CN106228192A - A kind of transmission line forest fire domain identification method analyzed based on double-threshold cluster - Google Patents
A kind of transmission line forest fire domain identification method analyzed based on double-threshold cluster Download PDFInfo
- Publication number
- CN106228192A CN106228192A CN201610607981.5A CN201610607981A CN106228192A CN 106228192 A CN106228192 A CN 106228192A CN 201610607981 A CN201610607981 A CN 201610607981A CN 106228192 A CN106228192 A CN 106228192A
- Authority
- CN
- China
- Prior art keywords
- mountain fire
- transmission line
- fire
- mountain
- region
- 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
- 230000005540 biological transmission Effects 0.000 title claims abstract description 54
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000012544 monitoring process Methods 0.000 claims abstract description 22
- 230000008569 process Effects 0.000 claims abstract description 7
- 238000007621 cluster analysis Methods 0.000 claims abstract description 5
- 230000005611 electricity Effects 0.000 claims description 19
- 238000001914 filtration Methods 0.000 claims description 7
- 238000000205 computational method Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 3
- 230000000452 restraining effect Effects 0.000 claims description 3
- 238000001931 thermography Methods 0.000 abstract description 3
- 238000005259 measurement Methods 0.000 abstract description 2
- 241000218202 Coptis Species 0.000 description 3
- 235000002991 Coptis groenlandica Nutrition 0.000 description 3
- 239000000284 extract Substances 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000010259 detection of temperature stimulus Effects 0.000 description 1
- 238000012850 discrimination method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000003331 infrared imaging Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention discloses a kind of transmission line forest fire domain identification method analyzed based on double-threshold cluster, after extracting and analyzing mountain fire infrared thermal imaging image, background area threshold value and the mountain fire region initial threshold of image is determined first with on-the-spot weather element, then cluster analysis is utilized to obtain background area and mountain fire region clustering center, and image is clustered, finally use Niblack algorithm and combine electric power line pole tower situ wet degrees of data mountain fire domain identification threshold value is modified；Calculating process is simple, practical, meet system to image procossing high efficiency while effectively reduce use single temperature threshold bring fire point fail to judge and judge by accident, it is achieved to transmission line forest fire accurate measurements.As the aid of transmission line forest fire monitoring system, the method is significant for raising mountain fire monitoring accuracy, minimizing mountain fire tripping operation.
Description
Technical field
The invention belongs to electric power project engineering field, be specifically related to a kind of transmission line of electricity mountain analyzed based on double-threshold cluster
Flame range territory discrimination method.
Background technology
In recent years, mountain fire is the most serious to the threat of transmission line of electricity or even whole operation of power networks.At present, for power transmission line
Road mountain fire monitoring technology there has been more research, mainly has distributed video monitoring method, Satellite Remote Sensing method and laser thunder
Reach monitoring method etc..Wherein, distributed terminal monitoring method based on real-time video is because monitoring accuracy is high, real-time, by meteorological ring
The border impact advantage such as little and be used widely.Have owing to infrared imaging system is operated in the long-wave band of spectrum, relatively visible ray
Higher penetration power and anti-interference, can preferably find mountain fire in early days.Existing infrared thermal imaging mountain fire monitoring method be by
Infrared image transfers pcolor to or gray-scale map carries out the detection of temperature, is judged as hot spot region when reaching certain temperature threshold.
But owing to monitored site environment there being many interference factors affect, such as the impact of the high temp objects such as sunlight, shaft tower so that
Mountain fire rate of false alarm based on single threshold value is higher, it is impossible to effectively carry out transmission line forest fire monitoring.
Current conventional Threshold have Two-peak method, Niblack threshold method, maximum variance between clusters, maximum entropy method (MEM),
Fuzzy binary images etc., but all should not be directly applied in transmission line forest fire monitoring.On the one hand, transmission line forest fire is monitored reality
Time property requires relatively strong, and rear three kinds of computational methods are actual owing to calculating process complexity is not particularly suited for engineering.On the other hand, Two-peak method
Although the rectangular histogram calculating simple but actual mountain fire infrared image is discrete, the most coarse, uneven, it is possible to shape
Become multiple the lowest point；Niblack threshold method is that a kind of local auto-adaptive method has and preferably suppresses noise immune, but due to mountain fire
Initial stage infrared heat point region mostly is Small object, and the method can produce the non-targeted mountain fire region of bulk during mountain fire extracts.
Summary of the invention
The technical problem to be solved in the present invention is, for transmission line forest fire monitoring fire point wrong report, fails to report problem, proposes one
Plant the transmission line forest fire domain identification method analyzed based on double-threshold cluster, it is possible to extract transmission line of electricity quickly and accurately
Mountain fire region in thermal infrared images, provides foundation for follow-up mountain fire behavior analysis.
A kind of transmission line forest fire domain identification method analyzed based on double-threshold cluster, including following step:
Step (1) obtains transmission line of electricity monitoring thermal infrared images, utilizes median filtering method that transmission line of electricity is monitored thermal infrared
Image carries out distortion correction and noise suppressed processes, and calculates the grey level histogram of filtering image；
The grey level histogram that step (2) obtains based on weather environment temperature data and step (1) determines background area and mountain
Flame range territory initial threshold, and whether transmission line of electricity occurs that mountain fire sentence at the beginning of carrying out；
Background area and mountain fire region initial threshold that step (3) obtains with step (2) respectively are cluster initial center, sharp
Background area and mountain fire region clustering bunch is obtained with cluster analysis；
Step (4) determines mountain fire domain identification threshold value based on Niblack algorithm and meteorological ambient humidity data；
The first of step (5) integrating step (2) sentences result, and the mountain fire territory identification threshold value that foundation step (4) obtains is in real time
The gray level image that the transmission line of electricity obtained monitors thermal infrared images corresponding carries out mountain fire domain identification.
With the temperature data in transmission line forest fire region to be monitored as foundation, by the temperature pair in transmission line forest fire region
The gray level answered is as background area threshold value；
In grey level histogram, maximum gray scale peak value is as mountain fire region initial threshold；
The gray level that the temperature in described transmission line forest fire region is corresponding refers to the temperature root in transmission line forest fire region
It is fitted after demarcating according to blackbody temperature obtaining the gray level corresponding with transmission line of electricity monitoring thermal infrared images；
Wherein, the grey level range of transmission line of electricity monitoring thermal infrared images is 0-255.
When whether transmission line of electricity is occurred mountain fire to carry out just to sentence refer to meet any one criterion following by described step (2)
Then labelling present image occurs without mountain fire, otherwise, there is mountain fire and may occur；
A () is when the humidity data in transmission line forest fire region to be monitored is more than 90%, it is determined that for rainy day, do not consider
Mountain fire generation situation；
B () is when mountain fire region initial threshold corresponding temperature is less than mountain fire contingent minimum temperature T0Time, do not consider mountain
There is situation in fire.
Described step (3) utilizes cluster analysis obtain the detailed process of background area and mountain fire region clustering bunch as follows:
Background area threshold value and mountain fire region initial threshold are clustered and at the beginning of mountain fire region clustering as background area
Beginning center, has stepped through the criterion function E calculating each pixel with cluster centre, distributes remaining pixel to two clusters
In bunch, and update cluster centre position until restraining；
Described criterion function computational methods are:
Wherein, (x y) represents correspondence position in filtering image (x, y) gray value of place's pixel, C to f1And C2Expression is selected
Two clustering cluster, T1And T2It is respectively the background area after updating and mountain fire region clustering central value.
The computing formula of described mountain fire domain identification threshold value T is as follows:
T=α+λ β
Wherein, α and β respectively correlation coefficient is average and the standard deviation of the pixel gray value of 2, and λ is according to be monitored
The constant that sets of power transmission line mountain fire region humidity data.
The temperature and humidity in power transmission line mountain fire region to be monitored all uses electric power line pole tower collection in worksite device to obtain.
By nearly 3 years mountain fire generation frequencies and on-the-spot humidity are carried out statistical analysis, table 1 below gives the reference value of λ.
Table 1
| On-the-spot humidity | < 30% | 30%～50% | 50%～70% | 70%～80% | > 80% |
| λ value | 3 | 2 | 3 | 4 | 5 |
Beneficial effect
The invention provides a kind of based on double-threshold cluster analyze transmission line forest fire domain identification method, extract and
After analyzing mountain fire infrared thermal imaging image, determine background area threshold value and the mountain fire of image first with on-the-spot weather element
Region initial threshold, then utilizes cluster analysis to obtain background area and mountain fire region clustering center, and clusters image,
Finally use Niblack algorithm and combine electric power line pole tower situ wet degrees of data mountain fire domain identification threshold value is modified,
Calculating process is simple, practical, meet system to image procossing high efficiency while effectively reduce use single temperature
The fire point that threshold value is brought is failed to judge and judges by accident, it is achieved to transmission line forest fire accurate measurements.As transmission line forest fire monitoring system
Aid, the method for improve mountain fire monitoring accuracy, reduce mountain fire tripping operation significant.
Accompanying drawing explanation
Fig. 1 is embodiment of the present invention transmission line forest fire domain identification flow chart.
Detailed description of the invention
1 couple of present invention is described in further detail below in conjunction with the accompanying drawings.The present invention is the transmission of electricity that a kind of weather environment is relevant
Knowledge method is sentenced in circuit mountain fire region, implements step and is:
Step one: obtain transmission line forest fire video monitoring thermal infrared images, obtains transmission line forest fire by sampling and regards
Frequency monitoring thermal infrared images, and utilize median filtering method to carry out distortion correction and noise suppressed, computing formula is:
F (x, y)=med{g (x-i, y-j), (i, j ∈ W) }
Wherein (x, y) with f (x, image correspondence position (x, y) gray scale of place's pixel after y) being respectively original image and processing for g
Value, W is 2 dimensional region module, takes 3*3 region in the present embodiment.
For above-mentioned image, by the pixel quantity of each gray level in statistical picture, calculate input infrared image sequence
The grey level histogram of row, computing formula is:
Wherein rkRepresent the kth gray level of image；nkExpression gray level is rkSum of all pixels；N is the pixel that image is total
Number；P(rk) it is gray level rkAccount for the frequency of total pixel number.
Step 2: determine image background regions threshold value and mountain fire region initial threshold based on weather element.Background threshold
The determination of value is to carry temperature data that meteorological sensor obtains as foundation, by ambient temperature with transmission line forest fire monitoring device
Corresponding gray level, as background area threshold value, takes in grey level histogram maximum gray scale peak value as the initial threshold in mountain fire region simultaneously
Value.
Whether occur mountain fire to carry out just transmission line of electricity based on above-mentioned analysis to sentence.When any one criterion below meeting then
Occurring without mountain fire in this image of labelling, calculating terminates.
A () is when transmission line forest fire monitoring device carries humidity data that meteorological sensor obtains more than 90%, it is determined that
For rainy day, do not consider mountain fire generation situation；
B () is when mountain fire region initial threshold corresponding temperature is less than mountain fire contingent minimum temperature T0Time, do not consider mountain
There is situation in fire.
In the present embodiment, the on-the-spot temperature data obtained is 19.30 DEG C, T0Take 80 degrees Celsius.
Step 3: the gray value that background area threshold value is corresponding with mountain fire region initial threshold is gathered as background area
Class and mountain fire region clustering initial center, have stepped through the criterion function E calculating each pixel with cluster centre, by remaining picture
Vegetarian refreshments distributes to two clustering cluster, and updates cluster centre position until restraining.Described criterion function computational methods are:
Wherein f (x, y) correspondence position (x, y) gray value of place's pixel, C in representative image1And C2Represent two selected to gather
Class bunch, T1And T2It is respectively the background area after updating and mountain fire region clustering central value.
Step 4: use Niblack algorithm to determine mountain fire domain identification threshold for the pixel in mountain fire region clustering bunch
Value T:
T=α+λ β
Wherein α and β respectively correlation coefficient is the average of pixel gray value and the standard deviation of 2, and λ is to monitor according to mountain fire
Device carries the constant of the humidity data setting that meteorological sensor obtains.The humidity data that in the present embodiment, scene obtains is
68.43%, λ value is 3.
The transmission line forest fire smog using above-mentioned weather environment relevant sentences knowledge method to Hunan during the Ching Ming Festival of 2016
Save extra high voltage direct current transmission line ± 800KV guest's gold thread mountain fire to monitor in real time.By the thermal infrared images obtained is carried out
Analyze, guest gold thread 1164# and guest gold thread 1302# two mountain fires were recognized accurately same day April 2, through on-the-spot circuit operation maintenance personnel
Checking, all there is mountain fire in above-mentioned shaft tower region.
The foregoing is only the preferred embodiments of the present invention, be not limited to the present invention, for the skill of this area
For art personnel, the present invention can have various modifications and variations.All within the spirit and principles in the present invention, that is made any repaiies
Change, equivalent, improvement etc., should be included within the scope of the present invention.
Claims (5)
1. the transmission line forest fire domain identification method analyzed based on double-threshold cluster, it is characterised in that include following several
Individual step:
Step (1) obtains transmission line of electricity monitoring thermal infrared images, utilizes median filtering method that transmission line of electricity is monitored thermal infrared images
Carry out distortion correction and noise suppressed processes, and calculate the grey level histogram of filtering image；
The grey level histogram that step (2) obtains based on weather environment temperature data and step (1) determines background area and mountain fire district
Territory initial threshold, and whether transmission line of electricity occurs that mountain fire sentence at the beginning of carrying out；
Background area and mountain fire region initial threshold that step (3) obtains with step (2) respectively are cluster initial center, utilize poly-
Alanysis obtains background area and mountain fire region clustering bunch；
Step (4) determines mountain fire domain identification threshold value based on Niblack algorithm and meteorological ambient humidity data；
The first of step (5) integrating step (2) sentences result, and the mountain fire territory identification threshold value obtained according to step (4) obtains real-time
Transmission line of electricity monitoring gray level image corresponding to thermal infrared images carry out mountain fire domain identification.
Method the most according to claim 1, it is characterised in that with the temperature data in transmission line forest fire region to be monitored
For foundation, using gray level corresponding for the temperature in transmission line forest fire region as background area threshold value；
In grey level histogram, maximum gray scale peak value is as mountain fire region initial threshold；
The gray level that the temperature in described transmission line forest fire region is corresponding refers to the temperature in transmission line forest fire region according to black
Temperature is fitted after demarcating obtaining the gray level corresponding with transmission line of electricity monitoring thermal infrared images；
Wherein, the grey level range of transmission line of electricity monitoring thermal infrared images is 0-255.
Method the most according to claim 2, it is characterised in that whether described step occurs mountain fire to transmission line of electricity in (2)
Carry out just sentencing when referring to meet any one criterion following and then labelling present image to occur without mountain fire, otherwise, there is mountain fire and send out
Raw possible；
A () is when the humidity data in transmission line forest fire region to be monitored is more than 90%, it is determined that for rainy day, do not consider mountain fire
There is situation；
B () is when mountain fire region initial threshold corresponding temperature is less than mountain fire contingent minimum temperature T0Time, do not consider that mountain fire occurs
Situation.
4. according to the method described in any one of claim 1-3, it is characterised in that described step utilizes cluster analysis to obtain in (3)
As follows to the detailed process of background area and mountain fire region clustering bunch:
Using background area threshold value and mountain fire region initial threshold as background area cluster and mountain fire region clustering initial in
The heart, has stepped through the criterion function E calculating each pixel with cluster centre, distributes remaining pixel to two clustering cluster
In, and update cluster centre position until restraining；
Described criterion function computational methods are:
Wherein, (x y) represents correspondence position in filtering image (x, y) gray value of place's pixel, C to f1And C2Represent selected two
Clustering cluster, T1And T2It is respectively the background area after updating and mountain fire region clustering central value.
Method the most according to claim 4, it is characterised in that the computing formula of described mountain fire domain identification threshold value T is as follows:
T=α+λ β
Wherein, α and β respectively correlation coefficient is average and the standard deviation of the pixel gray value of 2, and λ is according to be monitored defeated
The constant that electric wire mountain fire region humidity data sets.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610607981.5A CN106228192B (en) | 2016-07-28 | 2016-07-28 | A kind of transmission line forest fire domain identification method analyzed based on double-threshold cluster |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610607981.5A CN106228192B (en) | 2016-07-28 | 2016-07-28 | A kind of transmission line forest fire domain identification method analyzed based on double-threshold cluster |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106228192A true CN106228192A (en) | 2016-12-14 |
| CN106228192B CN106228192B (en) | 2017-08-18 |
Family
ID=57535127
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610607981.5A Active CN106228192B (en) | 2016-07-28 | 2016-07-28 | A kind of transmission line forest fire domain identification method analyzed based on double-threshold cluster |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106228192B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108846315A (en) * | 2018-05-08 | 2018-11-20 | 国网山西省电力公司电力科学研究院 | A kind of mountain fire automatic identifying method |
