CN105913033B - Multi layer cloud and single layer cloud-type compressive classification and knowledge method for distinguishing in remote sensing images - Google Patents
Multi layer cloud and single layer cloud-type compressive classification and knowledge method for distinguishing in remote sensing images Download PDFInfo
- Publication number
- CN105913033B CN105913033B CN201610237086.9A CN201610237086A CN105913033B CN 105913033 B CN105913033 B CN 105913033B CN 201610237086 A CN201610237086 A CN 201610237086A CN 105913033 B CN105913033 B CN 105913033B
- Authority
- CN
- China
- Prior art keywords
- cloud
- pixel
- layer
- single layer
- identification
- 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.)
- Active
Links
Classifications
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
Abstract
The invention discloses multi layer cloud in a kind of remote sensing images and single layer cloud-type compressive classification and method for distinguishing is known, this method comprises: step -1: there is the identification of cloud pixel;Step -2: single layer and multi layer cloud rough sort and label;Step -3: single layer cloud-type sophisticated category;Step -4: the classification of cloud layer phase and label;Thus complete have the identification of cloud pixel and the compressive classification of cloud layer and identification in remote sensing images.The present invention can obtain the identification of more fine cloud type and classification results, it can not only realize the differentiation to single layer cloud pixel and multi layer cloud pixel, and it can determine that the phase of multi layer cloud pixel and the cloud type of single layer cloud pixel, remote sensing images pixel is finally identified as clear sky (cloudless pixel) in detail, multilayer water cloud, nabivnoy ice cloud, cirrus, cirrostratus, vertical extension cloud, altocumulus, altostratus, nimbostratus, cumulus, stratocumulus, stratus and Filling power totally 13 class pixel, more abundant image information is provided for the subsequent processing and application of remote sensing images.
Description
Technical field
The present invention relates to the technical fields of remote sensing images cloud layer identification, and in particular to multi layer cloud and list in a kind of remote sensing images
The classification of stratus Type Synthesis and knowledge method for distinguishing.
Background technique
The presence of cloud layer is an Important Disturbed Factors for influencing spaceborne optical sensor earth observation imaging performance.Cloud layer
It is many kinds of, the spatial distribution of different type cloud layer and its scattering radiation are totally different with transmission characteristic, for the clear each cloud layer of research
Kinds of properties is to reject influence of the cloud layer to observation system, to identifying just into the key points and difficulties of research for cloud type
(referring to document [1-2]).In addition, either space-based sensor or ground based sensor observation all shows that the presence of multi layer cloud is very general
Time, and have a significant impact the characteristic of cloud layer (referring to document [3-8]).
Cloud layer can be divided into water cloud, ice cloud and mixing phase cloud by the phase according to cloud layer;It is distributed according to cloud layer cloud-top height
Cloud layer can be roughly classified into high-order, middle position and low level;Cloud layer can be divided into the types such as stratus, cumulus and cirrus according to cloud layer form
Cloud.The cloud layer spatial distribution of several frequently seen type is as shown in Figure 1, by identifying whether satellite image pixel is multi layer cloud overlapping
And its type of corresponding cloud phase and single layer layer, the shadow for even being eliminated the presence of cloud layer to observation system can be reduced
It rings.
Dotted line frame 1 show single layer cloud in Fig. 1, i.e., there is only a stratus layer, remaining wire frames in vertical direction (Z-direction)
Shown is multi layer cloud, i.e., occurs the overlapping of multilayer cloud layer in vertical direction, the only difference is that the number of plies of overlapping cloud layer.Fig. 1
Be two stratus shown in center 2 and frame 4, wherein two stratus shown in frame 2 are cumulonimbus, two stratus shown in frame 4 from
Top to bottm is respectively cirrus and nimbostratus;Frame 3 show four stratus, from top to bottom respectively cirrostratus, altostratus, stratocumulus and
Stratus.
The prior art one related to the present invention: the threshold method of single layer cloud-type identification
The technical solution of the prior art one are as follows:
It is current to know method for distinguishing mainly by threshold value differentiation, such as the threshold value of single layer cloud-type identification in single layer cloud-type
Method, document [1] INSAT international satellite's thin clouds are as plan (International Satellite Cloud Climatology
Project, ISCCP) i.e. according to cloud top pressure PtopRelatively cloud layer is carried out by fixed threshold with two variables of opticalthicknessτ
Identification and classification.The threshold value of cloud top pressure and optical thickness used by ISCCP cloud layer recognition is as shown in Fig. 2, the document gives
Nine kinds of single layer cloud-types as shown in Figure 2, wherein vertically extension cloud refers to the cloud that span is bigger in vertical direction, such as Fig. 1
In cumulonimbus be that one of the most common type vertically extends cloud.
The shortcomings that prior art one
ISCCP cloud layer recognition method realizes the judgement to cloud type according to threshold decision, but ISCCP cloud layer recognition method is false
If cloud layer to be determined is single layer, have ignored multi layer cloud overlapping there are the case where.It, i.e., can only be to most for Space borne detection
The cloud layer on upper layer is differentiated, and cannot achieve the overlapping cloud layer phase and the identification of type of lower layer.
The prior art two related to the present invention
The technical solution of the prior art two are as follows:
Document [2] combines the Moderate Imaging Spectroradiomete (Moderate on Terra satellite or Aqua satellite
Resolution Imaging Spectroradiometer, MODIS) multi layer cloud in data identifies (Multi-Layer
Flag, MLF) judge its pixel for single layer cloud pixel, multi layer cloud pixel or vertical by pixel image using threshold method
Cloud pixel is extended, Fig. 3 provides its multi layer cloud testing process.Required parameter in figure are as follows: cloud top pressure Ptop, opticalthicknessτ and multilayer
Cloud identifies FML, by the cloud layer data product MOD/MYD06 of MODIS data inversion, (the cloud layer data product of Terra satellite is
The cloud layer data product of MOD, Aqua satellite is MYD) it obtains.Wherein, MLF be pixel whether be multilayer pixel trust evaluation
Label, value are the integer of 0-9, wherein 0 represents clear sky, 1 represents single layer cloud, and 2-9 represents multi layer cloud, and the bigger representative of numerical value
It is higher (referring to document [6,7,9]) for the confidence level of multi layer cloud.
Variable Δ P in Fig. 3 decision boxtopCalculation formula are as follows:
P in formulasFor earth's surface pressure, PtopFor cloud top pressure, PtropIt is strong for troposphere press.The earth's surface pressure wherein used for
Ozone layer detection device (Dutch/Finnish Ozone Monitoring Instrument, OMI) detection data.
The shortcomings that prior art two
Document [2] is although realize the differentiation of single layer cloud pixel and multi layer cloud pixel, and there are still following deficiencies: the party
Satellite image pixel is only identified as single layer cloud pixel, multi layer cloud pixel and vertical extension cloud pixel three classes by method, is not both given in detail
The cloud type of single layer cloud out does not provide the phase of multi layer cloud yet.
Bibliography:
[1] http://isccp.giss.nasa.gov/cloudtypes.html#DIAGRAM, 2016.
[2]J.Joiner,A.P.Vasilkov,P.K.Bhartia,G.Wind,S.Platnick,W.P.Menzel,
Detection of Multi-layer and Vertically-extended Clouds Using A-train
Sensors.Atmospheric Measurement Techniques,2010.3:pp.233–247.
[3]R.Frey,B.A.Baum,A.Heidinger,S.Ackerman,B.Maddux,P.Menzel,MODIS CTP
(MOD06)Webinar#7.2014.
[4]J.D.Spinhirne,et al.,Cloud and Aerosol Measurements from GLAS:
Overview and Initial Results.Geophysical Research Letters,2005.32(L22S03):
pp.1-5.
[5]A.Behrangi,S.P.F.Casey and B.H.Lambrigtsen,Three-dimensional
Distribution of Cloud Types Over the USA and Surrounding Areas Observed by
CloudSat.International Journal of Remote Sensing,2012.33(16):pp.4856-4870.
[6]W.P.Menzel,R.A.Frey and B.A.Baum,Cloud Top Properties and Cloud
Phase Algorithm Theoretical Basis Document.2015.pp.1-73.
[7]S.Platnick,et al.,MODIS Cloud Optical Properties:User Guide for
the Collection 6Level-2 MOD06/MYD06 Product and Associated Level-3
Datasets.2015.
[8]J.D.Spinhirne,S.P.Palm and W.D.Hart,Antarctica Cloud Cover for
October 2003from GLAS Satellite Lidar Profiling.Geophysical Research Letters,
2005.32(22):pp.1-4.
[9] http://modis-atmos.gsfc.nasa.gov/, 2016.
Summary of the invention
The technical problems to be solved by the invention are as follows: for the problems in above-mentioned satellite image cloud type identification, this hair
A kind of bright multi layer cloud for proposing synthesis and single layer cloud-type recognition methods, by multi layer cloud mark, cloud top pressure and optical thickness
The bright temperature characteristics of threshold value and different phase cloud layer combine, and comprehensive judgement image picture elements belong to multi layer cloud pixel or single layer cloud
Pixel, while can also determine the phase of multi layer cloud pixel, the cloud type of single layer cloud pixel etc., it is perfect in remote sensing images
The identification of cloud type.
The technical solution adopted by the present invention are as follows: multi layer cloud and single layer cloud-type compressive classification and identification in a kind of remote sensing images
Method, this method comprises the following steps:
Step -1: there is the identification of cloud pixel
According to cloud mask data, satellite image pixel cloud pixel, clear sky pixel and Filling power pixel are divided into, this is filled out
Supplementing pixel with money is that can not sentence knowledge pixel, and being directed to has cloud pixel to complete following cloud layer recognition step;
Step -2: single layer and multi layer cloud rough sort and label
Utilize earth's surface pressure Ps, troposphere press strong Ptrop, cloud top pressure Ptop, opticalthicknessτ and multi layer cloud identify FMLIt presses
Rough sort is carried out to cloud layer according to following decision condition:
(1) meet Δ Ptop> 0.6 and τ > 12 item determine that the pixel is vertical extension cloud;
(2) meet Δ Ptop>0.6, τ<12 and FML>=2 determine the pixel for multi layer cloud pixel;
(3) pixel of (1) (2) is not satisfied, and then preliminary judgement is common single layer cloud pixel;
Step -3: single layer cloud-type sophisticated category
It is the pixel of common single layer cloud by preliminary judgement in step -2, utilizes cloud top pressure Ptop, opticalthicknessτ parameter presses
Single layer cloud pixel is further subdivided into vertical extension cloud, cirrostratus, cirrus, altostratus, altocumulus, random layer according to ISCCP threshold value
Cloud, cumulus, nine kinds of cloud types of stratocumulus and stratus pixel;
Step -4: the classification of cloud layer phase and label
It will be determined as the pixel of multi layer cloud in step -2, utilize 8.5 mu m wavebands and the bright temperature difference D of 11 mu m wavebands8.5-11With 11 μm
Wave band and the bright temperature difference D of 12 mu m wavebands11-12, multi layer cloud pixel is determined according to the following conditions:
If meeting D8.5-11≥D11-12Then determine pixel for nabivnoy ice cloud pixel;
If meeting D8.5-11<D11-12Then it is determined as multilayer water cloud pixel;
Thus complete have the identification of cloud pixel and the compressive classification of cloud layer and identification in remote sensing images.
Technical solution of the present invention bring has the beneficial effect that
Compared with technology -1 compared with technology -2, multi layer cloud and single layer cloud-type in remote sensing images proposed by the invention
Compressive classification and recognition methods available more fine cloud type identification and classification results.Using proposed by the invention
Method can not only realize the differentiation to single layer cloud pixel and multi layer cloud pixel, and can determine that multi layer cloud pixel phase and
Remote sensing images pixel is finally identified as clear sky (cloudless pixel), multilayer water cloud, more by the cloud type of single layer cloud pixel in detail
Layer ice cloud, cirrostratus, vertically extends cloud, altocumulus, altostratus, nimbostratus, cumulus, stratocumulus, stratus and Filling power at cirrus
Totally 13 class pixel provides more abundant image information for the subsequent processing and application of remote sensing images.
Detailed description of the invention
Fig. 1 is the cloud layer spatial distribution schematic diagram of several frequently seen type;
Fig. 2 is the cloud top pressure and optical thickness threshold value of ISCCP cloud layer classification (referring to document [1]);
Fig. 3 is multi layer cloud and extension cloud detection process (referring to document [2]);
Fig. 4 is multi layer cloud and single layer cloud-type compressive classification and identification process;
Fig. 5 is 2015152.0230 5 minutes band RGB images of MODIS Terra satellite;
Fig. 6 is that MOD06 cloud exposure mask differentiates result;
Fig. 7 is the result of multi layer cloud proposed by the invention and single layer cloud-type compressive classification and recognition methods, wherein figure
7 (a) identify MLF for MODIS multi layer cloud, and Fig. 7 (b) is the judging result of single layer cloud and multi layer cloud, and Fig. 7 (c) is that ISCCP threshold value is sentenced
Not as a result, Fig. 7 (d) is integrated multilayer cloud and single layer cloud-type recognition result.Designation explanation corresponding to colour code are as follows: St-
Stratus, Sc- stratocumulus, Cu- cumulus, Ns- nimbostratus, As- altostratus, Ac- altocumulus, De- vertically extend cloud, Cs- cirrostratus,
Ci- cirrus, Clear- clear sky, MLwater- multilayer water cloud, MLice- nabivnoy ice cloud;The lucky nothing of the recognition result of the area image
Filling power pixel.
Specific embodiment
With reference to the accompanying drawing and specific embodiment further illustrates the present invention.
The present invention proposes multi layer cloud and single layer cloud-type compressive classification in a kind of remote sensing images and knows method for distinguishing, for can
The method of comprehensive identification multi layer cloud phase and single layer channel type, concrete implementation process are as shown in Figure 4.
Each parameter is as follows in figure: τ is optical thickness;PtopFor cloud top pressure;PsFor earth's surface pressure;PtropFor convection current lamination
By force;FMLFor multi layer cloud mark;T8.5For the bright temperature of cloud layer under 8.5 mu m wavebands;T11It is bright for cloud layer under 11 mu m wavebands
Temperature;T12For the bright temperature of cloud layer under 12 mu m wavebands;D8.5-11For the bright temperature difference of cloud layer under 8.5 mu m wavebands and 11 mu m wavebands, D8.5-11=T8.5-
T11;D11-12For the bright temperature difference of cloud layer under 11 mu m wavebands and 12 mu m wavebands, D11-12=T11-T12.In addition, the common single layer cloud in figure is
Refer to not as the single layer cloud of vertical extension cloud;Filling power pixel (can not sentence and know pixel) is omitted in figure;ISCCP threshold value, which is meant, utilizes cloud
Press is strong and optical thickness determines threshold value corresponding to cloud-type.
Specific identification step is as follows:
Step -1: there is the identification of cloud pixel
According to cloud mask data, satellite image pixel has been divided into cloud pixel, clear sky pixel and Filling power pixel (can not
Sentence and know pixel), and being directed to has cloud pixel to complete following cloud layer recognition step.
Step -2: single layer and multi layer cloud rough sort and label
Utilize earth's surface pressure Ps, troposphere press strong Ptrop, cloud top pressure Ptop, opticalthicknessτ and multi layer cloud identify FMLIt presses
Rough sort is carried out to cloud layer according to following decision condition:
(1) meet Δ Ptop> 0.6 and τ > 12 item determine that the pixel is vertical extension cloud;
(2) meet Δ Ptop>0.6, τ<12 and FML>=2 determine the pixel for multi layer cloud pixel;
(3) pixel of (1) (2) is not satisfied, and then preliminary judgement is common single layer cloud pixel.
Step -3: single layer cloud-type sophisticated category
It is the pixel of common single layer cloud by preliminary judgement in step -2, utilizes cloud top pressure Ptop, opticalthicknessτ parameter presses
Single layer cloud pixel is further subdivided into vertical extension cloud, cirrostratus, cirrus, altostratus, altocumulus, random layer according to ISCCP threshold value
Cloud, cumulus, nine kinds of cloud types of stratocumulus and stratus pixel.
Step -4: the classification of cloud layer phase and label
It will be determined as the pixel of multi layer cloud in step -2, utilize 8.5 mu m wavebands and the bright temperature difference D of 11 mu m wavebands8.5-11With 11 μm
Wave band and the bright temperature difference D of 12 mu m wavebands11-12, multi layer cloud pixel is determined according to the following conditions:
If meeting D8.5-11≥D11-12Then determine pixel for nabivnoy ice cloud pixel;
If meeting D8.5-11<D11-12Then it is determined as multilayer water cloud pixel.
Thus complete have the identification of cloud pixel and the compressive classification of cloud layer and identification in remote sensing images.
Embodiment:
The concrete application mistake of integrated multilayer cloud proposed by the invention and single layer cloud-type recognition methods illustrated below
Journey.
Use the observation time that MODIS sensor is observed on June 1st, 2015 (Julian calendar 152 days) Terra satellite for
Track (the five minutes bands) data at the five-minute period interval of 02:30-02:35 have 5km resolution ratio 406 × 207 and 1km points
Resolution 2030 × 1,354 two kind specification.Fig. 5 is MODIS RGB pseudo color image, there is the cloud cover of large area in the image.
In addition, the cloud type occurred in the image is more more, and there is the case where multilayer cloud layer overlapping.Now using proposed by the invention
Method carries out multi layer cloud phase to the 5km resolution satellite image data in region corresponding to Fig. 5 and single layer cloud-type identifies.
The cloud mask data [9] of MODIS image is stored in the form of decimal integer, needs to convert decimal integer
At binary system and by " bit ", judged according to the digit of " bit " and numerical value corresponding to each mark, if a pixel institute
The binary number 2-0 " bit " of the first character section of corresponding cloud mask data (is numbered from a high position to low level and is followed successively by
76543210) value is 111, then determines the pixel for clear sky pixel.Differentiate result as schemed with cloud exposure mask corresponding to image in Fig. 5
Shown in 6.Clear sky, possible clear sky and uncertain label indicate that the confidence level that pixel is clear sky is respectively 99%, 95% and 66%.It will
It has been classified as cloud pixel labeled as possible clear sky, pixel that is uncertain and having cloud, has continued subsequent classification and identifies.
Fig. 7 shows the processing result of method proposed by the invention, and wherein Fig. 7 (a) is MODIS multi layer cloud in step -2
Result figure is identified, the multi layer cloud mark MLF value of MODIS is the integer within the scope of 0-9, wherein 0 represents clear sky;1 represents single layer
Cloud;2-9 represents multi layer cloud, and numerical value be expressed as more greatly multi layer cloud confidence level it is higher, MLF is more than or equal to 2 picture herein
Member is determined as multi layer cloud pixel;Fig. 7 (b) is the preliminary judgement result of single layer cloud and multi layer cloud in step -2;Fig. 7 (c) is step
Suddenly to the ISCCP threshold determination cloud-type result of single layer cloud pixel in -3;Fig. 7 (d) be the final multi layer cloud phase of the present invention and
The recognition result of single layer cloud-type.
Multi layer cloud and single layer cloud-type compressive classification and recognition methods Fig. 7 proposed by the invention as a result, colour code institute it is right
The designation explanation answered are as follows: St- stratus, Sc- stratocumulus, Cu- cumulus, Ns- nimbostratus, As- altostratus, Ac- altocumulus,
De- vertically extends cloud, Cs- cirrostratus, Ci- cirrus, Clear- clear sky, MLwater- multilayer water cloud, MLice- nabivnoy ice cloud;It should
The recognition result of area image is just without Filling power pixel
Others alternative solution of the invention can equally complete goal of the invention:
(1) this specification is by taking Terra satellite platform MODIS sensor remote sensing images as an example, illustrates of the invention basic
Technical thought, processing method and process, using the bright temperature characteristics or reflection characteristic of cloud layer under other observation platforms or its all band
Identification cloud layer phase, but processing method and stream are also completed instead of bright temperature characteristic under 8.5 μm, 11 μm in step -4 and 12 mu m wavebands
Cheng Wuxu makees substantive change;
(2) in this invention institute bill of lading layer and multi layer cloud identification, other multi layer cloud pixel recognition methods can also be used
It completes, for example, by using method discussed in PH algorithm (referring to document [7]) alternative steps -2, same achievable single layer and more
The identification of stratus.
Claims (1)
1. multi layer cloud and single layer cloud-type compressive classification and knowledge method for distinguishing in a kind of remote sensing images, which is characterized in that this method
Include the following steps:
Step -1: there is the identification of cloud pixel
According to cloud mask data, satellite image pixel cloud pixel, clear sky pixel and Filling power pixel, the Filling power have been divided into
Pixel is that can not sentence knowledge pixel, and being directed to has cloud pixel to complete following cloud layer recognition step;
Step -2: single layer and multi layer cloud rough sort and label
Utilize earth's surface pressure Ps, troposphere press strong Ptrop, cloud top pressure Ptop, opticalthicknessτ and multi layer cloud identify FMLAccording to
Lower decision condition carries out rough sort to cloud layer:
(1) meet Δ Ptop> 0.6 and τ > 12 then determines that the pixel is vertical extension cloud,Wherein PsFor earth's surface
Pressure, PtopFor cloud top pressure, PtropIt is strong for troposphere press;
(2) meet Δ Ptop> 0.6, τ < 12 and FML>=2 determine the pixel for multi layer cloud pixel;
(3) pixel of (1) (2) is not satisfied, and then preliminary judgement is common single layer cloud pixel;
Step -3: single layer cloud-type sophisticated category
It is the pixel of common single layer cloud by preliminary judgement in step -2, utilizes cloud top pressure Ptop, opticalthicknessτ parameter is according to state
In border Cloud meteorology plan (International Satellite Cloud Climatology Project, ISCCP)
Threshold value by single layer cloud pixel be further subdivided into vertical extension cloud, cirrostratus, cirrus, altostratus, altocumulus, nimbostratus, cumulus,
The pixel of nine kinds of cloud types of stratocumulus and stratus;
Step -4: the classification of cloud layer phase and label
It will be determined as the pixel of multi layer cloud in step -2, utilize 8.5 mu m wavebands and the bright temperature difference D of 11 mu m wavebands8.5-11With 11 mu m wavebands
With the bright temperature difference D of 12 mu m wavebands11-12, multi layer cloud pixel is determined according to the following conditions:
If meeting D8.5-11≥D11-12Then determine pixel for nabivnoy ice cloud pixel;
If meeting D8.5-11< D11-12Then it is determined as multilayer water cloud pixel;
Thus complete have the identification of cloud pixel and the compressive classification of cloud layer and identification in remote sensing images.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610237086.9A CN105913033B (en) | 2016-04-15 | 2016-04-15 | Multi layer cloud and single layer cloud-type compressive classification and knowledge method for distinguishing in remote sensing images |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610237086.9A CN105913033B (en) | 2016-04-15 | 2016-04-15 | Multi layer cloud and single layer cloud-type compressive classification and knowledge method for distinguishing in remote sensing images |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105913033A CN105913033A (en) | 2016-08-31 |
CN105913033B true CN105913033B (en) | 2019-05-14 |
Family
ID=56746227
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610237086.9A Active CN105913033B (en) | 2016-04-15 | 2016-04-15 | Multi layer cloud and single layer cloud-type compressive classification and knowledge method for distinguishing in remote sensing images |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105913033B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109446899A (en) * | 2018-09-20 | 2019-03-08 | 西安空间无线电技术研究所 | A kind of cloud object detection method based on four spectral coverage remote sensing images |
CN109541723B (en) * | 2018-11-23 | 2020-07-28 | 中国气象科学研究院 | Analysis method for freezing rain temperature and humidity structure |
CN109946235B (en) * | 2019-02-26 | 2021-11-02 | 南京信息工程大学 | Multilayer cloud inversion method of wind cloud 4A meteorological satellite multichannel scanning imaging radiometer |
CN110261341B (en) * | 2019-06-20 | 2020-10-02 | 中国矿业大学(北京) | Volcanic ash cloud detection method and system based on stationary meteorological satellite data |
CN111340093A (en) * | 2020-02-21 | 2020-06-26 | 上海眼控科技股份有限公司 | Cloud identification method and device |
CN114778454B (en) * | 2022-03-30 | 2022-09-20 | 中国人民解放军国防科技大学 | Multilayer cloud top height inversion method based on satellite-borne multi-channel radiation imager |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7058511B2 (en) * | 2003-11-24 | 2006-06-06 | The Boeing Company | Sub-visible cloud cover assessment: VNIR-SWIR |
CN102799903A (en) * | 2012-07-18 | 2012-11-28 | 中国科学院自动化研究所 | High-spectrum automatic cloud detection method based on space and spectral information |
CN103093243A (en) * | 2013-01-24 | 2013-05-08 | 哈尔滨工业大学 | High resolution panchromatic remote sensing image cloud discriminating method |
CN103150567A (en) * | 2013-02-04 | 2013-06-12 | 北京理工大学 | Optical remote sensing image cloud distinguishing method of integrating mode recognition and context knowledge |
CN103926634A (en) * | 2014-03-12 | 2014-07-16 | 长江水利委员会长江科学院 | Daytime land radiation fog remote sensing monitoring method based on object-oriented classification |
-
2016
- 2016-04-15 CN CN201610237086.9A patent/CN105913033B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7058511B2 (en) * | 2003-11-24 | 2006-06-06 | The Boeing Company | Sub-visible cloud cover assessment: VNIR-SWIR |
CN102799903A (en) * | 2012-07-18 | 2012-11-28 | 中国科学院自动化研究所 | High-spectrum automatic cloud detection method based on space and spectral information |
CN103093243A (en) * | 2013-01-24 | 2013-05-08 | 哈尔滨工业大学 | High resolution panchromatic remote sensing image cloud discriminating method |
CN103150567A (en) * | 2013-02-04 | 2013-06-12 | 北京理工大学 | Optical remote sensing image cloud distinguishing method of integrating mode recognition and context knowledge |
CN103926634A (en) * | 2014-03-12 | 2014-07-16 | 长江水利委员会长江科学院 | Daytime land radiation fog remote sensing monitoring method based on object-oriented classification |
Non-Patent Citations (2)
Title |
---|
"Detection of multi-layer and vertically-extended clouds using A-train sensors";J. Joiner et al.;《Atmospheric Measurement Techniques》;20101231;第233-247页 |
"基于MODIS数据的白天多层云检测算法";叶晶 等;《遥感技术与应用》;20070831;第22卷(第4期);第570-574页 |
Also Published As
Publication number | Publication date |
---|---|
CN105913033A (en) | 2016-08-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105913033B (en) | Multi layer cloud and single layer cloud-type compressive classification and knowledge method for distinguishing in remote sensing images | |
Wang et al. | Sea ice concentration estimation during melt from dual-pol SAR scenes using deep convolutional neural networks: A case study | |
Chen et al. | Multi-source remotely sensed data fusion for improving land cover classification | |
Huovinen et al. | Remote sensing of albedo-reducing snow algae and impurities in the Maritime Antarctica | |
Ganivet et al. | Towards rapid assessments of tree species diversity and structure in fragmented tropical forests: A review of perspectives offered by remotely-sensed and field-based data | |
Chen et al. | The application of the tasseled cap transformation and feature knowledge for the extraction of coastline information from remote sensing images | |
CN110390255A (en) | High-speed rail environmental change monitoring method based on various dimensions feature extraction | |
Calvino-Cancela et al. | Alien plant monitoring with ultralight airborne imaging spectroscopy | |
CN106971396A (en) | Ice sheet freeze thawing detection method based on super-pixel | |
CN102297822A (en) | Method for predicting ash content of coal particles by utilizing image analysis | |
Roelfsema et al. | The application of object based analysis of high spatial resolution imagery for mapping large coral reef systems in the west pacific at geomorphic and benthic community spatial scales | |
Sun et al. | Hierarchical fusion of optical and dual-polarized SAR on impervious surface mapping at city scale | |
CN101339613A (en) | Remote sensing image background noise reduction method | |
CN112560716A (en) | High-resolution remote sensing image water body extraction method based on low-level feature fusion | |
CN109308451A (en) | A kind of high score data information extraction system and method | |
CN106971397A (en) | Based on the city high-resolution remote sensing image dividing method for improving JSEG algorithms | |
Fang et al. | Street tree health from space? An evaluation using WorldView-3 data and the Washington DC Street Tree Spatial Database | |
CN102384972B (en) | Machine vision-based immunochromatography result interpretation method | |
De Klerk et al. | Probabilistic description of vegetation ecotones using remote sensing | |
Niang et al. | Retrieval of aerosol type and optical thickness over the Mediterranean from SeaWiFS images using an automatic neural classification method | |
Xu et al. | Issues and challenges of remote sensing-based local climate zone mapping for high-density cities | |
Heidary et al. | Urban change detection by fully convolutional siamese concatenate network with attention | |
Jawak et al. | High‐Resolution Remote Sensing for Mapping Glacier Facies in the Arctic | |
May et al. | Spectral signature selection for mapping unvegetated soils | |
Zilioli et al. | A correlation between optical properties from satellite data and some indicators of eutrophication in Lake Garda (Italy) |
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 |