CN113221634B - Low-radiation calibration precision optical remote sensing image cloud identification method, system and computer storage medium - Google Patents

Low-radiation calibration precision optical remote sensing image cloud identification method, system and computer storage medium Download PDF

Info

Publication number
CN113221634B
CN113221634B CN202110332475.0A CN202110332475A CN113221634B CN 113221634 B CN113221634 B CN 113221634B CN 202110332475 A CN202110332475 A CN 202110332475A CN 113221634 B CN113221634 B CN 113221634B
Authority
CN
China
Prior art keywords
image
band
pni
remote sensing
pixel
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
Application number
CN202110332475.0A
Other languages
Chinese (zh)
Other versions
CN113221634A (en
Inventor
熊先才
黄健
邓琳
胡勇
李晓俊
郑云云
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chongqing Planning And Natural Resources Investigation And Monitoring Institute
Original Assignee
Chongqing Planning And Natural Resources Investigation And Monitoring Institute
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Chongqing Planning And Natural Resources Investigation And Monitoring Institute filed Critical Chongqing Planning And Natural Resources Investigation And Monitoring Institute
Priority to CN202110332475.0A priority Critical patent/CN113221634B/en
Publication of CN113221634A publication Critical patent/CN113221634A/en
Application granted granted Critical
Publication of CN113221634B publication Critical patent/CN113221634B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N2021/1793—Remote sensing
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30181—Earth observation
    • G06T2207/30192—Weather; Meteorology

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Chemical & Material Sciences (AREA)
  • Remote Sensing (AREA)
  • Quality & Reliability (AREA)
  • Astronomy & Astrophysics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Multimedia (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Image Processing (AREA)

Abstract

The invention provides a low-radiation calibration precision optical remote sensing image cloud identification method, a system and a computer storage medium. The method has the advantages of less manual participation, high automation degree and high accuracy of the extraction result, can rapidly and accurately extract the cloud information of the optical remote sensing image with low radiation calibration precision, and solves the problems of low automation degree, long auxiliary data preparation time and the like of the traditional cloud identification method applied to the optical remote sensing image with low radiation calibration precision.

Description

Low-radiation calibration precision optical remote sensing image cloud identification method, system and computer storage medium
Technical Field
The invention belongs to the technical field of optical remote sensing image processing, and particularly relates to a cloud identification technology of an optical remote sensing image.
Background
The availability of most optical remote sensing images is reduced due to the strong influence of weather conditions during optical remote sensing imaging and the existence of weather factors such as aerosol, cloud and the like. While atmospheric correction may eliminate the effect of aerosols, atmospheric correction is not removable for clouds, especially thick clouds. Due to the shielding of the cloud on the ground object information, the cloud area in the optical remote sensing image cannot acquire the correct information of the ground object, and the next application of the optical remote sensing image is directly affected, including object extraction, change detection and the like. If the cloud remote sensing image is directly used for extracting the ground target and monitoring the change, an error result is caused. While this problem can be avoided with cloud-free images, for most regions of the world, there is less probability of acquiring cloud-free images. Therefore, cloud identification of optical remote sensing images is one of the important steps of remote sensing data processing.
The existing optical remote sensing image cloud identification method mainly comprises a reflectivity threshold method, a multi-time relative ratio detection method and a mode identification method. The optical remote sensing images with low radiation calibration precision by the methods have respective defects:
according to the reflectivity threshold method, according to sensor calibration parameters, geometric parameters and atmospheric parameters during satellite image imaging, a remote sensing image pixel Digital value (Digital Number-DN) is firstly converted into satellite reflectivity or earth surface reflectivity, and then a fixed threshold is set for certain characteristic wave bands or wave band four arithmetic results, so that cloud information in the remote sensing image is extracted. The method needs accurate sensor radiometric calibration parameters, if the method is applied to remote sensing images with low radiometric calibration precision, because the precision of the calibration coefficient of optical remote sensing with low radiometric calibration precision is poor, the calculated satellite reflectivity or earth surface reflectivity has large precision difference, and therefore, different images need to be respectively calculated and threshold values are respectively set to extract cloud information, so that the efficiency is low, and the automatic and efficient cloud identification processing is difficult to realize.
The multi-time relative ratio detection method comprises the steps of firstly selecting a cloud-free remote sensing image in the same area as an image to be processed as a reference image, enabling the spatial resolution of the reference image to be consistent with that of the image to be processed, then adopting a relative radiation correction method to eliminate or reduce the radiation difference between two-period images, and finally adopting a remote sensing image change detection algorithm to extract cloud information. The method needs to pre-establish cloud-free reference image data, is time-consuming and labor-consuming, and is particularly low in efficiency when being used for cloud identification of large-area data. In addition, the change of ground features between two-stage images also affects the extraction accuracy of cloud information.
The pattern recognition method is characterized in that cloud itself is used as an object, a cloud feature training set is built through priori data, then a cloud detector is built through artificial neural networks, clustering and other modes, and finally automatic cloud detection of an input image can be achieved. The performance of the method depends on the accuracy of training data and proper combination of different types of characteristics, but the cloud detection effect is greatly influenced by a cloud training set and a cloud detector, so that the failure of detection of non-training set characteristic clouds, cloud edges and low-brightness clouds is easy to cause, the accuracy of the training data set is difficult to ensure, the prior data training needs to consume a large amount of time, the calculation amount of the later cloud detection is large, and the overall efficiency is low.
Disclosure of Invention
Aiming at the problems that the existing cloud identification method is applied to an optical remote sensing image with low radiation calibration precision, has low automation degree or long auxiliary data preparation time and the like, the invention aims to provide the cloud identification method for the optical remote sensing image with low radiation calibration precision, which is based on a normalization method of DN value accumulation frequency distribution of the remote sensing image, and then sets a band threshold value to automatically extract cloud information. The method has the advantages of less manual participation, high automation degree and high accuracy of the extraction result, and can rapidly and accurately extract the optical remote sensing image cloud information with low radiation calibration precision.
The scheme for solving the technical problems is as follows:
a low-radiation calibration precision optical remote sensing image cloud identification method comprises the following steps:
step 1, adopting an accumulated frequency calculation method to normalize an optical remote sensing image with low radiation calibration precision band by band to obtain a normalized multiband image NI;
step 2, calculating the product of all wave bands pixel by pixel for the normalized data to obtain a single-band image PNI, counting the maximum value and the average value of the PNI, and calculating the maximum difference value image DNI of the wave bands of the normalized multi-band image NI;
and 3, setting thresholds of the PNI image and the DNI image, and automatically extracting cloud information.
Further, in the step 1, specifically, band-by-band normalization processing is performed on the optical remote sensing image X with low radiation calibration precision, so as to obtain a normalized multiband image NI, where the formula is as follows:
NI in i，j To normalize the value of image element i in band j, X i，j DN value of original image pixel i in wave band j, t j Is the effective value threshold for band j,indicating that DN value in band j is smaller than current pixel X i，j Is used for the number of the pixels,indicating the total number of active pixels in band j.
Further, the step 2 includes:
2.1, calculating the product of all wave bands on the normalized multiband image NI pixel by pixel to obtain a single-band image PNI, wherein the formula is as follows
Wherein N is the total number of wave bands and NI i，j The value of the normalized image pixel i in the band j is given;
2.2, calculating the maximum difference value of all wave bands pixel by pixel for the normalized multiband image NI to obtain a difference image DNI of a single wave band, wherein the formula is as follows
DNI i ＝MAX(NI i，* )-MIN(NI i，* )
MAX (NI) i，* ) To normalize the maximum value of image element i in all bands, MIN (NI i，* ) The minimum value of the pixel i of the normalized image in all wave bands.
Further, the automatic extraction method in the step 3 is as follows: according to PNI and DNI images, automatically extracting pixels meeting the following two conditions simultaneously as cloud pixels:
wherein MEAN (PNI) is the average value of PNI images, MAX (PNI) is the maximum value of PNI images, and k 1 、k 1 Is a threshold value.
The invention has the following beneficial effects:
compared with the prior art, the method aims at the optical remote sensing image with low radiation calibration precision, does not need to provide a cloud-free reference image or other auxiliary calibration parameters, adopts an accumulation frequency method to carry out automatic normalization processing, then calculates the normalized image and carries out characteristic value statistics, can finally realize the automatic identification and extraction of the optical remote sensing image cloud information with low radiation calibration precision, can rapidly and accurately extract the optical remote sensing image cloud information with low radiation calibration precision, greatly improves the efficiency, reduces the cost and provides a foundation for the further application of the remote sensing image
Drawings
Fig. 1 is a flowchart of a low-precision optical remote sensing image cloud identification method.
FIG. 2 is an example image diagram to be processed;
FIG. 3 is a partial view of an example image to be processed;
FIG. 4 is a normalized multi-band image plot;
FIG. 5 is a partial view of a normalized multi-band image;
FIG. 6 is a single band image view;
FIG. 7 is a partial view of a single band image;
FIG. 8 is a graph of a maximum difference image;
FIG. 9 is a partial view of a maximum difference image;
fig. 10 is a cloud information extraction result diagram;
fig. 11 is a partial view of the cloud information extraction result.
Detailed Description
Referring to fig. 1, the flow of the method of the present invention is mainly divided into three major parts:
the first part is to normalize the optical remote sensing image with low radiation calibration precision band by adopting an accumulated frequency calculation method, so that the data of each band has scale consistency.
The second part is based on normalized data, the product of all wave bands is calculated pixel by pixel to obtain a single-wave band image PNI, the maximum value and the average value of the PNI are counted, then the wave band maximum difference image DNI of the normalized image NI is calculated,
the third part is to set the threshold values of the PNI image and the DNI image, and perform threshold segmentation to realize automatic extraction of cloud information.
The following further illustrates the invention in terms of specific steps in connection with specific examples as follows:
in this embodiment, taking a high-resolution No. 1 multispectral optical satellite remote sensing image taken by 6 months and 30 days in 2020 as an example, the central coordinate point of the image is 108.7 degrees of east longitude and 30.8 degrees of north latitude. The high-score satellite No. 1 is launched into orbit in the period of 26 days of 4 months in 2013, and the design life of the satellite is 5-8 years. When the image is acquired, the high score No. 1 reaches the end of the design life, the performance attenuation of the sensor is serious, the image radiation calibration accuracy is low, and an example image is shown in fig. 2 and 3.
Step 1, optical remote sensing image normalization processing with low radiation calibration precision
The optical remote sensing image with low radiation calibration precision cannot be converted into accurate on-board reflectivity or earth surface reflectivity due to the fact that the accurate radiation calibration coefficient is not available, so that data consistency between different wave bands of the same image and different images is poor, and automatic cloud identification is difficult to perform. The invention marks the optical remote sensing image with low radiation calibration precision as X, firstly carries out wave band by wave band normalization processing to obtain a normalized multiband image NI, and the formula is as follows:
NI in i，j For normalizing the shadowThe value of pixel i in band j, X i，j DN value of original image pixel i in wave band j, t j Is the effective value threshold for band j,indicating that DN value in band j is smaller than current pixel X i，j Is used for the number of the pixels,indicating the total number of active pixels in band j.
The example images shown in fig. 2 and 3 are processed according to the normalization formula described in step 1 to obtain normalized multiband images, see fig. 4 and 5.
Step 2, normalized image processing
Step 2.1, calculating the product of all wave bands on the pixel-by-pixel basis of the multiband image normalized in step 1 to obtain a single-wave-band image PNI, wherein the formula is as follows
Wherein N is the total number of wave bands and NI i，j The value of the normalized image pixel i in the band j is obtained.
In this embodiment, the normalized multi-band image is processed according to the formula described in step 2.1, so as to obtain a single-band image, as shown in fig. 6 and 7.
Step 2.2, calculating the maximum difference value of all wave bands for each pixel of the multiband image normalized in step 1 to obtain a difference image DNI of a single wave band, wherein the formula is as follows
DNI i ＝MAX(NI i，* )-MIN(NI i，* )
MAX (NI) i，* ) To normalize the maximum value of image element i in all bands, MIN (NI i，* ) The minimum value of the pixel i of the normalized image in all wave bands.
In this embodiment, the normalized multiband image is processed according to the formula described in step 2.2, so as to obtain the image with the largest difference, as shown in fig. 8 and 9.
Step 3, cloud information extraction
According to the PNI and DNI images obtained in the step 2, automatically extracting pixels meeting the following two conditions simultaneously as cloud pixels:
wherein MEAN (PNI) is the average value of PNI images, MAX (PNI) is the maximum value of PNI images, and k 1 、k 1 Is a threshold value. General k 1 Can be set to 0.3, k 2 Set to 0.15.
In this embodiment, as shown in fig. 10 and 11, the extracted cloud information is white.
From the implementation process and the result diagram, the method has less manual participation, high automation degree and high accuracy of the extraction result, and achieves the purpose of rapidly and accurately extracting the optical remote sensing image cloud information with low radiation calibration precision.
The further embodiment of the invention also provides a low-radiation calibration precision optical remote sensing image cloud identification system for realizing the method, which comprises the following steps:
and the normalization processing module is used for carrying out normalization processing on the optical remote sensing image with low radiation calibration precision band by adopting an accumulated frequency calculation method to obtain a normalized multiband image NI.
And the single-band image PNI and band maximum difference image DNI calculation module is used for calculating products of all bands for normalized data pixel by pixel to obtain the single-band image PNI, counting the maximum value and the average value of the PNI, and calculating the band maximum difference image DNI of the normalized multiband image NI.
And the cloud information extraction module is used for setting a threshold value of the single-band image PNI and the band maximum difference image DNI and automatically extracting cloud information.
In a further embodiment, a computer storage medium is provided, on which a computer program is stored, which when executed by a processor implements the low-radiation calibration precision optical remote sensing image cloud identification method described above.
Finally, it should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention, and all such modifications and equivalents are intended to be encompassed in the scope of the claims of the present invention.

Claims (4)

1. The optical remote sensing image cloud identification method with low radiation calibration precision is characterized by comprising the following steps of:
step 1, adopting an accumulated frequency calculation method to normalize an optical remote sensing image with low radiation calibration precision band by band to obtain a normalized multiband image NI;
step 2, calculating the product of all wave bands pixel by pixel for the normalized data to obtain a single-band image PNI, counting the maximum value and the average value of the single-band image PNI, and calculating the wave band maximum difference image DNI of the normalized multi-band image NI;
step 3, setting a threshold value of a single-band image PNI and a band maximum difference image DNI, and automatically extracting cloud information;
the step 1 specifically comprises the steps of carrying out band-by-band normalization processing on an optical remote sensing image X with low radiation calibration precision to obtain a normalized multiband image NI, wherein the formula is as follows:
NI in i，j To normalize the value of image element i in band j, X i，j DN value of original image pixel i in wave band j, t j Is the effective value threshold for band j,indicating that DN value in band j is smaller than current pixel X i，j Image of (2)Number of elements (number of elements)>Representing the total number of effective pixels in the wave band j;
the step 2 comprises the following steps:
2.1, calculating the product of all wave bands on the normalized multiband image NI pixel by pixel to obtain a single-band image PNI, wherein the formula is as follows
Wherein N is the total number of wave bands and NI i，j The value of the normalized image pixel i in the band j is given;
2.2, calculating the maximum difference value of all wave bands from pixel to pixel of the normalized multiband image NI to obtain a band maximum difference image DNI of a single wave band, wherein the formula is as follows
DNI i ＝MAX(NI i，* )-MIN(NI i，* )
MAX (NI) i，* ) To normalize the maximum value of image element i in all bands, MIN (NI i，* ) The minimum value of the normalized image pixel i in all wave bands is set;
the automatic extraction method in the step 3 is as follows: according to the single-band image PNI and the band maximum difference image DNI, automatically extracting pixels meeting the following two conditions simultaneously to obtain cloud pixels:
wherein MEAN (PNI) is the average value of the PNI of the single-band images, MAX (PNI) is the maximum value of the PNI of the single-band images, and k 1 、k 2 Is a threshold value.
2. The method for cloud identification of low-radiation calibration precision optical remote sensing images according to claim 1, wherein k is 1 Can be set to 0.3, k 2 Set to 0.15.
3. The low-radiation calibration precision optical remote sensing image cloud identification system for realizing the method as claimed in claim 1 or 2, which is characterized by comprising the following steps:
the normalization processing module is used for carrying out normalization processing on the optical remote sensing images with low radiation calibration precision band by adopting an accumulated frequency calculation method to obtain normalized multiband images NI;
the single-band image PNI and band maximum difference image DNI calculation module is used for calculating products of all bands of normalized data pixel by pixel to obtain a single-band image PNI, counting the maximum value and the average value of the single-band image PNI, and calculating band maximum difference image DNI of the normalized multi-band image NI;
and the cloud information extraction module is used for setting a threshold value of the single-band image PNI and the band maximum difference image DNI and automatically extracting cloud information.
4. A computer storage medium having a computer program stored thereon, wherein the computer program when executed by a processor implements the low-radiometric calibration precision optical remote sensing image cloud identification method of any of claims 1-2.
CN202110332475.0A 2021-03-29 2021-03-29 Low-radiation calibration precision optical remote sensing image cloud identification method, system and computer storage medium Active CN113221634B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110332475.0A CN113221634B (en) 2021-03-29 2021-03-29 Low-radiation calibration precision optical remote sensing image cloud identification method, system and computer storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110332475.0A CN113221634B (en) 2021-03-29 2021-03-29 Low-radiation calibration precision optical remote sensing image cloud identification method, system and computer storage medium

Publications (2)

Publication Number Publication Date
CN113221634A CN113221634A (en) 2021-08-06
CN113221634B true CN113221634B (en) 2023-09-22

Family

ID=77084361

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110332475.0A Active CN113221634B (en) 2021-03-29 2021-03-29 Low-radiation calibration precision optical remote sensing image cloud identification method, system and computer storage medium

Country Status (1)

Country Link
CN (1) CN113221634B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105136732A (en) * 2015-08-24 2015-12-09 中国农业科学院农业环境与可持续发展研究所 Field crop dual band imaging NDVI measurement apparatus
CN108763782A (en) * 2018-05-31 2018-11-06 中南林业科技大学 The MODIS sensor multidate infra-red radiation normalizing methods differentiated applied to forest fires hot spot
CN109377476A (en) * 2018-09-20 2019-02-22 中国农业大学 The dynamic threshold acquisition methods and device of remote sensing image cloud detection characteristic parameter
WO2019184269A1 (en) * 2018-03-30 2019-10-03 长安大学 Landsat 8 snow-containing image-based cloud detection method

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105136732A (en) * 2015-08-24 2015-12-09 中国农业科学院农业环境与可持续发展研究所 Field crop dual band imaging NDVI measurement apparatus
WO2019184269A1 (en) * 2018-03-30 2019-10-03 长安大学 Landsat 8 snow-containing image-based cloud detection method
CN108763782A (en) * 2018-05-31 2018-11-06 中南林业科技大学 The MODIS sensor multidate infra-red radiation normalizing methods differentiated applied to forest fires hot spot
CN109377476A (en) * 2018-09-20 2019-02-22 中国农业大学 The dynamic threshold acquisition methods and device of remote sensing image cloud detection characteristic parameter

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
基于多时相光谱和物候特征的陕西省神木县地物遥感分类研究;唐欢;刘良云;贾建华;胡勇;;遥感信息(第02期);全文 *
空间分布频率分析法在太湖水华遥感监测中的应用;姜晟;李旭文;牛志春;金焰;茅晶晶;;中国环境监测(第01期);全文 *

Also Published As

Publication number Publication date
CN113221634A (en) 2021-08-06

Similar Documents

Publication Publication Date Title
CN108333148B (en) Method and device for identifying black and odorous water body
CN102565778B (en) Relative radiometric correction method for automatically extracting pseudo-invariant features for remote sensing image
CN109389049A (en) Crop Classification in Remote Sensing Image method based on multidate SAR data and multispectral data
CN101672646B (en) Satellite-image automatic, geometric and precise correction method
CN111832518B (en) Space-time fusion-based TSA remote sensing image land utilization method
CN108596103A (en) High resolution ratio satellite remote-sensing image building extracting method based on optimal spectrum Index selection
CN106780091A (en) Agricultural disaster information remote sensing extracting method based on vegetation index time space statistical nature
CN109523585B (en) Multisource remote sensing image feature matching method based on direction phase consistency
CN112285710B (en) Multi-source remote sensing reservoir water storage capacity estimation method and device
CN108986040B (en) NDVI shadow influence removing method based on remote sensing multispectral image
CN111553922A (en) Automatic cloud detection method for satellite remote sensing image
CN115578448B (en) Astronomical positioning method and system based on CCD observation data batch processing
Cui et al. Multiscale Intensity Propagation to Remove Multiplicative Stripe Noise From Remote Sensing Images.
CN113486975A (en) Ground object classification method, device, equipment and storage medium for remote sensing image
CN112419380B (en) Cloud mask-based high-precision registration method for stationary orbit satellite sequence images
CN113221634B (en) Low-radiation calibration precision optical remote sensing image cloud identification method, system and computer storage medium
CN116310883B (en) Agricultural disaster prediction method based on remote sensing image space-time fusion and related equipment
CN115631419B (en) Rice planting area and spatial distribution extraction method and device based on change detection
CN113706424B (en) Jelly effect image correction method and system based on artificial intelligence
CN111178186A (en) Rice extraction method, device and equipment based on sentinel remote sensing data
CN112017108B (en) Satellite image color relative correction method based on adjustment of independent model method
CN111127525B (en) Incremental farmland boundary precision calibration method and device with constraint point set registration
CN106097287B (en) A kind of multichannel image bearing calibration
CN116958833B (en) GF4 data geometric fine correction method
CN115205682B (en) NDVI maximum value remote sensing data product seamless production processing method

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