CN105488941A - Double-spectrum forest fire disaster monitoring method and double-spectrum forest fire disaster monitoring device based on infrared-visible light image - Google Patents
Double-spectrum forest fire disaster monitoring method and double-spectrum forest fire disaster monitoring device based on infrared-visible light image Download PDFInfo
- Publication number
- CN105488941A CN105488941A CN201610029028.7A CN201610029028A CN105488941A CN 105488941 A CN105488941 A CN 105488941A CN 201610029028 A CN201610029028 A CN 201610029028A CN 105488941 A CN105488941 A CN 105488941A
- Authority
- CN
- China
- Prior art keywords
- region
- infrared image
- image
- fire point
- visible images
- 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 57
- 238000012544 monitoring process Methods 0.000 title claims abstract description 35
- 238000001228 spectrum Methods 0.000 title claims abstract description 31
- 238000012806 monitoring device Methods 0.000 title claims abstract description 10
- 238000013507 mapping Methods 0.000 claims abstract description 13
- 239000011159 matrix material Substances 0.000 claims description 19
- 238000009826 distribution Methods 0.000 claims description 17
- 238000003709 image segmentation Methods 0.000 claims description 9
- 230000007246 mechanism Effects 0.000 claims description 8
- 230000008901 benefit Effects 0.000 abstract description 10
- 238000012795 verification Methods 0.000 abstract description 6
- 230000005855 radiation Effects 0.000 abstract 1
- 238000001514 detection method Methods 0.000 description 20
- 230000008569 process Effects 0.000 description 19
- 238000001914 filtration Methods 0.000 description 6
- 230000011218 segmentation Effects 0.000 description 6
- 238000003384 imaging method Methods 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000002485 combustion reaction Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000015572 biosynthetic process Effects 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000000691 measurement method Methods 0.000 description 2
- 230000000877 morphologic effect Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000001066 destructive effect Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000001535 kindling effect Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/005—Fire alarms; Alarms responsive to explosion for forest fires, e.g. detecting fires spread over a large or outdoors area
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/12—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
- G08B17/125—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions by using a video camera to detect fire or smoke
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Theoretical Computer Science (AREA)
- Fire-Detection Mechanisms (AREA)
- Closed-Circuit Television Systems (AREA)
- Image Analysis (AREA)
Abstract
An embodiment of the invention discloses a double-spectrum forest fire disaster monitoring method and a double-spectrum forest fire disaster monitoring device based on an infrared-visible light image. The double-spectrum forest fire disaster monitoring method comprises the steps of acquiring an infrared image and a visible light image of a current scene; determining a suspected fire point mark area in the infrared image; mapping the suspected fire point mark area to a corresponding position in the visible light image, and obtaining an interested area in the visible light image; verifying an image in the interested area, and determining whether a real fire point exists in the current scene according to a verification result. According to the double-spectrum forest fire disaster monitoring method and the double-spectrum forest fire disaster monitoring device, advantages in infrared image identification and advantages in visible light image identification are combined, and an interference caused by objects which have appearances similar with flame and radiation energy that is different from that of the flame to determination result can be prevented, thereby improving accuracy. Furthermore only the image in the interested area in the visible light image is verified, thereby reducing calculation amount, improving efficiency and ensuring high real-time performance in fire disaster monitoring.
Description
Technical field
The embodiment of the present invention relates to mobile device technical field, particularly relates to a kind of two spectrum fire monitoring method based on Infrared-Visible image and device.
Background technology
Forest fire is a kind of sudden strong, destructive large, disaster of disposing relief comparatively difficulty.Therefore, in forest fires dangerous situation monitoring link, promptness and the accuracy of discovery dangerous situation are particularly important, relevant staff can be made to take emergency measures as early as possible, reduce the loss of forest fire to greatest extent.
At present, The Cloud Terrace ocean weather station observation is the main forest fires detection means that China adopts, and in order to save manpower, usually adopts video image Automatic Measurement Technique to monitor forest fire.Common video image Automatic Measurement Technique comprises the fire point detection technique based on visible images and the fire point detection technique based on remote sensing images.Wherein, based in the fire point detection algorithm of visible images, make use of the visible light feature (as color characteristic, textural characteristics and motion feature etc.) of flame, be difficult to filtering outward appearance and the high object (as the red flag waved and light etc.) of flame similarity, warning accuracy rate is low, and algorithm moderate heat point carries out same process with background, needs to calculate larger data volume, efficiency is lower, is not especially suitable for the detection under remote and low-light (level) environment.Based in the fire point detection algorithm of remote sensing images, after mainly utilizing the False color image of some wave band through different modes of particular satellite, wave band algebraic operation, thresholding obtains fire point position, usually needs man-machine interactively process; In addition, remotely-sensed data is ground station reception, parsing, process point to send, and remote sensing images resolution is low, and when finding fire point, may cause disaster in ground, and therefore real-time aspect is comparatively inferior.
Summary of the invention
The object of the embodiment of the present invention is to provide a kind of two spectrum fire monitoring method based on Infrared-Visible image and device, to solve the low and problem of poor real of existing fire monitoring scheme accuracy.
On the one hand, embodiments provide a kind of two spectrum fire monitoring methods based on Infrared-Visible image, comprising:
Obtain infrared image and the visible images of current scene;
Determine the doubtful fire point marked region in described infrared image;
Described doubtful fire point marked region is mapped to the relevant position in described visible images, obtains the area-of-interest in described visible images;
Image in described area-of-interest is verified determine in described current scene, whether to there is true fiery point according to the result.
On the other hand, embodiments provide a kind of two spectrum fire monitoring devices based on Infrared-Visible image, comprising:
Image collection module, for obtaining infrared image and the visible images of current scene;
Doubtful fire point marked region determination module, for determining the doubtful fire point marked region in described infrared image;
Mapping block, for described doubtful fire point marked region being mapped to the relevant position in described visible images, obtains the area-of-interest in described visible images;
True fire point determination module, for verifying the image in described area-of-interest, determines whether there is true fiery point in described current scene according to the result.
A kind of two spectrum fire monitoring schemes based on Infrared-Visible image provided in the embodiment of the present invention, after obtaining the infrared image of current scene and visible images, first determine the doubtful fire point marked region in infrared image, again doubtful fire point marked region is mapped to the relevant position in described visible images, obtain the area-of-interest in visible images, and the image in area-of-interest is verified, finally according to whether there is true fiery point in the result determination current scene.By adopting technique scheme, infrared image is detected identification advantage and visible images to detect identification advantage and combine, first determine doubtful fire point marked region according to the imaging features of infrared image, again doubtful fire point marked region is mapped in visible images, outward appearance but object that emittance with flame different high from flame similarity can be eliminated to the interference of judged result, promote accuracy.And, only the image in area-of-interest is verified in visible images, avoid the defect that the background that in the forest zone image under night scenes, brightness is low account for the overwhelming majority, all pixels participate in calculating waste ample resources, calculated amount can be reduced, raising efficiency, ensures the real-time of fire monitoring.In addition, technique scheme can either overcome the deficiency of single visible ray forest fire algorithm under remote, low-light (level) environment, also be applicable to extensive search fire point and closely monitor the condition of a fire, the mode ratio combined with visible images with remote sensing images, the simplicity of the program and real-time are equally also very outstanding.
Accompanying drawing explanation
The schematic flow sheet of a kind of two spectrum fire monitoring methods based on Infrared-Visible image that Fig. 1 provides for the embodiment of the present invention one;
The schematic flow sheet of a kind of two spectrum fire monitoring methods based on Infrared-Visible image that Fig. 2 provides for the embodiment of the present invention two;
A kind of preferred schematic flow sheet based on two spectrum fire monitoring methods of Infrared-Visible image that Fig. 3 provides for the embodiment of the present invention three;
A kind of infrared heat point detection algorithm schematic flow sheet that Fig. 4 provides for the embodiment of the present invention three;
A kind of visible ray doubtful fire point checking algorithm flow schematic diagram that Fig. 5 provides for the embodiment of the present invention three;
The structured flowchart of a kind of two spectrum fire monitoring devices based on Infrared-Visible image that Fig. 6 provides for the embodiment of the present invention four.
Embodiment
Technical scheme of the present invention is further illustrated by embodiment below in conjunction with accompanying drawing.Be understandable that, specific embodiment described herein is only for explaining the present invention, but not limitation of the invention.It also should be noted that, for convenience of description, illustrate only part related to the present invention in accompanying drawing but not entire infrastructure.
Before in further detail exemplary embodiment being discussed, it should be mentioned that some exemplary embodiments are described as the process or method described as process flow diagram.Although each step is described as the process of order by process flow diagram, many steps wherein can be implemented concurrently, concomitantly or simultaneously.In addition, the order of each step can be rearranged.Described process can be terminated when its operations are completed, but can also have the additional step do not comprised in the accompanying drawings.Described process can correspond to method, function, code, subroutine, subroutine etc.
Embodiment one
The schematic flow sheet of a kind of two spectrum fire monitoring methods based on Infrared-Visible image that Fig. 1 provides for the embodiment of the present invention one, the method can be performed by the two spectrum fire monitoring devices based on Infrared-Visible image, wherein this device can by software and/or hardware implementing, and general accessible site is in fire monitoring system.As shown in Figure 1, the method comprises:
Step 110, the infrared image obtaining current scene and visible images.
Exemplary, described fire monitoring system can comprise billiard table (also known as The Cloud Terrace), infrared camera and Visible Light Camera, also can comprise ball machine opertaing device.Before starting monitoring, need cruising manner and presetting bit that billiard table is rationally set, to cover all regions to be monitored, installation infrared camera and Visible Light Camera on billiard table, and the position of infrared camera and Visible Light Camera and parameters etc. are adjusted.After above-mentioned preliminary work, billiard table can be controlled by ball machine opertaing device and turn to presetting bit position, the data of Real-time Obtaining infrared camera and Visible Light Camera, the infrared image of the acquisition current scene namely in this step and visible images.
It should be noted that, the viewfinder range size of infrared camera is identical from the large I of the viewfinder range of Visible Light Camera also can be different.If different, preferably, the viewfinder range of Visible Light Camera is greater than the viewfinder range of infrared camera.That is, comprise all scenes in infrared image in visible images, also can comprise other scenes non-existent in infrared image.
Step 120, the doubtful fire point marked region determined in infrared image.
The imaging characteristics of infrared image is the difference that can reflect the outside emittance of different objects, also can reflect the heat signature of object.Exemplary, because the heat signature of object can be weighed with the brightness value in infrared image, the brightness value of object in infrared image that heat is higher is higher, and the lower brightness value of object in infrared image of heat is lower, so tentatively can pick out the region of the heat signature meeting flame according to the brightness value characteristic distributions in infrared image, thus determine the doubtful fire point marked region in infrared image.The scenery of doubtful fire point is contained in doubtful fire point marked region.
Exemplary, shape and the size of described doubtful fire point marked region do not do concrete restriction, can arrange in advance, automatically can adjust according to the brightness value characteristic distributions of reality yet.Preferably, in order to easy analysis, described doubtful fire point marked region specifically can be doubtful fire point rectangle marked region.
Further, this step can be preferably: according to the brightness value characteristic distributions in infrared image, infrared Image Segmentation is become multiple region, adopts rectangle marked to draw a circle to approve the region of brightness value higher than predetermined luminance threshold value for doubtful fire point rectangle marked region.Exemplary, when carrying out region segmentation, can by pixel segmentation comparatively close for brightness value in same region, detailed partitioning scheme is not construed as limiting herein.When adopting rectangle marked delineation doubtful fire point rectangle marked region, the mean value of brightness value in current region can be calculated whether higher than predetermined luminance threshold value, if so, then current region being drawn a circle to approve as doubtful fire point rectangle marked region.
Step 130, doubtful fire point marked region is mapped to relevant position in visible images, obtains the area-of-interest in visible images.
Exemplary, infrared image and visible images contain current scene simultaneously, so the scenery comprised in the doubtful fire point marked region determined from infrared image is present in visible images too.It should be noted that, in the present embodiment, the relevant position that doubtful fire point marked region is mapped in visible images is referred to, the border of doubtful fire point marked region is mapped to the relevant position of visible images, but not the picture material comprised in doubtful fire point marked region is copied to the relevant position of visible images.According to preset algorithm, the doubtful fire point marked region in infrared image is mapped to relevant position in visible images, obtain the area-of-interest (regionofinterest in visible images, ROI), so comprise the scenery of doubtful fire point in area-of-interest equally, the resolution of scenery in visible images of this doubtful fiery point is higher, and whether be more conducive to doing is further the checking that true fire is put.It should be noted that, described preset algorithm is not unique, such as, can refer to Infrared-Visible camera combined calibrating technology, obtain the mapping matrix that Pixel-level between infrared image with visible images is corresponding, utilize this mapping matrix the doubtful fire in infrared image can be put marked region compound mapping on visible images.Those skilled in the art can choose suitable preset algorithm according to the configuring condition of practical situations and fire monitoring system, and the present embodiment does not do concrete restriction.
It should be noted that, the doubtful fire point marked region in infrared image can be multiple, so the area-of-interest in the visible images of correspondence also can be multiple.
Step 140, the image in area-of-interest to be verified, according to whether there is true fiery point in the result determination current scene.
Exemplary, existing verification mode be can refer to the mode that the image in the area-of-interest in visible images is verified.Such as, can verify aspects such as color characteristic, Luminance Distribution feature and motion features.Be with the key distinction of existing verification mode, in existing verification mode, need to verify whole visible images, all carry out same process to fire point and background, need to calculate larger data volume, efficiency is lower; And in the present embodiment, only the image comprised in the area-of-interest of doubtful fire point is verified, greatly reduce calculative data volume, raising efficiency, ensure real-time.
The two spectrum fire monitoring methods based on Infrared-Visible image that the embodiment of the present invention one provides, after obtaining the infrared image of current scene and visible images, first determine the doubtful fire point marked region in infrared image, again doubtful fire point marked region is mapped to the relevant position in described visible images, obtain the area-of-interest in visible images, and the image in area-of-interest is verified, finally according to whether there is true fiery point in the result determination current scene.By adopting technique scheme, infrared image is detected identification advantage and visible images to detect identification advantage and combine, first determine doubtful fire point marked region according to the imaging features of infrared image, again doubtful fire point marked region is mapped in visible images, outward appearance but object that emittance with flame different high from flame similarity can be eliminated to the interference of judged result, promote accuracy.And, only the image in area-of-interest is verified in visible images, avoid the defect that the background that in the forest zone image under night scenes, brightness is low account for the overwhelming majority, all pixels participate in calculating waste ample resources, calculated amount can be reduced, raising efficiency, ensures the real-time of fire monitoring.In addition, technique scheme can either overcome the deficiency of single visible ray forest fire algorithm under remote, low-light (level) environment, also be applicable to extensive search fire point and closely monitor the condition of a fire, the mode ratio combined with visible images with remote sensing images, the simplicity of the program and real-time are equally also very outstanding.
Embodiment two
The schematic flow sheet of a kind of two spectrum fire monitoring methods based on Infrared-Visible image that Fig. 2 provides for the embodiment of the present invention two, the present embodiment is optimized based on above-described embodiment, especially rectangle marked delineation doubtful fire point region is adopted, and utilize voting mechanism to process multiframe infrared image, improve the accuracy determining doubtful fire point rectangle marked region, under the prerequisite taking into account the motion of flickering by a small margin that fire point may exist, eliminate the interference that the objects such as motion car light cause.
Concrete, the method for the present embodiment comprises the steps:
Step 210, obtain the infrared image set of current scene and visible images, in infrared image set, comprise corresponding n the not infrared image in the same time of n frame.
Step 220, for each the frame infrared image in infrared image set, according to brightness value characteristic distributions, current infrared Image Segmentation is become multiple region, adopt rectangle marked to be rectangle marked region by brightness value higher than the region delineation of predetermined luminance threshold value; Pixel in rectangle marked region in current infrared image is labeled as 1, and the extra-regional pixel of rectangle marked is labeled as 0.
Concrete, infrared image set can be designated as { A1, A2, A3 ... An|n>0}, every frame infrared image Ai (0<i<n) is marked, pixel in rectangle marked region is labeled as 1, and the extra-regional pixel of rectangle marked is labeled as 0.
Step 230, add up in infrared image set different infrared images in the pixel at same position place be marked as 1 number of times, adopt voting mechanism that the pixel that the number of times being marked as 1 is not less than preset times is designated as 1, other pixels are designated as 0, form target bianry image.
Preferably, described preset times is 0.8n.
Step 240, contours extract is carried out to target bianry image, and adopt rectangle marked to draw a circle to approve doubtful fire point rectangle marked region.
Exemplary, the benefit performing step 210-step 240 is, to the doubtful fire point rectangle marked region that n frame infrared image obtains, adopt the voting mechanism of Pixel-level as final differentiation result, the interference that the objects such as motion car light cause can be eliminated, take into account fire simultaneously and put the motion of flickering by a small margin that may exist, finally obtain the doubtful fire point rectangle marked region that accuracy is higher.
Doubtful fire point rectangle marked area maps to the relevant position in visible images, is obtained the area-of-interest in visible images by step 250, employing image transform model.
Concrete, described image transform model is specially:
Wherein, C
1represent infrared camera, C
2represent Visible Light Camera; R is C
2relative to C
1rotation matrix, t is C
2relative to C
1motion vector; (u
1, v
1) be the coordinate of spatial point in infrared image, (u
2, v
2) be the coordinate of described spatial point in visible images; K
1for C
1intrinsic Matrix, K
2for C
2intrinsic Matrix; Z
c1for described spatial point is to C
1the distance of picture plane, Z
c2for described spatial point is to C
2the distance of picture plane.
Exemplary, the geometric transform relation between this model gives and obtains from different visual angles the two width images comprising Same Scene, can be referred to as the image transform model based on camera motion.According to the description of equipment that camera manufacturer provides, obtain the intrinsic parameter information of Visible Light Camera and infrared camera, comprise focal length, picture centre coordinate, pixel dimension etc., and it can be used as intrinsic parameter initial value, i.e. matrix K
1for and K
2.
Rotation matrix R in above-mentioned model formation can represent by 3 Eulerian angle, and namely around the angle [alpha] that X-axis rotates, around the angle beta that Y-axis rotates, the expression formula around the angle γ that Z axis rotates, R is
The expression formula of the translation vector t in above-mentioned model formation is t=[t
1t
2t
3]
t.
Preferably, before by doubtful fire point rectangle marked area maps to the relevant position in visible images, by the pixel of the outside continuation predetermined number of profile in doubtful fire point rectangle marked region, final doubtful fire point marked region can be formed.Subsequently, final doubtful fire point marked region is mapped to the relevant position in visible images, obtains the area-of-interest in visible images.The benefit done like this is, can eliminate mapping process and produce error and the impact that brings.It should be noted that, also can after doubtful fire be put rectangle marked area maps to the relevant position in visible images, obtain initial area-of-interest, again by the pixel of outside for initial area-of-interest profile continuation predetermined number, form final area-of-interest, the effect eliminating error effect can be arrived equally.
Step 260, the image in area-of-interest to be verified, according to whether there is true fiery point in the result determination current scene.
Concrete, this step can comprise: mated with default kidney-yang feelings color space model in current interest region, obtain the first matching degree; Described current interest region is mated with default pseudo-condition of a fire color space model, obtains the second matching degree; If the first matching degree is higher than the second matching degree, then determine that current interest region is doubtful fire point region; All doubtful fire point region in visible images is verified, according to whether there is true fiery point in the result determination current scene.
Exemplary, described default kidney-yang feelings color space model and default pseudo-condition of a fire color space model specifically can be and utilize mixed Gauss model technology respectively true kindling point (as trees, grassland etc.) and interference thermal source (as vehicle, light etc.) to be carried out to color space modeling respectively and obtain.Matching degree specifically can be used for weighing area-of-interest and the degree of closeness presetting kidney-yang feelings color space model or default pseudo-condition of a fire color space model, and matching degree is higher, then illustrate with corresponding model more close.When corresponding to the first matching degree of default kidney-yang feelings color space model higher than when corresponding to the second matching degree presetting pseudo-condition of a fire color space model, illustrate that current interest region is closer to default kidney-yang feelings color space model, then can determine that current interest region is doubtful fire point region.
Subsequently, all doubtful fire point region in visible images is verified, according to whether there is true fiery point in the result determination current scene.Such as, Luminance Distribution detection and motion feature detection etc. can be carried out.When carrying out Luminance Distribution and detecting, the regularity of distribution of flame pixels brightness can be analyzed, put flame envelope edge by the combustion centre of internal flame, due to the difference of temperature of combustion, colour brightness can successively be successively decreased, and utilizes luminance histogram statistics grey scale change rule, and screens doubtful fire point; When carrying out motion feature and detecting, gauss hybrid models (GaussianMixtureModel, GMM can be utilized; Also known as mixed Gauss model) background modeling technology carry out doubtful fire point screening, to eliminate the interference that the objects such as motion car light cause further, take into account fire simultaneously and put the motion of flickering by a small margin that may exist, motion feature needs multiframe visible images when detecting equally, preferably, when obtaining the infrared image set of current scene, the set of same acquisition visible images.
The embodiment of the present invention two is on the basis of embodiment one, adopt rectangle marked delineation doubtful fire point region, and utilize voting mechanism to process multiframe infrared image, improve the accuracy determining doubtful fire point rectangle marked region, under the prerequisite taking into account the motion of flickering by a small margin that fire point may exist, eliminate the interference that the objects such as motion car light cause, can further improve the accuracy of fire monitoring.Further, after eliminating the object interference such as motion car light, the total area in doubtful fire point rectangle marked region also can correspondingly reduce, thus the total area of area-of-interest is reduced, and can reduce calculated amount further, raising efficiency, ensure the real-time of fire monitoring.
Embodiment three
A kind of preferred schematic flow sheet based on two spectrum fire monitoring methods of Infrared-Visible image that Fig. 3 provides for the embodiment of the present invention three, as shown in Figure 3, the method specifically comprises the steps:
Step 310, billiard table turn to current presetting bit.
Step 320, the infrared image obtaining current scene corresponding to current presetting bit and visible images.
Step 330, operation infrared heat point detection algorithm, judge whether to draw doubtful fire point rectangle marked region, if so, then perform step 350; Otherwise, perform step 340.
Further, a kind of infrared heat point detection algorithm schematic flow sheet that Fig. 4 provides for the embodiment of the present invention three, as shown in Figure 4, this algorithm comprises the steps:
Step 331, pre-service is carried out to infrared image.
Concrete, the operations such as filtering enhancing can be carried out to infrared image, weaken or eliminate some interference of the more weak generation of light.
Step 332, Threshold segmentation is carried out to the infrared image after pre-service.
Utilize the imaging characteristics of infrared image, otherwise object brightness value in infrared image that namely heat is high is high then low, carries out Threshold segmentation, hot spot target can be separated from background every frame infrared image.
Step 333, morphological operation is carried out to the infrared image after Threshold segmentation.
Exemplary, after Threshold segmentation being carried out to infrared image in step 332, can binary map be formed, by carrying out the morphological operations such as expansion to binary map, to reach filling cavity, by the entirety of hot spot target instead of extracting section object out.
Step 334, employing rectangle marked delineation rectangle marked region.
Exemplary, find hot spot target profile, and with the outmost border of rectangle marked, obtain the rectangle marked region of doubtful fire point.
Step 335, judge whether current rectangle marked region meets filtering condition, if so, then perform step 336, otherwise perform step 337.
Exemplary, described filtering condition can comprise the priori of forest fires.
Step 336, filtering current rectangle marked region, perform step 338.
Step 337, reservation current rectangle marked region, perform step 338.
Step 338, judge whether current rectangle marked region is last, if so, process ends; Otherwise, perform step 339.
Step 339, next rectangle marked region is set to new current rectangle marked region, returns and perform step 335.
After filtration except the rectangle marked region remained is doubtful fire point rectangle marked region.
Preferably, also can carry out as the voting mechanism that utilizes in embodiment two processes multiframe infrared image, obtain final doubtful fire point rectangle marked region, to improve the accuracy determining doubtful fire point rectangle marked region further.Detail can refer to the associated description in the embodiment of the present invention two.
After infrared heat point detection algorithm flow process terminates, step 350 can be performed.If doubtful fire point rectangle marked region cannot be drawn according to infrared heat point detection algorithm, illustrate in current scene there is not doubtful fiery point, can step 340 be performed.
Step 340, next presetting bit is set as current presetting bit, and returns and perform step 310.
Step 350, doubtful fire point marked region is mapped to relevant position in visible images, obtains the area-of-interest in visible images.
Concrete, can adopt image transform model that doubtful fire is put rectangle marked area maps to the relevant position in visible images, obtain the area-of-interest in visible images.
Described image transform model is specially:
Wherein, C
1represent infrared camera, C
2represent Visible Light Camera; R is C
2relative to C
1rotation matrix, t is C
2relative to C
1motion vector; (u
1, v
1) be the coordinate of spatial point in infrared image, (u
2, v
2) be the coordinate of described spatial point in visible images; K
1for C
1intrinsic Matrix, K
2for C
2intrinsic Matrix; Z
c1for described spatial point is to C
1the distance of picture plane, Z
c2for described spatial point is to C
2the distance of picture plane.
Step 360, according to visible ray doubtful fire point verification algorithm the image in area-of-interest is verified, according to whether there is true fiery point in the result determination current scene, if so, then perform step 370; Otherwise, perform step 340.
Further, a kind of visible ray doubtful fire point checking algorithm flow schematic diagram that Fig. 5 provides for the embodiment of the present invention three, as shown in Figure 5, this algorithm specifically can comprise the steps:
Step 361, pre-service is carried out to current interest region.
Concrete, described pre-service can comprise the pixel of outside for area-of-interest profile continuation predetermined number, forms final area-of-interest, can to eliminate in follow-up mapping process produce the impact that error brings.
Step 362, color space model detection is carried out to the image in current interest region, judge whether testing result is passed through, if so, then perform step 365; Otherwise, perform step 363.
Concrete, current interest region can be mated with default kidney-yang feelings color space model and default pseudo-condition of a fire color space model respectively, obtain the first matching degree and the second matching degree; If the first matching degree is higher than the second matching degree, then determine that the testing result in current interest region is for passing through.Concrete detection mode can refer to the associated description in the embodiment of the present invention two step 260.
Step 363, judge whether current interest region is last area-of-interest, if so, then process ends; Otherwise, perform step 364.
Step 364, next area-of-interest is set to new current interest region, returns and perform step 361.
Step 365, Luminance Distribution detection is carried out to the image in current interest region, judge whether testing result is passed through, if so, then perform step 366; Otherwise, perform step 363.
Exemplary, the regularity of distribution of flame pixels brightness can be analyzed, flame envelope edge is put by the combustion centre of internal flame, due to the difference of temperature of combustion, colour brightness can successively be successively decreased, utilize luminance histogram statistics grey scale change rule, if this grey scale change rule of current interest region conforms, then can think that detection is passed through.
Step 366, motion feature detection is carried out to the image in current interest region, judge whether testing result is passed through, if so, then perform step 367; Otherwise, perform step 363.
Exemplary, gauss hybrid models (GaussianMixtureModel, GMM can be utilized; Also known as mixed Gauss model) background modeling technology carries out the screening of doubtful fire point, and to eliminate the interference that the objects such as motion car light cause further, take into account fire simultaneously and put the motion of flickering by a small margin that may exist.Such as, when current interest region is mated with the master pattern utilizing gauss hybrid models background modeling technology to set up, can think that detection is passed through.
Step 367, determine that current interest region memory is at true fiery point, and perform step 363.
It should be noted that, when determining to there is true fire point in current region in this step, first can perform step 370 and carry out the warning of fire point, warning relevant staff takes fire extinguishing related measure or controls relevant device to enter fire extinguishing flow process, continue to perform step 363 simultaneously, verify in next area-of-interest whether also there is true fiery point.
Step 370, carry out fire point report to the police.
It is a kind of preferably based on two spectrum fire monitoring methods of Infrared-Visible image that the embodiment of the present invention three provides, utilize infrared heat point detection algorithm to filter out doubtful fiery point that heat signature meets testing conditions, then doubtful fire point is mapped in visible images, carry out the ROI region as visible images after the continuation of some pixels again, finally utilize visible ray doubtful fire point verification algorithm to verify ROI region, thus filter out real fire and put and carry out the warning of fire point.The accuracy of the method is high, and calculated amount is little, can raise the efficiency, and ensures the real-time of fire monitoring.
Embodiment four
The structured flowchart of a kind of two spectrum fire monitoring devices based on Infrared-Visible image that Fig. 6 provides for the embodiment of the present invention four, this device can by software and/or hardware implementing, general accessible site, in fire monitoring system, monitors forest fire by performing based on two spectrum fire monitoring methods of Infrared-Visible image.As shown in Figure 6, this device comprises image collection module 601, doubtful fire point marked region determination module 602, mapping block 603 and true fire point determination module 604.
Wherein, image collection module 601, for obtaining infrared image and the visible images of current scene; Doubtful fire point marked region determination module 602, for determining the doubtful fire point marked region in described infrared image; Mapping block 603, for described doubtful fire point marked region being mapped to the relevant position in described visible images, obtains the area-of-interest in described visible images; True fire point determination module 604, for verifying the image in described area-of-interest, determines whether there is true fiery point in described current scene according to the result.
The two spectrum fire monitoring devices based on Infrared-Visible image that the embodiment of the present invention four provides, infrared image is detected identification advantage and visible images to detect identification advantage and combine, first determine doubtful fire point marked region according to the imaging features of infrared image, again doubtful fire point marked region is mapped in visible images, outward appearance but object that emittance with flame different high from flame similarity can be eliminated to the interference of judged result, promote accuracy.Further, only the image in area-of-interest is verified in visible images, can calculated amount be reduced, raising efficiency, ensure the real-time of fire monitoring.
On the basis of above-described embodiment, described doubtful fire point marked region specifically can be doubtful fire point rectangle marked region; Described doubtful fire point marked region determination module specifically can be used for: according to the brightness value characteristic distributions in described infrared image, described infrared Image Segmentation is become multiple region, adopts rectangle marked to draw a circle to approve the region of brightness value higher than predetermined luminance threshold value for doubtful fire point rectangle marked region.
On the basis of above-described embodiment, described image collection module specifically can be used for: obtain the infrared image set of current scene and visible images, comprises corresponding n the not infrared image in the same time of n frame in described infrared image set.Described doubtful fire point marked region determination module can comprise indexing unit, target bianry image forming unit and doubtful fire point rectangle marked area determination unit.Wherein, indexing unit, for for each the frame infrared image in described infrared image set, according to brightness value characteristic distributions, current infrared Image Segmentation is become multiple region, adopt rectangle marked to draw a circle to approve as rectangle marked region by brightness value higher than the region of predetermined luminance threshold value; Pixel in described rectangle marked region in described current infrared image is labeled as 1, and the extra-regional pixel of rectangle marked is labeled as 0.Target bianry image forming unit, pixel for adding up the same position place in the different infrared images in described infrared image set is marked as the number of times of 1, adopt voting mechanism that the pixel that the number of times being marked as 1 is not less than preset times is designated as 1, other pixels are designated as 0, form target bianry image.Doubtful fire point rectangle marked area determination unit, for carrying out contours extract to described target bianry image, and adopts rectangle marked to draw a circle to approve doubtful fire point rectangle marked region.
On the basis of above-described embodiment, described mapping block specifically can be used for: described doubtful fire point marked region is mapped to the relevant position in described visible images by employing image transform model, obtains the area-of-interest in described visible images;
Described image transform model is specially:
Wherein, C
1represent infrared camera, C
2represent Visible Light Camera; R is C
2relative to C
1rotation matrix, t is C
2relative to C
1motion vector; (u
1, v
1) be the coordinate of spatial point in infrared image, (u
2, v
2) be the coordinate of described spatial point in visible images; K
1for C
1intrinsic Matrix, K
2for C
2intrinsic Matrix; Z
c1for described spatial point is to C
1the distance of picture plane, Z
c2for described spatial point is to C
2the distance of picture plane.
On the basis of above-described embodiment, described mapping block specifically can be used for: a pixel is preset in the outside continuation of profile of described doubtful fire point marked region, forms final doubtful fire point marked region; Described final doubtful fire point marked region is mapped to the relevant position in described visible images, obtains the area-of-interest in described visible images.
On the basis of above-described embodiment, described true fire point determination module specifically can be used for: mated with default kidney-yang feelings color space model in current interest region, obtain the first matching degree; Described current interest region is mated with default pseudo-condition of a fire color space model, obtains the second matching degree; If described first matching degree is higher than described second matching degree, then determine that current interest region is doubtful fire point region; To all doubtful fire point region in described visible images verify determine in described current scene, whether to there is true fiery point according to the result.
The two spectrum fire monitoring devices based on Infrared-Visible image provided in above-described embodiment can perform the two spectrum fire monitoring methods based on Infrared-Visible image that any embodiment of the present invention provides, and possess and perform the corresponding functional module of the method and beneficial effect.The not ins and outs of detailed description in the above-described embodiments, the two spectrum fire monitoring methods based on Infrared-Visible image that can provide see any embodiment of the present invention.
Note, above are only preferred embodiment of the present invention and institute's application technology principle.Skilled person in the art will appreciate that and the invention is not restricted to specific embodiment described here, various obvious change can be carried out for a person skilled in the art, readjust and substitute and can not protection scope of the present invention be departed from.Therefore, although be described in further detail invention has been by above embodiment, the present invention is not limited only to above embodiment, when not departing from the present invention's design, can also comprise other Equivalent embodiments more, and scope of the present invention is determined by appended right.
Claims (10)
1., based on two spectrum fire monitoring methods for Infrared-Visible image, it is characterized in that, comprising:
Obtain infrared image and the visible images of current scene;
Determine the doubtful fire point marked region in described infrared image;
Described doubtful fire point marked region is mapped to the relevant position in described visible images, obtains the area-of-interest in described visible images;
Image in described area-of-interest is verified determine in described current scene, whether to there is true fiery point according to the result.
2. method according to claim 1, is characterized in that, described doubtful fire point marked region is specially doubtful fire point rectangle marked region;
Determine the doubtful fire point rectangle marked region in described infrared image, comprising:
According to the brightness value characteristic distributions in described infrared image, described infrared Image Segmentation is become multiple region, adopt rectangle marked to draw a circle to approve the region of brightness value higher than predetermined luminance threshold value for doubtful fire point rectangle marked region.
3. method according to claim 2, is characterized in that, the infrared image of described acquisition current scene and visible images, comprising:
Obtain the infrared image set of current scene and visible images, in described infrared image set, comprise corresponding n the not infrared image in the same time of n frame;
According to the brightness value characteristic distributions in described infrared image, described infrared Image Segmentation is become multiple region, adopts rectangle marked to draw a circle to approve the region of brightness value higher than predetermined luminance threshold value for doubtful fire point rectangle marked region, comprising:
For each the frame infrared image in described infrared image set, according to brightness value characteristic distributions, current infrared Image Segmentation is become multiple region, adopt rectangle marked to draw a circle to approve as rectangle marked region by brightness value higher than the region of predetermined luminance threshold value; Pixel in described rectangle marked region in described current infrared image is labeled as 1, and the extra-regional pixel of rectangle marked is labeled as 0;
The pixel at the same position place in the different infrared images of statistics in described infrared image set is marked as the number of times of 1, adopt voting mechanism that the pixel that the number of times being marked as 1 is not less than preset times is designated as 1, other pixels are designated as 0, form target bianry image;
Contours extract is carried out to described target bianry image, and adopts rectangle marked to draw a circle to approve doubtful fire point rectangle marked region.
4. method according to claim 1, is characterized in that, described doubtful fire point marked region is mapped to the relevant position in described visible images, obtains the area-of-interest in described visible images, comprising:
Described doubtful fire point marked region is mapped to the relevant position in described visible images by employing image transform model, obtains the area-of-interest in described visible images;
Described image transform model is specially:
Wherein, C
1represent infrared camera, C
2represent Visible Light Camera; R is C
2relative to C
1rotation matrix, t is C
2relative to C
1motion vector; (u
1, v
1) be the coordinate of spatial point in infrared image, (u
2, v
2) be the coordinate of described spatial point in visible images; K
1for C
1intrinsic Matrix, K
2for C
2intrinsic Matrix; Z
c1for described spatial point is to C
1the distance of picture plane, Z
c2for described spatial point is to C
2the distance of picture plane.
5. method according to claim 1, is characterized in that, described doubtful fire point marked region is mapped to the relevant position in described visible images, obtains the area-of-interest in described visible images, comprising:
By the pixel of the outside continuation predetermined number of profile of described doubtful fire point marked region, form final doubtful fire point marked region;
Described final doubtful fire point marked region is mapped to the relevant position in described visible images, obtains the area-of-interest in described visible images.
6. method according to claim 1, is characterized in that, verifies the image in described area-of-interest, determines whether there is true fiery point in described current scene, comprising according to the result:
Current interest region is mated with default kidney-yang feelings color space model, obtains the first matching degree; Described current interest region is mated with default pseudo-condition of a fire color space model, obtains the second matching degree;
If described first matching degree is higher than described second matching degree, then determine that current interest region is doubtful fire point region;
To all doubtful fire point region in described visible images verify determine in described current scene, whether to there is true fiery point according to the result.
7., based on two spectrum fire monitoring devices for Infrared-Visible image, it is characterized in that, comprising:
Image collection module, for obtaining infrared image and the visible images of current scene;
Doubtful fire point marked region determination module, for determining the doubtful fire point marked region in described infrared image;
Mapping block, for described doubtful fire point marked region being mapped to the relevant position in described visible images, obtains the area-of-interest in described visible images;
True fire point determination module, for verifying the image in described area-of-interest, determines whether there is true fiery point in described current scene according to the result.
8. device according to claim 7, is characterized in that, described doubtful fire point marked region is specially doubtful fire point rectangle marked region;
Described doubtful fire point marked region determination module specifically for:
According to the brightness value characteristic distributions in described infrared image, described infrared Image Segmentation is become multiple region, adopt rectangle marked to draw a circle to approve the region of brightness value higher than predetermined luminance threshold value for doubtful fire point rectangle marked region.
9. device according to claim 8, is characterized in that,
Described image collection module specifically for:
Obtain the infrared image set of current scene and visible images, in described infrared image set, comprise corresponding n the not infrared image in the same time of n frame;
Described doubtful fire point marked region determination module, comprising:
Indexing unit, for for each the frame infrared image in described infrared image set, according to brightness value characteristic distributions, current infrared Image Segmentation is become multiple region, adopt rectangle marked to draw a circle to approve as rectangle marked region by brightness value higher than the region of predetermined luminance threshold value; Pixel in described rectangle marked region in described current infrared image is labeled as 1, and the extra-regional pixel of rectangle marked is labeled as 0;
Target bianry image forming unit, pixel for adding up the same position place in the different infrared images in described infrared image set is marked as the number of times of 1, adopt voting mechanism that the pixel that the number of times being marked as 1 is not less than preset times is designated as 1, other pixels are designated as 0, form target bianry image;
Doubtful fire point rectangle marked area determination unit, for carrying out contours extract to described target bianry image, and adopts rectangle marked to draw a circle to approve doubtful fire point rectangle marked region.
10. method according to claim 7, is characterized in that, described mapping block specifically for:
Described doubtful fire point marked region is mapped to the relevant position in described visible images by employing image transform model, obtains the area-of-interest in described visible images;
Described image transform model is specially:
Wherein, C
1represent infrared camera, C
2represent Visible Light Camera; R is C
2relative to C
1rotation matrix, t is C
2relative to C
1motion vector; (u
1, v
1) be the coordinate of spatial point in infrared image, (u
2, v
2) be the coordinate of described spatial point in visible images; K
1for C
1intrinsic Matrix, K
2for C
2intrinsic Matrix; Z
c1for described spatial point is to C
1the distance of picture plane, Z
c2for described spatial point is to C
2the distance of picture plane.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610029028.7A CN105488941B (en) | 2016-01-15 | 2016-01-15 | Double spectrum fire monitoring method and devices based on Infrared-Visible image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610029028.7A CN105488941B (en) | 2016-01-15 | 2016-01-15 | Double spectrum fire monitoring method and devices based on Infrared-Visible image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105488941A true CN105488941A (en) | 2016-04-13 |
| CN105488941B CN105488941B (en) | 2018-10-30 |
Family
ID=55675901
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610029028.7A Active CN105488941B (en) | 2016-01-15 | 2016-01-15 | Double spectrum fire monitoring method and devices based on Infrared-Visible image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105488941B (en) |
Cited By (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105931409A (en) * | 2016-05-30 | 2016-09-07 | 重庆大学 | Infrared and visible light camera linkage-based forest fire monitoring method |
| CN106056594A (en) * | 2016-05-27 | 2016-10-26 | 四川桑莱特智能电气设备股份有限公司 | Double-spectrum-based visible light image extraction system and method |
| CN106228732A (en) * | 2016-08-22 | 2016-12-14 | 无锡信大气象传感网科技有限公司 | A kind of forest fire intelligent identifying system |
| CN107123227A (en) * | 2017-07-06 | 2017-09-01 | 合肥科大立安安全技术股份有限公司 | A kind of embedded image flame detector and its recognition methods based on two waveband |
| CN108090495A (en) * | 2017-12-22 | 2018-05-29 | 湖南源信光电科技股份有限公司 | A kind of doubtful flame region extracting method based on infrared light and visible images |
| CN108460804A (en) * | 2018-03-20 | 2018-08-28 | 重庆大学 | A kind of Three Degree Of Freedom position and posture detection method of transhipment docking mechanism and transhipment docking mechanism based on machine vision |
| CN109146904A (en) * | 2018-08-13 | 2019-01-04 | 合肥英睿系统技术有限公司 | The method and apparatus of infrared image object profile is shown in visible images |
| CN109243135A (en) * | 2018-09-26 | 2019-01-18 | 北京环境特性研究所 | A kind of intelligence fire detection and localization method, apparatus and system |
| CN109375068A (en) * | 2018-09-26 | 2019-02-22 | 北京环境特性研究所 | A kind of target identification method and device based on ultraviolet imagery corona detection |
| CN109670388A (en) * | 2017-10-17 | 2019-04-23 | 杭州萤石网络有限公司 | A kind of goal behavior detection method, device, electronic equipment and storage medium |
| CN109854964A (en) * | 2019-03-29 | 2019-06-07 | 沈阳天眼智云信息科技有限公司 | Steam leakage positioning system and method based on binocular vision |
| CN110009530A (en) * | 2019-04-16 | 2019-07-12 | 国网山西省电力公司电力科学研究院 | A kind of nerve network system and method suitable for portable power inspection |
| CN110060444A (en) * | 2019-03-11 | 2019-07-26 | 视联动力信息技术股份有限公司 | A kind of fire early-warning system and method based on view networking |
| CN110097030A (en) * | 2019-05-14 | 2019-08-06 | 武汉高德红外股份有限公司 | It is a kind of based on infrared and visible images protrusion identification methods and system |
| CN110244011A (en) * | 2019-06-26 | 2019-09-17 | 熊颖郡 | The river blowdown of unmanned plane monitors analyzing and alarming system automatically |
| CN110390788A (en) * | 2019-08-21 | 2019-10-29 | 深圳云感物联网科技有限公司 | A kind of forest fire protection firework identification method and its system |
| CN110569797A (en) * | 2019-09-10 | 2019-12-13 | 云南电网有限责任公司带电作业分公司 | earth stationary orbit satellite image forest fire detection method, system and storage medium thereof |
| CN110619293A (en) * | 2019-09-06 | 2019-12-27 | 沈阳天眼智云信息科技有限公司 | Flame detection method based on binocular vision |
| CN111199629A (en) * | 2020-02-18 | 2020-05-26 | 普宙飞行器科技（深圳）有限公司 | Heat source identification device, unmanned aerial vehicle and heat source identification method |
| CN112257667A (en) * | 2020-11-12 | 2021-01-22 | 珠海大横琴科技发展有限公司 | Small ship detection method and device, electronic equipment and storage medium |
| CN112257554A (en) * | 2020-10-20 | 2021-01-22 | 南京恩博科技有限公司 | Forest fire recognition method, system, program and storage medium |
| CN112860946A (en) * | 2021-01-18 | 2021-05-28 | 四川弘和通讯有限公司 | Method and system for converting video image information into geographic information |
| CN113283322A (en) * | 2021-05-14 | 2021-08-20 | 柳城牧原农牧有限公司 | Livestock trauma detection method, device, equipment and storage medium |
| CN113537204A (en) * | 2020-04-20 | 2021-10-22 | 富华科精密工业（深圳）有限公司 | Small flame detection method based on infrared features and machine learning and computer device |
| CN113626377A (en) * | 2020-05-06 | 2021-11-09 | 杭州海康微影传感科技有限公司 | Bare data storage control method, device and equipment and storage medium |
| WO2022117041A1 (en) * | 2020-12-03 | 2022-06-09 | 杭州海康微影传感科技有限公司 | Fire detection method, apparatus, system, and electronic device |
| CN114627124A (en) * | 2022-05-16 | 2022-06-14 | 江西武大扬帆科技有限公司 | Deep learning-based bubble spring detection method and interactive feedback system |
| WO2022121129A1 (en) * | 2020-12-12 | 2022-06-16 | 南方电网调峰调频发电有限公司 | Fire recognition method and apparatus, and computer device and storage medium |
| WO2022241964A1 (en) * | 2021-05-18 | 2022-11-24 | 深圳市沃特沃德信息有限公司 | Temperature measuring method, computer device, and computer-readable storage medium |
| WO2024083134A1 (en) * | 2022-10-20 | 2024-04-25 | 浙江华感科技有限公司 | Fire determination method, system and apparatus, and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201629019U (en) * | 2009-09-30 | 2010-11-10 | 青岛科恩锐通信息技术有限公司 | Forest fire detecting system |
| CN102693603A (en) * | 2012-06-26 | 2012-09-26 | 山东神戎电子股份有限公司 | Dual spectrum based intelligent monitoring system for forest fire prevention |
| JP2014093002A (en) * | 2012-11-05 | 2014-05-19 | Hochiki Corp | Flame detection apparatus and flame detection method |
| CN104867265A (en) * | 2015-04-22 | 2015-08-26 | 深圳市佳信捷技术股份有限公司 | Camera apparatus, and fire detection alarm system and method |
| CN204667578U (en) * | 2015-06-24 | 2015-09-23 | 山东神戎电子股份有限公司 | The two spectrum observation instrument of a kind of hand-held forest fire protection |
-
2016
- 2016-01-15 CN CN201610029028.7A patent/CN105488941B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201629019U (en) * | 2009-09-30 | 2010-11-10 | 青岛科恩锐通信息技术有限公司 | Forest fire detecting system |
| CN102693603A (en) * | 2012-06-26 | 2012-09-26 | 山东神戎电子股份有限公司 | Dual spectrum based intelligent monitoring system for forest fire prevention |
| JP2014093002A (en) * | 2012-11-05 | 2014-05-19 | Hochiki Corp | Flame detection apparatus and flame detection method |
| CN104867265A (en) * | 2015-04-22 | 2015-08-26 | 深圳市佳信捷技术股份有限公司 | Camera apparatus, and fire detection alarm system and method |
| CN204667578U (en) * | 2015-06-24 | 2015-09-23 | 山东神戎电子股份有限公司 | The two spectrum observation instrument of a kind of hand-held forest fire protection |
Cited By (37)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106056594A (en) * | 2016-05-27 | 2016-10-26 | 四川桑莱特智能电气设备股份有限公司 | Double-spectrum-based visible light image extraction system and method |
| CN105931409A (en) * | 2016-05-30 | 2016-09-07 | 重庆大学 | Infrared and visible light camera linkage-based forest fire monitoring method |
| CN106228732A (en) * | 2016-08-22 | 2016-12-14 | 无锡信大气象传感网科技有限公司 | A kind of forest fire intelligent identifying system |
| CN107123227A (en) * | 2017-07-06 | 2017-09-01 | 合肥科大立安安全技术股份有限公司 | A kind of embedded image flame detector and its recognition methods based on two waveband |
| CN109670388A (en) * | 2017-10-17 | 2019-04-23 | 杭州萤石网络有限公司 | A kind of goal behavior detection method, device, electronic equipment and storage medium |
| CN108090495A (en) * | 2017-12-22 | 2018-05-29 | 湖南源信光电科技股份有限公司 | A kind of doubtful flame region extracting method based on infrared light and visible images |
| CN108460804A (en) * | 2018-03-20 | 2018-08-28 | 重庆大学 | A kind of Three Degree Of Freedom position and posture detection method of transhipment docking mechanism and transhipment docking mechanism based on machine vision |
| CN109146904A (en) * | 2018-08-13 | 2019-01-04 | 合肥英睿系统技术有限公司 | The method and apparatus of infrared image object profile is shown in visible images |
| CN109243135A (en) * | 2018-09-26 | 2019-01-18 | 北京环境特性研究所 | A kind of intelligence fire detection and localization method, apparatus and system |
| CN109375068A (en) * | 2018-09-26 | 2019-02-22 | 北京环境特性研究所 | A kind of target identification method and device based on ultraviolet imagery corona detection |
| CN109375068B (en) * | 2018-09-26 | 2021-02-05 | 北京环境特性研究所 | Target identification method and device based on ultraviolet imaging corona detection |
| CN110060444A (en) * | 2019-03-11 | 2019-07-26 | 视联动力信息技术股份有限公司 | A kind of fire early-warning system and method based on view networking |
| CN109854964A (en) * | 2019-03-29 | 2019-06-07 | 沈阳天眼智云信息科技有限公司 | Steam leakage positioning system and method based on binocular vision |
| CN109854964B (en) * | 2019-03-29 | 2021-03-19 | 沈阳天眼智云信息科技有限公司 | Steam leakage positioning system and method based on binocular vision |
| CN110009530A (en) * | 2019-04-16 | 2019-07-12 | 国网山西省电力公司电力科学研究院 | A kind of nerve network system and method suitable for portable power inspection |
| CN110097030A (en) * | 2019-05-14 | 2019-08-06 | 武汉高德红外股份有限公司 | It is a kind of based on infrared and visible images protrusion identification methods and system |
| CN110244011A (en) * | 2019-06-26 | 2019-09-17 | 熊颖郡 | The river blowdown of unmanned plane monitors analyzing and alarming system automatically |
| CN110390788A (en) * | 2019-08-21 | 2019-10-29 | 深圳云感物联网科技有限公司 | A kind of forest fire protection firework identification method and its system |
| CN110619293A (en) * | 2019-09-06 | 2019-12-27 | 沈阳天眼智云信息科技有限公司 | Flame detection method based on binocular vision |
| CN110569797A (en) * | 2019-09-10 | 2019-12-13 | 云南电网有限责任公司带电作业分公司 | earth stationary orbit satellite image forest fire detection method, system and storage medium thereof |
| CN110569797B (en) * | 2019-09-10 | 2023-05-26 | 云南电网有限责任公司带电作业分公司 | Method, system and storage medium for detecting mountain fire of geostationary orbit satellite image |
| CN111199629A (en) * | 2020-02-18 | 2020-05-26 | 普宙飞行器科技（深圳）有限公司 | Heat source identification device, unmanned aerial vehicle and heat source identification method |
| CN111199629B (en) * | 2020-02-18 | 2021-11-23 | 普宙科技(深圳)有限公司 | Heat source identification device, unmanned aerial vehicle and heat source identification method |
| CN113537204A (en) * | 2020-04-20 | 2021-10-22 | 富华科精密工业（深圳）有限公司 | Small flame detection method based on infrared features and machine learning and computer device |
| CN113626377A (en) * | 2020-05-06 | 2021-11-09 | 杭州海康微影传感科技有限公司 | Bare data storage control method, device and equipment and storage medium |
| CN112257554A (en) * | 2020-10-20 | 2021-01-22 | 南京恩博科技有限公司 | Forest fire recognition method, system, program and storage medium |
| CN112257554B (en) * | 2020-10-20 | 2021-11-05 | 南京恩博科技有限公司 | Forest fire recognition method, system, program and storage medium based on multiple spectra |
| CN112257667A (en) * | 2020-11-12 | 2021-01-22 | 珠海大横琴科技发展有限公司 | Small ship detection method and device, electronic equipment and storage medium |
| WO2022117041A1 (en) * | 2020-12-03 | 2022-06-09 | 杭州海康微影传感科技有限公司 | Fire detection method, apparatus, system, and electronic device |
| WO2022121129A1 (en) * | 2020-12-12 | 2022-06-16 | 南方电网调峰调频发电有限公司 | Fire recognition method and apparatus, and computer device and storage medium |
| CN112860946A (en) * | 2021-01-18 | 2021-05-28 | 四川弘和通讯有限公司 | Method and system for converting video image information into geographic information |
| CN112860946B (en) * | 2021-01-18 | 2023-04-07 | 四川弘和通讯集团有限公司 | Method and system for converting video image information into geographic information |
| CN113283322A (en) * | 2021-05-14 | 2021-08-20 | 柳城牧原农牧有限公司 | Livestock trauma detection method, device, equipment and storage medium |
| WO2022241964A1 (en) * | 2021-05-18 | 2022-11-24 | 深圳市沃特沃德信息有限公司 | Temperature measuring method, computer device, and computer-readable storage medium |
| CN114627124B (en) * | 2022-05-16 | 2022-07-26 | 江西武大扬帆科技有限公司 | Deep learning-based bubble spring detection method and interactive feedback system |
| CN114627124A (en) * | 2022-05-16 | 2022-06-14 | 江西武大扬帆科技有限公司 | Deep learning-based bubble spring detection method and interactive feedback system |
| WO2024083134A1 (en) * | 2022-10-20 | 2024-04-25 | 浙江华感科技有限公司 | Fire determination method, system and apparatus, and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105488941B (en) | 2018-10-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105488941A (en) | Double-spectrum forest fire disaster monitoring method and double-spectrum forest fire disaster monitoring device based on infrared-visible light image | |
| CN103116746B (en) | A kind of video flame detection method based on multiple features fusion technology | |
| CN102175613B (en) | Image-brightness-characteristic-based pan/tilt/zoom (PTZ) video visibility detection method | |
| CN103646250B (en) | Pedestrian monitoring method and device based on distance image head and shoulder features | |
| CN109655825A (en) | Data processing method, device and the multiple sensor integrated method of Multi-sensor Fusion | |
| US20140028842A1 (en) | Calibration device and method for use in a surveillance system for event detection | |
| CN107202982A (en) | A kind of beacon arrangement calculated based on UAV position and orientation and image processing method | |
| Choi et al. | A sensor fusion system with thermal infrared camera and LiDAR for autonomous vehicles and deep learning based object detection | |
| CN109416413A (en) | Solar energy forecast | |
| Nyaruhuma et al. | Verification of 2D building outlines using oblique airborne images | |
| US9860770B1 (en) | Optimizing antenna placement based on LIDAR data | |
| CN106297142A (en) | A kind of unmanned plane mountain fire exploration control method and system | |
| CN103400463B (en) | A kind of forest fires localization method based on two dimensional image and device | |
| CN104408746A (en) | Passenger flow statistical system based on depth information | |
| CN103413135B (en) | A kind of vehicle head lamp bright dark border line detecting method, device and system | |
| CN105608417A (en) | Traffic signal lamp detection method and device | |
| CN104574365A (en) | Barrier detection device and method | |
| CN205890910U (en) | Limit detecting device is invaded with track foreign matter that infrared light combines to visible light | |
| CN113033315A (en) | Rare earth mining high-resolution image identification and positioning method | |
| CN109740522A (en) | A kind of personnel's detection method, device, equipment and medium | |
| CN114202695A (en) | Remote sensing image automatic identification system based on artificial intelligence technology | |
| CN114037910A (en) | Unmanned aerial vehicle forest fire detecting system | |
| CN109064444A (en) | Track plates Defect inspection method based on significance analysis | |
| CN114252859A (en) | Target area determination method and device, computer equipment and storage medium | |
| CN114252884A (en) | Method and device for positioning and monitoring roadside radar, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |