CN113870110B - Image fusion method and device of remote sensing image, electronic equipment and storage medium - Google Patents
Image fusion method and device of remote sensing image, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113870110B CN113870110B CN202111059738.1A CN202111059738A CN113870110B CN 113870110 B CN113870110 B CN 113870110B CN 202111059738 A CN202111059738 A CN 202111059738A CN 113870110 B CN113870110 B CN 113870110B
- Authority
- CN
- China
- Prior art keywords
- image
- remote sensing
- spatial
- images
- resolution
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000007500 overflow downdraw method Methods 0.000 title claims abstract description 24
- 230000009466 transformation Effects 0.000 claims abstract description 29
- 238000000034 method Methods 0.000 claims abstract description 18
- 230000002194 synthesizing effect Effects 0.000 claims abstract description 15
- 230000004927 fusion Effects 0.000 claims abstract description 10
- 238000011084 recovery Methods 0.000 claims abstract description 10
- 238000006243 chemical reaction Methods 0.000 claims description 29
- 230000008859 change Effects 0.000 claims description 24
- 238000012952 Resampling Methods 0.000 claims description 14
- 230000015572 biosynthetic process Effects 0.000 claims description 8
- 238000003786 synthesis reaction Methods 0.000 claims description 8
- 238000012986 modification Methods 0.000 claims description 4
- 230000004048 modification Effects 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 230000003595 spectral effect Effects 0.000 abstract description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 238000000701 chemical imaging Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000004088 simulation Methods 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
-
- 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)
- Image Processing (AREA)
Abstract
The invention provides an image fusion method of a remote sensing image, which comprises the following steps: and respectively acquiring a plurality of high-spatial-resolution multispectral remote sensing images and n low-spatial-resolution multispectral remote sensing images. And synthesizing the n multispectral remote sensing images with low spatial resolution to obtain a first full-color band image. And synthesizing the plurality of high-spatial-resolution multispectral remote sensing images to obtain a second full-color band image. And carrying out GS transformation on the original n multispectral remote sensing images with low spatial resolution based on a phase recovery method. And carrying out GS inverse transformation on the plurality of the GS-transformed wave band images to obtain a fused image. An image fusion device, electronic equipment and storage medium of the remote sensing image are also provided. The image fusion method, the device, the electronic equipment and the storage medium of the remote sensing image can improve the spatial resolution of the multispectral remote sensing image with low spatial resolution, and meanwhile, the spectral characteristics are kept unchanged.
Description
Technical Field
The present invention relates to the field of image processing technologies of remote sensing images, and in particular, to an image fusion method, apparatus, electronic device, and storage medium for remote sensing images.
Background
The sentinel 2A/B satellite is a multispectral imaging satellite emitted by European sky office in 2015, 6 months, and is mainly used in the fields of environment monitoring, quantitative parameter inversion, surface change monitoring and the like. The breadth reaches 290 km, the shortest revisit period of the two-star networking earth observation can reach three days, and the application range of satellite images is greatly improved. Meanwhile, the high-performance imaging load carried by the imaging device greatly improves the image quality. The sentinel 2A/B band parameters are as follows:
sentinel 2A/B image parameter table
As can be seen from the above table, the satellite has 4 10 meters high spatial resolution bands and6 20 meters low spatial resolution bands. How to improve the spatial resolution of 6 20 meter wave bands to 10 meters has very important practical value.
In the prior art, the remote sensing image fusion (Pansharpening) method mostly fuses a full-color high-resolution image with a plurality of low-resolution multispectral images, and researches on how to fuse the high-resolution multispectral images with the low-resolution multispectral images are very few. However, the sentinel 2A/B satellite having a plurality of high spatial resolution bands and a plurality of low spatial resolution bands cannot be fused by the prior art, so that a new image fusion method of remote sensing images needs to be provided.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provide an image fusion method, device, electronic equipment and storage medium of a remote sensing image, wherein the spatial resolution of the low-spatial-resolution multispectral remote sensing image is improved by fusing a plurality of high-spatial-resolution multispectral remote sensing images with the low-spatial-resolution multispectral remote sensing image, and meanwhile, the spectral characteristics are kept unchanged, so that effective data support is provided for subsequent image application.
In order to achieve the above purpose, the invention adopts the following technical scheme:
an image fusion method of remote sensing images comprises the following steps:
respectively acquiring a plurality of high-spatial-resolution multispectral remote sensing images and n low-spatial-resolution multispectral remote sensing images; wherein n is more than or equal to 1;
performing geometric registration and resampling on n multispectral remote sensing images with low spatial resolution, and synthesizing to obtain a simulated first panchromatic wave band image;
synthesizing the plurality of high-spatial-resolution multispectral remote sensing images to obtain a simulated second panchromatic wave band image;
based on a phase recovery method, taking the first full-color band image as a first component of GS conversion, carrying out GS conversion on the original n multispectral remote sensing images with low spatial resolution, and outputting a plurality of band images after GS conversion, wherein the image corresponding to the first full-color band image is the first component after GS conversionA band image GS 1 The images respectively corresponding to the rest of the multispectral remote sensing images with low spatial resolution are subsequent wave band images GS after GS conversion 2 、GS 3 ……GS n+1 ；
Modifying the second full-color band image according to the first component of the GS transformation to obtain a modified image;
replacing the GS with the modified image 1 And performing GS inverse transformation on the plurality of GS-transformed band images as first components of the GS inverse transformation, outputting n+1 GS-inverse-transformed band images, and removing the GS-inverse-transformed first band images corresponding to the GS-inverse-transformed first components to obtain fused images.
The technical scheme is further improved as follows:
the image fusion method of the remote sensing images is characterized in that the plurality of high-spatial-resolution multispectral remote sensing images and the plurality of low-spatial-resolution multispectral remote sensing images are acquired based on a sentinel 2A/B satellite, wherein the number of the high-spatial-resolution multispectral remote sensing images is 4, and the number of the low-spatial-resolution multispectral remote sensing images is 6.
The geometric registration specifically comprises the following steps:
randomly selecting one high-spatial-resolution multispectral remote sensing image as a reference datum image;
automatically acquiring characteristic points of the high-spatial-resolution multispectral remote sensing image and the low-spatial-resolution multispectral remote sensing image by adopting a SIFT algorithm, screening the characteristic points by utilizing a one-time polynomial global change model, and calculating projection change model parameter estimation to obtain projection change parameters;
and performing geometric change and image interpolation on the low-spatial-resolution multispectral remote sensing image by utilizing the projection change parameters to obtain the registered image.
The spatial resampling specifically comprises:
and performing spatial resampling on the low-spatial-resolution multispectral remote sensing image by using a bicubic convolution interpolation algorithm to obtain a resampled image, wherein the size and the pixels of the resampled image are the same as those of the high-spatial-resolution multispectral remote sensing image.
The synthesizing the plurality of high-spatial-resolution multispectral remote sensing images to obtain a second panchromatic band image specifically comprises the following steps: and obtaining a second full-color band image by means of mean value synthesis based on the high-spatial-resolution multispectral remote sensing images.
The formula of the mean synthesis is as follows:
in the above formula, band i Indicating the i-th band and n the number of bands.
The phase recovery method is based on a Gram-Schmidt algorithm, and a specific GS transformation formula is as follows:
in GS T Is the T component generated after GS conversion, B T Is the T-th band image of the original low-spatial-resolution multispectral remote sensing image, u T Is the average value of gray values of the T-th original low-spatial-resolution multispectral remote sensing image.
The invention also provides an image fusion device of the remote sensing image, which comprises:
the acquisition module is used for respectively acquiring a plurality of high-spatial-resolution multispectral remote sensing images and n low-spatial-resolution multispectral remote sensing images; wherein n is more than or equal to 1;
the registration resampling module is used for carrying out geometric registration and resampling on the n multispectral remote sensing images with low spatial resolution to obtain simulated full-color wave band images with low spatial resolution;
the synthesizing module is used for synthesizing the plurality of high-spatial-resolution multispectral remote sensing images into a high-spatial-resolution panchromatic wave band image;
the conversion module is used for converting the data into the data,the method is used for taking the low-spatial-resolution panchromatic band image as a first component of GS conversion based on a phase recovery method, carrying out GS conversion on the original n low-spatial-resolution multispectral remote sensing images, and outputting a plurality of band images after GS conversion, wherein the image corresponding to the low-spatial-resolution panchromatic band image is a first band image GS after GS conversion 1 The images corresponding to the rest of the multispectral remote sensing images with low spatial resolution are subsequent wave band images GS after GS conversion 2 、GS 3 ……GS n+1 ；
The modification module is used for modifying the high-spatial resolution panchromatic band image according to the first component of the GS transformation to obtain a modified image;
a fusion module for replacing the GS with the modified image 1 And performing GS inverse transformation on the plurality of GS-transformed band images as first components of the GS inverse transformation, outputting n+1 GS-inverse-transformed band images, and removing the GS-inverse-transformed first band images corresponding to the GS-inverse-transformed first components to obtain fused images.
The invention also provides an electronic device comprising a processor, and a memory coupled to the processor, the memory storing program instructions executable by the processor; and the processor realizes the road network change detection method when executing the program instructions stored in the memory.
The invention also provides a storage medium, wherein the storage medium stores program instructions which are executed by a processor to realize the road network change detection method.
According to the technical scheme of the invention, the image fusion method of the remote sensing image fuses a plurality of high-spatial-resolution multispectral remote sensing images with a plurality of low-spatial-resolution multispectral remote sensing images, can effectively improve the spatial resolution of the low-spatial-resolution multispectral remote sensing images, can keep the spectral characteristics unchanged, and provides more effective data support for subsequent image application. The method synthesizes a plurality of high-spatial-resolution multispectral remote sensing images into a high-spatial-resolution panchromatic wave band image, and the high-spatial-resolution panchromatic wave band image can be used for reference and correction, so that the fused image has higher precision.
Drawings
Fig. 1 is a flowchart of an image fusion method of a remote sensing image according to an embodiment of the present invention.
Fig. 2 is a schematic structural diagram of an image fusion device for remote sensing images according to an embodiment of the present invention.
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Fig. 4 is a schematic structural diagram of a storage medium according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the invention. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
Fig. 1 is a flowchart of an image fusion method of a remote sensing image according to a first embodiment of the present invention. It should be noted that, if there are substantially the same results, the method of the present invention is not limited to the flow sequence shown in fig. 1.
Example 1: as shown in fig. 1, the image fusion method of the remote sensing image of the present embodiment includes the following steps:
s10, respectively acquiring a plurality of high-spatial-resolution multispectral remote sensing images and n low-spatial-resolution multispectral remote sensing images; wherein n.gtoreq.1, n in this example has a value of 6.
In this embodiment, the image fusion method of the remote sensing image obtains the plurality of high spatial resolution multispectral remote sensing images and the plurality of low spatial resolution multispectral remote sensing images based on the sentinel 2A/B satellite, wherein the number of the high spatial resolution multispectral remote sensing images is 4, and the high spatial resolution multispectral remote sensing images are Band 2-blue Band, band 3-green Band, band 4-red Band and Band 8-near infrared Band in the sentinel 2A/B Band parameter table respectively. That is, in the present embodiment, the spatial resolution is equal to 10 meters, which is a high spatial resolution multispectral remote sensing image. The number of the multispectral remote sensing images with low spatial resolution is 6, and the multispectral remote sensing images are Band 5-red Band, band 6-red Band, band 7-red Band, band 8A-narrow near infrared, band 11-short wave infrared and Band 12-short wave infrared in the sentinel 2A/B Band parameter table respectively. That is, in the present embodiment, the spatial resolution is equal to 20 meters, which is a multispectral remote sensing image with low spatial resolution.
And S20, performing geometric registration and resampling on the 6 low-spatial-resolution multispectral remote sensing images, and synthesizing the registered and resampled low-spatial-resolution multispectral remote sensing images to obtain a simulated first panchromatic wave band image.
S21, the geometric registration specifically comprises the following steps:
and randomly selecting one high-spatial-resolution multispectral remote sensing image as a reference datum image.
And automatically acquiring characteristic points of the high-spatial-resolution multispectral remote sensing image and the low-spatial-resolution multispectral remote sensing image by adopting a SIFT algorithm, screening the characteristic points by utilizing a one-time polynomial global change model, and calculating projection change model parameter estimation to obtain projection change parameters.
And performing geometric change and image interpolation on the low-spatial-resolution multispectral remote sensing image by utilizing the projection change parameters to obtain the registered image.
S22, the spatial resampling specifically comprises:
and performing spatial resampling on the low-spatial-resolution multispectral remote sensing image by using a bicubic convolution interpolation algorithm to obtain a resampled image, wherein the size and the pixels of the resampled image are the same as those of the high-spatial-resolution multispectral remote sensing image.
The formula of the bicubic convolution interpolation algorithm is as follows:
where h represents the sampling interval, x k Represents interpolation points, u represents kernel for interpolation convolution, g is interpolation function, c k To rely on parameters of the sample point data, they must satisfy g (x k )＝f(x k ) Is a condition of (2).
S23, simulation: obtaining a first full-color band image by adopting a mean value synthesis mode, wherein the mean value synthesis formula is as follows:
in the above formula, band i Indicating the i-th band and n the number of bands.
And S30, synthesizing the plurality of high-spatial-resolution multispectral remote sensing images to obtain a simulated second full-color band image.
And obtaining a second full-color band image by adopting a mean value synthesis mode, wherein the mean value synthesis formula is as follows:
in the above formula, band i Indicating the i-th band and n the number of bands.
S40, taking the first full-color band image as a first component of GS conversion based on a phase recovery method, carrying out GS conversion on the original n low-spatial-resolution multispectral remote sensing images, and outputting a plurality of band images after GS conversion, wherein the band images are matched with the first full-color band imageThe corresponding image is a first band image GS after GS conversion 1 The images respectively corresponding to the rest of the multispectral remote sensing images with low spatial resolution are subsequent wave band images GS after GS conversion 2 、GS 3 ……GS n+1 。
The phase recovery method is based on Gram-Schmidt algorithm, adopts Schmidt orthogonalization, and the formula of the Schmidt orthogonalization is as follows:
v 1 ＝u 1 ；
……
wherein v is 1 、v 2 ……v n Are mutually independent vectors; u (u) 1 、u 2 ……u n Is the constructed orthogonal vector.
The specific formula of the GS transform is as follows:
in GS T Is the T component generated after GS conversion, B T Is the T-th band image of the original low-spatial-resolution multispectral remote sensing image, u T Is the average value of gray values of the T-th original low-spatial-resolution multispectral remote sensing image.
S50, modifying the second full-color band image according to the first component of the GS conversion to obtain a modified image. Specifically, the mean value and standard deviation of the second full-color band image, and the mean value and standard deviation of the GS1 are calculated respectively, and the second full-color band image is modified according to the two sets of data, so as to obtain a modified image.
The specific modification formula is as follows:
k 2 ＝u intensity -(k 1 ×u pan )；
wherein P is the gray value of the first full-color band image, e intensity For the variance of the luminance component I, e pan Variance of the first panchromatic band image; u (u) intensity For the mean value of the luminance component, u pan Is the gray average value of the first full-color band image. k (k) 1 Is gain, k 2 Is offset.
S60, replacing the GS with the modified image 1 And performing GS inverse transformation on the plurality of GS-transformed band images as first components of the GS inverse transformation, outputting n+1 GS-inverse-transformed band images, and removing the GS-inverse-transformed first band images corresponding to the GS-inverse-transformed first components to obtain fused images.
The specific GS inverse transform formula is as follows:
wherein B is T Is the T-th wave band image after GS inverse transformation, GS T Is the T-th component generated after GS conversion, u T Is the average value of gray values of the image of the T-th wave band after GS conversion. GS l Representing matching the first component after Gram-Schmidt transformation by adjusting the statistics of the high resolution band images.
The image fusion method of the remote sensing image can effectively improve the spatial resolution of the original low-spatial-resolution multispectral remote sensing image while maintaining the spectral characteristics of the original low-spatial-resolution multispectral remote sensing image, adopts a GS algorithm to fuse a plurality of low-spatial-resolution multispectral remote sensing images with a plurality of high-spatial-resolution multispectral remote sensing images, so that the spatial resolution of the image fusion method is improved to be consistent with the spatial resolution of the high-spatial-resolution multispectral remote sensing image, and finally provides better remote sensing image data for information extraction, quantitative parameter inversion and the like.
As shown in fig. 2, this embodiment further provides an image fusion apparatus for remote sensing images, including:
an acquiring module 31, configured to acquire a plurality of high spatial resolution multispectral remote sensing images and n low spatial resolution multispectral remote sensing images respectively; wherein n is greater than or equal to 1.
The registration resampling module 32 is configured to geometrically register and resample the n low spatial resolution multispectral remote sensing images to obtain a simulated low spatial resolution panchromatic band image.
The synthesizing module 33 is configured to synthesize the plurality of high spatial resolution multispectral remote sensing images into a high spatial resolution panchromatic band image.
A transformation module 34, configured to perform a GS transformation on the original n low-spatial-resolution multispectral remote sensing images with the low-spatial-resolution panchromatic band image as a first component of the GS transformation based on a phase recovery method, and output a plurality of GS-transformed band images, where the image corresponding to the low-spatial-resolution panchromatic band image is the GS-transformed first band image GS 1 The images corresponding to the rest of the multispectral remote sensing images with low spatial resolution are subsequent wave band images GS after GS conversion 2 、GS 3 ……GS n+1 。
A modifying module 35, configured to modify the high spatial resolution panchromatic band image according to the first component of the GS transform, to obtain a modified image.
A fusion module 36 for replacing the GS with the modified image 1 And performing GS inverse transformation on the plurality of GS-transformed band images as first components of the GS inverse transformation, outputting n+1 GS-inverse-transformed band images, and removing the GS-inverse-transformed first band images corresponding to the GS-inverse-transformed first components to obtain fused images.
As shown in fig. 3, the present embodiment further provides an electronic device 40, where the electronic device 40 includes a processor 41, and a memory 42 coupled to the processor 41, and the memory 42 stores program instructions executable by the processor 41; the processor 41 implements the road network change-detecting method described above when executing the program instructions stored in the memory 42.
As shown in fig. 4, the present embodiment further provides a storage medium 60, where the storage medium 60 stores program instructions 61, and the program instructions 61 implement the road network change detection method described above when executed by a processor.
In the several embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of elements is merely a logical functional division, and there may be additional divisions of actual implementation, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units. The foregoing is only the embodiments of the present invention, and the patent scope of the invention is not limited thereto, but is also covered by the patent protection scope of the invention, as long as the equivalent structures or equivalent processes of the present invention and the contents of the accompanying drawings are changed, or the present invention is directly or indirectly applied to other related technical fields.
While the invention has been described with respect to the above embodiments, it should be noted that modifications can be made by those skilled in the art without departing from the inventive concept, and these are all within the scope of the invention.
Claims (9)
1. The image fusion method of the remote sensing image is characterized by comprising the following steps of:
respectively acquiring a plurality of high-spatial-resolution multispectral remote sensing images and n low-spatial-resolution multispectral remote sensing images; wherein n is more than or equal to 1;
performing geometric registration and resampling on n multispectral remote sensing images with low spatial resolution, and synthesizing to obtain a simulated first panchromatic wave band image;
synthesizing the plurality of high-spatial-resolution multispectral remote sensing images to obtain a simulated second panchromatic wave band image;
based on a phase recovery method, taking the first full-color band image as a first component of GS conversion, carrying out GS conversion on the original n multispectral remote sensing images with low spatial resolution, and outputting a plurality of band images after GS conversion, wherein the image corresponding to the first full-color band image is a first band image GS after GS conversion 1 The images respectively corresponding to the rest of the multispectral remote sensing images with low spatial resolution are subsequent wave band images GS after GS conversion 2 、GS 3 ……GS n+1 ；
Modifying the second full-color band image according to the first component of the GS transformation to obtain a modified image;
use stationThe modified image replaces the GS 1 Performing GS inverse transformation on a plurality of the GS-transformed band images as first components of the GS inverse transformation, outputting n+1 GS-inverse-transformed band images, and removing the GS-inverse-transformed first band images corresponding to the GS-inverse-transformed first components to obtain fused images;
the geometric registration specifically comprises the following steps:
randomly selecting one high-spatial-resolution multispectral remote sensing image as a reference datum image;
automatically acquiring characteristic points of the high-spatial-resolution multispectral remote sensing image and the low-spatial-resolution multispectral remote sensing image by adopting a SIFT algorithm, screening the characteristic points by utilizing a one-time polynomial global change model, and calculating projection change model parameter estimation to obtain projection change parameters;
and performing geometric change and image interpolation on the low-spatial-resolution multispectral remote sensing image by utilizing the projection change parameters to obtain the registered image.
2. The image fusion method of remote sensing images according to claim 1, wherein: the image fusion method of the remote sensing images is characterized in that the plurality of high-spatial-resolution multispectral remote sensing images and the plurality of low-spatial-resolution multispectral remote sensing images are acquired based on a sentinel 2A/B satellite, wherein the number of the high-spatial-resolution multispectral remote sensing images is 4, and the number of the low-spatial-resolution multispectral remote sensing images is 6.
3. The image fusion method of remote sensing images according to claim 1, wherein: the spatial resampling specifically comprises:
and performing spatial resampling on the low-spatial-resolution multispectral remote sensing image by using a bicubic convolution interpolation algorithm to obtain a resampled image, wherein the size and the pixels of the resampled image are the same as those of the high-spatial-resolution multispectral remote sensing image.
4. The image fusion method of remote sensing images according to claim 1, wherein: the synthesizing the plurality of high-spatial-resolution multispectral remote sensing images to obtain a simulated second full-color band image comprises the following specific steps: and obtaining a second full-color band image by means of mean value synthesis based on the high-spatial-resolution multispectral remote sensing images.
5. The method for image fusion of remote sensing images according to claim 4, wherein: the formula of the mean synthesis is as follows: in the above formula, bandi represents the i-th band, and n represents the number of bands.
6. The image fusion method of remote sensing images according to claim 1, wherein: the phase recovery method is based on a Gram-Schmidt algorithm, and a specific GS transformation formula is as follows: in GS T Is the T component generated after GS conversion, B T Is the T-th band image of the original low-spatial-resolution multispectral remote sensing image, u T Is the average value of gray values of the T-th original low-spatial-resolution multispectral remote sensing image.
7. An image fusion device of remote sensing image, its characterized in that: comprising
The acquisition module is used for respectively acquiring a plurality of high-spatial-resolution multispectral remote sensing images and n low-spatial-resolution multispectral remote sensing images; wherein n is more than or equal to 1;
the registration resampling module is used for carrying out geometric registration and resampling on the n multispectral remote sensing images with low spatial resolution to obtain simulated full-color wave band images with low spatial resolution;
the synthesizing module is used for synthesizing the plurality of high-spatial-resolution multispectral remote sensing images into a high-spatial-resolution panchromatic wave band image;
a transformation module for performing GS transformation on the original n low spatial resolution multispectral remote sensing images based on a phase recovery method by using the low spatial resolution panchromatic band image as a first component of the GS transformation, and outputting a plurality of band images after the GS transformation, wherein the first component is a first component of the GS transformationThe image corresponding to the low spatial resolution panchromatic band image is a first band image GS after GS conversion 1 The images corresponding to the rest of the multispectral remote sensing images with low spatial resolution are subsequent wave band images GS after GS conversion 2 、GS 3 ……GS n+1 ；
The modification module is used for modifying the high-spatial resolution panchromatic band image according to the first component of the GS transformation to obtain a modified image;
a fusion module for replacing the GS with the modified image 1 As a first component of the GS inverse transformation, performing GS inverse transformation on a plurality of the GS-transformed band images, outputting n+1 GS-inverse-transformed band images, and removing the GS-inverse-transformed first band images corresponding to the GS-inverse-transformed first component to obtain a fused image;
the geometric registration specifically comprises the following steps:
randomly selecting one high-spatial-resolution multispectral remote sensing image as a reference datum image;
automatically acquiring characteristic points of the high-spatial-resolution multispectral remote sensing image and the low-spatial-resolution multispectral remote sensing image by adopting a SIFT algorithm, screening the characteristic points by utilizing a one-time polynomial global change model, and calculating projection change model parameter estimation to obtain projection change parameters;
and performing geometric change and image interpolation on the low-spatial-resolution multispectral remote sensing image by utilizing the projection change parameters to obtain the registered image.
8. An electronic device comprising a processor, and a memory coupled to the processor, the memory storing program instructions executable by the processor, characterized by: the processor, when executing the program instructions stored in the memory, implements the image fusion method of the remote sensing image according to any one of claims 1 to 6.
9. A storage medium, characterized by: the storage medium stores program instructions that when executed by a processor implement the image fusion method of a remote sensing image according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111059738.1A CN113870110B (en) | 2021-09-10 | 2021-09-10 | Image fusion method and device of remote sensing image, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111059738.1A CN113870110B (en) | 2021-09-10 | 2021-09-10 | Image fusion method and device of remote sensing image, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113870110A CN113870110A (en) | 2021-12-31 |
| CN113870110B true CN113870110B (en) | 2023-06-13 |
Family
ID=78995278
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111059738.1A Active CN113870110B (en) | 2021-09-10 | 2021-09-10 | Image fusion method and device of remote sensing image, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113870110B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116977868B (en) * | 2023-06-07 | 2024-03-01 | 珠江水利委员会珠江水利科学研究院 | Image product fusion method, system and storage medium based on feature matching |
| CN117197625B (en) * | 2023-08-29 | 2024-04-05 | 珠江水利委员会珠江水利科学研究院 | Remote sensing image space-spectrum fusion method, system, equipment and medium based on correlation analysis |
| CN117253125B (en) * | 2023-10-07 | 2024-03-22 | 珠江水利委员会珠江水利科学研究院 | Space-spectrum mutual injection image fusion method, system and readable storage medium |
| CN117724006B (en) * | 2024-02-07 | 2024-05-24 | 深圳市魔方卫星科技有限公司 | Satellite power supply abnormal state detection method and system |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6011875A (en) * | 1998-04-29 | 2000-01-04 | Eastman Kodak Company | Process for enhancing the spatial resolution of multispectral imagery using pan-sharpening |
| CN105096286B (en) * | 2015-06-30 | 2018-05-04 | 中国石油天然气股份有限公司 | The fusion method and device of remote sensing images |
| CN106384332B (en) * | 2016-09-09 | 2019-12-03 | 中山大学 | Unmanned plane image and multispectral image fusion method based on Gram-Schmidt |
| CN109447922B (en) * | 2018-07-10 | 2021-02-12 | 中国资源卫星应用中心 | Improved IHS (induction heating system) transformation remote sensing image fusion method and system |
| CN113033670B (en) * | 2021-03-29 | 2023-06-23 | 华南农业大学 | Rice planting area extraction method based on Sentinel-2A/B data |
-
2021
- 2021-09-10 CN CN202111059738.1A patent/CN113870110B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113870110A (en) | 2021-12-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113870110B (en) | Image fusion method and device of remote sensing image, electronic equipment and storage medium | |
| JP7159057B2 (en) | Free-viewpoint video generation method and free-viewpoint video generation system | |
| US8879865B2 (en) | Panchromatic sharpening method of spectral image based on fusion of overall structural information and spatial detail information | |
| Li et al. | Remote sensing image fusion via sparse representations over learned dictionaries | |
| Yang et al. | Remote sensing image super-resolution: Challenges and approaches | |
| Li et al. | Super resolution for remote sensing images based on a universal hidden Markov tree model | |
| Claus et al. | A rational function lens distortion model for general cameras | |
| Xu et al. | High-fidelity component substitution pansharpening by the fitting of substitution data | |
| CN110415199B (en) | Multispectral remote sensing image fusion method and device based on residual learning | |
| CN111986134B (en) | Remote sensing imaging method and device for area-array camera | |
| CN111681171B (en) | Full-color and multispectral image high-fidelity fusion method and device based on block matching | |
| JP2010511256A (en) | Spatial and spectral calibration of panchromatic multispectral image pairs | |
| CN108090872B (en) | Single-frame multispectral image super-resolution reconstruction method and system based on gradient extraction | |
| CN108932708A (en) | Satellite-borne multispectral remote sensing image fusion method based on super-resolution enhancing | |
| JP2006203296A (en) | Interpolation processing method, interpolation processing program, and imaging apparatus | |
| Zhao et al. | A hybrid image fusion model for generating high spatial-temporal-spectral resolution data using OLI-MODIS-Hyperion satellite imagery | |
| CN113409193B (en) | Super-resolution reconstruction method and device for hyperspectral image | |
| CN113284045A (en) | HSI super-resolution reconstruction method based on transfer learning and spectrum recovery and related equipment | |
| Li et al. | Superresolution reconstruction of multispectral data for improved image classification | |
| Bhujel et al. | Dynamic convolutional neural network for image super-resolution | |
| JP5846048B2 (en) | Image processing apparatus and imaging apparatus | |
| Rao et al. | Restoration of high frequency details while constructing the high resolution image | |
| CN112598717A (en) | Full-spectrum registration method and medium for hyperspectral satellite images | |
| JP7316004B1 (en) | Information processing device, information processing method, and program | |
| JP2016167736A (en) | Image conversion device, image conversion method and image conversion program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |