CN116703769B - Satellite remote sensing image full-color sharpening system - Google Patents
Satellite remote sensing image full-color sharpening system Download PDFInfo
- Publication number
- CN116703769B CN116703769B CN202310678358.9A CN202310678358A CN116703769B CN 116703769 B CN116703769 B CN 116703769B CN 202310678358 A CN202310678358 A CN 202310678358A CN 116703769 B CN116703769 B CN 116703769B
- Authority
- CN
- China
- Prior art keywords
- image
- resolution
- module
- full
- unit
- 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
- 230000004927 fusion Effects 0.000 claims abstract description 34
- 238000000034 method Methods 0.000 claims abstract description 24
- 238000007781 pre-processing Methods 0.000 claims abstract description 22
- 238000001228 spectrum Methods 0.000 claims abstract description 16
- 230000009466 transformation Effects 0.000 claims description 23
- 238000000605 extraction Methods 0.000 claims description 19
- 238000003708 edge detection Methods 0.000 claims description 16
- 238000012706 support-vector machine Methods 0.000 claims description 12
- 238000010276 construction Methods 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 5
- 238000012847 principal component analysis method Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 3
- 230000002787 reinforcement Effects 0.000 claims description 3
- 230000015556 catabolic process Effects 0.000 claims description 2
- 238000006731 degradation reaction Methods 0.000 claims description 2
- 238000001914 filtration Methods 0.000 claims description 2
- 238000003384 imaging method Methods 0.000 claims description 2
- 238000000513 principal component analysis Methods 0.000 claims description 2
- 238000012549 training Methods 0.000 claims description 2
- 230000001131 transforming effect Effects 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 abstract description 3
- 230000003595 spectral effect Effects 0.000 description 8
- 238000013527 convolutional neural network Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000000701 chemical imaging Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration by the use of more than one image, e.g. averaging, subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4053—Super resolution, i.e. output image resolution higher than sensor resolution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
- G06T2207/10036—Multispectral image; Hyperspectral image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
-
- 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
Abstract
The invention discloses a satellite remote sensing image full-color sharpening system, which comprises: the system comprises an image data acquisition module, an image preprocessing module, an image super-resolution reconstruction module, an image fusion module and a full-color sharpening module; the image data acquisition module is used for acquiring an original image, wherein the original image comprises a multispectral image and a full-color image; the image preprocessing module is connected with the image data acquisition module and is used for preprocessing an original image; the image super-resolution reconstruction module is connected with the image preprocessing module and is used for converting the preprocessed low-resolution image into a high-resolution image; the image fusion module is respectively connected with the image super-resolution reconstruction module and the image preprocessing module and is used for satellite remote sensing image fusion; the full-color sharpening module is connected with the image fusion module and is used for obtaining the full-color sharpened image. The method can obtain accurate space and spectrum information, and can be used in the remote sensing technical fields of target identification, ground object classification, environment monitoring and the like.
Description
Technical Field
The invention relates to the technical field of remote sensing image processing, in particular to a satellite remote sensing image full-color sharpening system.
Background
Multispectral images have been well applied in environmental monitoring, mining and agriculture. Due to the hardware limitations of the sensors, optical telemetry satellites are typically only able to measure some low resolution multispectral images (LRMS) and high resolution panchromatic images (PAN). The spatial resolution of the multispectral image can be increased by fusing the panchromatic image and the multispectral image to obtain an image with both high spatial resolution and high spectral resolution, i.e., by extracting the spatial detail information of the panchromatic image and injecting it into the multispectral image, a process also known as panchromatic sharpening.
Panchromatic sharpening refers to increasing the resolution of a multispectral image to have the same spatial resolution as a panchromatic image, while maintaining its original spectral characteristics undistorted. The image subjected to full-color sharpening has high spatial resolution and spectral resolution, and is favorable for realizing the processing of detection, identification, classification and the like of targets. In the full-color sharpening process, the key and requirements of the full-color and spectral image fusion method are as follows: the spectrum resolution is fidelity, namely the fusion image is consistent with the spectrum information of the spectrum image; the spatial resolution is fidelity, namely the fusion image is consistent with the spatial information of the full-color image; the time and the calculation redundancy are low, namely the large-scale multi-size remote sensing image fusion process can be completed rapidly. The traditional full color sharpening method includes: component substitution, multi-resolution analysis, and relative spectral contribution. In recent years, based on the appearance of large-scale data and the development of deep neural networks, a deep learning method becomes an important research direction in the field of machine learning. The convolutional neural network (ConvolutionalNeuralNetwork, CNN) has strong characteristic learning capability, the characteristic data obtained by deep network model learning is more essentially representative to the original data, and the deep learning architecture model trained by large-scale data can extract rich internal information, so that the method is beneficial to visualization and classification problem treatment.
Because of the diversity of remote sensing image data and the complexity of information contained in the remote sensing image, the existing downscaling method still has great limitation, and a satellite remote sensing image full-color sharpening system suitable for complex geographic scenes is needed.
Disclosure of Invention
In view of the above, the invention aims to overcome the defects of the prior art, and provides a satellite remote sensing image full-color sharpening system.
In order to achieve the technical purpose, the invention provides the following technical scheme: a satellite remote sensing image full color sharpening system, comprising: the system comprises an image data acquisition module, an image preprocessing module, an image super-resolution reconstruction module, an image fusion module and a full-color sharpening module;
the image data acquisition module is used for acquiring an original image, wherein the original image comprises a multispectral image and a full-color image;
the image preprocessing module is connected with the image data acquisition module and is used for preprocessing the original image;
the image super-resolution reconstruction module is connected with the image preprocessing module and is used for converting the preprocessed low-resolution image into a high-resolution image;
the image fusion module is respectively connected with the image super-resolution reconstruction module and the image preprocessing module and is used for satellite remote sensing image fusion;
the full-color sharpening module is connected with the image fusion module and is used for obtaining the full-color sharpened image.
Preferably, the image data acquisition module comprises a first data acquisition unit and a second data acquisition unit;
the first data acquisition unit is used for acquiring a low-resolution multispectral image;
the second data acquisition module is used for acquiring a high-resolution full-color image.
Preferably, the image preprocessing module includes: the device comprises an image clipping unit, a spectrum information extraction unit and a space information extraction unit;
the image clipping unit is respectively connected with the first data acquisition unit and the second data acquisition unit. For cropping the low resolution multispectral image to a size of 32 x 32 and the high resolution panchromatic image to a size of 128 x 128;
the spectrum information extraction unit is connected with the image clipping unit and is used for extracting the characteristic information of the preprocessed low-resolution multispectral image;
the space information extraction unit is connected with the image clipping unit and is used for extracting the characteristic information of the preprocessed high-resolution full-color image.
Preferably, the spatial information extraction unit includes an edge detection subunit and a convolution subunit;
the edge detection subunit is used for obtaining a gradient map corresponding to the edge detection operator based on a plurality of edge detection operators, and the number of channels of the gradient map is the same;
the convolution subunit is connected with the edge detection subunit and is used for extracting the characteristics of the gradient images to obtain the characteristic images of the preprocessed high-resolution full-color images.
Preferably, the image super-resolution reconstruction module includes: a super-resolution reconstruction unit and a transformation model unit;
the super-resolution reconstruction unit is connected with the spatial information extraction unit and is used for acquiring a low-resolution panchromatic image based on the feature map of the preprocessed high-resolution panchromatic image;
the transformation model unit is connected with the super-resolution reconstruction unit and is used for obtaining a super-resolution multispectral image.
Preferably, the transformation model unit comprises a model construction subunit and a transformation subunit;
the model construction subunit is used for constructing a support vector machine regression model;
the transformation unit is used for carrying out image contour transformation reconstruction based on a support vector machine regression model to obtain a super-resolution multispectral image.
Preferably, the image fusion module comprises a fusion unit;
the fusion unit is used for carrying out space spectrum fusion on the preprocessed super-resolution multispectral image and the high-resolution panchromatic image based on a principal component analysis method.
Preferably, the full-color sharpening module performs compensation sharpening on the spatial spectrum fusion image based on an edge enhancement method;
wherein the edge reinforcement method comprises: translational and differential edge stiffening and laplace edge stiffening.
The invention has the following technical effects:
according to the invention, based on a plurality of edge detection operators, the spatial information feature extraction is carried out, so that more detail features of the high-resolution panchromatic image are obtained, and the mapping relation between the high-resolution panchromatic image and the low-resolution panchromatic image is facilitated to be obtained;
compared with the traditional super-resolution reconstruction model, the method provided by the invention has the advantages that the spatial information and the spectral information contained in the low-resolution multispectral are reserved to the greatest extent, and the accuracy of information extraction and spatial downscaling is obviously improved;
the invention fuses the super-resolution multispectral image and the high-resolution panchromatic image based on the principal component analysis method, thereby solving the technical problem of information loss caused by the fusion of the traditional remote sensing images;
the full-color sharpening method can be effectively improved and a better full-color sharpening result can be obtained;
the method can obtain accurate space and spectrum information, and can be used in the remote sensing fields such as target identification, ground object classification, environment monitoring and the like.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a system flow diagram in an embodiment of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
As shown in fig. 1, the present embodiment provides a satellite remote sensing image full-color sharpening system, including:
the image data acquisition module is used for acquiring an original image, and the original image comprises a multispectral image and a full-color image;
as a preferable mode of the present embodiment, the image data acquisition module acquires a low-resolution multispectral image based on the first data acquisition unit, and acquires a high-resolution panchromatic image based on the second data acquisition unit; typically, spectral imaging involves multiple narrow spectral bands obtained by the sensor, i.e., it contains multiple components.
As a preferred scheme of the embodiment, the embodiment adopts a remote sensing image set such as SpaceNet on AWS and the like disclosed by a network to construct a data set, and takes an RIO data set in the SpaceNet as an example.
As a preferred scheme of the embodiment, the image preprocessing module is connected with the image data acquisition module and is used for preprocessing the acquired original image;
as a preferable mode of the present embodiment, the image preprocessing module includes an image cropping unit, a spectrum information extraction unit, and a spatial information extraction unit.
Firstly, an obtained original image is subjected to image clipping through an image clipping unit, the clipping size ratio of a multispectral image to a full-color image is 1:4, and as a preferable scheme of the embodiment, the clipping size of the multispectral image is 32 x 32, and the clipping size of the full-color image is 128 x 128;
then extracting the characteristic information of the low-resolution multispectral image and the characteristic information of the high-resolution panchromatic image based on the spectral information extraction unit and the spatial information extraction unit respectively;
as a preferred aspect of the present embodiment, the process of extracting the feature information of the high-resolution full-color image includes: sobel, scharr, laplace, roberts and Prewitt edge detection algorithms were introduced. Combining Sobel, scharr, laplace, roberts with Prewitt operators can effectively detect edges, preserve edges, and sharpen edges.
As a preferred scheme of the embodiment, the edge detection subunit constructs a feature extraction network, receives feature mapping from a certain layer of the network as input, detects and reserves edges by using Sobel, scharr, laplace, roberts and Prewitt operators and a combination operator thereof, extracts texture information, and obtains gradient graphs corresponding to the edge detection operators, wherein the number of channels of the gradient graphs is the same.
As a preferred solution of this embodiment, the convolution subunit performs cascade on a plurality of gradient maps with the same number of channels based on the mixed gradient attention model, and the process for obtaining the high-resolution panchromatic image feature map includes:
the mixed gradient attention model encodes a gradient map obtained based on Sobel, scharr, laplace, roberts and Prewitt operators, redistributes the weight of the feature map, reduces noise and extracts detail features; and carrying out gradient image cascade based on point multiplication operation to obtain a feature image of the full-color image.
