CN104867139A - Remote sensing image cloud and shadow detection method based on radiation field - Google Patents
Remote sensing image cloud and shadow detection method based on radiation field Download PDFInfo
- Publication number
- CN104867139A CN104867139A CN201510239763.6A CN201510239763A CN104867139A CN 104867139 A CN104867139 A CN 104867139A CN 201510239763 A CN201510239763 A CN 201510239763A CN 104867139 A CN104867139 A CN 104867139A
- Authority
- CN
- China
- Prior art keywords
- remote sensing
- image
- numerical value
- sensing image
- value
- 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
Abstract
The invention discloses a remote sensing image cloud and shadow detection method based on a radiation field. The method comprises the steps of: obtaining an atmosphere radiation transmission model corresponding to an optical remote sensing image to be detected, and generating a simulation radiation field corresponding to the optical remote sensing image to be detected by utilizing the atmosphere radiation transmission model and using a surface albedo product, a atmospheric temperature-humidity profile under a preset clear sky condition, and an aerosol optical thickness as driving data; calculating a ratio index image corresponding to the optical remote sensing image according to the optical remote sensing image and the simulation radiation field; extracting a value corresponding to a clear non-shadow region in the ratio index image, and obtaining a value set; obtaining a first value and a second value in the value set, wherein the first value is larger than the second value; and carrying out density division on the ratio index image by adopting the first value and the second value, and obtaining classifications of clouds and shadows. According to the invention, the cloud and shadow detection method high in universality and precision is provided.
Description
Technical field
The present invention relates to technical field of remote sensing image processing, specifically, particularly cloud and shade universal test method on remote sensing image is also a kind of remote sensing image clouds based on radiation field and shadow detection method.
Background technology
A key link of remote sensing image processing and analysis produces cloud mask (identifying the bianry image whether cloud exists), to determine the position of cloud and shade, these information goes to analyze further have territory, cloud sector or clear sky area image feature, the information required for extraction for user.
On current remote sensing images, the detection method of cloud and shade mainly comprises following two kinds of methods: the first: by the detection method of spectral information; The second, based on the geometric relationship determination cloud of cloud-sensor-sun and the detection method of shade.Wherein, in first method, specific wave band is mainly utilized to carry out the detection of cloud and shade, but also the sensor of not all has the wave band that can be used for cloud detection, such as, current most typical cloud detection algorithm is MODIS cloud mask algorithm, it makes use of very multiwave cooperation.And general image, as the satellite datas such as TM, SPOT then do not possess these typical wave bands, therefore, the method detecting cloud and shade on remote sensing images by spectral information is not general, and in addition, the method also easily causes mixed point of snow-cloud, mixed point of water-shade, thus cause the accuracy of detection low.In the second approach, need the parameters such as the cloud level as necessary input, but these parameters are but difficult to directly obtain, therefore, cannot to obtain under the isoparametric situation of the cloud level and inapplicable based on the geometric relationship determination cloud of cloud-sensor-sun and the detection method of shade, the versatility of the method is also bad, in addition, due to the parameter poor accuracy such as the cloud level obtained, so cloud and shadow Detection have very large uncertainty, the determination at cloud and Shadow edge position is also more difficult accurately portrays.
Detection method about cloud on remote sensing images in prior art and shade does not possess the problem of versatility, not yet proposes effective solution at present.
Summary of the invention
Fundamental purpose of the present invention is to provide a kind of remote sensing image clouds based on radiation field and shadow detection method, does not possess the problem of versatility with the detection method solving cloud and shade on remote sensing images in prior art.
According to one aspect of the present invention, provide a kind of remote sensing image clouds based on radiation field and shadow detection method, the method comprises: obtain the atmospheric radiation transmission that remote sensing image to be detected is corresponding; With the atmospheric temperature-moisture profile under earth surface albedo product and the clear sky condition preset, aerosol optical depth under default clear sky condition for driving data, atmospheric radiation transmission is utilized to generate simulation radiation field corresponding to remote sensing image to be detected; The Ratio index image corresponding according to the remote sensing image that remote sensing image to be detected is to be detected with simulation computation of radiation field; Extract the numerical value that on Ratio index image, clear sky unshadowed area is corresponding, obtain numerical value set; The first numerical value in acquisition number value set and second value, wherein, the first numerical value is greater than second value; The first numerical value and second value correlative value index image is adopted to carry out density slice, to obtain the classification of cloud and shade.
Further, specifically comprise according to the step of the remote sensing image to be detected Ratio index image corresponding with simulation computation of radiation field remote sensing image to be detected: remote sensing image to be detected and each wave band radiance of simulation radiation field are asked ratio; Each ratio of trying to achieve is carried out product calculation, to obtain the Ratio index image of cloud corresponding to remote sensing image to be detected and shade.
Further, extract the numerical value that on Ratio index image, clear sky unshadowed area is corresponding, the step obtaining numerical value set specifically comprises: calculate remote sensing image to be detected and the similarity simulating radiation field; On Ratio index image, determine that the region that similarity is greater than default similarity is clear sky unshadowed area; Extract the numerical value that clear sky unshadowed area is corresponding, obtain numerical value set.
Further, calculate remote sensing image to be detected to be specially with the step of the similarity of simulation radiation field: adopt structural similarity texture recognition algorithm to calculate remote sensing image to be detected and the similarity simulating radiation field.
Further, the first numerical value in acquisition number value set and second value specifically comprise: the numerical value in logarithm value set sorts according to size; Remove in numerical value set the numerical value of front and back end 2% of sorting; In numerical value set, obtain the maximal value after removing the numerical value of 2% as the first numerical value, minimum value is as second value.
Further, the first numerical value and second value correlative value index image is adopted to carry out density slice, specifically comprise using the classification obtaining cloud and shade: by the first numerical value and second value as initial segmentation threshold value, correlative value index image carries out density slice, to obtain the preliminary classification of cloud and shade; According to the classification results adjustment initial segmentation threshold value of preliminary classification, the segmentation threshold correlative value index image after adjustment is adopted to carry out density slice, to obtain cloud mask.
Further, remote sensing image to be detected can be MODIS image, TM/ETM+ image, VIIRS image, SPOT image, ASTER image, AVHRR image or HJ-1A/B image etc.
Pass through the present invention, adopt the atmospheric radiation transmission corresponding with remote sensing image to be detected, and with the atmospheric temperature-moisture profile under earth surface albedo product and default clear sky condition, aerosol optical depth under the clear sky condition preset is driving data, simulation generates simulation radiation field corresponding to remote sensing image to be detected, then corresponding according to the remote sensing image that remote sensing image to be detected is to be detected with simulation computation of radiation field Ratio index image, extract the numerical value that on Ratio index image, clear sky unshadowed area is corresponding, obtain numerical value set, the first numerical value in acquisition number value set and second value, wherein, first numerical value is greater than second value, final employing first numerical value and second value correlative value index image carry out density slice, to obtain the classification of cloud and shade, in this method, the direct radiation field of simulation that adopts is come for reference, can detect cloud and shade simultaneously, and not by earth's surface Xue Gai, the impact of water body, there is versatility, nearly all remote sensing images can directly be applied, do not limit by wave band, the detection method solving cloud and shade on remote sensing images in prior art does not possess the problem of versatility.
Above-mentioned explanation is only the general introduction of technical solution of the present invention, in order to technological means of the present invention can be better understood, and can be implemented according to the content of instructions, and can become apparent, below especially exemplified by the specific embodiment of the present invention to allow above and other objects of the present invention, feature and advantage.
Accompanying drawing explanation
By reading hereafter detailed description of the preferred embodiment, various other advantage and benefit will become cheer and bright for those of ordinary skill in the art.Accompanying drawing only for illustrating the object of preferred implementation, and does not think limitation of the present invention.And in whole accompanying drawing, represent identical process by identical reference symbol.In the accompanying drawings:
Fig. 1 be according to a first embodiment of the present invention based on the remote sensing image clouds of radiation field and the process flow diagram of shadow detection method;
Fig. 2 be according to a second embodiment of the present invention based on the remote sensing image clouds of radiation field and the process flow diagram of shadow detection method.
Embodiment
Below in conjunction with the drawings and specific embodiments, the present invention will be further described.It is pointed out that when not conflicting, the embodiment in the application and the feature in embodiment can combine mutually.
Embodiment one
First, the embodiment of the present invention one provides a kind of remote sensing image clouds based on radiation field and shadow detection method, and see Fig. 1, the method can comprise the following steps:
Step S102: obtain the atmospheric radiation transmission that remote sensing image to be detected is corresponding.
In this step, according to the kind of remote sensing image to be detected, obtain the atmospheric radiation transmission corresponded, such as, remote sensing image to be detected is MODIS image, then the atmospheric radiation transmission obtained is MODTRAN radiative transfer model.
Step S104: with the atmospheric temperature-moisture profile under earth surface albedo product and the clear sky condition preset, aerosol optical depth under default clear sky condition for driving data, utilize atmospheric radiation transmission to generate simulation radiation field corresponding to remote sensing image to be detected.
Wherein, earth surface albedo product preferably adopts the earth surface albedo product of MCD43B3.Atmospheric temperature-moisture profile under the clear sky condition preset, the aerosol optical depth under default clear sky condition are the empirical parameter under typical clear sky condition.
Step S106: the Ratio index image corresponding according to the remote sensing image that remote sensing image to be detected is to be detected with simulation computation of radiation field.
Particularly, remote sensing image to be detected and each wave band radiance of simulation radiation field are asked ratio, and then carry out product calculation to each ratio, the result of product calculation is Ratio index image corresponding to remote sensing image to be detected.
Step S108: extract the numerical value that on Ratio index image, clear sky unshadowed area is corresponding, obtain numerical value set.
Particularly, first clear sky unshadowed area is determined: adopt structural similarity texture recognition algorithm to calculate remote sensing image to be detected and the similarity simulating radiation field, on Ratio index image, determine that the region that similarity is greater than default similarity is clear sky unshadowed area, then extract numerical value corresponding to clear sky unshadowed area, obtain numerical value set.
Step S110: the first numerical value in acquisition number value set and second value, wherein, the first numerical value is greater than second value.
Particularly, the set of following steps logarithm value is adopted to process, and obtaining the first numerical value and second value: the numerical value first in logarithm value set sorts according to size, then the numerical value of front and back end 2% of sorting is removed in numerical value set, in numerical value set, finally obtain the maximal value after removing the numerical value of 2% as the first numerical value, minimum value is as second value.
Step S112: adopt the first numerical value and second value correlative value index image to carry out density slice, to obtain the classification of cloud and shade.
Particularly, can using the first numerical value and second value as initial segmentation threshold value, correlative value index image carries out density slice, to obtain the preliminary classification of cloud and shade, then according to the classification results adjustment initial segmentation threshold value of preliminary classification, the segmentation threshold correlative value index image after adjustment is adopted again to carry out density slice, to obtain cloud mask.
Because cloud shows high reverse--bias characteristic at reflected waveband, and cloud shade shows low reflection characteristic at reflected waveband, and the two is the extreme case of reflectance spectrum, if do not have cloud or cloud shade, then wave band radiation is in therebetween.Therefore, in this embodiment, by the radiation field under simulation clear sky condition as a reference, cloud and cloud shade can be distinguished, and can detect cloud and shade simultaneously, not by the impact of earth's surface Xue Gai, water body, there is versatility, nearly all remote sensing images, comprise MODIS image, TM/ETM+ image, VIIRS image, SPOT image, ASTER image, AVHRR image or HJ-1A/B image, directly can apply, not limit by wave band, the detection method solving cloud and shade on remote sensing images in prior art does not possess the problem of versatility.
Embodiment two
This embodiment is the preferred remote sensing image clouds based on radiation field and shadow detection method further on the basis of embodiment one, and in the method, with remote sensing image to be detected for MODIS image example, see Fig. 2, the step that the method comprises is described below:
(1) utilize the earth surface albedo product of MODTRAN radiative transfer model, MCD43B3, typical Cloudless atmosphere temperature-humidity profile and aerosol optical depth etc. for driving data, simulation generates 7 wave band radiances of the MODIS shortwave radiation under clear sky condition.
(2) with MODIS 7 wave band radiances for ambient field, build the cloud detection index of skip band, MODIS image (to be detected) and the radiation field subrane of simulation are asked ratio, then the Ratio index image that computing obtains cloud and shade is seized the opportunity to each ratio;
(3) to MODIS image (to be detected) and simulation radiation field adopt structural similarity texture recognition algorithm (SSIM) calculate both similarity, similarity is greater than 0.9 and thinks clear sky unshadowed area.
(4) numerical value on Ratio index image corresponding with the above-mentioned clear sky unshadowed area utilizing texture recognition algorithm to obtain on locus is extracted in, sort according to size, remove the numerical value of front and back end 2%, then obtain minimum and maximum threshold value, this threshold value is then as the follow-up preliminary threshold carrying out cloud and shadow Detection.
(5) utilize preliminary threshold correlative value index image to carry out density slice, obtain the preliminary classification of cloud and shade, then according to classification situation adjustment threshold value, obtain the reliable cloud mask of precision, shadow image, detect while realizing remote sensing image clouds and shade.
Although here for MODIS image, the method is applicable to any remote sensing image, comprises, a series of classical satellite image such as TM/ETM+, VIIRS, SPOT, ASTER, AVHRR, HJ-1A/B.
Adopt the method that this embodiment provides, the high precision test of cloud and shade can be realized, thus for remote sensing image classification research, remote sensing images inverting research and utilize remote sensing images to carry out atmospheric research to provide gordian technique and authentic data support.
From the description of above each embodiment, can find out, the embodiment of the present invention achieves following technique effect:
(1) based on the cloud detection technology of radiomimesis field, no longer relying on spectral information and observation geological information, is a kind of brand-new cloud detection thinking;
(2) cloud detection technology different from the past, detects while the method can realize cloud and shade, not by the restriction on underlying surface high reverse--bias earth's surface (e.g., ice and snow, desert etc.) and low reflection earth's surface (e.g., water body) etc.;
(3) compared with being only applicable to the detection method of specific remote sensing images in prior art, this method goes for any remote sensing image, not by any restriction of wave band, have extremely strong versatility, and precision is reliable.
Each embodiment in this instructions all adopts the mode of going forward one by one to describe, and what each embodiment stressed is the difference with other embodiments, between each embodiment identical similar part mutually see.
The above; be only the present invention's preferably embodiment, but protection scope of the present invention is not limited thereto, any people being familiar with this technology is in the technical scope disclosed by the present invention; the change that can expect easily or replacement, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain of claim.
Claims (7)
1., based on remote sensing image clouds and the shadow detection method of radiation field, it is characterized in that, comprising:
Obtain the atmospheric radiation transmission that remote sensing image to be detected is corresponding;
With the atmospheric temperature-moisture profile under earth surface albedo product and the clear sky condition preset, aerosol optical depth under default clear sky condition for driving data, described atmospheric radiation transmission is utilized to generate simulation radiation field corresponding to described remote sensing image to be detected;
The Ratio index image corresponding with remote sensing image to be detected described in described simulation computation of radiation field according to described remote sensing image to be detected;
Extract the numerical value that on described Ratio index image, clear sky unshadowed area is corresponding, obtain numerical value set;
Obtain the first numerical value in described numerical value set and second value, wherein, described first numerical value is greater than described second value;
Described first numerical value and described second value is adopted to carry out density slice to described Ratio index image, to obtain the classification of cloud and shade.
2. the remote sensing image clouds based on radiation field according to claim 1 and shadow detection method, it is characterized in that, the step according to the described remote sensing image to be detected Ratio index image corresponding with remote sensing image to be detected described in described simulation computation of radiation field specifically comprises:
Each wave band radiance of described remote sensing image to be detected and described simulation radiation field is asked ratio;
Each ratio of trying to achieve is carried out product calculation, to obtain Ratio index image corresponding to described remote sensing image to be detected.
3. the remote sensing image clouds based on radiation field according to claim 1 and shadow detection method, is characterized in that, extract the numerical value that on described Ratio index image, clear sky unshadowed area is corresponding, the step obtaining numerical value set specifically comprises:
Calculate the similarity of described remote sensing image to be detected and described simulation radiation field;
On described Ratio index image, determine that the region that described similarity is greater than default similarity is clear sky unshadowed area;
Extract the numerical value that described clear sky unshadowed area is corresponding, obtain described numerical value set.
4. the remote sensing image clouds based on radiation field according to claim 3 and shadow detection method, is characterized in that, the step calculating the similarity of described remote sensing image to be detected and described simulation radiation field is specially:
Structural similarity texture recognition algorithm is adopted to calculate the similarity of described remote sensing image to be detected and described simulation radiation field.
5. the remote sensing image clouds based on radiation field according to claim 1 and shadow detection method, is characterized in that, obtains the first numerical value in described numerical value set and second value specifically comprises:
Numerical value in described numerical value set is sorted according to size;
Remove in described numerical value set the numerical value of front and back end 2% of sorting;
In described numerical value set, obtain the maximal value after removing the numerical value of 2% as described first numerical value, minimum value is as described second value.
6. the remote sensing image clouds based on radiation field according to claim 1 and shadow detection method, it is characterized in that, adopt described first numerical value and described second value to carry out density slice to described Ratio index image, specifically comprise with the classification obtaining cloud and shade:
Using described first numerical value and described second value as initial segmentation threshold value, density slice is carried out to described Ratio index image, to obtain the preliminary classification of cloud and shade;
Adjust described initial segmentation threshold value according to the classification results of described preliminary classification, adopt the segmentation threshold after adjustment to carry out density slice to described Ratio index image, to obtain cloud mask.
7. the remote sensing image clouds based on radiation field according to claim 1 and shadow detection method, it is characterized in that, described remote sensing image to be detected can be MODIS image, TM/ETM+ image, VIIRS image, SPOT image, ASTER image, AVHRR image or HJ-1A/B image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510239763.6A CN104867139B (en) | 2015-05-12 | 2015-05-12 | A kind of remote sensing image clouds and shadow detection method based on radiation field |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510239763.6A CN104867139B (en) | 2015-05-12 | 2015-05-12 | A kind of remote sensing image clouds and shadow detection method based on radiation field |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104867139A true CN104867139A (en) | 2015-08-26 |
| CN104867139B CN104867139B (en) | 2018-02-09 |
Family
ID=53912954
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510239763.6A Active CN104867139B (en) | 2015-05-12 | 2015-05-12 | A kind of remote sensing image clouds and shadow detection method based on radiation field |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104867139B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105426903A (en) * | 2015-10-27 | 2016-03-23 | 航天恒星科技有限公司 | Cloud determination method and system for remote sensing satellite images |
| CN105678777A (en) * | 2016-01-12 | 2016-06-15 | 武汉大学 | Feature-combined optical satellite image cloud and cloud shadow detection method |
| CN107944413A (en) * | 2017-12-04 | 2018-04-20 | 中国科学院南京地理与湖泊研究所 | Aquatic vegetation Classification in Remote Sensing Image threshold value calculation method based on spectral index ranking method |
| CN110599488A (en) * | 2019-09-27 | 2019-12-20 | 广西师范大学 | Cloud detection method based on Sentinel-2 aerosol wave band |
| CN112889089A (en) * | 2018-10-19 | 2021-06-01 | 克莱米特公司 | Machine learning technique for identifying clouds and cloud shadows in satellite imagery |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101034477A (en) * | 2007-03-29 | 2007-09-12 | 上海大学 | Method for eliminating shadow on remote sensing digital image and recovering picture element remote sensing value in shadow |
| CN103901420A (en) * | 2014-04-18 | 2014-07-02 | 山东科技大学 | Method for dynamic threshold method remote sensing data cloud identification supported by prior surface reflectance |
| CN104156923A (en) * | 2014-08-12 | 2014-11-19 | 西北工业大学 | Multispectral remote sensing image cloud removing method based on sparse representation |
-
2015
- 2015-05-12 CN CN201510239763.6A patent/CN104867139B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101034477A (en) * | 2007-03-29 | 2007-09-12 | 上海大学 | Method for eliminating shadow on remote sensing digital image and recovering picture element remote sensing value in shadow |
| CN103901420A (en) * | 2014-04-18 | 2014-07-02 | 山东科技大学 | Method for dynamic threshold method remote sensing data cloud identification supported by prior surface reflectance |
| CN104156923A (en) * | 2014-08-12 | 2014-11-19 | 西北工业大学 | Multispectral remote sensing image cloud removing method based on sparse representation |
Non-Patent Citations (2)
| Title |
|---|
| 姬大彬: "基于 MODIS 数据的高分辨率气溶胶光学厚度反演", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 陈晓东 等: "基于MPHD算法的高分辨率遥感影像对海洋上空的云及其阴影的识别与匹配", 《海洋学研究》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105426903A (en) * | 2015-10-27 | 2016-03-23 | 航天恒星科技有限公司 | Cloud determination method and system for remote sensing satellite images |
| CN105678777A (en) * | 2016-01-12 | 2016-06-15 | 武汉大学 | Feature-combined optical satellite image cloud and cloud shadow detection method |
| CN105678777B (en) * | 2016-01-12 | 2018-03-13 | 武汉大学 | A kind of optical satellite image cloud of multiple features combining and cloud shadow detection method |
| CN107944413A (en) * | 2017-12-04 | 2018-04-20 | 中国科学院南京地理与湖泊研究所 | Aquatic vegetation Classification in Remote Sensing Image threshold value calculation method based on spectral index ranking method |
| CN112889089A (en) * | 2018-10-19 | 2021-06-01 | 克莱米特公司 | Machine learning technique for identifying clouds and cloud shadows in satellite imagery |
| CN112889089B (en) * | 2018-10-19 | 2024-03-05 | 克莱米特有限责任公司 | Machine learning techniques for identifying clouds and cloud shadows in satellite imagery |
| CN110599488A (en) * | 2019-09-27 | 2019-12-20 | 广西师范大学 | Cloud detection method based on Sentinel-2 aerosol wave band |
| CN110599488B (en) * | 2019-09-27 | 2022-04-29 | 广西师范大学 | Cloud detection method based on Sentinel-2 aerosol wave band |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104867139B (en) | 2018-02-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104867139A (en) | Remote sensing image cloud and shadow detection method based on radiation field | |
| CN110189344B (en) | Method for extracting straight line segment in electric power disconnecting link image | |
| CN108051371B (en) | A kind of shadow extraction method of ecology-oriented environment parameter remote-sensing inversion | |
| CN104408705A (en) | Anomaly detection method of hyperspectral image | |
| CN102254319A (en) | Method for carrying out change detection on multi-level segmented remote sensing image | |
| CN106815819B (en) | More strategy grain worm visible detection methods | |
| CN111339948B (en) | Automatic identification method for newly-added buildings of high-resolution remote sensing images | |
| CN104504686A (en) | Hyper-spectral image abnormity detection method adopting local self-adaptive threshold segmentation | |
| CN102831436B (en) | High spectrum image classifying method based on reference diagram mutual information wave band selection and EMD (Empirical Mode Decomposition) | |
| CN110443139B (en) | Hyperspectral remote sensing image noise band detection method for classification | |
| US11151377B2 (en) | Cloud detection method based on landsat 8 snow-containing image | |
| CN107992856B (en) | High-resolution remote sensing building shadow detection method under urban scene | |
| CN104166838B (en) | Layering High Resolution SAR image Ship Detection based on multi-layer C FAR | |
| CN105160362A (en) | Runway FOD (Foreign Object Debris) image detection method and device | |
| CN103020649A (en) | Forest type identification method based on texture information | |
| CN107421892A (en) | A kind of hyperspectral data processing method for water body information | |
| CN105184804A (en) | Sea surface small target detection method based on airborne infrared camera aerially-photographed image | |
| CN105718924B (en) | High score satellite image cloud detection method of optic based on combination features and machine learning | |
| CN102800101A (en) | Satellite-borne infrared remote sensing image airport ROI rapid detection method | |
| Paget et al. | Determining the floe-size distribution of East Antarctic sea ice from digital aerial photographs | |
| Abraham et al. | Unsupervised building extraction from high resolution satellite images irrespective of rooftop structures | |
| Syarif et al. | The effect of minimum noise fraction on multispectral imagery data for vegetation canopy density modelling | |
| CN110378294B (en) | Hyperspectral target detection method and system based on local energy constraint and feature fusion | |
| Wang et al. | Cloud detection for landsat images by fusion of multi-temporal data | |
| Yang et al. | Automated cloud detection algorithm for multi-spectral high spatial resolution images using Landsat-8 OLI |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |