CN109492527B - A kind of remote sensing images sub-pixed mapping localization method based on panchromatic sharpening technique - Google Patents

A kind of remote sensing images sub-pixed mapping localization method based on panchromatic sharpening technique Download PDF

Info

Publication number
CN109492527B
CN109492527B CN201811138541.5A CN201811138541A CN109492527B CN 109492527 B CN109492527 B CN 109492527B CN 201811138541 A CN201811138541 A CN 201811138541A CN 109492527 B CN109492527 B CN 109492527B
Authority
CN
China
Prior art keywords
sub
image
resolution
pixed mapping
remote sensing
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201811138541.5A
Other languages
Chinese (zh)
Other versions
CN109492527A (en
Inventor
王鹏
张弓
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing University of Aeronautics and Astronautics
Original Assignee
Nanjing University of Aeronautics and Astronautics
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nanjing University of Aeronautics and Astronautics filed Critical Nanjing University of Aeronautics and Astronautics
Priority to CN201811138541.5A priority Critical patent/CN109492527B/en
Publication of CN109492527A publication Critical patent/CN109492527A/en
Application granted granted Critical
Publication of CN109492527B publication Critical patent/CN109492527B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/13—Satellite images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • 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
    • G06T2207/10024—Color 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
    • G06T2207/10—Image acquisition modality
    • G06T2207/10032—Satellite or aerial image; Remote sensing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30181—Earth observation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/194—Terrestrial scenes using hyperspectral data, i.e. more or other wavelengths than RGB

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Astronomy & Astrophysics (AREA)
  • Remote Sensing (AREA)
  • Multimedia (AREA)
  • Image Processing (AREA)

Abstract

The invention discloses a kind of remote sensing images sub-pixed mapping localization method based on panchromatic sharpening technique, include the following steps: that (1) merges the remote sensing images of original low-resolution with the high spatial resolution full-colour image from the same area by the panchromatic sharpening technique for substituting CS based on ingredient, generates the remote sensing images with high spectral resolution and spatial resolution；(2) remote sensing images with high spectral resolution and spatial resolution obtained by panchromatic sharpening technique mix technology by spectrum solution and obtain the high-resolution abundance image comprising abundant original image sky-spectrum information；(3) according to the soft attribute value of sub-pixed mapping provided comprising the high-resolution abundance image for enriching sky-spectrum information, hard attribute value is assigned in each sub-pixed mapping by classification distribution method, obtains final sub-pixed mapping positioning result.The present invention can more make full use of sky-spectrum information of original image, obtain the higher result of positioning accuracy.