As a preferred scheme of the embodiment, the image super-resolution reconstruction module is connected with the image preprocessing module and is used for converting the preprocessed low-resolution image into a high-resolution image;
as a preferred solution of the present embodiment, the image super-resolution reconstruction module includes: a super-resolution reconstruction unit and a transformation model unit;
as a preferable scheme of the present embodiment, the super-resolution reconstruction unit performs a degradation imaging process on the high-resolution panchromatic image after the pretreatment based on operations such as low-pass filtering, downsampling, noise addition, and the like, to obtain a low-resolution panchromatic image of a resolution consistent with the low-resolution multispectral.
As a preferable mode of the present embodiment, a super-resolution multispectral image is obtained based on the transformation model unit.
As a preferable mode of the present embodiment, the transformation model unit includes a model construction subunit and a transformation subunit;
the model construction subunit is used for constructing a support vector machine regression model;
the transformation unit is used for carrying out image contour transformation reconstruction based on the support vector machine regression model to obtain a super-resolution multispectral image.
As a preferred aspect of the present embodiment, the process of acquiring the super-resolution multispectral image based on the transformation model unit includes:
carrying out support vector value transformation on the low-resolution panchromatic image and the preprocessed low-resolution multispectral image to obtain a first coefficient and a second coefficient;
performing support vector machine regression training based on the first coefficient and the second coefficient to obtain a trained support vector machine regression model;
transforming the preprocessed high-resolution panchromatic image based on the trained support vector machine regression model to obtain a predicted value;
and carrying out inverse support vector value transformation based on the predicted value to obtain a super-resolution reconstructed image of the low-resolution multispectral image.
As a preferred scheme of the embodiment, the image fusion module is respectively connected with the image super-resolution reconstruction module and the image preprocessing module and is used for satellite remote sensing image fusion;
as a preferred scheme of the embodiment, the image fusion module performs spatial spectrum fusion on the super-resolution multispectral image and the preprocessed high-resolution panchromatic image based on a fusion unit, and the specific process comprises the following steps:
and carrying out principal component analysis on the super-resolution multispectral image based on a principal component analysis method to obtain a first principal component and other principal components, carrying out histogram matching on the first principal component and the preprocessed high-resolution panchromatic image to obtain a histogram-matched panchromatic image, and replacing the histogram-matched panchromatic image with the first principal component to obtain the high-resolution multispectral fusion image.
As a preferred solution of this embodiment, the full-color sharpening module is connected to the image fusion module, and is used for obtaining a full-color sharpened image.
As a preferred scheme of the embodiment, the full-color sharpening module performs compensation sharpening on the spatial spectrum fusion image based on an edge enhancement method;
wherein the edge reinforcement method comprises: translational and differential edge stiffening and laplace edge stiffening.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (2)
1. A satellite remote sensing image full color sharpening system, comprising: the system comprises an image data acquisition module, an image preprocessing module, an image super-resolution reconstruction module, an image fusion module and a full-color sharpening module;
the image data acquisition module is used for acquiring an original image, wherein the original image comprises a multispectral image and a full-color image;
the image preprocessing module is connected with the image data acquisition module and is used for preprocessing the original image;
the image super-resolution reconstruction module is connected with the image preprocessing module and is used for converting the preprocessed low-resolution image into a high-resolution image;
the image fusion module is respectively connected with the image super-resolution reconstruction module and the image preprocessing module and is used for satellite remote sensing image fusion;
the full-color sharpening module is connected with the image fusion module and is used for obtaining a full-color sharpened image;
the image data acquisition module comprises a first data acquisition unit and a second data acquisition unit;
the first data acquisition unit is used for acquiring a low-resolution multispectral image;
the second data acquisition unit is used for acquiring a high-resolution full-color image;
the image preprocessing module comprises: the device comprises an image clipping unit, a spectrum information extraction unit and a space information extraction unit;
the image clipping unit is respectively connected with the first data acquisition unit and the second data acquisition unit and is used for clipping the low-resolution multispectral image to 32 x 32 size and clipping the high-resolution panchromatic image to 128 x 128 size;
the spectrum information extraction unit is connected with the image clipping unit and is used for extracting the characteristic information of the preprocessed low-resolution multispectral image;
the space information extraction unit is connected with the image clipping unit and is used for extracting the characteristic information of the preprocessed high-resolution full-color image;
the spatial information extraction unit comprises an edge detection subunit and a convolution subunit;
the edge detection subunit is used for obtaining a gradient map corresponding to the edge detection operator based on a plurality of edge detection operators, and the number of channels of the gradient map is the same; the method specifically comprises the following steps: the edge detection subunit detects and reserves edges based on Sobel operators, scharr operators, laplace operators, roberts operators and Prewitt operators and combination operators thereof, extracts texture information, and obtains gradient graphs corresponding to the edge detection operators, wherein the number of channels of the gradient graphs is the same;
the convolution subunit is connected with the edge detection subunit and is used for extracting the characteristics of a plurality of gradient images based on a mixed gradient attention model to obtain a characteristic image of the preprocessed high-resolution full-color image; the method specifically comprises the following steps: the mixed gradient attention model encodes a gradient map obtained based on Sobel, scharr, laplace, roberts and Prewitt operators, redistributes the weight of the feature map, reduces noise and extracts detail features; performing gradient image cascade based on point multiplication operation to obtain a feature image of the full-color image;
the image super-resolution reconstruction module comprises: a super-resolution reconstruction unit and a transformation model unit;
the super-resolution reconstruction unit is connected with the spatial information extraction unit and is used for carrying out degradation imaging processing on the feature map of the preprocessed high-resolution panchromatic image based on low-pass filtering, downsampling and noise increasing operation to obtain a low-resolution panchromatic image;
the transformation model unit is connected with the super-resolution reconstruction unit and is used for obtaining a super-resolution multispectral image;
the transformation model unit comprises a model construction subunit and a transformation subunit;
the model construction subunit is used for constructing a support vector machine regression model;
the transformation subunit is used for carrying out image contour transformation reconstruction based on a support vector machine regression model to obtain a super-resolution multispectral image; the method specifically comprises the following steps: carrying out support vector value transformation on the low-resolution panchromatic image and the preprocessed low-resolution multispectral image to obtain a first coefficient and a second coefficient;
performing support vector machine regression training based on the first coefficient and the second coefficient to obtain a trained support vector machine regression model;
transforming the preprocessed high-resolution panchromatic image based on the trained support vector machine regression model to obtain a predicted value;
based on the predicted value, carrying out inverse transformation of the support vector value to obtain a super-resolution reconstructed image of the low-resolution multispectral image;
the image fusion module comprises a fusion unit;
the fusion unit is used for carrying out space spectrum fusion on the super-resolution multispectral image and the preprocessed high-resolution panchromatic image based on a principal component analysis method, and specifically comprises the following steps: and carrying out principal component analysis on the super-resolution multispectral image based on a principal component analysis method to obtain a first principal component and other principal components, carrying out histogram matching on the first principal component and the preprocessed high-resolution panchromatic image to obtain a histogram-matched panchromatic image, and replacing the histogram-matched panchromatic image with the first principal component to obtain the high-resolution multispectral fusion image.
2. The satellite remote sensing image full-color sharpening system of claim 1, wherein the full-color sharpening module performs compensation sharpening on the spatial spectrum fusion image based on an edge enhancement method;
wherein the edge reinforcement method comprises: translational differential edge stiffening and laplace edge stiffening.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310678358.9A CN116703769B (en) | 2023-06-08 | 2023-06-08 | Satellite remote sensing image full-color sharpening system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310678358.9A CN116703769B (en) | 2023-06-08 | 2023-06-08 | Satellite remote sensing image full-color sharpening system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116703769A CN116703769A (en) | 2023-09-05 |
| CN116703769B true CN116703769B (en) | 2024-03-12 |
Family
ID=87842812
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310678358.9A Active CN116703769B (en) | 2023-06-08 | 2023-06-08 | Satellite remote sensing image full-color sharpening system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116703769B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020975A (en) * | 2012-12-29 | 2013-04-03 | 北方工业大学 | Wharf and ship segmentation method combining multi-source remote sensing image characteristics |
| CN111951202A (en) * | 2020-06-24 | 2020-11-17 | 中国电力科学研究院有限公司 | Power transmission line satellite remote sensing image fusion method and device |
| CN116109535A (en) * | 2022-12-29 | 2023-05-12 | 浙江大华技术股份有限公司 | Image fusion method, device and computer readable storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7769241B2 (en) * | 2007-01-09 | 2010-08-03 | Eastman Kodak Company | Method of sharpening using panchromatic pixels |
-
2023
- 2023-06-08 CN CN202310678358.9A patent/CN116703769B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020975A (en) * | 2012-12-29 | 2013-04-03 | 北方工业大学 | Wharf and ship segmentation method combining multi-source remote sensing image characteristics |
| CN111951202A (en) * | 2020-06-24 | 2020-11-17 | 中国电力科学研究院有限公司 | Power transmission line satellite remote sensing image fusion method and device |
| CN116109535A (en) * | 2022-12-29 | 2023-05-12 | 浙江大华技术股份有限公司 | Image fusion method, device and computer readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| Deep Learning-Based Super-Resolution Reconstruction and Algorithm Acceleration of Mars Hyperspectral CRISM Data;Mingbo Sun等;《remote sensing》;20220625;第1-24页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116703769A (en) | 2023-09-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Deng et al. | Machine learning in pansharpening: A benchmark, from shallow to deep networks | |
| Rao et al. | A residual convolutional neural network for pan-shaprening | |
| CN110428387B (en) | Hyperspectral and full-color image fusion method based on deep learning and matrix decomposition | |
| Fasbender et al. | Bayesian data fusion for adaptable image pansharpening | |
| CN110415199B (en) | Multispectral remote sensing image fusion method and device based on residual learning | |
| CN114119444B (en) | Multi-source remote sensing image fusion method based on deep neural network | |
| Moonon et al. | Remote sensing image fusion method based on nonsubsampled shearlet transform and sparse representation | |
| CN111127374A (en) | Pan-sharing method based on multi-scale dense network | |
| CN106204450B (en) | Based on the sparse multiple dimensioned geometry remote sensing image fusion method from coding of depth | |
| CN106157269B (en) | Full-colour image sharpening method based on the multiple dimensioned group's low-rank decomposition in direction | |
| CN113191325B (en) | Image fusion method, system and application thereof | |
| Zhao et al. | FGF-GAN: A lightweight generative adversarial network for pansharpening via fast guided filter | |
| CN111696043A (en) | Hyperspectral image super-resolution reconstruction algorithm of three-dimensional FSRCNN | |
| Qu et al. | Hyperspectral and panchromatic image fusion via adaptive tensor and multi-scale retinex algorithm | |
| Zhong et al. | Attention_FPNet: Two-branch remote sensing image pansharpening network based on attention feature fusion | |
| Long et al. | Dual self-attention Swin transformer for hyperspectral image super-resolution | |
| Jing et al. | Cloud removal for optical remote sensing imagery using the SPA-CycleGAN network | |
| Lal et al. | Enhanced dictionary based sparse representation fusion for multi-temporal remote sensing images | |
| Lei et al. | Convolution neural network with edge structure loss for spatiotemporal remote sensing image fusion | |
| CN116703769B (en) | Satellite remote sensing image full-color sharpening system | |
| Sun et al. | A two-stage spatiotemporal fusion method for remote sensing images | |
| CN114511470B (en) | Attention mechanism-based double-branch panchromatic sharpening method | |
| Li et al. | Model-based variational pansharpening method with fast generalized intensity–hue–saturation | |
| CN114638761A (en) | Hyperspectral image panchromatic sharpening method, device and medium | |
| CN109785253B (en) | Panchromatic sharpening post-processing method based on enhanced back projection |
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 |