| CN108898159A (en) * | 2018-05-31 | 2018-11-27 | 中南林业科技大学 | False forest fires hot spot filter method based on DBSCAN algorithm |
| CN110363382A (en) * | 2019-06-03 | 2019-10-22 | 华东电力试验研究院有限公司 | Almightiness type Township Merging integrated business integration technology |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102117408A (en) * | 2011-02-01 | 2011-07-06 | 环境保护部卫星环境应用中心 | Information extracting method for remote sensing image continuous target field based on cluster analysis |
| CN103955618A (en) * | 2014-05-08 | 2014-07-30 | 国家电网公司 | Method for intelligently predicting power transmission line forest fires in large scale |
| CN104850919A (en) * | 2015-06-15 | 2015-08-19 | 国家电网公司 | Forest fire prediction method for power transmission line |
| CN105184668A (en) * | 2015-08-24 | 2015-12-23 | 国家电网公司 | Forest fire risk area dividing method for power transmission line based on cluster analysis |
-
2016
- 2016-07-28 CN CN201610607981.5A patent/CN106228192B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102117408A (en) * | 2011-02-01 | 2011-07-06 | 环境保护部卫星环境应用中心 | Information extracting method for remote sensing image continuous target field based on cluster analysis |
| CN103955618A (en) * | 2014-05-08 | 2014-07-30 | 国家电网公司 | Method for intelligently predicting power transmission line forest fires in large scale |
| CN104850919A (en) * | 2015-06-15 | 2015-08-19 | 国家电网公司 | Forest fire prediction method for power transmission line |
| CN105184668A (en) * | 2015-08-24 | 2015-12-23 | 国家电网公司 | Forest fire risk area dividing method for power transmission line based on cluster analysis |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108846315A (en) * | 2018-05-08 | 2018-11-20 | 国网山西省电力公司电力科学研究院 | A kind of mountain fire automatic identifying method |
| CN108898159A (en) * | 2018-05-31 | 2018-11-27 | 中南林业科技大学 | False forest fires hot spot filter method based on DBSCAN algorithm |
| CN108898159B (en) * | 2018-05-31 | 2022-05-27 | 中南林业科技大学 | False forest fire hot spot filtering method based on DBSCAN algorithm |
| CN110363382A (en) * | 2019-06-03 | 2019-10-22 | 华东电力试验研究院有限公司 | Almightiness type Township Merging integrated business integration technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106228192B (en) | 2017-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111008599B (en) | Mountain fire synchronous satellite monitoring and early warning method and system based on time scale feature evaluation | |
| Mu et al. | Validating GEOV1 fractional vegetation cover derived from coarse-resolution remote sensing images over croplands | |
| Jiang et al. | Spatio-temporal pattern of ecological droughts and their impacts on health of vegetation in Northwestern China | |
| Zahraei et al. | Short-term quantitative precipitation forecasting using an object-based approach | |
| CN112164062A (en) | Wasteland information extraction method and device based on remote sensing time sequence analysis | |
| CN104269012A (en) | Method for monitoring mountain fire nearby electric transmission line based on MODIS data | |
| Ahmad et al. | A novel method for vegetation encroachment monitoring of transmission lines using a single 2D camera | |
| CN106228192B (en) | A kind of transmission line forest fire domain identification method analyzed based on double-threshold cluster | |
| Li et al. | A hybrid contextual approach to wildland fire detection using multispectral imagery | |
| CN103919258A (en) | Densification tobacco flue-cure dry-wet bulb temperature automatic control technique based on tobacco image processing | |
| CN113850139A (en) | Multi-source remote sensing-based forest annual phenological monitoring method | |
| CN113221057B (en) | Straw burning fire point monitoring method based on multi-temporal satellite images | |
| CN107462331B (en) | Iron and steel enterprise's production history remote-sensing monitoring method and system | |
| CN210570820U (en) | Agricultural detection early warning system | |
| CN110310448A (en) | A kind of transmission line forest fire monitoring method of collection smog and infrared identification linkage | |
| Hally et al. | Assessment of the utility of the advanced Himawari imager to detect active fire over Australia | |
| KR102034193B1 (en) | Automatic Information System for hazard map of facilities collapse using Modis satellite image and AWS materials | |
| CN107403004B (en) | Remote-measuring rainfall site suspicious numerical inspection method based on terrain data | |
| CN109902666A (en) | A kind of potential forest fire method of power grid mountain fire based on two-dimentional OTSU | |
| CN113269175B (en) | Fire monitoring method and device | |
| Jones et al. | A semi-Lagrangian method for detecting and tracking deep convective clouds in geostationary satellite observations | |
| CN114964514A (en) | Time-varying energy threshold fire remote sensing monitoring method based on GK-2A | |
| CN115293190B (en) | Sand storm dynamic inversion method based on microwave signal blind source separation and SCA | |
| CN114550006A (en) | Polar-orbit meteorological satellite fire point identification system, storage medium and equipment | |
| CN112784703B (en) | Multispectral-based personnel action track determination method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |