CN114565843A - Time series remote sensing image fusion method - Google Patents
Time series remote sensing image fusion method Download PDFInfo
- Publication number
- CN114565843A CN114565843A CN202210161274.3A CN202210161274A CN114565843A CN 114565843 A CN114565843 A CN 114565843A CN 202210161274 A CN202210161274 A CN 202210161274A CN 114565843 A CN114565843 A CN 114565843A
- Authority
- CN
- China
- Prior art keywords
- image
- resolution
- time
- multispectral
- reflectivity
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
Abstract
The invention belongs to the field of image processing, and particularly relates to a time series remote sensing image fusion method. The method comprises the steps of reconstructing a coarse resolution remote sensing image by using a time sequence model to obtain day-by-day coarse resolution time sequence data; carrying out panchromatic multispectral image fusion on the remote sensing image with the fine resolution to obtain a high-resolution multispectral image; and performing space-time fusion by using the existing high-resolution image and the reconstructed coarse-resolution image at the corresponding position to obtain the day-by-day high-resolution remote sensing image. The invention combines the space-time fusion technology, the panchromatic multispectral image fusion technology and the time sequence modeling interpolation technology, thereby realizing the reconstruction of a high time sequence and improving the spatial resolution of the image.
Description
Technical Field
The invention belongs to the field of image processing, and particularly relates to a time sequence remote sensing image fusion method.
Background
The current remote sensing data reconstruction method mainly comprises space-time fusion, an interpolation technology, image repairing, a super-resolution reconstruction technology and the like. Among them, the most widely used is the spatio-temporal fusion technique. The essence of the space-time fusion technology is that a radiation association mode established by low-space-high-time-resolution remote sensing images based on a plurality of acquired time phases is applied to high-space-low-time-resolution remote sensing images of corresponding time phases, and then the high-space-low-time-resolution remote sensing images under a target time phase are predicted by using the high-space-low-time-resolution images of the known time phases and the low-space-high-time-resolution data of the multiple time phases. The panchromatic multispectral image fusion method can effectively improve the spatial resolution of the reconstructed data, but the reconstruction of a high time sequence cannot be realized due to the self limitation of the sensor. The time sequence modeling interpolation technology is to fit missing data by using a model according to the similarity of time or space, and finally complete interpolation filling, but the improvement on the spatial resolution is not large. The invention combines the space-time fusion technology, the panchromatic multispectral image fusion technology and the time sequence modeling interpolation technology, thereby realizing the reconstruction of a high time sequence and improving the spatial resolution of the image.
Disclosure of Invention
The invention aims to solve the technical problem of providing a time series remote sensing image fusion method which can realize the reconstruction of a high-spatial-resolution remote sensing image day by day.
The technical scheme adopted by the invention is as follows:
a time series remote sensing image fusion method comprises the following steps:
step 1, reference time T is adjustedkFine resolution original multi-spectral shadowPerforming orthorectification, radiometric calibration and atmospheric calibration on the image, the fine-resolution original panchromatic image and the coarse-resolution original multispectral image at all known moments T (i, …, k, …, m), and respectively obtaining TkFine resolution multispectral reflectivity image M covering same area at timekAnd fine resolution panchromatic band reflectance image PkAnd a coarse resolution multispectral reflectance image L of the corresponding region at all known times T (i, …, k, …, m)i、…、Lk、…、Lm(ii) a Wherein the fine resolution multispectral reflectance image MkAnd all coarse resolution multispectral reflectance images Li、…、Lk、…、LmThe number of the wave bands is B;
step 2, making the panchromatic waveband reflectivity image P with fine resolutionkPerforming wavelet decomposition to obtain low-frequency information PLThen P is addedLMultispectral reflectance image M at fine resolutionkThe radiation value proportion of the multispectral wave band is injected into the multispectral reflectivity image M with fine resolutionkObtaining a high-resolution multispectral reflectivity image H consistent with the full-color image spatial resolution in each wave bandk;
Step 3, utilizing clustering algorithm to carry out high-resolution multispectral reflectivity image HkAll B wave bands are subjected to image classification processing to obtain a pixel reflectivity setIs TkHigh resolution image at time HkThe j, j belongs to [1, B ]]The S, S E [1, S ] on each band]The pixel reflectivity set of the ground object is obtained, and s is the total number of the ground object categories obtained after classification;
and 4, under the condition that the non-quaternary phase change does not occur in all the object types in the image within the time T (i, …, k, …, m), enabling a certain class S, S E [1, S ] in the multispectral reflectivity image with coarse resolution to belong to]At j, j ∈ [1, B ]]Time series T of mean values of earth surface reflectivity over a plurality of wave bandsi、…、Tk、…、TmThe change of the time is established by adopting the following robust weighted iterative least square methodSequence fitting model:
in the formula (I), the compound is shown in the specification,for the wave band j, j in the multispectral reflectivity image with coarse resolution belongs to [1, B ∈ ]]Above class s ground objects at TiThe mean value of the earth surface reflectivity at each moment;the deviation coefficient of the mean value of the earth surface reflectivity of the s class ground object on the wave band j in the coarse resolution ratio multispectral reflectivity image is obtained;andthe annual variation coefficients of the mean values of the earth surface reflectivities of the s-th class ground objects on the wave bands j in the coarse resolution multispectral reflectivity image are respectively;the annual variation coefficient of the mean value of the surface reflectivity of the s-th class ground object on the wave band j in the coarse resolution multispectral reflectivity image is obtained;is a time TiDays spent in a natural year;
step 5, respectively calculating and obtaining the surface reflectivity mean value of the s-th class ground object on the coarse resolution multispectral reflectivity image wave band j at the time T (i, …, k, …, m) by using the image classification processing result obtained in the step 3 and the known time sequence data And combining the values obtained by calculation at T (i, …, k, …, m)Fitting the values to obtain the value in formula (1) by using a robust weighted iterative least squares methodAnda coefficient value;
step 6, substituting all unknown time into the formula (1) by using the parameters obtained in the step 5 to obtain surface reflectance values corresponding to corresponding time and position, and completing the reconstruction of day-by-day coarse resolution data;
step 7, utilizing the high-resolution image H with known timekAnd corresponding spatio-temporal coarse resolution multi-spectral reflectance image LkAnd taking the day-by-day coarse resolution data reconstructed in the step 6 as low resolution data at the predicted time, and generating corresponding day-by-day high resolution data by using a single data time-space fusion method.
Further, in step 1, after performing orthorectification, radiometric calibration and atmospheric correction, resampling pixel size of all coarse-resolution multispectral reflectivity images to a fine-resolution panchromatic waveband reflectivity image P by using the sampling methodkSame, at the same time with TkTime-wise fine-resolution panchromatic waveband reflectivity image PkOn a fine resolution multi-spectral reflectance image MkAnd all coarse resolution multispectral reflectance images Li、…、Lk、…、LmSpatial registration is performed.
The invention has the following advantages:
(1) the invention combines the time-space fusion technology, the panchromatic multispectral image fusion technology and the time sequence modeling interpolation technology, thereby realizing the reconstruction of a high time sequence and improving the spatial resolution of the image;
(2) the time sequence reconstruction method, the image fusion method and the space-time fusion method provided by the invention are not limited to a time sequence harmonic analysis method, an AWLP method and a STRAFM method, and all methods capable of carrying out time sequence interpolation reconstruction, panchromatic multispectral fusion and space-time fusion can be realized according to the idea of the invention.
Drawings
FIG. 1 is an overall flow chart of the present invention;
FIG. 2 is a flow chart of panchromatic multispectral fusion;
FIG. 3 is a graph of the fusion result of the test data of score 2;
FIG. 4 is a graph of harmonic model fitting results;
FIG. 5 is a flow diagram of single data versus spatiotemporal fusion;
FIG. 6 is a data diagram of spatiotemporal fusion results.
Detailed Description
The technical solution of the present invention will be further described with reference to the accompanying drawings and the detailed description.
As shown in FIG. 1, the invention provides a time series remote sensing image fusion method, which can realize the reconstruction of a remote sensing image with high spatial resolution day by day. The basic idea of the invention is as follows: reconstructing the coarse resolution remote sensing image by using a time sequence model to obtain day-by-day coarse resolution time sequence data; carrying out panchromatic multispectral image fusion on the remote sensing image with the fine resolution to obtain a high-resolution multispectral image; and performing space-time fusion by using the existing high-resolution image and the reconstructed coarse-resolution image at the corresponding position to obtain the day-by-day high-resolution remote sensing image. The invention utilizes a time sequence harmonic model, an AWLP panchromatic sharpening method and a STRAFM space-time fusion method to realize the reconstruction of high-time and space-time resolution remote sensing images by generating day-by-day coarse resolution data. The method comprises the following steps:
step 1, data preprocessing: for reference time TkPerforming orthorectification, radiometric calibration and atmospheric calibration on the fine-resolution original multispectral image, the fine-resolution original panchromatic image and the coarse-resolution original multispectral image at all known moments T (i, …, k, …, m), and respectively obtaining T correspondinglykFine resolution multispectral reflectivity image M covering the same area at timekAnd fine resolutionPanchromatic waveband reflectivity image PkAnd a coarse resolution multispectral reflectance image L of the corresponding region at all known times T (i, …, k, …, m)i、…、Lk、…、Lm(ii) a After orthometric correction, radiometric calibration and atmospheric correction, resampling pixel size of all coarse-resolution multispectral reflectivity images to a fine-resolution panchromatic waveband reflectivity image P by using an upper sampling methodkSame, at the same time with TkTime-wise fine-resolution panchromatic waveband reflectivity image PkFor fine resolution multispectral reflectance image M as a referencekAnd all coarse resolution multispectral reflectance images Li、…、Lk、…、LmCarrying out spatial registration; wherein the fine resolution multispectral reflectance image MkAnd all coarse resolution multispectral reflectance images Li、…、Lk、…、LmThe number of the wave bands is B;
step 2, making the panchromatic waveband reflectivity image P with fine resolutionkPerforming wavelet decomposition to obtain low-frequency information PLThen P is addedLMultispectral reflectance image M at fine resolutionkThe spectral band of radiation values are proportionally injected into the fine resolution multispectral reflectivity image MkObtaining a high-resolution multispectral reflectivity image H consistent with the full-color image spatial resolution in each wave bandk(ii) a As shown in fig. 2;
step 3, utilizing clustering algorithm to carry out high-resolution multispectral reflectivity image HkAll B wave bands are subjected to image classification processing to obtain a pixel reflectivity setIs TkHigh resolution image H at timekThe j, j ∈ [1, B ]]The S, S E [1, S ] on each band]The pixel reflectivity of the ground object is collected, and S is the total number of the ground object categories obtained after classification;
and 4, under the condition that the object types in the image do not change in a non-quaternary phase within the time T (i, …, k, …, m), determining a certain type S in the coarse resolution multispectral reflectivity image, wherein the S belongs to [1, S ∈ [, S [ ]]At j, j ∈ [1, B ]]Ground on a wave bandMean value of surface reflectance over time series Ti、…、Tk、…、TmThe change of the time sequence fitting model is established by adopting the following steady weighted iterative least square method based on the band-by-band category reflectivity of the coarse resolution image:
in the formula (I), the compound is shown in the specification,for the wave band j, j E [1, B ] in the multispectral reflectivity image with coarse resolution]Above the s-th class of ground objects at TiThe mean value of the earth surface reflectivity at each moment;the deviation coefficient of the mean value of the earth surface reflectivity of the s class ground object on the wave band j in the coarse resolution ratio multispectral reflectivity image is obtained;andthe annual variation coefficients of the mean values of the earth surface reflectivities of the s-th class ground objects on the wave bands j in the coarse resolution multispectral reflectivity image are respectively;the annual variation coefficient of the mean value of the surface reflectivity of the s-th class ground object on the wave band j in the coarse resolution multispectral reflectivity image is obtained;is a time TiThe number of days spent in a natural year,
step 5, using the image classification processing result obtained in step 3 and the known time sequence data to respectively countCalculating to obtain the mean value of the surface reflectivity of the s-th class ground object on the wave band j of the coarse resolution multispectral reflectivity image at the time T (i, …, k, …, m) And combining the values obtained by calculation at T (i, …, k, …, m)Values obtained by fitting the values in the formula (1) by using a robust weighted iterative least squares methodAnda coefficient value;
step 6, substituting all unknown time into the formula (1) by using the parameters obtained in the step 5 to obtain surface reflectance values corresponding to corresponding time and position, and completing the reconstruction of day-by-day coarse resolution data; as shown in fig. 4.
Step 7, utilizing the high-resolution image H with known timekAnd corresponding spatio-temporal coarse resolution multi-spectral reflectance image LkAnd taking the day-by-day coarse resolution data reconstructed in the step 6 as low resolution data at the predicted time, and generating corresponding day-by-day high resolution data by using a single data time-space fusion method. As shown in fig. 5.
The effect of the present method can be further illustrated by the following tests:
1. test conditions.
The computer is configured with Intel core i7-3770CPU3.4Ghz and 64GB memory, and the operating system is Windows 764 professional edition.
2. Test methods.
The coarse resolution remote sensing image is a GF1 image with the resolution of 16 m, the fine resolution multispectral image is a GF2 image with the resolution of 4 m, and the fine resolution panchromatic image is a corresponding panchromatic image with the resolution of 1 m. And fitting and modeling the existing coarse resolution image by using a harmonic model to obtain day-by-day data. And fusing the panchromatic multispectral images of the remote sensing images with the fine resolution to obtain the multispectral images with the high resolution. And obtaining the corresponding high-time-sequence and high-resolution remote sensing image by utilizing a space-time fusion algorithm based on the rough-resolution remote sensing image at the predicted moment.
3. And (5) testing results.
The harmonic model fitting results are shown in fig. 4, the data fusion results are shown in fig. 3, and the spatio-temporal fusion results are shown in fig. 6.
Test results show that the method can obtain the corresponding high-time-sequence and high-resolution remote sensing image based on the coarse-resolution remote sensing image.
Claims (2)
1. A time series remote sensing image fusion method is characterized by comprising the following steps:
step 1, reference time T is adjustedkPerforming orthorectification, radiometric calibration and atmospheric calibration on the fine-resolution original multispectral image, the fine-resolution original panchromatic image and the coarse-resolution original multispectral image at all known moments T (i, …, k, …, m), and respectively obtaining T correspondinglykFine resolution multispectral reflectivity image M covering the same area at timekAnd fine resolution panchromatic band reflectance image PkAnd a coarse resolution multispectral reflectance image L of the corresponding region at all known times T (i, …, k, …, m)i、...、Lk、...、Lm(ii) a Wherein the fine resolution multispectral reflectance image MkAnd all coarse resolution multispectral reflectance images Li、...、Lk、...、LmThe number of the wave bands is B;
step 2, making the panchromatic waveband reflectivity image P with fine resolutionkPerforming wavelet decomposition to obtain low-frequency information PLThen P is addedLMultispectral reflectance image M at fine resolutionkThe radiation value proportion of the multispectral wave band is injected into the multispectral reflectivity image M with fine resolutionkEach wave band of (1) to obtain a high score consistent with the spatial resolution of the full-color imageResolution multispectral reflectivity image Hk;
Step 3, utilizing clustering algorithm to carry out high-resolution multispectral reflectivity image HkAll B wave bands are subjected to image classification processing to obtain a pixel reflectivity set Is TkHigh resolution image at time HkThe j, j ∈ [1, B ]]The S, S E [1, S ] on each band]The pixel reflectivity of the ground object is collected, and S is the total number of the ground object categories obtained after classification;
and 4, under the condition that the object types in the image do not change in a non-quaternary phase within the time T (i, …, k, …, m), determining a certain type S in the coarse resolution multispectral reflectivity image, wherein the S belongs to [1, S ∈ [, S [ ]]At j, j ∈ [1, B ]]Time series T of mean values of earth surface reflectivity over a plurality of wave bandsi、...、Tk、...、TmThe change of the time sequence fitting model is established by adopting the following steady weighted iterative least square method based on the band-by-band category reflectivity of the coarse resolution image:
in the formula (I), the compound is shown in the specification,for the wave band j, j in the multispectral reflectivity image with coarse resolution belongs to [1, B ∈ ]]Above class s ground objects at TiThe mean value of the earth surface reflectivity at each moment;the deviation coefficient of the mean value of the earth surface reflectivity of the s class ground object on the wave band j in the coarse resolution ratio multispectral reflectivity image is obtained;andthe annual variation coefficients of the mean values of the earth surface reflectivities of the s-th class ground objects on the wave bands j in the coarse resolution multispectral reflectivity image are respectively;the annual variation coefficient of the mean value of the surface reflectivity of the s-th class ground object on the wave band j in the coarse resolution multispectral reflectivity image is obtained;is a time TiDays spent in a natural year;
step 5, respectively calculating and obtaining the surface reflectivity mean value of the s-th class ground object on the coarse resolution multispectral reflectivity image wave band j at the time T (i, …, k, …, m) by using the image classification processing result obtained in the step 3 and the known time sequence data And combining the values obtained by calculation at T (i, …, k, …, m)Values obtained by fitting the values in the formula (1) by using a robust weighted iterative least squares methodAnda coefficient value;
step 6, substituting all unknown time into the formula (1) by using the parameters obtained in the step 5 to obtain surface reflectance values corresponding to corresponding time and position, and completing the reconstruction of day-by-day coarse resolution data;
step 7, utilizing the high-resolution image H with known timekAnd corresponding spatio-temporal coarse resolution multi-spectral reflectance image LkAnd taking the day-by-day coarse resolution data reconstructed in the step 6 as low resolution data at the predicted time, and generating corresponding day-by-day high resolution data by using a single data time-space fusion method.
2. The method for fusing time-series remote sensing images according to claim 1, wherein in step 1, after the ortho-correction, the radiometric calibration and the atmospheric correction are performed, all the coarse-resolution multispectral reflectivity images are resampled to the low-resolution panchromatic band reflectivity image P by the pixel size by using the up-sampling methodkSame, simultaneously with TkTime-wise fine-resolution panchromatic waveband reflectivity image PkFor fine resolution multispectral reflectance image M as a referencekAnd all coarse resolution multispectral reflectance images Li、...、Lk、...、LmSpatial registration is performed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210161274.3A CN114565843A (en) | 2022-02-22 | 2022-02-22 | Time series remote sensing image fusion method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210161274.3A CN114565843A (en) | 2022-02-22 | 2022-02-22 | Time series remote sensing image fusion method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114565843A true CN114565843A (en) | 2022-05-31 |
Family
ID=81714651
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210161274.3A Pending CN114565843A (en) | 2022-02-22 | 2022-02-22 | Time series remote sensing image fusion method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114565843A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115063332A (en) * | 2022-06-29 | 2022-09-16 | 河北科技师范学院 | Method for constructing high-spatial-resolution time sequence remote sensing data |
CN115901640A (en) * | 2022-10-19 | 2023-04-04 | 山东大学 | Unfavorable geology advanced prediction method and system integrating spectral imaging and space-time distribution |
CN116071644A (en) * | 2022-12-20 | 2023-05-05 | 中化现代农业有限公司 | Method, device, equipment and storage medium for inversion of sun leaf area index data |
CN116310883A (en) * | 2023-05-17 | 2023-06-23 | 山东建筑大学 | Agricultural disaster prediction method based on remote sensing image space-time fusion and related equipment |
CN117036889A (en) * | 2023-08-22 | 2023-11-10 | 黑龙江省网络空间研究中心(黑龙江省信息安全测评中心、黑龙江省国防科学技术研究院) | MLP-based remote sensing image fusion method |
CN117807154A (en) * | 2024-02-28 | 2024-04-02 | 成都菲宇科技有限公司 | Time sequence data visualization method, device and medium for display system |
-
2022
- 2022-02-22 CN CN202210161274.3A patent/CN114565843A/en active Pending
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115063332A (en) * | 2022-06-29 | 2022-09-16 | 河北科技师范学院 | Method for constructing high-spatial-resolution time sequence remote sensing data |
CN115063332B (en) * | 2022-06-29 | 2024-04-30 | 河北科技师范学院 | Method for constructing high-spatial-resolution time sequence remote sensing data |
CN115901640A (en) * | 2022-10-19 | 2023-04-04 | 山东大学 | Unfavorable geology advanced prediction method and system integrating spectral imaging and space-time distribution |
CN115901640B (en) * | 2022-10-19 | 2024-03-15 | 山东大学 | Poor geology advanced forecasting method and system integrating spectrum imaging and space-time distribution |
CN116071644A (en) * | 2022-12-20 | 2023-05-05 | 中化现代农业有限公司 | Method, device, equipment and storage medium for inversion of sun leaf area index data |
CN116071644B (en) * | 2022-12-20 | 2023-08-08 | 中化现代农业有限公司 | Method, device, equipment and storage medium for inversion of sun leaf area index data |
CN116310883A (en) * | 2023-05-17 | 2023-06-23 | 山东建筑大学 | Agricultural disaster prediction method based on remote sensing image space-time fusion and related equipment |
CN116310883B (en) * | 2023-05-17 | 2023-10-20 | 山东建筑大学 | Agricultural disaster prediction method based on remote sensing image space-time fusion and related equipment |
CN117036889A (en) * | 2023-08-22 | 2023-11-10 | 黑龙江省网络空间研究中心(黑龙江省信息安全测评中心、黑龙江省国防科学技术研究院) | MLP-based remote sensing image fusion method |
CN117807154A (en) * | 2024-02-28 | 2024-04-02 | 成都菲宇科技有限公司 | Time sequence data visualization method, device and medium for display system |
CN117807154B (en) * | 2024-02-28 | 2024-04-30 | 成都菲宇科技有限公司 | Time sequence data visualization method, device and medium for display system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114565843A (en) | Time series remote sensing image fusion method | |
Li et al. | Spatio-temporal fusion for remote sensing data: An overview and new benchmark | |
US8411903B2 (en) | Generating agricultural information products using remote sensing | |
CN112991288B (en) | Hyperspectral remote sensing image fusion method based on abundance image sharpening reconstruction | |
Herold et al. | The spectral dimension in urban land cover mapping from high-resolution optical remote sensing data | |
CN110032963B (en) | Dynamic monitoring method for spartina alterniflora new-born plaques | |
JP2007018387A (en) | Apparatus and method for preparing map of green covering ratio, and program | |
CN115511767B (en) | Self-supervised learning multi-modal image fusion method and application thereof | |
CN104794681A (en) | Remote sensing image fusion method based on multi-redundancy dictionary and sparse reconstruction | |
CN113327218A (en) | Hyperspectral and full-color image fusion method based on cascade network | |
AU2009260127B2 (en) | Compact representation of a reflectance spectrum | |
CN116309070A (en) | Super-resolution reconstruction method and device for hyperspectral remote sensing image and computer equipment | |
CN115510377B (en) | Soil erosion intensity estimation method and system and storage medium | |
CN115546636A (en) | Vegetation restoration monitoring method after geological disaster based on high-resolution remote sensing image | |
CN109671038A (en) | One kind is based on the classified and layered relative radiometric correction method of pseudo- invariant features point | |
CN115272144A (en) | Spatio-temporal spectrum fusion method for hyperspectral image and multispectral image | |
CN115565045A (en) | Hyperspectral and multispectral image fusion method based on multi-scale space-spectral transformation | |
CN109359264B (en) | Chlorophyll product downscaling method and device based on MODIS | |
Li et al. | Spatial-temporal super-resolution land cover mapping with a local spatial-temporal dependence model | |
Long et al. | Dual self-attention Swin transformer for hyperspectral image super-resolution | |
Meng et al. | Improving the spatial resolution of hyperspectral image using panchromatic and multispectral images: An integrated method | |
CN113744134A (en) | Hyperspectral image super-resolution method based on spectrum unmixing convolution neural network | |
Wang et al. | A comprehensive review of spatial-temporal-spectral information reconstruction techniques | |
CN111523451A (en) | Method for constructing high-space-time resolution NDVI data | |
CN111091113A (en) | Hyperspectral image data fusion 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 |