CN106897653A - Forest zone firework detecting method and its detecting system based on the fusion of infrared and visible light video - Google Patents
Forest zone firework detecting method and its detecting system based on the fusion of infrared and visible light video Download PDFInfo
- Publication number
- CN106897653A CN106897653A CN201510954704.7A CN201510954704A CN106897653A CN 106897653 A CN106897653 A CN 106897653A CN 201510954704 A CN201510954704 A CN 201510954704A CN 106897653 A CN106897653 A CN 106897653A
- Authority
- CN
- China
- Prior art keywords
- image
- visible light
- video image
- infrared
- module
- 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
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000004927 fusion Effects 0.000 title claims abstract description 23
- 238000001514 detection method Methods 0.000 claims abstract description 19
- 230000002159 abnormal effect Effects 0.000 claims description 48
- 230000011218 segmentation Effects 0.000 claims description 32
- 239000011159 matrix material Substances 0.000 claims description 10
- 230000003044 adaptive effect Effects 0.000 claims description 4
- 238000009499 grossing Methods 0.000 claims description 4
- 239000002023 wood Substances 0.000 claims description 4
- 238000005303 weighing Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 230000005855 radiation Effects 0.000 description 3
- 238000010191 image analysis Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 235000019504 cigarettes Nutrition 0.000 description 1
- 238000000205 computational method Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000004079 fireproofing Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/35—Categorising the entire scene, e.g. birthday party or wedding scene
- G06V20/38—Outdoor scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/005—Fire alarms; Alarms responsive to explosion for forest fires, e.g. detecting fires spread over a large or outdoors area
-
- 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
Abstract
The present invention provides a kind of forest zone firework detecting method based on the fusion of infrared and visible light video, including S1：The Infrared video image and visible light video image in forest zone are gathered and stored respectively；S2：The Infrared video image and the visible light video image are merged using improved fractional order differential method, obtains fused images；S3:The fused images are calculated, it is determined that specific forest fire area.The present invention also proposes a kind of forest zone pyrotechnics detecting system simultaneously, including：Data acquisition module, including infrared collecting submodule and visible light collection submodule, are respectively used to gather and store the Infrared video image and visible light video image in forest zone；Image co-registration module, is merged using improved fractional order differential method to the Infrared video image and the visible light video image, obtains fused images；Fire detection module, by being calculated the fused images to determine specific forest fire area.
Description
Technical field
The present invention relates to forest protection and monitoring technology field, more particularly to one kind can be quickly and accurately positioned Forest Fire
The forest zone firework detecting method and its detecting system of calamity.
Background technology
Forest fire has turned into a global problem at present, and to reduce the loss of forest fire, countries in the world are very
Pay attention to the research of forest fires detection technique, it is to carry out the premise of fireproofing to improve forest fires detection technique.
Traditional forest fire monitoring technology is mainly achieved electronic equipment by way of being manually combined, and it passes through
Ground manpower and the method for aircraft cruise monitoring are not only costly, and it is quite numerous and diverse to work, especially to the inspection of forest blind area
Survey accuracy very low, with the fast development of computer technology and image analysis technology, can be by using video image information
Accurately monitoring fire, makes detection mode to image conversion and intelligent development.Image analysis technology is applied to forestry
It is that monitor in real time is carried out to forest scene using camera in fire monitoring, it is entered after regularly thinks the incoming monitoring image of server
Row treatment and analysis, the result drawn by image judge whether fire, and big fire is nipped in the bud.
Visible light video can provide in scene clearly details, abundant color and texture information etc., can be good at
Reflect the smoke and fire flame feature of forest fire stage of development；In infrared video, object temperature gets over the infra-red radiation of high emission
Can be more, therefore object from normal working temperature during burning-point is risen to, and will be sent out to the ultrared power of external radiation
The very big change of life, the size of the radiation energy according to the object for detecting processes the thermal image for being changed into target object through system,
With gray level or pseudo-color processing out after can preferably represent forest fire feature.It is infrared and visible in forest fire monitoring
Light data has a respective advantage and disadvantage, thus how by two kinds of fusing image datas together, while its each advantage is played
Shortcoming can be evaded again, be computer video analytical technology problem demanding prompt solution in forest fire monitoring application.
The content of the invention
It is an object of the invention to the detection of existing visible light video is blended with infrared video detection technique, there is provided
A kind of forest zone firework detecting method and its detecting system that can be quickly and accurately positioned forest fire.
It is present invention firstly provides a kind of forest zone firework detecting method based on the fusion of infrared and visible light video including following
Step：
S1：The Infrared video image and visible light video image in forest zone are gathered and stored respectively；
S2：The Infrared video image and the visible light video image are melted using improved fractional order differential method
Close, obtain fused images；
S3:The fused images are calculated, it is determined that specific forest fire area.
According to the forest zone firework detecting method merged based on infrared and visible light video proposed by the present invention, wherein, it is described
Step S2 includes：
S21：The Infrared video image and visible light video image are scanned by improved Tiansi templates T, institute is calculated
State the fractional order differential value of Infrared video image and visible light video image；
Calculate fractional order differential formula be：
Wherein, D is fractional order differential value, and v is differential order, and its empirical value is to include the infrared video figure for 0.1, P
The picture element matrix of the original image of picture and visible light video image；The improved Tiansi templates T is：
S22：Scheme the fractional order differential value of Infrared video image at same position and visible light video image as measurement
As the significance level of information, and weight coefficient W is worth to using the fractional order differentialAAnd WB：
Wherein A and B are respectively the picture element matrix of Infrared video image and visible light video image；
S23：Calculate the gray value of fused images F：
CF(x, y)=WACA(x,y)+WBCB(x,y)
Wherein x, y are respectively the abscissa value and ordinate value of pixel.
According to the forest zone firework detecting method merged based on infrared and visible light video proposed by the present invention, wherein, it is described
Step S3 includes：
S31：By the sequence image of the fused images and reference picture subtraction, present image is judged by difference
Whether it is abnormal frame, specific calculating formula includes：
F in above formulai(x, y) is the current sequence image of fused images, and wherein i=0,1,2 ... N, N are continuous sequence image
Frame number, f0(x, y) is reference picture, Δ fi(x, y) is two differences of image；M is empirical value；
As Δ fi(x, y) shows that current sequence image is normal when being less than M, as Δ fi(x, y) shows to work as when being more than or equal to M
Presequence image is abnormal frame；
S32：The reference picture and the abnormal frame are carried out into difference and obtains frame difference image, then using moment preserving method pair
The frame difference image enters row threshold division；
S33：R-C method Threshold segmentations are carried out to abnormal frame；
S34：The Threshold segmentation image of abnormal frame takes intersection area with the Threshold segmentation image of frame difference image；
S35：Noise in the intersection area is removed using adaptive local smoothing method, suspicious points administrative division map is obtained
Picture；
S36：The conflagration area that gets out of the wood is marked in fused images.
In addition, the present invention also proposes a kind of forest zone pyrotechnics detecting system based on the fusion of infrared and visible light video, including：
Data acquisition module, including infrared collecting submodule and visible light collection submodule, are respectively used to gather and store
The Infrared video image and visible light video image in forest zone；
Image co-registration module, is connected with the data acquisition module, using improved fractional order differential method to described infrared
Video image and the visible light video image are merged, and obtain fused images；
Fire detection module, is connected with described image Fusion Module, is calculated to determine by the fused images
Specific forest fire area.
According to the forest zone pyrotechnics detecting system merged based on infrared and visible light video proposed by the present invention, wherein, it is described
Image co-registration module includes：
Fractional order differential value computing module, the Infrared video image and visible is scanned by improved Tiansi templates T
Light video image, calculates the fractional order differential value of the Infrared video image and visible light video image；
Calculate fractional order differential formula be：
Wherein, D is fractional order differential value, and v is differential order, and its empirical value is to include the infrared video figure for 0.1, P
The picture element matrix of the original image of picture and visible light video image；The improved Tiansi templates T is：
Weight coefficient computing module, is connected with the fractional order differential value computing module, for will be infrared at same position
The fractional order differential value of video image and visible light video image is divided as the significance level for weighing image information using described
Number rank differential is worth to weight coefficient WAAnd WB：
Wherein A and B are respectively the picture element matrix of Infrared video image and visible light video image；
Gray value computing module, is connected with the weight coefficient computing module, the gray value for calculating fused images F：
CF(x, y)=WACA(x,y)+WBCB(x,y)
Wherein x, y are respectively the abscissa value and ordinate value of pixel, and C (x, y) represents the gray value of image.
According to the forest zone pyrotechnics detecting system merged based on infrared and visible light video proposed by the present invention, wherein, it is described
Fire detection module includes：
Abnormal frame judge module, for by the sequence image of the fused images and reference picture subtraction, passing through
Difference judges whether present image is abnormal frame, and specific calculating formula includes：
F in above formulai(x, y) is the current sequence image of fused images, and wherein i=0,1,2 ... N, N are continuous sequence image
Frame number, f0(x, y) is reference picture, Δ fi(x, y) is two differences of image；M is empirical value；
As Δ fi(x, y) shows that current sequence image is normal when being less than M, as Δ fi(x, y) shows to work as when being more than or equal to M
Presequence image is abnormal frame；
Frame difference image Threshold segmentation module, is connected with the abnormal frame judge module, for by the reference picture and institute
State abnormal frame and carry out difference and obtain frame difference image, row threshold division is then entered to the frame difference image using moment preserving method；
Abnormal frame Threshold segmentation module, is connected with the abnormal frame judge module, for carrying out R-C method threshold values to abnormal frame
Segmentation；
Area determination module, respectively with the frame difference image Threshold segmentation module and the abnormal frame Threshold segmentation module phase
Even, for the Threshold segmentation image of the image of abnormal frame and frame difference image to be taken into intersection area, and smoothed using adaptive local
Method removes the noise in the intersection area, obtains suspicious points area image, and then the fire that gets out of the wood is marked in fused images
Disaster area domain.
The present invention creatively will be seen that light video image and Infrared video image are merged, the image tool after fusion
There is more abundant data message；On the basis of fused images, real-time and accurately automatic segmentation, profit are further carried out to target
Optimal threshold is chosen with the information of fused images itself, object boundary is clear after segmentation, and ambient noise is small, can be rapidly and accurately
Determine the particular location of forest fire.
Brief description of the drawings
Fig. 1 is the topological diagram of pyrotechnics detecting system in forest zone of the invention；
Fig. 2 is the composition structured flowchart of pyrotechnics detecting system in forest zone of the invention；
Fig. 3-Fig. 6 is respectively the specific embodiment of the generation schematic diagram of fused images, wherein Fig. 3 A, Fig. 4 A, Fig. 5 A and figure
6A is visible ray original image, and Fig. 3 B, Fig. 4 B, Fig. 5 B and Fig. 6 B are infrared original image, and Fig. 3 C, Fig. 4 C, Fig. 5 C and Fig. 6 C are fusion
Image；
Fig. 7 A are the fused images Background of forest fire；
Fig. 7 B are the forest fire image of fused images；
Fig. 7 C are the segmentation result figure of frame difference image；
Fig. 7 D are the segmentation result figure of abnormal two field picture；
Fig. 7 E are the segmentation common factor result figure of frame difference image and abnormal two field picture；
Fig. 7 F are suspicious fire point area image；
Fig. 7 G are forest fire testing result figure.
Fig. 8 is the flow chart of forest zone firework detecting method of the invention.
Description of reference numerals：10- data acquisition modules, 11- infrared collecting submodules；The visible light collection submodules of 12-；20- schemes
As Fusion Module；21- fractional order differential value computing modules；22- weight coefficient computing modules；23- gray value computing modules；30-
Fire detection module；31- abnormal frame judge modules；32- frame difference image Threshold segmentation modules；33- abnormal frame Threshold segmentation modules；
34- area determination modules.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not paid
Embodiment, belongs to the scope of protection of the invention.
Fig. 1 is referred to, is the topological diagram of pyrotechnics detecting system in forest zone of the invention.Surveillance center can be in forest zone not first
Multiple cameras are set with position to monitor forest zone situation, the distribution bearing data of wherein bottom video camera is maintained in monitoring
The heart.The Infrared video image and visible light video image in camera Real-time Collection forest zone, and both images are carried out at fusion
Reason.Once there is the condition of a fire in forest, the present invention will be accurately positioned the specified place of fire generation within the shortest time and will examine
Survey result and be back to Surveillance center, facilitate tour personnel's real time inspection.
Fig. 2 is the composition structured flowchart of pyrotechnics detecting system in forest zone of the invention.As shown in Fig. 2 forest zone cigarette of the invention
Fiery detecting system includes data acquisition module 10, image co-registration module 20 and fire detection module 30.Wherein data acquisition module
10 include infrared collecting submodule 11 and visible light collection submodule 12, are respectively used to gather and store the infrared video figure in forest zone
Picture and visible light video image；Image co-registration module 20 is connected with data acquisition module 10, using improved fractional order differential method
The Infrared video image and the visible light video image are merged, fused images are obtained；Fire detection module 30 with
Image co-registration module 20 is connected, by being calculated the fused images to determine specific forest fire area.
Specifically, in image co-registration module 20, the fusion of Infrared video image and visible light video image is used and is based on
The fusion rule of fractional order differential, algorithm mainly replaces the gradient information of input picture using fractional calculus thought, in drop
While low algorithm complex, strengthen the neighborhood information of pixel, so as to obtain more preferable marginal information.Due to fractional calculus
Calculating process it is complicated, in order to reduce the complexity of algorithm, image is estimated there is employed herein improved 5*5Tiansi templates T
Fractional order differential value, its form of expression is：
Image co-registration module 20 of the invention include fractional order differential value computing module 21, weight coefficient computing module 22 with
And gray value computing module 23.
Fractional order differential value computing module 21 scans the Infrared video image and visible by improved Tiansi templates T
Light video image, calculates the fractional order differential value of the Infrared video image and visible light video image.Specifically, it is sharp first
Calculating fractional order differential with improved Tiansi templates T replaces the formula of pixel Grad as follows：
Wherein, D is fractional order differential value, and v is differential order, and its empirical value is to include the infrared video figure for 0.1, P
The picture element matrix of the original image of picture and visible light video image.
Weight coefficient computing module 22 is connected with the fractional order differential value computing module 21, for will be red at same position
The fractional order differential value of outer video image and visible light video image utilizes described as the significance level for weighing image information
Fractional order differential is worth to weight coefficient WAAnd WB：
Wherein A and B are respectively the picture element matrix of Infrared video image and visible light video image.
Gray value computing module 23 is connected with the weight coefficient computing module 22, the gray scale for calculating fused images F
Value：
CF(x, y)=WACA(x,y)+WBCB(x,y) (4)
Wherein x, y are respectively the abscissa value and ordinate value of pixel.
Fig. 3-Fig. 6 is in the present invention it will be seen that the specific embodiment that is merged of photo artwork picture and infrared original image.By scheming
The image that 4- Fig. 7 can be seen that after fusion has more preferable marginal information.
After obtaining fused images, specific fire location next will be determined by fire detection module 30.This hair
Bright fire detection module 30 includes abnormal frame judge module 31, frame difference image Threshold segmentation module 32, abnormal frame Threshold segmentation
Module 33 and area determination module 34.
Wherein, abnormal frame judge module 31 is used to, by the sequence image of fused images and reference picture subtraction, lead to
Cross difference and judge whether present image is abnormal frame, specific calculating formula includes：
F in above formulai(x, y) is the current sequence image of fused images, and wherein i=0,1,2 ... N, N are continuous sequence image
Frame number, f0(x, y) is reference picture, Δ fi(x, y) is two differences of image；M is empirical value.
As Δ fi(x, y) shows that current sequence image is normal when being less than M, as Δ fi(x, y) shows to work as when being more than or equal to M
Presequence image is abnormal frame.If there is abnormal conditions, subsequent module will be to the further treatment of abnormal frame；If do not occurred
Abnormal conditions, camera will continue monitoring.
Frame difference image Threshold segmentation module 32 is connected with the abnormal frame judge module 31, for by the reference picture with
The abnormal frame carries out difference and obtains frame difference image, then enters row threshold division to the frame difference image using moment preserving method.
Abnormal frame Threshold segmentation module 33 is connected with the abnormal frame judge module 31, for carrying out R-C methods to abnormal frame
Threshold segmentation；
Then just can be by k1And k2Abnormal two field picture is split.
Area determination module 34 respectively with the frame difference image Threshold segmentation module 32 and the abnormal frame Threshold segmentation mould
Block 33 is connected, for the Threshold segmentation image of the image of abnormal frame and frame difference image to be taken into intersection area, and using self adaptation office
Portion's smoothing method removes the noise in the intersection area, obtains suspicious points area image, and then marked in fused images
Forest fire area.
Fig. 7 A to Fig. 7 G are the specific embodiment using the final fire detection result obtained by fire detection module 30.From
As can be seen that the present invention can very clearly frame selects fire scope exactly in the figures above.
On the basis of the above-mentioned forest zone pyrotechnics detecting system based on the fusion of infrared and visible light video, the present invention is also proposed
A kind of forest zone firework detecting method based on the fusion of infrared and visible light video, the flow of the method refers to accompanying drawing 3, specifically
Including：
S1：The Infrared video image and visible light video image in forest zone are gathered and stored respectively；
S2：The Infrared video image and the visible light video image are melted using improved fractional order differential method
Close, obtain fused images；
S3:The fused images are calculated, it is determined that specific forest fire area.
The specific forest fire area of determination that the image co-registration and step S3 mentioned above in connection with step S2 are mentioned,
The image co-registration module 20 and fire detection module 30 in the pyrotechnics detecting system of forest zone are corresponded respectively to, is taken in two steps
Circular is identical with the computational methods mentioned in above-mentioned module, repeats no more here.
One of ordinary skill in the art will appreciate that：Accompanying drawing is the schematic diagram of one embodiment, module in accompanying drawing or
Flow is not necessarily implemented necessary to the present invention.
One of ordinary skill in the art will appreciate that：The module in device in embodiment can be according to embodiment description point
It is distributed in the device of embodiment, it is also possible to carry out respective change and be disposed other than in one or more devices of the present embodiment.On
Stating the module of embodiment can merge into a module, it is also possible to be further split into multiple submodule.
Finally it should be noted that：The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
The present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those within the art that：It still may be used
Modified with to the technical scheme described in previous embodiment, or equivalent is carried out to which part technical characteristic；And
These modifications are replaced, and do not make the spirit and model of the essence disengaging embodiment of the present invention technical scheme of appropriate technical solution
Enclose.
Claims (6)
1. it is a kind of based on the infrared forest zone firework detecting method with visible light video fusion, it is characterised in that to comprise the following steps：
S1：The Infrared video image and visible light video image in forest zone are gathered and stored respectively；
S2：The Infrared video image and the visible light video image are merged using improved fractional order differential method,
Obtain fused images；
S3:The fused images are calculated, it is determined that specific forest fire area.
2. according to claim 1 based on the infrared forest zone firework detecting method with visible light video fusion, its feature exists
In the step S2 includes：
S21：The Infrared video image and visible light video image are scanned by improved Tiansi templates T, is calculated described red
The fractional order differential value of outer video image and visible light video image；
Calculate fractional order differential formula be：
Wherein, D be fractional order differential value, v is differential order, its empirical value be 0.1, P be include the Infrared video image with
The picture element matrix of the original image of visible light video image；The improved Tiansi templates T is：
S22：The fractional order differential value of Infrared video image at same position and visible light video image is believed as image is weighed
The significance level of breath, and it is worth to weight coefficient W using the fractional order differentialAAnd WB：
Wherein A and B are respectively the picture element matrix of Infrared video image and visible light video image；
S23：Calculate the gray value of fused images F：
CF(x, y)=WACA(x,y)+WBCB(x,y)
Wherein x, y are respectively the abscissa value and ordinate value of pixel, and C (x, y) represents the gray value of image.
3. according to claim 2 based on the infrared forest zone firework detecting method with visible light video fusion, its feature exists
In the step S3 includes：
S31：By the sequence image of the fused images and reference picture subtraction, whether present image is judged by difference
It is abnormal frame, specific calculating formula includes：
F in above formulai(x, y) is the current sequence image of fused images, and wherein i=0,1,2 ... N, N are the frame of continuous sequence image
Number, f0(x, y) is reference picture, Δ fi(x, y) is two differences of image；M is empirical value；
As Δ fi(x, y) shows that current sequence image is normal when being less than M, as Δ fi(x, y) shows to work as preamble when being more than or equal to M
Row image is abnormal frame；
S32：The reference picture and the abnormal frame are carried out into difference and obtains frame difference image, then using moment preserving method to described
Frame difference image enters row threshold division；
S33：R-C method Threshold segmentations are carried out to abnormal frame；
S34：The Threshold segmentation image of abnormal frame takes intersection area with the Threshold segmentation image of frame difference image；
S35：Noise in the intersection area is removed using adaptive local smoothing method, suspicious points area image is obtained；
S36：The conflagration area that gets out of the wood is marked in fused images.
4. a kind of based on the infrared forest zone pyrotechnics detecting system with visible light video fusion, it is characterised in that including：
Data acquisition module, including infrared collecting submodule and visible light collection submodule, are respectively used to gather and store forest zone
Infrared video image and visible light video image；
Image co-registration module, is connected with the data acquisition module, using improved fractional order differential method to the infrared video
Image and the visible light video image are merged, and obtain fused images；
Fire detection module, is connected with described image Fusion Module, specific to determine by being calculated the fused images
Forest fire area.
5. according to claim 4 based on the infrared forest zone pyrotechnics detecting system with visible light video fusion, its feature exists
In, it is characterised in that described image Fusion Module includes：
Fractional order differential value computing module, scans the Infrared video image and visible ray is regarded by improved Tiansi templates T
Frequency image, calculates the fractional order differential value of the Infrared video image and visible light video image；
Calculate fractional order differential formula be：
Wherein, D be fractional order differential value, v is differential order, its empirical value be 0.1, P be include the Infrared video image with
The picture element matrix of the original image of visible light video image；The improved Tiansi templates T is：
Weight coefficient computing module, is connected with the fractional order differential value computing module, for by infrared video at same position
The fractional order differential value of image and visible light video image utilizes the fractional order as the significance level for weighing image information
Differential is worth to weight coefficient WAAnd WB：
Wherein A and B are respectively the picture element matrix of Infrared video image and visible light video image；
Gray value computing module, is connected with the weight coefficient computing module, the gray value for calculating fused images F：
CF(x, y)=WACA(x,y)+WBCB(x,y)
Wherein x, y are respectively the abscissa value and ordinate value of pixel, and C (x, y) represents the gray value of image.
6. according to claim 5 based on the infrared forest zone pyrotechnics detecting system with visible light video fusion, its feature exists
In the fire detection module includes：
Abnormal frame judge module, for by the sequence image of the fused images and reference picture subtraction, by difference
Judge whether present image is abnormal frame, specific calculating formula includes：
F in above formulai(x, y) is the current sequence image of fused images, and wherein i=0,1,2 ... N, N are the frame of continuous sequence image
Number, f0(x, y) is reference picture, Δ fi(x, y) is two differences of image；M is empirical value；
As Δ fi(x, y) shows that current sequence image is normal when being less than M, as Δ fi(x, y) shows to work as preamble when being more than or equal to M
Row image is abnormal frame；
Frame difference image Threshold segmentation module, is connected with the abnormal frame judge module, for the reference picture is different with described
Normal frame carries out difference and obtains frame difference image, then enters row threshold division to the frame difference image using moment preserving method；
Abnormal frame Threshold segmentation module, is connected with the abnormal frame judge module, for carrying out R-C methods threshold value point to abnormal frame
Cut；
Area determination module, is connected with the frame difference image Threshold segmentation module and the abnormal frame Threshold segmentation module respectively,
For the Threshold segmentation image of the image of abnormal frame and frame difference image to be taken into intersection area, and use adaptive local smoothing method
The noise in the intersection area is removed, suspicious points area image is obtained, and then the fire zone that gets out of the wood is marked in fused images
Domain.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510954704.7A CN106897653B (en) | 2015-12-17 | 2015-12-17 | Forest region smoke and fire detection method and detection system based on infrared and visible light video fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510954704.7A CN106897653B (en) | 2015-12-17 | 2015-12-17 | Forest region smoke and fire detection method and detection system based on infrared and visible light video fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106897653A true CN106897653A (en) | 2017-06-27 |
| CN106897653B CN106897653B (en) | 2020-03-20 |
Family
ID=59189607
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510954704.7A Active CN106897653B (en) | 2015-12-17 | 2015-12-17 | Forest region smoke and fire detection method and detection system based on infrared and visible light video fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106897653B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107886670A (en) * | 2017-10-17 | 2018-04-06 | 湖北林青测控科技有限公司 | Forest zone initial fire disaster quickly identifies and localization method, storage medium, electronic equipment |
| CN108566538A (en) * | 2018-05-22 | 2018-09-21 | 华电电力科学研究院有限公司 | Based on the circular coal yard personnel safety guard of Infrared-Visible fusion tracking and the monitoring system and method for spontaneous combustion |
| CN109581324A (en) * | 2018-10-31 | 2019-04-05 | 歌尔股份有限公司 | The processing method and processing device of abnormal frame data |
| CN109859156A (en) * | 2018-10-31 | 2019-06-07 | 歌尔股份有限公司 | The processing method and processing device of abnormal frame data |
| CN111339997A (en) * | 2020-03-20 | 2020-06-26 | 浙江大华技术股份有限公司 | Method and apparatus for determining ignition region, storage medium, and electronic apparatus |
| WO2021021935A1 (en) * | 2019-07-30 | 2021-02-04 | Snap-On Incorporated | Adaptive image processing |
| CN113486697A (en) * | 2021-04-16 | 2021-10-08 | 成都思晗科技股份有限公司 | Forest smoke and fire monitoring method based on space-based multi-modal image fusion |
| CN114783141A (en) * | 2022-04-24 | 2022-07-22 | 王江湖 | Fire safety system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102129655A (en) * | 2011-02-20 | 2011-07-20 | 西安电子科技大学 | Wavelet domain-based method for weighting fractional differential image digital watermark |
| WO2013024810A1 (en) * | 2011-08-12 | 2013-02-21 | 株式会社モーションラボ | High-speed computation device, high-speed computation program and recording medium upon which high-speed computation program is recorded, apparatus control system, as well as simulation system |
| CN103427789A (en) * | 2013-07-23 | 2013-12-04 | 四川大学 | Library graphic and text information denoising filter based on fractional order calculating equation |
| CN104361314A (en) * | 2014-10-21 | 2015-02-18 | 华北电力大学（保定） | Method and device for positioning power transformation equipment on basis of infrared and visible image fusion |
-
2015
- 2015-12-17 CN CN201510954704.7A patent/CN106897653B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102129655A (en) * | 2011-02-20 | 2011-07-20 | 西安电子科技大学 | Wavelet domain-based method for weighting fractional differential image digital watermark |
| WO2013024810A1 (en) * | 2011-08-12 | 2013-02-21 | 株式会社モーションラボ | High-speed computation device, high-speed computation program and recording medium upon which high-speed computation program is recorded, apparatus control system, as well as simulation system |
| CN103427789A (en) * | 2013-07-23 | 2013-12-04 | 四川大学 | Library graphic and text information denoising filter based on fractional order calculating equation |
| CN104361314A (en) * | 2014-10-21 | 2015-02-18 | 华北电力大学（保定） | Method and device for positioning power transformation equipment on basis of infrared and visible image fusion |
Non-Patent Citations (3)
| Title |
|---|
| PEDRAM GHAMISI ETAL.: "An efficient method for segmentation of images based on fractional calculus", 《EXPERT SYSTEMS WITH APPLICATIONS》 * |
| XIAOJUN SUN ETAL.: "Weighted Measurement Fusion Fractional Order Kalman", 《PROCEDIA ENGINEERING》 * |
| 彭禹等: "森林火灾监测及相关技术综述", 《安徽农业科学》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107886670A (en) * | 2017-10-17 | 2018-04-06 | 湖北林青测控科技有限公司 | Forest zone initial fire disaster quickly identifies and localization method, storage medium, electronic equipment |
| CN108566538A (en) * | 2018-05-22 | 2018-09-21 | 华电电力科学研究院有限公司 | Based on the circular coal yard personnel safety guard of Infrared-Visible fusion tracking and the monitoring system and method for spontaneous combustion |
| CN109581324A (en) * | 2018-10-31 | 2019-04-05 | 歌尔股份有限公司 | The processing method and processing device of abnormal frame data |
| CN109859156A (en) * | 2018-10-31 | 2019-06-07 | 歌尔股份有限公司 | The processing method and processing device of abnormal frame data |
| CN109859156B (en) * | 2018-10-31 | 2023-06-30 | 歌尔股份有限公司 | Abnormal frame data processing method and device |
| US11605157B2 (en) | 2019-07-30 | 2023-03-14 | Snap-On Incorporated | Adaptive image processing |
| US11144780B2 (en) * | 2019-07-30 | 2021-10-12 | Snap-On Incorporated | Adaptive image processing |
| WO2021021935A1 (en) * | 2019-07-30 | 2021-02-04 | Snap-On Incorporated | Adaptive image processing |
| CN111339997B (en) * | 2020-03-20 | 2023-05-09 | 浙江大华技术股份有限公司 | Fire point area determination method and device, storage medium and electronic device |
| CN111339997A (en) * | 2020-03-20 | 2020-06-26 | 浙江大华技术股份有限公司 | Method and apparatus for determining ignition region, storage medium, and electronic apparatus |
| CN113486697A (en) * | 2021-04-16 | 2021-10-08 | 成都思晗科技股份有限公司 | Forest smoke and fire monitoring method based on space-based multi-modal image fusion |
| CN113486697B (en) * | 2021-04-16 | 2024-02-13 | 成都思晗科技股份有限公司 | Forest smoke and fire monitoring method based on space-based multimode image fusion |
| CN114783141A (en) * | 2022-04-24 | 2022-07-22 | 王江湖 | Fire safety system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106897653B (en) | 2020-03-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106897653A (en) | Forest zone firework detecting method and its detecting system based on the fusion of infrared and visible light video | |
| CN112435207B (en) | Forest fire monitoring and early warning method based on sky-ground integration | |
| EP3869459B1 (en) | Target object identification method and apparatus, storage medium and electronic apparatus | |
| Jia et al. | Fractional vegetation cover estimation algorithm for Chinese GF-1 wide field view data | |
| CN104966372B (en) | The forest fire intelligent identifying system and method for multi-data fusion | |
| Rudz et al. | Investigation of a novel image segmentation method dedicated to forest fire applications | |
| CN106297142A (en) | A kind of unmanned plane mountain fire exploration control method and system | |
| CN111047818A (en) | Forest fire early warning system based on video image | |
| CN110264570A (en) | A kind of autonomous cruising inspection system in forest land based on unmanned plane | |
| CN108267175B (en) | Crop monitoring method and device based on unmanned aerial vehicle | |
| CN106646651A (en) | Fire point detection method | |
| CN109559310A (en) | Power transmission and transformation inspection image quality evaluating method and system based on conspicuousness detection | |
| CN107560593B (en) | Special unmanned aerial vehicle image air-three free network construction method based on minimum spanning tree | |
| CN103729620B (en) | A kind of multi-view pedestrian detection method based on multi-view Bayesian network | |
| CN103400463B (en) | A kind of forest fires localization method based on two dimensional image and device | |
| CN111368817A (en) | Method and system for quantitatively evaluating heat effect based on earth surface type | |
| CN109919250B (en) | Soil moisture-considered evapotranspiration space-time characteristic fusion method and device | |
| CN115481368A (en) | Vegetation coverage estimation method based on full remote sensing machine learning | |
| Cervantes et al. | Utilization of low cost, sky-imaging technology for irradiance forecasting of distributed solar generation | |
| Toulouse et al. | A multimodal 3D framework for fire characteristics estimation | |
| CN113947555A (en) | Infrared and visible light fused visual system and method based on deep neural network | |
| CN106920231A (en) | A kind of remote sensing image clouds appraisal procedure based on full-colour image statistical nature | |
| CN111461013A (en) | Real-time fire scene situation sensing method based on unmanned aerial vehicle | |
| Zhao et al. | Image dehazing based on haze degree classification | |
| CN114037910A (en) | Unmanned aerial vehicle forest fire detecting system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |