unit, if the ratio is more than the default ratio, and the current distance value is no more than described the
Two pre-determined distance values judge whether the pixel number with fluctuation characteristic is more than predetermined number in first macro block；
4th determination unit determines the first sub-goal object if the pixel number is more than the predetermined number
For flame.
In embodiments of the present invention, it is described determine K macro block after, described device further includes：
Third judging unit, if being more than L pixel institute shape of second preset temperature threshold in first macro block
At first area area be more than the first preset area, judge whether the ratio is more than default ratio；
5th determination unit, if the ratio is more than the default ratio, and the first area area is less than second in advance
If area, determine that the first sub-goal object is flame, wherein second preset area is more than the described first default face
Product.
In embodiments of the present invention, described device further includes：
4th judging unit, if the ratio is more than the default ratio, and the first area area is not less than described
Second preset area judges whether the pixel number with fluctuation characteristic is more than predetermined number in first macro block；
6th determination unit determines the first sub-goal object if the pixel number is more than the predetermined number
For flame.
The another aspect of the embodiment of the present invention provides a kind of terminal, and the terminal includes processor, memory and deposits
The computer program that can be run in the memory and on the processor is stored up, such as：It is wrapped by thermal infrared imager
Include the gradation data of target object, wherein the gradation data includes N number of pixel, and N number of pixel corresponds to N number of temperature
Value, N are the positive integer more than 1；Gradation data is divided into M macro block, M is the positive integer less than N；The gradation data is carried out
Analysis, determines the fluctuation characteristic of K macro block in the M macro block, wherein the K macro maximum temperature values in the block are more than pre-
If threshold value, K is the positive integer less than M；If the fluctuation characteristic meets preset condition, determine that the target object is flame.Institute
State the step realized when processor executes the computer program in the embodiment of the method described in above-mentioned various aspects, such as Fig. 1 institutes
The method and step shown.Alternatively, the processor realizes each unit in above-mentioned each device embodiment when executing the computer program
Function.
Illustratively, the computer program can be divided into one or more module/units, one or more
A module/unit is stored in the memory, and is executed by the processor, to complete the present invention.It is one or more
A module/unit can be the series of computation machine program instruction section that can complete specific function, and the instruction segment is for describing institute
State implementation procedure of the computer program in the fire detection device/terminal.For example, the computer program can be divided
At obtaining unit, the first determination unit, the second determination unit, each module concrete function is as follows：Obtaining unit, for by infrared
Thermal imaging system acquisition includes the first frame gradation data of target object, wherein the first frame gradation data includes N number of pixel, N
For the positive integer more than 1；First determination unit determines the M for the first frame gradation data to be divided into M macro block
The fluctuation characteristic of K macro block in a macro block, wherein each macro block includes that temperature value is more than predetermined threshold value in the K macro block
At least one pixel, M are the positive integer more than 1, and K is the positive integer no more than M；Second determination unit, if the K macro block
Fluctuation characteristic meet preset condition, determine the target object be flame.
Fire detection device/the terminal can be desktop PC, notebook, palm PC and cloud server etc.
Computing device.Fire detection device/the terminal may include, but be not limited only to, processor, memory.Those skilled in the art
It is appreciated that the schematic diagram is only the example of the fire detection device/terminal, does not constitute and dress is detected to the fire behavior
/ the restriction of terminal is set, may include either combining certain components or different components than illustrating more or fewer components,
Such as fire detection device/the terminal can also include input-output equipment, network access equipment, bus etc..
Alleged processor can be central processing unit (Central Processing Unit, CPU), can also be it
His general processor, digital signal processor (Digital Signal Processor, DSP), application-specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor can also be any conventional processor
Deng the processor is the control centre of the fire detection device/terminal, entirely described using various interfaces and connection
The various pieces of fire detection device/terminal.
The memory can be used for storing the computer program and/or module, and the processor is by running or executing
Computer program in the memory and/or module are stored, and calls the data being stored in memory, described in realization
The various functions of fire detection device/terminal.The memory can include mainly storing program area and storage data field, wherein
Storing program area can storage program area, (for example sound-playing function, image play the application program needed at least one function
Function etc.) etc.；Storage data field can be stored uses created data (such as audio data, phone directory etc.) according to mobile phone
Deng.Can also include nonvolatile memory in addition, memory may include high-speed random access memory, such as hard disk, interior
It deposits, plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card,
Flash card (Flash Card), at least one disk memory, flush memory device or other volatile solid-state parts.
The another aspect of the embodiment of the present invention provides a kind of readable storage medium storing program for executing, is stored thereon with computer program, institute
State the method realized when computer program is executed by processor as described in above-mentioned various aspects.
If the integrated module/unit of the fire detection device/terminal is realized in the form of SFU software functional unit and makees
It is independent product sale or in use, can be stored in a computer read/write memory medium.Based on this understanding,
The present invention realizes all or part of flow in above-described embodiment method, can also be instructed by computer program relevant hard
Part is completed, and the computer program can be stored in a readable storage medium storing program for executing, which is being executed by processor
When, it can be achieved that the step of above-mentioned each embodiment of the method.Wherein, the computer program includes computer program code, described
Computer program code can be source code form, object identification code form, executable file or certain intermediate forms etc..It is described can
Reading medium may include：Any entity or device, recording medium, USB flash disk, mobile hard of the computer program code can be carried
Disk, magnetic disc, CD, computer storage, read-only memory (ROM, Read-Only Memory), random access memory
(RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It needs to illustrate
It is that the content that the computer-readable medium includes can be fitted according to legislation in jurisdiction and the requirement of patent practice
When increase and decrease, such as in certain jurisdictions, according to legislation and patent practice, computer-readable medium does not include that electric carrier wave is believed
Number and telecommunication signal.
Include the first frame gray scale of target object by thermal infrared imager acquisition in the technical solution of the embodiment of the present invention
Data, wherein the first frame gradation data includes N number of pixel, and N is the positive integer more than 1；By the first frame grey
According to M macro block is divided into, the fluctuation characteristic of K macro block in the M macro block is determined, wherein each macro block in the K macro block
It is more than at least one pixel of predetermined threshold value including temperature value, M is the positive integer more than 1, and K is the positive integer no more than M；If
The fluctuation characteristic of the K macro block meets preset condition, determines that the target object is flame.That is, by including
The fluctuation characteristic of local macro block in the gradation data of target object is detected, and then determines whether the target object is fire
Flame further comes in conjunction with the fluctuation characteristic of local macro block comprehensive while realizing on the whole to fire behavior progress Preliminary detection
Judgement is closed, to solve the technical problem relatively low for the fire behavior detection method accuracy of fire of the existing technology, is carried
The accuracy of the high fire behavior detection method for fire.
In the technical solution of the embodiment of the present invention, if first macro block characterization the first sub-goal object with it is described red
Current distance value between outer thermal imaging system is less than the first pre-determined distance value, judges whether the ratio is more than default ratio；If described
Ratio is more than the default ratio, and the current distance value is more than the second pre-determined distance value, determines first sub-goal pair
As for flame, wherein the second pre-determined distance value is less than the first pre-determined distance value.That is, in the first sub-goal
Current distance between object and thermal infrared imager be middle distance (between closely and it is remote between) in the case of, need further
Ground carries out fire behavior detection in conjunction with the fluctuation characteristic of the maximum temperature value of first macro block, to improve for middle apart from feelings
Fire behavior detection under condition.
In the technical solution of the embodiment of the present invention, if the ratio is more than the default ratio, and the current distance
Value is not more than the second pre-determined distance value, judges whether the pixel number with fluctuation characteristic is more than in first macro block
Predetermined number；If the pixel number is more than the predetermined number, determine that the first sub-goal object is flame.Namely
It says, in the case that the current distance between the first sub-goal object and thermal infrared imager is short distance, if in first macro block
The fluctuation characteristic of maximum temperature value meet condition (standard deviation of such as maximum temperature value and the ratio of mean value be more than a default ratio
Value), fire behavior detection need to be carried out further combined with the positional fluctuation feature of L pixel position, to improve
For the fire behavior detection in the case of short distance.
Although preferred embodiments of the present invention have been described, it is created once a person skilled in the art knows basic
Property concept, then additional changes and modifications may be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as
It selects embodiment and falls into all change and modification of the scope of the invention.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
God and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (13)
1. a kind of fire behavior detection method, which is characterized in that including：
It include the first frame gradation data of target object by thermal infrared imager acquisition, wherein the first frame gradation data packet
N number of pixel is included, N is the positive integer more than 1；
The first frame gradation data is divided into M macro block, determines the fluctuation characteristic of K macro block in the M macro block,
In, each macro block includes at least one pixel that temperature value is more than predetermined threshold value in the K macro block, and M is just whole more than 1
Number, K are the positive integer no more than M；
If the fluctuation characteristic of the K macro block meets preset condition, determine that the target object is flame.
2. the method as described in claim 1, which is characterized in that the fluctuation of K macro block is special in the determination M macro block
Sign, including：
Determine the fluctuation characteristic of the first temperature value in each macro block of the K macro block more than the first preset temperature threshold；With/
Or,
Determine the positional fluctuation feature of L pixel in each macro block of the K macro block more than the second preset temperature threshold,
Wherein, second preset temperature threshold is not more than the first preset temperature threshold.
3. method as claimed in claim 2, which is characterized in that be more than the in each macro block of the determination K macro block
The fluctuation characteristic of first temperature value of one preset temperature threshold, including：
The P frame gradation datas including the first frame gradation data are obtained by the thermal infrared imager, and will be grey per frame
Degrees of data is divided into M macro block, wherein P is the positive integer more than 1；
From determining to include the macro block more than the first preset temperature threshold in the P frames gradation data in the M macro block,
K macro block is determined altogether；
Determine P of first macro block on the P frames gradation data the first temperature values in the K macro block；
The standard deviation and mean value of the P the first temperature values are calculated, and determines the standard deviation and mean value of P first temperature value
Ratio；
Based on the P standard deviations of the first temperature value and the ratio of mean value, determines the fluctuation characteristic of first macro block, obtain altogether
Obtain the fluctuation characteristic of the K macro block.
4. method as claimed in claim 2, which is characterized in that be more than the in each macro block of the determination K macro block
The positional fluctuation feature of L pixel of two preset temperature thresholds, including：
It determines in the K macro block and exists more than the first pixel in L pixel of the second preset temperature threshold in the first macro block
First position and first pixel in the first frame gradation data are being included by the thermal infrared imager
The second position in second frame gradation data of target object；
Temperature gap based on the first position and the second position between front and back two frames gradation data, determines described first
The positional fluctuation feature of pixel obtains the positional fluctuation feature of the L pixel altogether.
5. method as claimed in claim 4, which is characterized in that the method further includes：
If the temperature gap is more than preset temperature difference, determine that first pixel has fluctuation characteristic；
Count the pixel number with fluctuation characteristic in first macro block；
If the pixel number is more than predetermined number, determine that the first sub-goal object of the first macro block characterization is flame.
6. method as claimed in claim 3, which is characterized in that it is described determine K macro block after, the method is also wrapped
It includes：
If the current distance value between the first sub-goal object and the thermal infrared imager of the first macro block characterization is less than first
Pre-determined distance value, judges whether the ratio is more than default ratio；
If the ratio is more than the default ratio, and the current distance value is more than the second pre-determined distance value, determines described the
One sub-goal object is flame, wherein the second pre-determined distance value is less than the first pre-determined distance value.
7. method as claimed in claim 6, which is characterized in that the method further includes：
If the ratio is more than the default ratio, and the current distance value is not more than the second pre-determined distance value, judges
Whether the pixel number with fluctuation characteristic is more than predetermined number in first macro block；
If the pixel number is more than the predetermined number, determine that the first sub-goal object is flame.
8. method as claimed in claim 3, which is characterized in that it is described determine K macro block after, the method is also wrapped
It includes：
If it is big that L pixel for being more than second preset temperature threshold in first macro block is formed by first area area
In the first preset area, judge whether the ratio is more than default ratio；
If the ratio is more than the default ratio, and the first area area is less than the second preset area, determines described the
One sub-goal object is flame, wherein second preset area is more than first preset area.
9. method as claimed in claim 8, which is characterized in that the method further includes：
If the ratio is more than the default ratio, and the first area area is not less than second preset area, judges
Whether the pixel number with fluctuation characteristic is more than predetermined number in first macro block；
If the pixel number is more than the predetermined number, determine that the first sub-goal object is flame.
10. a kind of fire detection device, which is characterized in that including：
Thermal infrared imager, for obtain include target object first frame gradation data, wherein the first frame gradation data packet
N number of pixel is included, N is the positive integer more than 1；
Processor determines the wave of K macro block in the M macro block for the first frame gradation data to be divided into M macro block
Dynamic feature, wherein each macro block includes at least one pixel that temperature value is more than predetermined threshold value in the K macro block, and M is big
In 1 positive integer, K is the positive integer no more than M；If the fluctuation characteristic of the K macro block meets preset condition, the mesh is determined
Mark object is flame.
11. a kind of fire detection device, which is characterized in that including：
Obtaining unit, for including the first frame gradation data of target object by thermal infrared imager acquisition, wherein described first
Frame gradation data includes N number of pixel, and N is the positive integer more than 1；
First determination unit determines that K is a macro in the M macro block for the first frame gradation data to be divided into M macro block
The fluctuation characteristic of block, wherein each macro block includes at least one pixel that temperature value is more than predetermined threshold value in the K macro block
Point, M are the positive integer more than 1, and K is the positive integer no more than M；
Second determination unit determines that the target object is flame if the fluctuation characteristic of the K macro block meets preset condition.
12. a kind of terminal, which is characterized in that the terminal includes processor, and the processor is stored for executing in memory
Computer program when the step of realizing fire behavior detection method as described in any one of claim 1-9.
13. a kind of readable storage medium storing program for executing, is stored thereon with computer program, which is characterized in that the computer program is handled
The step of fire behavior detection method as described in any one of claim 1-9 is realized when device executes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810034509.6A CN108335454B (en) | 2018-01-15 | 2018-01-15 | A kind of fire behavior detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810034509.6A CN108335454B (en) | 2018-01-15 | 2018-01-15 | A kind of fire behavior detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108335454A true CN108335454A (en) | 2018-07-27 |
| CN108335454B CN108335454B (en) | 2019-09-17 |
Family
ID=62923523
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810034509.6A Active CN108335454B (en) | 2018-01-15 | 2018-01-15 | A kind of fire behavior detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108335454B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109360370A (en) * | 2018-11-30 | 2019-02-19 | 广州高新兴机器人有限公司 | A method of it is detected based on robot pyrotechnics |
| CN110867044A (en) * | 2018-08-27 | 2020-03-06 | 浙江大华技术股份有限公司 | Fire detection method and equipment |
| CN112460737A (en) * | 2020-12-28 | 2021-03-09 | 浙江肯特科技股份有限公司 | Monitoring and early warning processing system for production of warm-keeping shawl |
| CN112504473A (en) * | 2020-12-01 | 2021-03-16 | 浙江大华技术股份有限公司 | Fire detection method, device, equipment and computer readable storage medium |
| CN112785809A (en) * | 2020-12-31 | 2021-05-11 | 四川弘和通讯有限公司 | Fire re-ignition prediction method and system based on AI image recognition |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101650866A (en) * | 2009-09-22 | 2010-02-17 | 华南理工大学 | Fire detecting system applied to unmanned helicopter and fire detecting method thereof |
| EP3159861A1 (en) * | 2015-10-19 | 2017-04-26 | FFE Limited | Improvements in or relating to flame detectors and associated methods |
| CN106997461A (en) * | 2017-03-28 | 2017-08-01 | 浙江大华技术股份有限公司 | A kind of firework detecting method and device |
| JP2017167616A (en) * | 2016-03-14 | 2017-09-21 | 大阪瓦斯株式会社 | Fire alarm device |
| CN107330884A (en) * | 2017-07-06 | 2017-11-07 | 北京安宁威尔科技发展有限公司 | Ignition point detection method and device |
-
2018
- 2018-01-15 CN CN201810034509.6A patent/CN108335454B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101650866A (en) * | 2009-09-22 | 2010-02-17 | 华南理工大学 | Fire detecting system applied to unmanned helicopter and fire detecting method thereof |
| EP3159861A1 (en) * | 2015-10-19 | 2017-04-26 | FFE Limited | Improvements in or relating to flame detectors and associated methods |
| JP2017167616A (en) * | 2016-03-14 | 2017-09-21 | 大阪瓦斯株式会社 | Fire alarm device |
| CN106997461A (en) * | 2017-03-28 | 2017-08-01 | 浙江大华技术股份有限公司 | A kind of firework detecting method and device |
| CN107330884A (en) * | 2017-07-06 | 2017-11-07 | 北京安宁威尔科技发展有限公司 | Ignition point detection method and device |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110867044A (en) * | 2018-08-27 | 2020-03-06 | 浙江大华技术股份有限公司 | Fire detection method and equipment |
| CN109360370A (en) * | 2018-11-30 | 2019-02-19 | 广州高新兴机器人有限公司 | A method of it is detected based on robot pyrotechnics |
| CN112504473A (en) * | 2020-12-01 | 2021-03-16 | 浙江大华技术股份有限公司 | Fire detection method, device, equipment and computer readable storage medium |
| CN112504473B (en) * | 2020-12-01 | 2022-08-09 | 浙江大华技术股份有限公司 | Fire detection method, device, equipment and computer readable storage medium |
| CN112460737A (en) * | 2020-12-28 | 2021-03-09 | 浙江肯特科技股份有限公司 | Monitoring and early warning processing system for production of warm-keeping shawl |
| CN112785809A (en) * | 2020-12-31 | 2021-05-11 | 四川弘和通讯有限公司 | Fire re-ignition prediction method and system based on AI image recognition |
| CN112785809B (en) * | 2020-12-31 | 2022-08-16 | 四川弘和通讯有限公司 | Fire re-ignition prediction method and system based on AI image recognition |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108335454B (en) | 2019-09-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108335454B (en) | A kind of fire behavior detection method and device | |
| CN111739250B (en) | Fire detection method and system combining image processing technology and infrared sensor | |
| EP1732314B1 (en) | Infrared camera with humidity sensor | |
| EP2071280B1 (en) | Normal information generating device and normal information generating method | |
| CN111458039B (en) | Augmented reality body temperature measurement method and device based on infrared temperature measurement camera | |
| CN104751593B (en) | Method and system for fire detection, warning, positioning and extinguishing | |
| CN111337142A (en) | Body temperature correction method and device and electronic equipment | |
| JP2001324305A (en) | Image correspondent position detector and range finder equipped with the same | |
| CN105844240A (en) | Method and device for detecting human faces in infrared temperature measurement system | |
| CN109854964B (en) | Steam leakage positioning system and method based on binocular vision | |
| US9064178B2 (en) | Edge detection apparatus, program and method for edge detection | |
| CN102881106A (en) | Dual-detection forest fire identification system through thermal imaging video and identification method thereof | |
| JP6383439B2 (en) | Method and system for calibrating a sensor using a recognized object | |
| CN113205075A (en) | Method and device for detecting smoking behavior and readable storage medium | |
| CN113358231B (en) | Infrared temperature measurement method, device and equipment | |
| CN114399882A (en) | Fire source detection, identification and early warning method for fire-fighting robot | |
| CN103903002B (en) | Ambient brightness detection method and system | |
| CN109841028B (en) | Thermal infrared imager-based heat source detection method and system and storage medium | |
| JP4111660B2 (en) | Fire detection equipment | |
| JP4991356B2 (en) | Image processing apparatus, image processing method, and image processing program | |
| CN111414967A (en) | Method for improving robustness of temperature measurement system and monitoring system | |
| CN111721201A (en) | Temperature detection method | |
| CN107575750B (en) | A kind of pipeline leakage detection method and pipeline leakage testing device | |
| CN108629342A (en) | Binocular camera flame distance measurement method and device | |
| JP7491039B2 (en) | Color change degree estimation system, color change degree estimation method and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230825 Address after: Room 201, Building A, Integrated Circuit Design Industrial Park, No. 858, Jianshe 2nd Road, Economic and Technological Development Zone, Xiaoshan District, Hangzhou City, Zhejiang Province, 311215 Patentee after: Zhejiang Huagan Technology Co.,Ltd. Address before: Hangzhou City, Zhejiang province Binjiang District 310053 shore road 1187 Patentee before: ZHEJIANG DAHUA TECHNOLOGY Co.,Ltd. |
|
| TR01 | Transfer of patent right |