CN113610730B - Method and system for removing non-uniform thin cloud of satellite image - Google Patents
Method and system for removing non-uniform thin cloud of satellite image Download PDFInfo
- Publication number
- CN113610730B CN113610730B CN202110901053.0A CN202110901053A CN113610730B CN 113610730 B CN113610730 B CN 113610730B CN 202110901053 A CN202110901053 A CN 202110901053A CN 113610730 B CN113610730 B CN 113610730B
- Authority
- CN
- China
- Prior art keywords
- data
- cloud
- matrix
- pixel
- remote sensing
- 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
- 238000000034 method Methods 0.000 title claims abstract description 22
- 239000011159 matrix material Substances 0.000 claims abstract description 78
- 238000012216 screening Methods 0.000 claims abstract description 35
- 238000002834 transmittance Methods 0.000 claims abstract description 32
- 238000001914 filtration Methods 0.000 claims abstract description 11
- 238000012935 Averaging Methods 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000010606 normalization Methods 0.000 claims description 9
- 230000015556 catabolic process Effects 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 6
- 238000006731 degradation reaction Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 description 3
- 238000011084 recovery Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000012805 post-processing Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- 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
- G06T2207/10032—Satellite or aerial image; Remote sensing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a method and a system for removing non-uniform thin clouds of satellite images. The method comprises the following steps: collecting cloud remote sensing data of satellites; screening and normalizing the data, and selecting minimum value data of three wave band data according to the normalized data to construct a first matrix; performing minimum filtering treatment on a matrix block with a preset size in the first matrix to obtain a dark channel matrix; selecting pixel data in normalized data corresponding to the brightest n pixel points in the dark channel matrix to construct a second matrix; averaging pixel values in the second matrix to obtain atmospheric light; calculating a transmittance map from the atmospheric light and dark channel matrix; determining first reduction data according to the transmittance map and the atmospheric light; and restoring the extreme pixel data according to the position information data to obtain second restored data. The invention realizes the reconstruction of satellite image detail information under the heterogeneous thin cloud cover and simultaneously ensures the color fidelity of the satellite image.
Description
Technical Field
The invention relates to the technical field of remote sensing images, in particular to a method and a system for removing non-uniform thin clouds of satellite images.
Background
The application of the remote sensing image is wider and wider, and the quality requirement on the remote sensing image is also improved. The high-resolution satellite image acquisition cost is high, the cloud coverage image reduces the image utilization rate, and about 80% of the optical remote sensing images are interfered by the cloud to reduce the utilization value, so that the image acquisition cost is increased. The acquired data can be utilized to a greater extent through effective remote sensing image cloud removal and information recovery processing, so that the use cost is reduced while smooth information collection is ensured, and therefore, the remote sensing image thin cloud removal technology has important research significance and practical application value.
The cloud coverage of the remote sensing image shows the characteristics of uneven local coverage and uneven thickness distribution of the full coverage cloud. The existing remote sensing image thin cloud removing technology mainly utilizes a defogging field method to remove the thin cloud of the whole image, and lacks a non-uniform cloud removing algorithm. The uneven cloud is not thoroughly removed, or the color distortion of the image in the cloud-free area is serious.
The area covered by the heterogeneous thin cloud in the remote sensing image contains the cloud and the ground object information, so that many researches focus on removing the thin cloud and reconstructing the ground object information. This is an important preprocessing step for remote sensing images, and depth information generated by cloud removal is also important for subsequent information processing and satellite image application.
Disclosure of Invention
The invention aims to provide a method and a system for removing non-uniform thin clouds of satellite images, which are used for realizing reconstruction of satellite image detail information under the coverage of the non-uniform thin clouds and ensuring color fidelity of the satellite images.
In order to achieve the above object, the present invention provides the following solutions:
a method for removing non-uniform thin clouds of satellite images comprises the following steps:
collecting cloud remote sensing data of satellites; the satellite cloud remote sensing data comprises three wave band data, namely R wave band data, G wave band data and B wave band data;
screening and normalizing the satellite cloud remote sensing data to obtain screening data and normalized data; the screening data comprises extreme pixel data and position information data corresponding to the extreme pixel data;
selecting minimum value data of three wave band data according to the normalized data to construct a first matrix;
performing minimum filtering treatment on a matrix block with a preset size in the first matrix to obtain a dark channel matrix;
selecting pixel data in normalized data corresponding to the brightest n pixel points in the dark channel matrix to construct a second matrix;
averaging pixel values in the second matrix to obtain atmospheric light;
calculating a transmittance map from the atmospheric light and the dark channel matrix;
determining first reduction data from the transmittance map and the atmospheric light;
restoring the extreme pixel data according to the position information data to obtain second restored data;
and obtaining the remote sensing image after cloud removal based on the first reduction data and the second reduction data.
Further, the screening and normalizing the satellite cloud remote sensing data specifically includes:
screening 2% of pixel data with highest pixel value and 2% of pixel data with lowest pixel value in the satellite cloud remote sensing data to form extreme pixel data, and counting position information data corresponding to the extreme pixel data; the first extreme pixel data includes maximum value data and minimum value data;
and linearly stretching the residual data in the cloud remote sensing data of the satellite to 0-255 to obtain normalized data.
Further, the calculation formula of the transmittance map is as follows:
wherein T represents a transmittance map, D represents a dark channel matrix, A c Represents atmospheric light.
Further, the determining the first reduction data according to the transmittance map and the atmospheric light specifically includes:
according to the transmissivity graph and the atmospheric light, initial cloud image data are obtained through inverse solution of an atmospheric degradation model;
and carrying out inverse normalization processing on the initial cloud removal data to obtain first reduction data.
Further, the calculation formula of the initial cloud image data is as follows:
wherein J' represents initial de-cloud image data, TRepresenting a transmittance graph, A c Represents atmospheric light.
The invention also provides a system for removing the non-uniform thin cloud of the satellite image, which comprises the following steps:
the data acquisition module is used for acquiring cloud remote sensing data of satellites; the satellite cloud remote sensing data comprises three wave band data, namely R wave band data, G wave band data and B wave band data;
the screening and normalizing processing module is used for screening and normalizing the cloud remote sensing data of the satellite to obtain screening data and normalized data; the screening data comprises extreme pixel data and position information data corresponding to the extreme pixel data;
the first matrix construction module is used for selecting minimum value data of three wave band data to construct a first matrix according to the normalized data;
the dark channel matrix determining module is used for carrying out minimum filtering processing on a matrix block with a preset size in the first matrix to obtain a dark channel matrix;
the second matrix construction module is used for selecting pixel data in normalized data corresponding to the brightest n pixel points in the dark channel matrix to construct a second matrix;
the atmosphere light calculation module is used for averaging the pixel values in the second matrix to obtain atmosphere light;
a transmittance map calculation module for calculating a transmittance map from the atmospheric light and the dark channel matrix;
a first restoration data determining module for determining first restoration data according to the transmittance map and the atmospheric light;
the second restoration data determining module is used for restoring the extreme pixel data according to the position information data to obtain second restoration data;
and the remote sensing image determining module after cloud removal is used for obtaining the remote sensing image after cloud removal based on the first reduction data and the second reduction data.
Further, the screening and normalizing module specifically includes:
the screening unit is used for screening 2% of pixel data with the highest pixel value and 2% of pixel data with the lowest pixel value in the satellite cloud remote sensing data to form extreme pixel data, and counting position information data corresponding to the extreme pixel data; the first extreme pixel data includes maximum value data and minimum value data;
and the linear stretching unit is used for linearly stretching the residual data in the cloud remote sensing data of the satellite to 0-255 to obtain normalized data.
Further, the calculation formula of the transmittance map is as follows:
wherein T represents a transmittance map, D represents a dark channel matrix, A c Represents atmospheric light.
Further, the first restoration data determining module specifically includes:
the initial cloud image data determining unit is used for obtaining initial cloud image data by inverse solution of an atmospheric degradation model according to the transmissivity image and the atmospheric light;
and the inverse normalization processing unit is used for performing inverse normalization processing on the initial cloud removal data to obtain first restored data.
Further, the calculation formula of the initial cloud image data is as follows:
wherein J' represents initial de-cloud image data, T represents transmittance map, A c Represents atmospheric light.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
according to the cloud removing method, cloud removing can be realized on single remote sensing images with non-uniform thin clouds and different cloud layer distribution and density through the steps of data preprocessing, dark channel calculation, weighted least square filtering, atmospheric light estimation, transmissivity image refinement, cloud-free image recovery, post-processing and the like.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a method for removing non-uniform thin clouds from satellite images according to an embodiment of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention aims to provide a method and a system for removing non-uniform thin clouds of satellite images, which are used for realizing reconstruction of satellite image detail information under the coverage of the non-uniform thin clouds and ensuring color fidelity of the satellite images.
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
As shown in fig. 1, the method for removing the non-uniform thin cloud of the satellite image provided by the invention comprises the following steps:
step 101: collecting cloud remote sensing data of satellites; the satellite cloud remote sensing data comprises three wave band data, namely R wave band data, G wave band data and B wave band data.
Step 102: screening and normalizing the satellite cloud remote sensing data to obtain screening data and normalized data; the filtering data includes extreme pixel data and position information data corresponding to the extreme pixel data.
The method specifically comprises the following steps:
screening 2% of pixel data with highest pixel value and 2% of pixel data with lowest pixel value in the satellite cloud remote sensing data to form extreme pixel data, and counting position information data corresponding to the extreme pixel data; the first extreme pixel data includes maximum value data and minimum value data;
and linearly stretching the residual data in the cloud remote sensing data of the satellite to 0-255 to obtain normalized data.
Step 103: and selecting minimum value data of three wave band data according to the normalized data to construct a first matrix.
Step 104: and performing minimum filtering processing on a matrix block with a preset size in the first matrix to obtain a dark channel matrix.
Step 105: and selecting pixel data in normalized data corresponding to the brightest n pixel points in the dark channel matrix to construct a second matrix.
Step 106: and averaging pixel values in the second matrix to obtain atmospheric light.
Step 107: and calculating a transmittance map according to the atmospheric light and the dark channel matrix.
Step 108: first reduction data is determined from the transmittance map and the atmospheric light.
Step 109: and restoring the extreme pixel data according to the position information data to obtain second restored data.
Step 1010: and obtaining the remote sensing image after cloud removal based on the first reduction data and the second reduction data.
Specific examples are as follows:
step 1: collecting cloud remote sensing data A of a satellite;
step 2: storing the RGB three-band data of the remote sensing data A acquired in the step 1 into a matrix I= { I 1 ,I 2 ,I 3 }, wherein I 1 Storing R-band data，I 2 Storing G band data, I 3 B-band data is stored.
Step 3: and (5) normalizing the data.
Step 3.1: r wave band I in statistical image RGB data I 1 Will be I 1 2% pixel data I with highest median value 1max Store array I max ，I 1max At I 1 Corresponding position information data L 1max Store into array L max . Will I 1 2% pixel data I with lowest median value 1min Store array I min ，I 1min At I 1 Corresponding position data L in 1min Store into array L min ；
Step 3.2: pair I 1 Is greater than I 1min And is less than I 1max Is linearly stretched to 0-255 for I 1min Data set to 0 for I 1max Is set to 255, resulting in I 1 Normalized matrix I o1 ；
Step 3.3: g band I in statistical image RGB data I 2 Will be I 2 2% pixel data I with highest median value 2max Store array I max ，I 2max At I 2 Corresponding position information data L 2max Store into array L max . Will I 2 2% pixel data I with lowest median value 2min Store array I min ，I 2min At I 2 Corresponding position data L in 2min Store into array L min ；
Step 3.4: pair I 2 Is greater than I 2min And is less than I 2max Is linearly stretched to 0-255 for I 2min Data set to 0 for I 2max Is set to 255, resulting in I 2 Normalized matrix I o2 ；
Step 3.5: b band I in statistical image RGB data I 3 Will be I 3 2% pixel data I with highest median value 3max Store array I max ，I 3max At I 3 Corresponding position information data L 3max Store into array L max . Will I 3 2% pixel data I with lowest median value 3min Store array I min ，I 3min At I 3 Corresponding position data L in 3min Store into array L min ；
Step 3.6: pair I 3 Is greater than I 3min And is less than I 3max Is linearly stretched to 0-255 for I 3min Data set to 0 for I 3max Is set to 255, resulting in I 3 Normalized matrix I o3 。
Finally, normalized pixel data I is obtained o ＝{I o1 ,I o2 ,I o3 Extreme pixel data I stored max ＝{I 1max ,I 2max ,I 3max Sum I min ＝{I 1min ,I 2min ,I 3min Location information L of } and extreme data max ＝{L 1max ,L 2max ,L 3max Sum L min ＝{L 1min ,L 2min ,L 3min }。
Step 4: according to the normalized data I obtained in the step 3 o Selecting minimum value data of three wavebands of RGBDeposit matrix I omin In the process, I is selected omin The matrix block Ω of the inner 5*5 size is subjected to minimum filtering to obtain a dark channel matrix of Io: />
Step 5: constructing a matrix D according to the dark channel data D of the image data obtained in the step 4 max Selecting the brightest 0.1% pixel point position in D to correspond to I o Data store D in (C) max And matrix D max The pixel values in the array are averaged to obtain atmospheric light A c 。
Step 6: using the atmospheric light A described in step 5 c And calculating a transmittance map for the dark channel D in step 4:
step 7: using the transmission map T and the atmospheric light A obtained in the step 6 c The cloud-removed image data J' are obtained by inverse solution of the atmospheric degradation model:
step 8: performing inverse normalization processing on the cloud removed image data J' in the step 7, and restoring data J= { J with corresponding size 1 ,J 2 ,J 3 }；
Step 9: corresponds to L max And L min The position information in step 3 will be the data I in step 3 max And I min Reducing; and obtaining the remote sensing image J after cloud removal.
According to the cloud removing method, cloud removing can be realized on single remote sensing images with non-uniform thin clouds and different cloud layer distribution and density through the steps of data preprocessing, dark channel calculation, weighted least square filtering, atmospheric light estimation, transmissivity image refinement, cloud-free image recovery, post-processing and the like.
The invention also provides a system for removing the non-uniform thin cloud of the satellite image, which comprises the following steps:
the data acquisition module is used for acquiring cloud remote sensing data of satellites; the satellite cloud remote sensing data comprises three wave band data, namely R wave band data, G wave band data and B wave band data;
the screening and normalizing processing module is used for screening and normalizing the cloud remote sensing data of the satellite to obtain screening data and normalized data; the screening data comprises extreme pixel data and position information data corresponding to the extreme pixel data;
the first matrix construction module is used for selecting minimum value data of three wave band data to construct a first matrix according to the normalized data;
the dark channel matrix determining module is used for carrying out minimum filtering processing on a matrix block with a preset size in the first matrix to obtain a dark channel matrix;
the second matrix construction module is used for selecting pixel data in normalized data corresponding to the brightest n pixel points in the dark channel matrix to construct a second matrix;
the atmosphere light calculation module is used for averaging the pixel values in the second matrix to obtain atmosphere light;
a transmittance map calculation module for calculating a transmittance map from the atmospheric light and the dark channel matrix;
a first restoration data determining module for determining first restoration data according to the transmittance map and the atmospheric light;
the second restoration data determining module is used for restoring the extreme pixel data according to the position information data to obtain second restoration data;
and the remote sensing image determining module after cloud removal is used for obtaining the remote sensing image after cloud removal based on the first reduction data and the second reduction data.
Wherein, the screening and normalizing module specifically includes:
the screening unit is used for screening 2% of pixel data with the highest pixel value and 2% of pixel data with the lowest pixel value in the satellite cloud remote sensing data to form extreme pixel data, and counting position information data corresponding to the extreme pixel data; the first extreme pixel data includes maximum value data and minimum value data;
and the linear stretching unit is used for linearly stretching the residual data in the cloud remote sensing data of the satellite to 0-255 to obtain normalized data.
The first restoration data determining module specifically includes:
the initial cloud image data determining unit is used for obtaining initial cloud image data by inverse solution of an atmospheric degradation model according to the transmissivity image and the atmospheric light;
and the inverse normalization processing unit is used for performing inverse normalization processing on the initial cloud removal data to obtain first restored data.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The principles and embodiments of the present invention have been described herein with reference to specific examples, the description of which is intended only to assist in understanding the methods of the present invention and the core ideas thereof; also, it is within the scope of the present invention to be modified by those of ordinary skill in the art in light of the present teachings. In view of the foregoing, this description should not be construed as limiting the invention.
Claims (6)
1. A method for removing non-uniform thin cloud of satellite images is characterized by comprising the following steps:
collecting cloud remote sensing data of satellites; the satellite cloud remote sensing data comprises three wave band data, namely R wave band data, G wave band data and B wave band data;
screening and normalizing the satellite cloud remote sensing data to obtain screening data and normalized data; the screening data comprises extreme pixel data and position information data corresponding to the extreme pixel data;
selecting minimum value data of three wave band data according to the normalized data to construct a first matrix;
performing minimum filtering treatment on a matrix block with a preset size in the first matrix to obtain a dark channel matrix;
selecting pixel data in normalized data corresponding to the brightest n pixel points in the dark channel matrix to construct a second matrix;
averaging pixel values in the second matrix to obtain atmospheric light;
calculating a transmittance map from the atmospheric light and the dark channel matrix;
determining first reduction data from the transmittance map and the atmospheric light;
restoring the extreme pixel data according to the position information data to obtain second restored data;
obtaining a remote sensing image after cloud removal based on the first reduction data and the second reduction data;
the screening and normalizing process for the cloud remote sensing data of the satellite specifically comprises the following steps:
screening 2% of pixel data with highest pixel value and 2% of pixel data with lowest pixel value in the satellite cloud remote sensing data to form extreme pixel data, and counting position information data corresponding to the extreme pixel data; the extreme pixel data includes maximum value data and minimum value data;
linearly stretching the residual data in the cloud remote sensing data of the satellite to 0-255 to obtain normalized data;
the determining first reduction data according to the transmittance map and the atmospheric light specifically includes:
according to the transmissivity graph and the atmospheric light, initial cloud image data are obtained through inverse solution of an atmospheric degradation model;
and carrying out inverse normalization processing on the initial cloud image data to obtain first restored data.
2. The method for removing non-uniform thin clouds from a satellite image according to claim 1, wherein the transmittance map is calculated as follows:
wherein T represents a transmittance map, D represents a dark channel matrix, A c Represents atmospheric light.
3. The method for removing non-uniform thin clouds from a satellite image according to claim 1, wherein the calculation formula of the initial cloud removal image data is as follows:
wherein J' represents initial de-cloud image data, T represents transmittance map, A c Represents atmospheric light.
4. A satellite image non-uniform thin cloud removal system, comprising:
the data acquisition module is used for acquiring cloud remote sensing data of satellites; the satellite cloud remote sensing data comprises three wave band data, namely R wave band data, G wave band data and B wave band data;
the screening and normalizing processing module is used for screening and normalizing the cloud remote sensing data of the satellite to obtain screening data and normalized data; the screening data comprises extreme pixel data and position information data corresponding to the extreme pixel data;
the first matrix construction module is used for selecting minimum value data of three wave band data to construct a first matrix according to the normalized data;
the dark channel matrix determining module is used for carrying out minimum filtering processing on a matrix block with a preset size in the first matrix to obtain a dark channel matrix;
the second matrix construction module is used for selecting pixel data in normalized data corresponding to the brightest n pixel points in the dark channel matrix to construct a second matrix;
the atmosphere light calculation module is used for averaging the pixel values in the second matrix to obtain atmosphere light;
a transmittance map calculation module for calculating a transmittance map from the atmospheric light and the dark channel matrix;
a first restoration data determining module for determining first restoration data according to the transmittance map and the atmospheric light;
the second restoration data determining module is used for restoring the extreme pixel data according to the position information data to obtain second restoration data;
the remote sensing image determining module after cloud removal is used for obtaining a remote sensing image after cloud removal based on the first reduction data and the second reduction data;
the screening and normalizing module specifically comprises:
the screening unit is used for screening 2% of pixel data with the highest pixel value and 2% of pixel data with the lowest pixel value in the satellite cloud remote sensing data to form extreme pixel data, and counting position information data corresponding to the extreme pixel data; the extreme pixel data includes maximum value data and minimum value data;
the linear stretching unit is used for linearly stretching the residual data in the cloud remote sensing data of the satellite to 0-255 to obtain normalized data;
the first restoration data determining module specifically includes:
the initial cloud image data determining unit is used for obtaining initial cloud image data by inverse solution of an atmospheric degradation model according to the transmissivity image and the atmospheric light;
and the inverse normalization processing unit is used for carrying out inverse normalization processing on the initial cloud image removal data to obtain first restored data.
5. The system of claim 4, wherein the transmittance map is calculated as follows:
wherein T represents a transmittance map, D represents a dark channel matrix, A c Represents atmospheric light.
6. The system for removing non-uniform thin clouds from a satellite image according to claim 5, wherein the initial de-clouded image data is calculated as follows:
wherein J' tableThe initial de-cloud image data is shown, T represents the transmittance map, A c Represents atmospheric light.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110901053.0A CN113610730B (en) | 2021-08-06 | 2021-08-06 | Method and system for removing non-uniform thin cloud of satellite image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110901053.0A CN113610730B (en) | 2021-08-06 | 2021-08-06 | Method and system for removing non-uniform thin cloud of satellite image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113610730A CN113610730A (en) | 2021-11-05 |
| CN113610730B true CN113610730B (en) | 2023-08-29 |
Family
ID=78307380
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110901053.0A Active CN113610730B (en) | 2021-08-06 | 2021-08-06 | Method and system for removing non-uniform thin cloud of satellite image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113610730B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115496685A (en) * | 2022-09-21 | 2022-12-20 | 重庆地质矿产研究院 | Rapid cloud thinning method for high-resolution second-order satellite remote sensing image |
| CN115760641B (en) * | 2022-12-06 | 2024-01-23 | 二十一世纪空间技术应用股份有限公司 | Remote sensing image cloud and fog removing method and equipment based on multiscale characteristic attention network |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105225210A (en) * | 2015-10-14 | 2016-01-06 | 南京第五十五所技术开发有限公司 | A kind of self-adapting histogram based on dark strengthens defogging method capable |
| CN107038691A (en) * | 2017-04-12 | 2017-08-11 | 北京爱特拉斯信息科技有限公司 | The dark primary remote sensing image defogging method aided in based on cloud detection |
| CN107316284A (en) * | 2017-07-19 | 2017-11-03 | 山东财经大学 | Intense light source hypograph defogging method and device |
| CN108257094A (en) * | 2016-12-29 | 2018-07-06 | 广东中科遥感技术有限公司 | The quick minimizing technology of remote sensing image mist based on dark |
| CN108596853A (en) * | 2018-04-28 | 2018-09-28 | 上海海洋大学 | Underwater picture Enhancement Method based on bias light statistical model and transmission map optimization |
| CN110428371A (en) * | 2019-07-03 | 2019-11-08 | 深圳大学 | Image defogging method, system, storage medium and electronic equipment based on super-pixel segmentation |
| CN111489299A (en) * | 2020-02-25 | 2020-08-04 | 天津大学 | Defogging method for multispectral remote sensing satellite image |
| CN112750089A (en) * | 2020-12-27 | 2021-05-04 | 同济大学 | Optical remote sensing image defogging method based on local block maximum and minimum pixel prior |
| CN112767278A (en) * | 2021-01-28 | 2021-05-07 | 湖南大学 | Image defogging method based on non-uniform atmospheric light prior and related equipment |
-
2021
- 2021-08-06 CN CN202110901053.0A patent/CN113610730B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105225210A (en) * | 2015-10-14 | 2016-01-06 | 南京第五十五所技术开发有限公司 | A kind of self-adapting histogram based on dark strengthens defogging method capable |
| CN108257094A (en) * | 2016-12-29 | 2018-07-06 | 广东中科遥感技术有限公司 | The quick minimizing technology of remote sensing image mist based on dark |
| CN107038691A (en) * | 2017-04-12 | 2017-08-11 | 北京爱特拉斯信息科技有限公司 | The dark primary remote sensing image defogging method aided in based on cloud detection |
| CN107316284A (en) * | 2017-07-19 | 2017-11-03 | 山东财经大学 | Intense light source hypograph defogging method and device |
| CN108596853A (en) * | 2018-04-28 | 2018-09-28 | 上海海洋大学 | Underwater picture Enhancement Method based on bias light statistical model and transmission map optimization |
| CN110428371A (en) * | 2019-07-03 | 2019-11-08 | 深圳大学 | Image defogging method, system, storage medium and electronic equipment based on super-pixel segmentation |
| CN111489299A (en) * | 2020-02-25 | 2020-08-04 | 天津大学 | Defogging method for multispectral remote sensing satellite image |
| CN112750089A (en) * | 2020-12-27 | 2021-05-04 | 同济大学 | Optical remote sensing image defogging method based on local block maximum and minimum pixel prior |
| CN112767278A (en) * | 2021-01-28 | 2021-05-07 | 湖南大学 | Image defogging method based on non-uniform atmospheric light prior and related equipment |
Non-Patent Citations (1)
| Title |
|---|
| 孟祥超.多源时—空—谱光学遥感影像的变分融合方法.《中国博士学位论文全文数据库 基础科学辑》.2018,(第06期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113610730A (en) | 2021-11-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113610730B (en) | Method and system for removing non-uniform thin cloud of satellite image | |
| CN108876741B (en) | Image enhancement method under complex illumination condition | |
| AU2020100462A4 (en) | Edge-preserving image super-resolution via low rank and total variation model | |
| CN110517327B (en) | Underwater image enhancement method based on color correction and contrast stretching | |
| Xiao et al. | Removing stripe noise from infrared cloud images via deep convolutional networks | |
| CN109509160A (en) | Hierarchical remote sensing image fusion method utilizing layer-by-layer iteration super-resolution | |
| CN107563965A (en) | Jpeg compressed image super resolution ratio reconstruction method based on convolutional neural networks | |
| CN106780338B (en) | Rapid super-resolution reconstruction method based on anisotropy | |
| CN114723630B (en) | Image deblurring method and system based on cavity double-residual multi-scale depth network | |
| CN107833182A (en) | The infrared image super resolution ratio reconstruction method of feature based extraction | |
| Pan et al. | De-scattering and edge-enhancement algorithms for underwater image restoration | |
| CN105894477A (en) | Astronomical image noise removal method | |
| CN112233046B (en) | Image restoration method under Cauchy noise and application thereof | |
| Yang et al. | Low-light image enhancement based on Retinex theory and dual-tree complex wavelet transform | |
| CN113962905B (en) | Single image rain removing method based on multi-stage characteristic complementary network | |
| CN112150356A (en) | Single compressed image super-resolution reconstruction method based on cascade framework | |
| CN106296591B (en) | Non local uniform digital image de-noising method based on mahalanobis distance | |
| CN114764752B (en) | Night image defogging algorithm based on deep learning | |
| CN111626943B (en) | Total variation image denoising method based on first-order forward and backward algorithm | |
| CN110175959B (en) | Typhoon cloud picture enhancement method | |
| CN106846286B (en) | Video super-resolution algorithm for reconstructing based on a variety of complementary priori | |
| CN115456912A (en) | Tone mapping method based on multi-scale WLS filtering fusion | |
| CN116029934A (en) | Low-dose DR image and CT image denoising method | |
| CN115937031A (en) | Enhancement method for low-illumination image | |
| CN107871311A (en) | A kind of image enhaucament and fusion method applied to cmos image sensor |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | 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 |