CN116167913A - Spectrum super-division method, device, equipment and storage medium based on spectrum library - Google Patents
Spectrum super-division method, device, equipment and storage medium based on spectrum library Download PDFInfo
- Publication number
- CN116167913A CN116167913A CN202211089779.XA CN202211089779A CN116167913A CN 116167913 A CN116167913 A CN 116167913A CN 202211089779 A CN202211089779 A CN 202211089779A CN 116167913 A CN116167913 A CN 116167913A
- Authority
- CN
- China
- Prior art keywords
- spectrum
- library
- target
- spectral
- additional
- 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
- 238000001228 spectrum Methods 0.000 title claims abstract description 395
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000003860 storage Methods 0.000 title claims abstract description 14
- 230000003595 spectral effect Effects 0.000 claims description 105
- 239000011159 matrix material Substances 0.000 claims description 58
- 238000002310 reflectometry Methods 0.000 claims description 35
- 238000005316 response function Methods 0.000 claims description 12
- 238000012216 screening Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 230000000694 effects Effects 0.000 abstract description 5
- 238000013507 mapping Methods 0.000 abstract description 2
- 239000000523 sample Substances 0.000 description 54
- 230000008569 process Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000011160 research Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 241000607479 Yersinia pestis Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000000701 chemical imaging Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000011065 in-situ storage Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4053—Scaling of whole images or parts thereof, e.g. expanding or contracting based on super-resolution, i.e. the output image resolution being higher than the sensor resolution
-
- 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
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/10—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention belongs to the technical field of mapping remote sensing, and discloses a spectrum hyperspectral method, a device, equipment and a storage medium based on a spectrum library. The method comprises the following steps: obtaining the land information of the target area; determining an additional spectrum sample according to the ground type information; establishing a private spectrum library according to a preset spectrum library and an additional spectrum sample; and performing spectrum super-division on the multispectral image corresponding to the target area acquired in real time according to the private spectrum library to obtain a target hyperspectral image corresponding to the target area. By the method, the additional spectrum sample is determined based on the ground information of the target area, so that the additional spectrum sample is combined with the preset spectrum library to form the private spectrum library aiming at the target area, and finally, the image superdivision is carried out on the multispectral image acquired in real time based on the private spectrum library, so that the spectrum superdivision can be realized without the low-spatial resolution hyperspectral image and the high-spatial resolution multispectral image of the same scene of the target area, the implementation difficulty of the spectrum superdivision is reduced, and the implementation effect is maintained.
Description
Technical Field
The invention relates to the technical field of mapping remote sensing, in particular to a spectrum hyperspectral method, a device, equipment and a storage medium based on a spectrum library.
Background
The hyperspectral imaging technology can divide the spectrum range from visible light to infrared band into hundreds to thousands of bands, so that the hyperspectral remote sensing image can provide richer spectrum information compared with the multispectral image, and is applied to the fields of precise agriculture, environmental monitoring, pest and disease monitoring and the like in a large number.
With the wide application of hyperspectral in various industries, the need for obtaining high spatial resolution and high spectral resolution image data to meet more refined applications is becoming more and more urgent. The method comprises the following steps of a fusion direction, a sparse expression direction and a deep learning direction. However, most of the data sources required by the existing spectral super-resolution method are low-spatial resolution hyperspectral image and high-spatial resolution multispectral image based on the same scene. In practical application, the image pair is difficult to obtain, and although researches have been proposed to finish the spectrum super-resolution of the image by only one multispectral image and a public hyperspectral library, the method still limits the large-scale application based on the premise that the public spectrum library contains all the types of the target area. In summary, to obtain a spectral hyperspectral image of a region, a hyperspectral image and a multispectral image of the region at the same time are required, and the existing in-orbit mainstream multispectral satellites are diversified in load design and orbit design, and the space-borne hyperspectral sensors are relatively few, so that the images are difficult to obtain, and become a major obstacle to large-scale application of the spectral hyperspectral technology.
The foregoing is provided merely for the purpose of facilitating understanding of the technical solutions of the present invention and is not intended to represent an admission that the foregoing is prior art.
Disclosure of Invention
The invention mainly aims to provide a spectrum hyper-resolution method, a device, equipment and a storage medium based on a spectrum library, which aim to solve the technical problem that the implementation condition is difficult to realize because a data source required by the image hyper-resolution in the prior art is difficult to acquire.
In order to achieve the above object, the present invention provides a spectrum hyper-splitting method based on a spectrum library, the method comprising the steps of:
obtaining the land information of the target area;
determining an additional spectrum sample according to the ground type information;
establishing a private spectrum library according to a preset spectrum library and the additional spectrum sample;
and performing spectrum hyperspectral super-division on the multispectral image corresponding to the target area acquired in real time according to the private spectrum library to obtain a target hyperspectral image corresponding to the target area.
Optionally, the establishing a private spectrum library according to a preset spectrum library and the additional spectrum sample includes:
acquiring preset wavelength information of a preset spectrum library;
matching the preset wavelength information with the additional wavelength information of the additional spectrum sample to obtain target reflectivity data;
and adding the target reflectivity data into the preset spectrum library to form a private spectrum library.
Optionally, the matching the preset wavelength information with the additional wavelength information of the additional spectrum sample to obtain target reflectivity data includes:
determining preset wavelengths and preset wavelength ranges of the preset spectrum library according to the preset wavelength information;
acquiring additional wavelength information corresponding to the additional spectrum sample;
determining an additional wavelength and an additional wavelength range according to the additional wavelength information;
determining a target matching wavelength according to the preset wavelength and the additional wavelength;
determining a target matching range according to the preset wavelength range and the additional wavelength range;
extracting matching reflectivity data conforming to the target matching wavelength and the target matching range from the additional spectrum sample;
and carrying out data screening on the matched reflectivity data to obtain target reflectivity data.
Optionally, the performing spectral super-division on the multispectral image corresponding to the target area acquired in real time according to the private spectrum library includes:
acquiring multispectral images acquired in real time;
extracting observation image information of the multispectral image and spectrum library information of a private spectrum library;
determining a spectrum reconstruction expression of the multispectral image and the target hyperspectral image according to the observed image information and the spectrum library information;
and performing spectrum super-division according to the spectrum library information and the spectrum reconstruction expression to obtain a target spectrum image.
Optionally, a target spectrum dictionary and a target sparse coefficient matrix corresponding to the target hyperspectral image are obtained;
obtaining a hyperspectral image linear expression according to the target spectrum dictionary and the target sparse coefficient matrix;
determining a library spectrum dictionary and a library sparse coefficient matrix according to the spectrum library information;
determining a spectrum library linear relation according to the library spectrum dictionary and the library sparse coefficient matrix;
and obtaining a target hyperspectral image according to the hyperspectral image linear expression, the spectral library linear relation and the spectral reconstruction expression.
Optionally, the obtaining the target hyperspectral image according to the hyperspectral image linear expression, the spectral library linear relation and the spectrum reconstruction expression includes:
performing band matching on the private spectrum library through a band matching matrix to obtain a matched spectrum library;
extracting a matching library spectrum dictionary of the matched spectrum library;
determining a first affiliation of the private spectrum library and the target hyperspectral image;
determining a second dependence relationship of the matched spectrum library and the target hyperspectral image according to the first dependence relationship;
determining an equivalent sparse coefficient matrix according to the matching library spectrum dictionary, the second subordination relation, the spatial transformation matrix, the reconstructed image linear expression and the spectrum library linear relation;
and obtaining a target hyperspectral image according to the equivalent sparse coefficient matrix and the spectrum reconstruction expression.
Optionally, the obtaining the target hyperspectral image according to the equivalent sparse coefficient matrix and the spectrum reconstruction expression includes:
acquiring a spectral response function and zero-mean Gaussian noise;
determining a reconstructed superdivision model of the target hyperspectral image according to the spectral response function, the zero-mean Gaussian noise and the spectral reconstruction expression;
and solving the reconstructed super-division model according to the equivalent sparse coefficient matrix to obtain a target hyperspectral image.
In addition, in order to achieve the above object, the present invention further provides a spectrum hyper-splitting device based on a spectrum library, where the spectrum hyper-splitting device based on the spectrum library includes:
the ground type acquisition module is used for acquiring the ground type information of the target area;
the sample determining module is used for determining an additional spectrum sample according to the ground type information;
the spectrum library establishing module is used for establishing a private spectrum library according to a preset spectrum library and the additional spectrum sample;
and the spectrum hyper-splitting module is used for performing spectrum hyper-splitting on the multispectral image corresponding to the target area acquired in real time according to the private spectrum library to obtain a target hyperspectral image corresponding to the target area.
In addition, in order to achieve the above object, the present invention also provides a spectrum hyper-splitting apparatus based on a spectrum library, the spectrum hyper-splitting apparatus based on a spectrum library includes: a memory, a processor, and a spectral library-based spectral superdistribution program stored on the memory and executable on the processor, the spectral library-based spectral superdistribution program configured to implement the steps of the spectral library-based spectral superdistribution method as described above.
In addition, in order to achieve the above object, the present invention also proposes a storage medium having stored thereon a spectrum hyper-splitting program based on a spectrum library, which when executed by a processor, implements the steps of the spectrum hyper-splitting method based on a spectrum library as described above.
The method acquires the land information of the target area; determining an additional spectrum sample according to the ground type information; establishing a private spectrum library according to a preset spectrum library and the additional spectrum sample; and performing spectrum hyperspectral super-division on the multispectral image corresponding to the target area acquired in real time according to the private spectrum library to obtain a target hyperspectral image corresponding to the target area. According to the method, the additional spectrum sample is determined based on the ground information of the target area for research, so that the additional spectrum sample is combined with the preset spectrum library to form the private spectrum library aiming at the target area, and finally, the image superdivision is carried out on the multispectral image acquired in real time based on the private spectrum library, so that the spectrum superdivision can be realized without the low-spatial-resolution hyperspectral image and the high-spatial-resolution multispectral image of the same scene of the target area, the implementation difficulty of the spectrum superdivision is reduced, and the implementation effect of the spectrum superdivision is maintained.
Drawings
FIG. 1 is a schematic diagram of a spectral library-based spectral superdivision device of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a flow chart of a first embodiment of a spectral library-based spectral superdivision method according to the present invention;
FIG. 3 is a schematic diagram of a private spectrum library establishment process in an embodiment of a spectrum hyper-resolution method based on a spectrum library according to the invention;
FIG. 4 is a flow chart of a second embodiment of a spectral library-based spectral superdivision method according to the present invention;
fig. 5 is a block diagram of a first embodiment of a spectral library-based spectral super-division device of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a spectral library-based spectrum superdivision device in a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the spectral library-based spectral superdivision apparatus may include: a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (Wi-Fi) interface). The Memory 1005 may be a high-speed random access Memory (Random Access Memory, RAM) Memory or a stable nonvolatile Memory (NVM), such as a disk Memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
Those skilled in the art will appreciate that the structure shown in fig. 1 does not constitute a limitation of a spectral library-based spectral superdistribution apparatus, and may include more or fewer components than shown, or may combine certain components, or may be arranged in different components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and a spectrum hyper-splitting program based on a spectrum library may be included in the memory 1005 as one storage medium.
In the spectral library-based spectral superdivision apparatus shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the spectrum hyper-splitting device based on the spectrum library can be arranged in the spectrum hyper-splitting device based on the spectrum library, and the spectrum hyper-splitting device based on the spectrum library calls the spectrum hyper-splitting program based on the spectrum library stored in the memory 1005 through the processor 1001 and executes the spectrum hyper-splitting method based on the spectrum library provided by the embodiment of the invention.
The embodiment of the invention provides a spectrum hyper-splitting method based on a spectrum library, and referring to fig. 2, fig. 2 is a flow chart of a first embodiment of the spectrum hyper-splitting method based on the spectrum library.
In this embodiment, the spectrum hyper-splitting method based on the spectrum library includes the following steps:
step S10: and obtaining the ground type information of the target area.
It should be noted that, the execution body of the embodiment is a server, which may be an entity server or a cloud server, and is mainly a server for implementing a spectrum hyper-splitting method based on a spectrum library, or other devices capable of implementing the function, which is not limited in this embodiment.
It should be understood that, at present, the spectrum hyperspectral method for the remote sensing image needs to acquire the image pairs of the low-spatial resolution hyperspectral image and the high-spatial resolution multispectral image of the same scene in real time, then the deep learning is performed based on the image pairs to finish the spectrum hyperspectral, but the acquisition condition of the image pairs is very harsh, so that the implementation difficulty of the spectrum hyperspectral is very high, while the scheme of the embodiment determines the additional spectrum sample based on the ground information of the target area, so as to combine with the preset spectrum library, thereby forming the private spectrum library for the target area, and finally the image hyperspectral image and the high-spatial resolution multispectral image of the same scene without the target area are realized, so that the implementation difficulty of the spectrum hyperspectral is reduced and the implementation effect of the spectrum hyperspectral is maintained.
In a specific implementation, the target area refers to an area, which is defined by a user and needs to be subjected to spectrum super-division, and may be any contour, any area and any position, which is not limited in this embodiment.
The land information refers to land related information of the target area, and the land may be agricultural land, construction land, unused land, or the like, so the land information of the target area refers to land related information corresponding to each position of the target area.
Step S20: and determining an additional spectrum sample according to the ground type information.
It should be understood that determining additional spectral samples from the ground-class information refers to: after the ground type information of the target area is determined, spectrum sampling is carried out, the acquired spectrum is selected as far as possible, and the acquisition work is carried out in a period of 10:30 to 13:30. During collection, the probe dip angle is 90 degrees, and the distance from the probe dip angle to the sample height is about 1 m; the placement of the reference plate is perpendicular to the measurement direction of the scanning probe, and auxiliary parameters such as the property of an observation target (the name, health degree, coverage degree and surrounding vegetation of plants), the type weather condition of an instrument, the measurement time, the observation and recording personnel, the spectrum naming and recording number, the geographic coordinates, the elevation, the field photo number and the like are recorded in detail in the measurement process; the collecting part is vegetation canopy, and 5 typical 2m x 2m sample formulas are selected for each vegetation. The spectrum data finally acquired is the spectrum reflectivity. And then extracting data needing to be added into the private spectrum library based on the ground type information and the acquired spectrum data, and taking the data as an additional spectrum sample. The additional spectrum sample is a ground object spectrum sample obtained by taking the ground class T of the target area as the interested class.
Step S30: and establishing a private spectrum library according to a preset spectrum library and the additional spectrum sample.
In a specific implementation, after determining the additional spectrum sample, the additional spectrum sample is first wavelength matched with a preset spectrum library, so as to be combined into a private spectrum library.
It should be noted that the preset spectrum library is a USGS spectrum library, and belongs to an open-source public spectrum library.
It should be appreciated that the private spectrum library is created based on the USGG spectrum library plus the extended class, i.e., the additional spectrum sample of the target area, as shown in fig. 3, which illustrates the private spectrum library creation process.
Further, in order to accurately perform expansion of the spectrum library to obtain the private spectrum library, step S30 includes: acquiring preset wavelength information of a preset spectrum library; matching the preset wavelength information with the additional wavelength information of the additional spectrum sample to obtain target reflectivity data; and adding the target reflectivity data into the preset spectrum library to form a private spectrum library.
It should be understood that the preset wavelength information refers to related information such as a wavelength, a range, and the like corresponding to the preset spectrum library.
In a specific implementation, matching the preset wavelength information with the additional wavelength information of the additional spectrum sample to obtain the target reflectivity data refers to: and matching and extracting the additional wavelength information corresponding to the additional spectrum sample from the preset wavelength information, so as to extract corresponding data matched with the wavelength of the preset spectrum library in the additional spectrum sample as target reflectivity data.
It should be noted that, after the target reflectivity data is obtained, the target reflectivity data is added to the preset spectrum library, so that the data of the preset spectrum library is expanded to become a private spectrum library.
In this way, when the method is used for field sampling, a ground type often collects a plurality of points, and the data of each point can be influenced by illumination conditions, weather conditions and the like, so that a proper sample is required to be screened from the additional spectrum samples and preprocessed to be added into a spectrum library as reflectivity data of the ground type, and a private spectrum library is formed.
Further, in order to complete wavelength matching, the step of matching the preset wavelength information with the additional wavelength information of the additional spectrum sample to obtain target reflectivity data includes: determining preset wavelengths and preset wavelength ranges of the preset spectrum library according to the preset wavelength information; acquiring additional wavelength information corresponding to the additional spectrum sample; determining an additional wavelength and an additional wavelength range according to the additional wavelength information; determining a target matching wavelength according to the preset wavelength and the additional wavelength; determining a target matching range according to the preset wavelength range and the additional wavelength range; extracting matching reflectivity data conforming to the target matching wavelength and the target matching range from the additional spectrum sample; and carrying out data screening on the matched reflectivity data to obtain target reflectivity data.
It should be understood that determining the preset wavelength and the preset wavelength range of the preset spectrum library according to the preset wavelength information refers to: and determining the relevant information of the data corresponding to the wavelength corresponding to the preset spectrum library and the value range of the wavelength range as the preset wavelength and the preset wavelength range respectively according to the preset wavelength information.
In a specific implementation, the additional wavelength information refers to wavelength related information corresponding to the additional spectral sample. The additional wavelength and the additional wavelength range refer to data corresponding to each wavelength of the additional spectrum sample and a range of wavelength values.
The target matching wavelength is determined according to the preset wavelength and the additional wavelength; and determining that the target matching range corresponds to the wavelength range and the wavelength related information of the matching of the additional spectrum sample and the preset spectrum library and the existence of the overlapping part according to the preset wavelength range and the additional wavelength range.
It should be appreciated that extracting matching reflectivity data from the additional spectral sample that corresponds to the target matching wavelength and the target matching range refers to: after the target matching range and the target matching wavelength are determined, all reflectivity data conforming to the target matching range and the target matching wavelength are taken as matching reflectivity data in the additional spectral sample.
In specific implementation, after the matched reflectivity data is obtained, data screening is performed, and the data of the same place is screened and kept, so that the non-repeated reflectivity data is finally obtained and is the target reflectivity data.
By the method, the operations of data matching and data screening are accurately completed, so that the private spectrum library is built more accurately and redundant data does not exist.
Step S40: and performing spectrum hyperspectral super-division on the multispectral image corresponding to the target area acquired in real time according to the private spectrum library to obtain a target hyperspectral image corresponding to the target area.
After the private spectrum library is established, performing spectrum super-division on the multispectral image of the target area acquired in real time according to the private spectrum library, and finally obtaining a target hyperspectral image corresponding to the target area.
The embodiment obtains the ground type information of the target area; determining an additional spectrum sample according to the ground type information; establishing a private spectrum library according to a preset spectrum library and the additional spectrum sample; and performing spectrum hyperspectral super-division on the multispectral image corresponding to the target area acquired in real time according to the private spectrum library to obtain a target hyperspectral image corresponding to the target area. According to the method, the additional spectrum sample is determined based on the ground information of the target area for research, so that the additional spectrum sample is combined with the preset spectrum library to form the private spectrum library aiming at the target area, and finally, the image superdivision is carried out on the multispectral image acquired in real time based on the private spectrum library, so that the spectrum superdivision can be realized without the low-spatial-resolution hyperspectral image and the high-spatial-resolution multispectral image of the same scene of the target area, the implementation difficulty of the spectrum superdivision is reduced, and the implementation effect of the spectrum superdivision is maintained.
Referring to fig. 4, fig. 4 is a flow chart of a second embodiment of a spectrum hyper-splitting method based on a spectrum library according to the present invention.
Based on the first embodiment, the spectrum hyper-splitting method based on the spectrum library in this embodiment includes, at step S40:
step S401: and acquiring multispectral images acquired in real time.
The multispectral image acquired in real time is a remote sensing image acquired through a remote sensing technology, and specifically, the multispectral image is a remote sensing image corresponding to a target area.
Step S402: and extracting the observed image information of the multispectral image and the spectrum library information of the private spectrum library.
It should be understood that the observed image information refers to related information corresponding to the multispectral image, and may include related information such as wavelengths of the multispectral image. The spectrum library information comprises related information of a library spectrum dictionary and a library sparse coefficient matrix corresponding to the private spectrum library.
Step S403: and determining a spectrum reconstruction expression of the multispectral image and the target hyperspectral image according to the observed image information and the spectrum library information.
In a specific implementation, the spectrum reconstruction expression refers to an expression for performing spectrum reconstruction on a multispectral image, specifically:
X＝SH+N X
wherein X is a multispectral image, H is a target hyperspectral image, S is a spectral response function, and Nx is zero-mean Gaussian noise.
Step S404: and performing spectrum super-division according to the spectrum library information and the spectrum reconstruction expression to obtain a target spectrum image.
After determining the spectrum reconstruction expression, processing and solving equations by combining the library spectrum dictionary determined by the spectrum library information and the library sparse coefficient matrix to obtain the target hyperspectral image.
Further, to determine the current expression of the hyperspectral image and the linear relation of the spectral library for solving the reconstructed hyperspectral model, step S404 includes: acquiring a target spectrum dictionary and a target sparse coefficient matrix corresponding to the target spectrum image; obtaining a hyperspectral image linear expression according to the target spectrum dictionary and the target sparse coefficient matrix; determining a library spectrum dictionary and a library sparse coefficient matrix according to the spectrum library information; determining a spectrum library linear relation according to the library spectrum dictionary and the library sparse coefficient matrix; and obtaining a target hyperspectral image according to the hyperspectral image linear expression, the spectral library linear relation and the spectral reconstruction expression.
It should be understood that the target spectral dictionary and the target sparse coefficient matrix are the spectral dictionary and the sparse coefficient matrix corresponding to the target spectral image, respectively.
In a specific implementation, the hyperspectral image linear expression is:
H＝D H A H
wherein H is the target hyperspectral image,
for the target spectrum dictionary A H ∈R K×N And the sparse coefficient matrix is a target sparse coefficient matrix. Specifically lambda H The number of spectral bands of the target hyperspectral image is N, the number of pixels in each band of the target hyperspectral image is N, and K is the number of columns of the target spectral dictionary.
In a specific implementation, the spectral library linear relationship is:
L＝D L A L
it should be noted that, L is a private spectrum library,
for library spectra dictionary, A L ∈R K×M Is a library sparse coefficient matrix. Specifically lambda L The number of spectral bands of the target hyperspectral image is M, the number of pixels in each band of the target hyperspectral image is M, and K is the number of library spectral dictionary columns.
It should be understood that obtaining the target hyperspectral image from the hyperspectral image linear expression, the spectral library linear relation, and the spectral reconstruction expression refers to: and after obtaining the linear expression of the hyperspectral image, performing band matching to obtain the linear expression of the reconstructed image, thereby obtaining the target hyperspectral image by combining the linear relation of the spectrum library.
By the method, the operation of spectrum superdivision based on the combination of the hyperspectral image linear expression and the spectrum library linear relation expression and the spectrum reconstruction expression is realized, and the result of spectrum superdivision is more accurate.
Further, in order to obtain an equivalent sparse coefficient matrix, the step of obtaining the target hyperspectral image according to the hyperspectral image linear expression, the spectral library linear relation and the spectral reconstruction expression includes: performing band matching on the private spectrum library through a band matching matrix to obtain a matched spectrum library; extracting a matching library spectrum dictionary of the matched spectrum library; determining a first affiliation of the private spectrum library and the target hyperspectral image; determining a second dependence relationship of the matched spectrum library and the target hyperspectral image according to the first dependence relationship; determining an equivalent sparse coefficient matrix according to the matching library spectrum dictionary, the second subordination relation, the spatial transformation matrix, the reconstructed image linear expression and the spectrum library linear relation; and obtaining a target hyperspectral image according to the equivalent sparse coefficient matrix and the spectrum reconstruction expression.
In a specific implementation, the private spectrum library is subjected to band matching through a band matching matrix, so that the band matching matrix is in the matched spectrum library
And then carrying out band matching on the private spectrum library L through P to obtain a matched spectrum library PL.
It should be noted that, in space, the private spectrum library L covers all the types of features in H, and the relationship between H and L can be regarded as a subordinate relationship, due to D H And D L Can represent H and PL respectively, so that the dependency also exists in D H And D L Is a kind of medium. So the first subordinate relation is the subordinate relation of H and L at the moment, and then the first subordinate relation is generalized to D H And D L The corresponding second subordinate relation is the first subordinate relation. Spectrum dictionary D H And D L Each atom in (a) can be regarded as having no physical meaning, a broader spectral feature, i.e. they are no longer pure spectral end members
It should be understood that determining an equivalent sparse coefficient matrix from the matching library spectral dictionary, the second membership, the spatial transformation matrix, and the reconstructed image linear expression and the spectral library linear relation refers to: introducing a spatial transformation matrix Q epsilon R K×K The equivalent sparse coefficient matrix may then be written as:
A q ＝QA H
wherein A is q Is an equivalent sparse coefficient matrix.
In a specific implementation, after an equivalent sparse coefficient matrix exists, the hyperspectral image linear expression can be expressed as:
H＝PD L QA H ＝D p A q
wherein D is H ＝PD L Q，D p ＝PD L And (5) a matched spectrum dictionary.
In this way, the common spectrum library is mapped into the specific spectrum library corresponding to the target hyperspectral image wave band through the spectrum dictionary, so that the equivalent sparse coefficient matrix is obtained, and the equivalent sparse coefficient matrix can be substituted into the spectrum reconstruction expression to calculate and obtain the target spectrum image.
Further, in order to obtain a target hyperspectral image, the step of obtaining the target hyperspectral image according to the equivalent sparse coefficient matrix and the spectral reconstruction expression includes: acquiring a spectral response function and zero-mean Gaussian noise; determining a reconstructed superdivision model of the target hyperspectral image according to the spectral response function, the zero-mean Gaussian noise and the spectral reconstruction expression; and solving the reconstructed super-division model according to the equivalent sparse coefficient matrix to obtain a target hyperspectral image.
It should be noted that, determining the reconstructed hyperspectral model of the target hyperspectral image according to the spectral response function, the zero-mean gaussian noise and the spectral reconstruction expression refers to: substituting the spectral response function and zero-mean Gaussian noise into a spectral reconstruction expression to obtain a reconstruction superdivision model.
Specifically, the reconstructed hyperspectral model is:
X＝SH+N X
wherein, the liquid crystal display device comprises a liquid crystal display device,
as a spectral response function, N X Is zero mean Gaussian noise in the model, +.>
For target hyperspectral image, < >>
Is multispectral image, N and M (N is common in general application scene>>M represents the number of pixels in each of the H and L bands, lambda H 、λ X And lambda (lambda) L (λ L ≥λ H >>λ X ) The numbers of spectral bands H, X and L, respectively.
It should be understood that the multispectral image X may be represented as spectral degradation of H, and the estimation of H in the reconstructed hyperspectral model is a pathological inverse problem, which can be solved by introducing sparse expression, that is, substituting an equivalent sparse coefficient matrix into the reconstructed hyperspectral model can be solved to obtain the target hyperspectral image.
The embodiment acquires the multispectral image acquired in real time; extracting observation image information of the multispectral image and spectrum library information of a private spectrum library; determining a spectrum reconstruction expression of the multispectral image and the target hyperspectral image according to the observed image information and the spectrum library information; and performing spectrum super-division according to the spectrum library information and the spectrum reconstruction expression to obtain a target spectrum image. By the method, accurate and efficient spectrum superdivision of spectrum library information based on the private spectrum library is realized, so that the spectrum superdivision of multispectral images can be completed by utilizing the existing public hyperspectral library and partial interested samples, and compared with other spectrum superdivision research directions, the method has lower requirements on image sources. The hyperspectral and multispectral image pairs in the same region and the same period are not required to be acquired, and only multispectral images and in-situ sampling samples are required.
In addition, the embodiment of the invention also provides a storage medium, wherein the storage medium is stored with a spectrum hyper-splitting program based on a spectrum library, and the spectrum hyper-splitting program based on the spectrum library realizes the steps of the spectrum hyper-splitting method based on the spectrum library when being executed by a processor.
The storage medium adopts all the technical solutions of all the embodiments, so that the storage medium has at least all the beneficial effects brought by the technical solutions of the embodiments, and is not described in detail herein.
Referring to fig. 5, fig. 5 is a block diagram illustrating a first embodiment of a spectral super-division apparatus based on a spectral library according to the present invention.
As shown in fig. 5, a spectral library-based spectrum hyperspectral device according to an embodiment of the present invention includes:
the ground type acquisition module 10 is configured to acquire ground type information of a target area.
A sample determination module 20 for determining additional spectral samples from the ground class information.
The spectrum library establishing module 30 is configured to establish a private spectrum library according to a preset spectrum library and the additional spectrum sample.
And the spectrum hyper-splitting module 40 is used for performing spectrum hyper-splitting on the multispectral image corresponding to the target area acquired in real time according to the private spectrum library to obtain a target hyperspectral image corresponding to the target area.
The embodiment obtains the ground type information of the target area; determining an additional spectrum sample according to the ground type information; establishing a private spectrum library according to a preset spectrum library and the additional spectrum sample; and performing spectrum hyperspectral super-division on the multispectral image corresponding to the target area acquired in real time according to the private spectrum library to obtain a target hyperspectral image corresponding to the target area. According to the method, the additional spectrum sample is determined based on the ground information of the target area for research, so that the additional spectrum sample is combined with the preset spectrum library to form the private spectrum library aiming at the target area, and finally, the image superdivision is carried out on the multispectral image acquired in real time based on the private spectrum library, so that the spectrum superdivision can be realized without the low-spatial-resolution hyperspectral image and the high-spatial-resolution multispectral image of the same scene of the target area, the implementation difficulty of the spectrum superdivision is reduced, and the implementation effect of the spectrum superdivision is maintained.
In an embodiment, the spectrum library creating module 30 is further configured to obtain preset wavelength information of a preset spectrum library; matching the preset wavelength information with the additional wavelength information of the additional spectrum sample to obtain target reflectivity data; and adding the target reflectivity data into the preset spectrum library to form a private spectrum library.
In an embodiment, the spectrum library creating module 30 is further configured to determine a preset wavelength and a preset wavelength range of the preset spectrum library according to the preset wavelength information; acquiring additional wavelength information corresponding to the additional spectrum sample; determining an additional wavelength and an additional wavelength range according to the additional wavelength information; determining a target matching wavelength according to the preset wavelength and the additional wavelength; determining a target matching range according to the preset wavelength range and the additional wavelength range; extracting matching reflectivity data conforming to the target matching wavelength and the target matching range from the additional spectrum sample; and carrying out data screening on the matched reflectivity data to obtain target reflectivity data.
In one embodiment, the spectrum hyper-splitting module 40 is further configured to acquire a multispectral image acquired in real time; extracting observation image information of the multispectral image and spectrum library information of a private spectrum library; determining a spectrum reconstruction expression of the multispectral image and the target hyperspectral image according to the observed image information and the spectrum library information; and performing spectrum super-division according to the spectrum library information and the spectrum reconstruction expression to obtain a target spectrum image.
In an embodiment, the spectrum hyper-splitting module 40 is further configured to acquire a target spectrum dictionary and a target sparse coefficient matrix corresponding to the target hyperspectral image; obtaining a hyperspectral image linear expression according to the target spectrum dictionary and the target sparse coefficient matrix; determining a library spectrum dictionary and a library sparse coefficient matrix according to the spectrum library information; determining a spectrum library linear relation according to the library spectrum dictionary and the library sparse coefficient matrix; and obtaining a target hyperspectral image according to the hyperspectral image linear expression, the spectral library linear relation and the spectral reconstruction expression.
In an embodiment, the spectrum hyper-splitting module 40 is further configured to perform band matching on the private spectrum library through a band matching matrix to obtain a matched spectrum library; extracting a matching library spectrum dictionary of the matched spectrum library; determining a first affiliation of the private spectrum library and the target hyperspectral image; determining a second dependence relationship of the matched spectrum library and the target hyperspectral image according to the first dependence relationship; determining an equivalent sparse coefficient matrix according to the matching library spectrum dictionary, the second subordination relation, the spatial transformation matrix, the reconstructed image linear expression and the spectrum library linear relation; and obtaining a target hyperspectral image according to the equivalent sparse coefficient matrix and the spectrum reconstruction expression.
In one embodiment, the spectrum hyper-dividing module 40 is further configured to obtain a spectrum response function and zero-mean gaussian noise; determining a reconstructed superdivision model of the target hyperspectral image according to the spectral response function, the zero-mean Gaussian noise and the spectral reconstruction expression; and solving the reconstructed super-division model according to the equivalent sparse coefficient matrix to obtain a target hyperspectral image.
It should be understood that the foregoing is illustrative only and is not limiting, and that in specific applications, those skilled in the art may set the invention as desired, and the invention is not limited thereto.
It should be noted that the above-described working procedure is merely illustrative, and does not limit the scope of the present invention, and in practical application, a person skilled in the art may select part or all of them according to actual needs to achieve the purpose of the embodiment, which is not limited herein.
In addition, technical details not described in detail in the present embodiment may refer to the spectral library-based spectral super-division method provided in any embodiment of the present invention, which is not described herein.
Furthermore, it should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. Read Only Memory)/RAM, magnetic disk, optical disk) and including several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (10)
1. The spectrum hyper-division method based on the spectrum library is characterized by comprising the following steps of:
obtaining the land information of the target area;
determining an additional spectrum sample according to the ground type information;
establishing a private spectrum library according to a preset spectrum library and the additional spectrum sample;
and performing spectrum hyperspectral super-division on the multispectral image corresponding to the target area acquired in real time according to the private spectrum library to obtain a target hyperspectral image corresponding to the target area.
2. The method of claim 1, wherein the establishing a private spectrum library from a preset spectrum library and the additional spectrum sample comprises:
acquiring preset wavelength information of a preset spectrum library;
matching the preset wavelength information with the additional wavelength information of the additional spectrum sample to obtain target reflectivity data;
and adding the target reflectivity data into the preset spectrum library to form a private spectrum library.
3. The method of claim 2, wherein the matching the predetermined wavelength information with the additional wavelength information of the additional spectral sample to obtain the target reflectivity data comprises:
determining preset wavelengths and preset wavelength ranges of the preset spectrum library according to the preset wavelength information;
acquiring additional wavelength information corresponding to the additional spectrum sample;
determining an additional wavelength and an additional wavelength range according to the additional wavelength information;
determining a target matching wavelength according to the preset wavelength and the additional wavelength;
determining a target matching range according to the preset wavelength range and the additional wavelength range;
extracting matching reflectivity data conforming to the target matching wavelength and the target matching range from the additional spectrum sample;
and carrying out data screening on the matched reflectivity data to obtain target reflectivity data.
4. The method of claim 1, wherein performing spectral super-division on the multispectral image corresponding to the target region acquired in real time according to the private spectrum library comprises:
acquiring multispectral images acquired in real time;
extracting observation image information of the multispectral image and spectrum library information of a private spectrum library;
determining a spectrum reconstruction expression of the multispectral image and the target hyperspectral image according to the observed image information and the spectrum library information;
and performing spectrum super-division according to the spectrum library information and the spectrum reconstruction expression to obtain a target spectrum image.
5. The method of claim 4, wherein said obtaining a target hyperspectral image from said spectral library information and said spectral reconstruction expression comprises:
acquiring a target spectrum dictionary and a target sparse coefficient matrix corresponding to the target spectrum image;
obtaining a hyperspectral image linear expression according to the target spectrum dictionary and the target sparse coefficient matrix;
determining a library spectrum dictionary and a library sparse coefficient matrix according to the spectrum library information;
determining a spectrum library linear relation according to the library spectrum dictionary and the library sparse coefficient matrix;
and obtaining a target hyperspectral image according to the hyperspectral image linear expression, the spectral library linear relation and the spectral reconstruction expression.
6. The method of claim 5, wherein said deriving a target hyperspectral image from said hyperspectral image linear expression, said spectral library linear relation, and said spectral reconstruction expression comprises:
performing band matching on the private spectrum library through a band matching matrix to obtain a matched spectrum library;
extracting a matching library spectrum dictionary of the matched spectrum library;
determining a first affiliation of the private spectrum library and the target hyperspectral image;
determining a second dependence relationship of the matched spectrum library and the target hyperspectral image according to the first dependence relationship;
determining an equivalent sparse coefficient matrix according to the matching library spectrum dictionary, the second subordination relation, the spatial transformation matrix, the reconstructed image linear expression and the spectrum library linear relation;
and obtaining a target hyperspectral image according to the equivalent sparse coefficient matrix and the spectrum reconstruction expression.
7. The method of claim 6, wherein said obtaining a target hyperspectral image from said equivalent sparse coefficient matrix and said spectral reconstruction expression comprises:
acquiring a spectral response function and zero-mean Gaussian noise;
determining a reconstructed superdivision model of the target hyperspectral image according to the spectral response function, the zero-mean Gaussian noise and the spectral reconstruction expression;
and solving the reconstructed super-division model according to the equivalent sparse coefficient matrix to obtain a target hyperspectral image.
8. A spectral library-based spectral superdivision apparatus, the spectral library-based spectral superdivision apparatus comprising:
the ground type acquisition module is used for acquiring the ground type information of the target area;
the sample determining module is used for determining an additional spectrum sample according to the ground type information;
the spectrum library establishing module is used for establishing a private spectrum library according to a preset spectrum library and the additional spectrum sample;
and the spectrum hyper-splitting module is used for performing spectrum hyper-splitting on the multispectral image corresponding to the target area acquired in real time according to the private spectrum library to obtain a target hyperspectral image corresponding to the target area.
9. A spectral library-based spectral superdivision apparatus, the apparatus comprising: a memory, a processor, and a spectral library-based spectral superdistribution program stored on the memory and executable on the processor, the spectral library-based spectral superdistribution program configured to implement the spectral library-based spectral superdistribution method of any of claims 1-7.
10. A storage medium having stored thereon a spectral library-based spectral superdistribution program which, when executed by a processor, implements the spectral library-based spectral superdistribution method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211089779.XA CN116167913A (en) | 2022-09-07 | 2022-09-07 | Spectrum super-division method, device, equipment and storage medium based on spectrum library |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211089779.XA CN116167913A (en) | 2022-09-07 | 2022-09-07 | Spectrum super-division method, device, equipment and storage medium based on spectrum library |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116167913A true CN116167913A (en) | 2023-05-26 |
Family
ID=86415145
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211089779.XA Pending CN116167913A (en) | 2022-09-07 | 2022-09-07 | Spectrum super-division method, device, equipment and storage medium based on spectrum library |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116167913A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111358573A (en) * | 2020-02-26 | 2020-07-03 | 西安交通大学医学院第二附属医院 | Hyperspectral imaging surgical area rapid detection and marking device and detection method |
| KR20200120403A (en) * | 2019-04-12 | 2020-10-21 | 대한민국(산림청 국립산림과학원장) | System and method of tree species classification using satellite image |
| CN113390799A (en) * | 2021-06-24 | 2021-09-14 | 中国烟草总公司郑州烟草研究院 | Method for identifying and detecting stems in tobacco leaves |
| CN114022364A (en) * | 2021-11-22 | 2022-02-08 | 清华大学 | Multispectral image spectrum hyper-segmentation method and system based on spectrum library optimization learning |
-
2022
- 2022-09-07 CN CN202211089779.XA patent/CN116167913A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20200120403A (en) * | 2019-04-12 | 2020-10-21 | 대한민국(산림청 국립산림과학원장) | System and method of tree species classification using satellite image |
| CN111358573A (en) * | 2020-02-26 | 2020-07-03 | 西安交通大学医学院第二附属医院 | Hyperspectral imaging surgical area rapid detection and marking device and detection method |
| CN113390799A (en) * | 2021-06-24 | 2021-09-14 | 中国烟草总公司郑州烟草研究院 | Method for identifying and detecting stems in tobacco leaves |
| CN114022364A (en) * | 2021-11-22 | 2022-02-08 | 清华大学 | Multispectral image spectrum hyper-segmentation method and system based on spectrum library optimization learning |
Non-Patent Citations (2)
| Title |
|---|
| R.J. ZOMER 等: ""Building spectral libraries for wetlands land cover classification and hyperspectral remote sensing"", 《JOURNAL OF ENVIRONMENTAL MANAGEMENT》, vol. 90, no. 7, 31 May 2009 (2009-05-31), pages 2170 - 2177, XP026096665, DOI: 10.1016/j.jenvman.2007.06.028 * |
| 常世桢: ""基于背景建模与异常判别的高光谱目标探测研究"", 《中国优秀硕士学位论文全文数据库（基础科学辑）》, 15 June 2022 (2022-06-15), pages 1 - 137 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Nguyen et al. | A novel intelligence approach based active and ensemble learning for agricultural soil organic carbon prediction using multispectral and SAR data fusion | |
| Wu et al. | Use of MODIS and Landsat time series data to generate high-resolution temporal synthetic Landsat data using a spatial and temporal reflectance fusion model | |
| Tilly et al. | Multitemporal crop surface models: accurate plant height measurement and biomass estimation with terrestrial laser scanning in paddy rice | |
| Xie et al. | Remote sensing imagery in vegetation mapping: a review | |
| Culbert et al. | Modeling broad-scale patterns of avian species richness across the Midwestern United States with measures of satellite image texture | |
| Hagen et al. | Mapping total vegetation cover across western rangelands with moderate-resolution imaging spectroradiometer data | |
| Mitchell et al. | Subpixel abundance estimates in mixture-tuned matched filtering classifications of leafy spurge (Euphorbia esula L.) | |
| Baig et al. | Above ground biomass estimation of Dalbergia sissoo forest plantation from dual-polarized ALOS-2 PALSAR data | |
| Leitão et al. | From sample to pixel: multi‐scale remote sensing data for upscaling aboveground carbon data in heterogeneous landscapes | |
| CN108961199A (en) | Multi- source Remote Sensing Data data space-time fusion method and device | |
| Reyes-Muñoz et al. | Quantifying Fundamental Vegetation Traits over Europe Using the Sentinel-3 OLCI Catalogue in Google Earth Engine | |
| Zhang et al. | Spatial domain bridge transfer: An automated paddy rice mapping method with no training data required and decreased image inputs for the large cloudy area | |
| Gaveau et al. | Forest woody biomass classification with satellite-based radar coherence over 900 000 km2 in Central Siberia | |
| Rumora et al. | Contemporary comparative assessment of atmospheric correction influence on radiometric indices between Sentinel-2A and Landsat 8 imagery | |
| CN115829118A (en) | Forest carbon sink remote sensing monitoring method, device, equipment and storage medium | |
| Jiang et al. | Synergistic use of optical and InSAR data for urban impervious surface mapping: a case study in Hong Kong | |
| Braun et al. | Above-ground biomass estimates based on active and passive microwave sensor imagery in low-biomass savanna ecosystems | |
| Conlin et al. | SurfRCaT: A tool for remote calibration of pre-existing coastal cameras to enable their use as quantitative coastal monitoring tools | |
| Booth et al. | Ground-cover measurements: assessing correlation among aerial and ground-based methods | |
| Camacho et al. | Hyperspectral and multispectral image fusion addressing spectral variability by an augmented linear mixing model | |
| CN115629388A (en) | Radar echo simulation method based on infrared and microwave imager data | |
| Jing et al. | Sub-pixel accuracy evaluation of FY-3D MERSI-2 geolocation based on OLI reference imagery | |
| Lu et al. | Leaf area index estimation in a heterogeneous grassland using optical, SAR, and DEM Data | |
| Gallardo‐Cruz et al. | Relating species richness to the structure of continuous landscapes: alternative methodological approaches | |
| Dai et al. | Spectral dimensionality of imaging spectroscopy data over diverse landscapes and spatial resolutions |
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 |