Description

A kind of remote sensing images sub-pixed mapping localization method based on panchromatic sharpening technique
Technical field
The present invention relates to remote sensing information process technical field, especially a kind of remote sensing images based on panchromatic sharpening technique are sub- Pixel positioning method.
Background technique
Mixed pixel caused by the diversity of Land cover types and the limitation of sensor instantaneous field of view is to restrict height The principal element of spectrum picture spatial resolution.These restrict so that accurately ground object target identification produce very big difficulty, And accurately target identification suffers from highly important meaning to industry, agricultural, environment and military affairs etc..Therefore, now One of the hot issue of remote sensing information process technical field is exactly to handle mixed pixel to improve ground object target accuracy of identification.Sub- picture Each mixed pixel is subdivided into sub- picture by certain ratio scale by first location technology (also referred to as superresolution mapping technology) Member and the atural object classification for estimating each sub-pixed mapping, realize from the abundance image (spectrum solution mixes result) of low resolution and are transformed into height The process of the ground object target identification image of resolution ratio.
Doctor Tatem proposes a series of sub-pixed mapping localization methods based on Hopfield neural network model.Muad etc. Continued discussing different parameter settings in the sub-pixed mapping localization method based on Hopfield neural network model to identification not With the ability of scaled target.It is fixed that doctor Mertens of Ghent, Belgium university proposes the sub-pixed mapping based on spatial attraction model Position method and the sub-pixed mapping localization method based on BP neural network.Later doctor Mertens is again by the network and wavelet transformation phase In conjunction with to excavating more spatial distribution details, and then improve this method mesh positioning accuracy.However these sub-pixed mappings position Method, which is directly acted on, mixes the coarse abundance image that technology obtains by spectrum solution, due to original high spectrum image spatial resolution Low and current spectrum solution mixes the limitation of technology, so that abundance image is difficult sufficiently to carry sky-spectrum information of original image, influences Final positioning accuracy.
Summary of the invention
Technical problem to be solved by the present invention lies in provide a kind of remote sensing images sub-pixed mapping based on panchromatic sharpening technique Localization method can more make full use of sky-spectrum information of original image, obtain the higher result of positioning accuracy.
In order to solve the above technical problems, the present invention provides a kind of remote sensing images sub-pixed mapping positioning based on panchromatic sharpening technique Method includes the following steps:
(1) remote sensing images of original low-resolution and the high spatial resolution full-colour image from the same area are passed through into base It is merged in the panchromatic sharpening technique of ingredient substitution CS, generates the remote sensing figure with high spectral resolution and spatial resolution Picture；
(2) pass through light by the remote sensing images with high spectral resolution and spatial resolution that panchromatic sharpening technique obtains Spectrum solves mixed technology and obtains the high-resolution abundance image comprising abundant original image sky-spectrum information；
(3) according to the soft attribute value of sub-pixed mapping (each Asia provided comprising the high-resolution abundance image for enriching sky-spectrum information Pixel belongs to the probability membership values of each classification), hard attribute value (class label) is assigned to by classification distribution method each In sub-pixed mapping, final sub-pixed mapping positioning result is obtained.
Preferably, in step (1), the panchromatic sharpening technique based on ingredient substitution CS is merged specifically: CS will be original Low resolution remote sensing images Y projection is to another space, so that space structure and spectral information to be separated in heterogeneity；With Afterwards, using high spatial resolution full-colour image P replacement include the ingredient of space structure, and then enhance the space point of transform domain image Resolution, full-colour image be replaced by point between correlation it is bigger, the spectrum distortion that fusion method introduces is smaller；It is sent out in replacement Histogram Matching is carried out to full-colour image and selected ingredient before life, will show and to replace by the full-colour image of Histogram Matching The identical mean value of the ingredient changed and variance；Finally, obtaining blending image using inverse transformation, completes panchromatic based on CS and sharpened Journey；Panchromatic sharpening model based on CS can generally be indicated by following formula:
Wherein b (b=1,2 ..., N, N are remote sensing images wave band sum) indicates that b spectral band, Y represent original low latitude Between resolution remote sensing images,It is the image obtained after panchromatic sharpening,Indicate b spectral band by the figure after panchromatic sharpening Picture,Image after representing b wave band original low-resolution remote-sensing picture interpolation to full-colour image size, gb=[g1, g2,...,gN] it is gain vector, P represents high spatial resolution full-colour image, while I is defined as:
Wherein weight vector wb=[w1,...,wi,...,wN]TThe light being used between measure spectrum wave band and full-colour image Spectrum overlapping.
Preferably, in step (2), spectrum solution mixes technology specifically: the image that panchromatic sharpening obtains is utilized based on linear mixed The spectrum solution mixing method of molding type obtains the high-resolution abundance image of each classification, and linear mixed model is assumed in mixed pixel The linear syntagmatic of ratio shared by pixel of atural object classification and the category, passing through formula (3) indicates:
WhereinIt is the image obtained after panchromatic sharpening；The matrix that E is made of spectrum end member；X is that sub-pixed mapping belongs to often The probability value of a atural object classification, the i.e. soft attribute value of sub-pixed mapping；N is random noise.Linear unmixing model usually needs to utilize minimum Two methods multiplied seek the optimal estimation in the smallest situation of random noise n, while also needing additional staff cultivation condition (normalizing Change and nonnegativity restriction) to meet actual physical meaning.Normalization constraint condition refers to that the sum of Abundances of all categories are 1；It is non-negative Property constraint condition refer to that Abundances of all categories are greater than 0 and less than 1.
Preferably, in step (3), classification distribution method specifically: soft according to the sub-pixed mapping on high-resolution abundance image Class label is assigned in each sub-pixed mapping by attribute value using the classification distribution method based on linear optimization technology, thus real Existing sub-pixed mapping positioning；Classification distribution method based on linear optimization technology is that the mathematical model of foundation formula (4) makes all sub- pictures The sum of the soft attribute value of member tJIt maximizes under conditions of carrying out, carries out classification distribution；
Wherein ratio scale is S, then each thick pixel will be divided into S × S sub-pixed mapping；CJIndicate a mixing picture Member, J=1,2 ..., M, M are the numbers of mixed pixel in original coarse image；cjRepresent a sub-pixed mapping, j=1,2 ..., MS2,MS2It is the number of sub-pixed mapping；Hk(cj) indicate sub-pixed mapping cjBelong to the soft attribute value of sub-pixed mapping of k-th of classification, k=1, 2 ..., K, K are the numbers of atural object classification；Hk(cj) image that obtains after namely panchromatic sharpeningIt is obtained after being mixed by spectrum solution Value；X is defined simultaneouslyk(cj) are as follows:
The model is to make the sum of the soft attribute value of all sub-pixed mappings t according to formula (4)JReach maximum value, by all sub- pictures First whole progress classification distribution.
The invention has the benefit that method of the invention can more make full use of sky-spectrum information of original image, obtain Obtain the higher result of positioning accuracy.
Detailed description of the invention
Fig. 1 is that the present invention is based on the panchromatic sharpening technique schematic illustrations of CS.
Fig. 2 is the method for the present invention flow diagram.
Fig. 3 (a) is the evaluation reference image schematic diagram of the multi-spectral remote sensing image data set in Rome area.
Fig. 3 (b) is the sub-pixed mapping positioning based on edge-oriented interpolation of the multi-spectral remote sensing image data set in Rome area Method sub-pixed mapping positioning result schematic diagram.
Fig. 3 (c) is the multi-spectral remote sensing image data set in Rome area based on blending image Hopfield nerve The sub-pixed mapping localization method positioning result schematic diagram of network model.
Fig. 3 (d) is the sub-pixed mapping positioning based on panchromatic sharpening technique of the multi-spectral remote sensing image data set in Rome area Method positioning result schematic diagram.
Fig. 4 (a) is the evaluation reference image schematic diagram of the high-spectrum remote sensing data set of Washington Region.
Fig. 4 (b) is that the sub-pixed mapping based on edge-oriented interpolation of the high-spectrum remote sensing data set of Washington Region is fixed Position method sub-pixed mapping positioning result schematic diagram.
Fig. 4 (c) is that the sub-pixed mapping based on panchromatic sharpening technique of the high-spectrum remote sensing data set of Washington Region is fixed Position method positioning result schematic diagram.
Fig. 4 (d) is that the sub-pixed mapping based on panchromatic sharpening technique of the high-spectrum remote sensing data set of Washington Region is fixed Position method positioning result schematic diagram.
Fig. 5 (a) is PCC (%) schematic diagram of three kinds of algorithms relevant to ratio scale S of the invention.
Fig. 5 (b) is the Kappa schematic diagram of three kinds of algorithms relevant to ratio scale S of the invention.
Specific embodiment
As shown in Figure 1, a kind of remote sensing images sub-pixed mapping localization method based on panchromatic sharpening technique, includes the following steps:
(1) input is the height of original low-resolution remote sensing images Y and size MS × NS from the same area of size M × N Spatial resolution full-colour image P passes through the panchromatic sharpening technique based on ingredient substitution (component substitution, CS) It is merged, generates the panchromatic sharpening result with high spectral resolution and spatial resolution
CS is by original original low-resolution remote sensing images Y projection to another space, to believe space structure and spectrum Breath is separated in heterogeneity.It then, include the ingredient of space structure using high spatial resolution full-colour image P replacement, in turn Enhance the spatial resolution of transform domain image.Full-colour image be replaced by point between correlation it is bigger, fusion method introduces Spectrum distortion it is smaller.For this purpose, carrying out Histogram Matching to full-colour image and selected ingredient before replacement occurs, pass through histogram Mean value identical with the ingredient to be replaced and variance will be shown by scheming matched full-colour image.Finally, being merged using inverse transformation Image completes the panchromatic sharpening process based on CS.Panchromatic sharpening model based on CS can generally be indicated by following formula:
Wherein b (b=1,2 ..., N, N are remote sensing images wave band sum) indicates that b spectral band, Y represent original low latitude Between resolution remote sensing images,It is the image obtained after panchromatic sharpening,Indicate b spectral band by the figure after panchromatic sharpening Picture,Image after representing b wave band original low-resolution remote-sensing picture interpolation to full-colour image size, gb=[g1, g2,...,gN] it is gain vector, P represents high spatial resolution full-colour image, while I is defined as:
Wherein weight vector wb=[w1,...,wi,...,wN]TThe light being used between measure spectrum wave band and full-colour image Spectrum overlapping.
(2) the panchromatic sharpening result obtained by panchromatic sharpening techniqueIt is mixed by the spectrum solution based on linear mixed model Method obtains the K panel height resolution ratio abundance image H comprising abundant original image sky-spectrum informationk(k=1,2 ..., K, K are remote sensing Classification sum in image).
(3) according to the high-resolution abundance image H comprising enriching sky-spectrum informationkThe soft attribute value H of the sub-pixed mapping of offerk(cj) (the probability membership values that each sub-pixed mapping belongs to each classification) pass through base under the premise of each classification sub-pixed mapping is fixed number of Hard attribute value (class label) is assigned in each sub-pixed mapping in the classification distribution method of linear optimization technology, is obtained final Sub-pixed mapping positioning result.
Remote sensing images sub-pixed mapping proposed by the present invention based on panchromatic sharpening technique positions (Subpixel Mapping Based on Pansharpening Technology for Remote Sensing Image, PAN) method realize block diagram As shown in Figure 2.
Fig. 3 (a)-Fig. 3 (d) is the sub-pixed mapping positioning result of the multi-spectral remote sensing image data set in Rome area.Wherein: a) Evaluation reference image, b) based on edge-oriented interpolation sub-pixed mapping localization method (Edge-directed Interpolation, EI), c) based on sub-pixed mapping localization method (the Hopfield neural with blending image Hopfield neural network model Network with fused image, HNNF), d) the sub-pixed mapping localization method (PAN) based on panchromatic sharpening technique.
Fig. 4 (a)-Fig. 4 (d) is the sub-pixed mapping positioning result of the high-spectrum remote sensing data set of Washington Region.Wherein: A) evaluation reference image, b) the sub-pixed mapping localization method (Edge-directed based on edge-oriented interpolation Interpolation, EI), c) based on the sub-pixed mapping localization method with blending image Hopfield neural network model (Hopfield neural network with fused image, HNNF), d) sub-pixed mapping based on panchromatic sharpening technique is fixed Position method (PAN).
Fig. 5 (a) is the PCC (%) for being three kinds of algorithms relevant to ratio scale S, and Fig. 5 (b) is to be and ratio scale S phase The Kappa of the three kinds of algorithms closed.
We prove the height of proposed method by the way that proposition method of the present invention is applied to two groups of different remote sensing images Effect property.In order to be quantitatively evaluated, to original fine remote sensing images progress down-sampling to generate simulation low-resolution image, the One group of image drop sampling ratio and magnification ratio take S=4, for performance of the test method under different proportion scale, second group Image drop sampling ratio and magnification ratio take S=3, S=5 and S=8.Since in the case where down-sampling, the soil of sub-pixel It is known for covering class, therefore convenient for directly influence of the assessment Images Registration to technology.Meanwhile in order to avoid full-colour image Influence of the Acquisition Error to final positioning result is only considered influence of the panchromatic sharpening technique to positioning result, is defended using IKONOS The spectral response of star generates suitable synthesis full-colour image.It is evaluated using each classification positioning accuracy and overall accuracy (percentage of correctly classified, PCC) and Kappa coefficient carry out quantitative assessment.
In battery of tests, target is the multi-spectral remote sensing image data set in Rome somewhere, and Fig. 3 (a)-Fig. 3 (d) is pair The sub-pixed mapping positioning result of low-resolution image, it can be seen from the figure that the result of PAN method is closest to reference picture, effect More preferably.Table 1 is that the positioning accuracy of each classification of various methods and overall accuracy evaluate PCC in first group of experiment, is further tested Advantage of the method proposed in sub-pixed mapping positioning is demonstrate,proved.
High-spectrum remote sensing of the width from Washington Region is chosen in second group of experiment.Fig. 4 (a)-Fig. 4 (d) is illustrated The positioning result of three kinds of methods.Fig. 5 (a) and Fig. 5 (b) is the PCC (%) and Kappa of three kinds of methods under three kinds of ratio scale. Similar to first group of experiment conclusion, there are clear superiorities still in sub-pixed mapping localization method by the method PAN proposed.
The data analysis result (%) of 1 first group of various method of experiment of table

Claims (3)

1. a kind of remote sensing images sub-pixed mapping localization method based on panchromatic sharpening technique, which comprises the steps of:
(1) by the remote sensing images of original low-resolution and the high spatial resolution full-colour image from the same area pass through based at Divide the panchromatic sharpening technique of substitution CS to be merged, generates the remote sensing images with high spectral resolution and spatial resolution；Base It is merged in the panchromatic sharpening technique of ingredient substitution CS specifically: CS is by original low-resolution remote sensing images Y projection to another A space, so that space structure and spectral information to be separated in heterogeneity；Then, high spatial resolution full-colour image is utilized P replacement includes the ingredient of space structure, and then enhances the spatial resolution of transform domain image, full-colour image and is replaced by point it Between correlation it is bigger, fusion method introduce spectrum distortion it is smaller；To full-colour image and selected ingredient before replacement occurs Histogram Matching is carried out, mean value identical with the ingredient to be replaced and variance will be shown by the full-colour image of Histogram Matching； Finally, obtaining blending image using inverse transformation, the panchromatic sharpening process based on CS is completed；Panchromatic sharpening model based on CS is general It can be indicated by following formula:
Wherein b (b=1,2 ..., N, N are remote sensing images wave band sum) indicates that b spectral band, Y represent original low spatial point Resolution remote sensing images,It is the image obtained after panchromatic sharpening,Indicate b spectral band by the image after panchromatic sharpening, Image after representing b wave band original low-resolution remote-sensing picture interpolation to full-colour image size, gb=[g1,g2,...,gN] be Gain vector, P represents high spatial resolution full-colour image, while I is defined as:
Wherein weight vector wb=[w1,...,wi,...,wN]TThe spectrum weight being used between measure spectrum wave band and full-colour image It is folded；
(2) pass through spectrum solution by the remote sensing images with high spectral resolution and spatial resolution that panchromatic sharpening technique obtains Mixed technology obtains the high-resolution abundance image comprising abundant original image sky-spectrum information；
(3) according to the soft attribute value of sub-pixed mapping provided comprising the high-resolution abundance image for enriching sky-spectrum information, pass through classification point Hard attribute value is assigned in each sub-pixed mapping by method of completing the square, obtains final sub-pixed mapping positioning result.
2. the remote sensing images sub-pixed mapping localization method based on panchromatic sharpening technique as described in claim 1, which is characterized in that step Suddenly in (2), spectrum solution mixes technology specifically: the image that panchromatic sharpening obtains utilizes the mixed side of the spectrum solution based on linear mixed model Method obtains the high-resolution abundance image of each classification, and linear mixed model assumes the atural object classification and the category in mixed pixel The linear syntagmatic of ratio shared by pixel is indicated by formula (3):
WhereinIt is the image obtained after panchromatic sharpening；The matrix that E is made of spectrum end member；X is that sub-pixed mapping belongs to each atural object The soft attribute value of the probability value of classification, i.e. sub-pixed mapping；N is random noise.
3. the remote sensing images sub-pixed mapping localization method based on panchromatic sharpening technique as described in claim 1, which is characterized in that step Suddenly in (3), classification distribution method specifically: according to the soft attribute value of sub-pixed mapping on high-resolution abundance image, using based on line Property optimisation technique classification distribution method class label is assigned in each sub-pixed mapping, thus realize sub-pixed mapping position；It is based on The classification distribution method of linear optimization technology is that the mathematical model of foundation formula (4) makes the sum of the soft attribute value of all sub-pixed mappings tJMost Under conditions of bigization carries out, classification distribution is carried out；
Wherein ratio scale is S, then each thick pixel will be divided into S × S sub-pixed mapping；CJIndicate a mixed pixel, J= 1,2 ..., M, M are the numbers of mixed pixel in original coarse image；cjRepresent a sub-pixed mapping, j=1,2 ..., MS2,MS2 It is the number of sub-pixed mapping；Hk(cj) indicate sub-pixed mapping cjBelong to the soft attribute value of sub-pixed mapping of k-th of classification, k=1,2 ..., K, K It is the number of atural object classification；Hk(cj) image that obtains after namely panchromatic sharpeningThe value obtained after mixed by spectrum solution；Simultaneously Define xk(cj) are as follows:
The model is to make the sum of the soft attribute value of all sub-pixed mappings t according to formula (4)JReach maximum value, all sub-pixed mappings are whole Carry out classification distribution.
CN201811138541.5A 2018-09-28 2018-09-28 A kind of remote sensing images sub-pixed mapping localization method based on panchromatic sharpening technique Active CN109492527B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811138541.5A CN109492527B (en) 2018-09-28 2018-09-28 A kind of remote sensing images sub-pixed mapping localization method based on panchromatic sharpening technique

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811138541.5A CN109492527B (en) 2018-09-28 2018-09-28 A kind of remote sensing images sub-pixed mapping localization method based on panchromatic sharpening technique

Publications (2)

Publication Number Publication Date
CN109492527A CN109492527A (en) 2019-03-19
CN109492527B true CN109492527B (en) 2019-09-10

Family

ID=65690031

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811138541.5A Active CN109492527B (en) 2018-09-28 2018-09-28 A kind of remote sensing images sub-pixed mapping localization method based on panchromatic sharpening technique

Country Status (1)

Country Link
CN (1) CN109492527B (en)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110210300B (en) * 2019-04-26 2023-05-26 南京航空航天大学 Urban construction sub-pixel positioning method integrating multispectral image space-spectrum information
CN110298883B (en) * 2019-05-13 2022-06-24 南京航空航天大学 Remote sensing image sub-pixel positioning method based on extended random walk algorithm
CN112883823A (en) * 2021-01-21 2021-06-01 南京航空航天大学 Land cover category sub-pixel positioning method based on multi-source remote sensing data fusion
CN112991288B (en) * 2021-03-09 2022-11-18 东南大学 Hyperspectral remote sensing image fusion method based on abundance image sharpening reconstruction
CN113902650B (en) * 2021-12-07 2022-04-12 南湖实验室 Remote sensing image sharpening method based on parallel deep learning network architecture
CN116935214B (en) * 2023-06-27 2024-04-12 福建鼎旸信息科技股份有限公司 Space-time spectrum fusion method for satellite multi-source remote sensing data

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102446278A (en) * 2011-09-14 2012-05-09 哈尔滨工程大学 Multitemporal remote sensing image-based subpixel positioning method
CN104851077A (en) * 2015-06-03 2015-08-19 四川大学 Adaptive remote sensing image panchromatic sharpening method

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10176603B2 (en) * 2013-08-07 2019-01-08 The University Of Chicago Sinogram (data) domain pansharpening method and system for spectral CT

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102446278A (en) * 2011-09-14 2012-05-09 哈尔滨工程大学 Multitemporal remote sensing image-based subpixel positioning method
CN104851077A (en) * 2015-06-03 2015-08-19 四川大学 Adaptive remote sensing image panchromatic sharpening method

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
"Revealing Implicit Assumptions of the Component Substitution Pansharpening Methods";Bin Xie etc.;《remote sensing》;20170505;第443卷(第9期);论文第1-2.1节
"基于光谱和空间特性的高光谱解混方法";贾森等;《深圳大学学报理工版》;20090731;第26卷(第3期);论文第1节
"遥感影像亚像元定位研究综述";凌峰等;《中国图像图形学报》;20110831;第16卷(第8期);论文第1,2.1节

Also Published As

Publication number Publication date
CN109492527A (en) 2019-03-19

Similar Documents

Publication Publication Date Title
CN109492527B (en) A kind of remote sensing images sub-pixed mapping localization method based on panchromatic sharpening technique
CN110070518B (en) Hyperspectral image super-resolution mapping method based on dual-path support
He et al. HyperPNN: Hyperspectral pansharpening via spectrally predictive convolutional neural networks
Han et al. SSF-CNN: Spatial and spectral fusion with CNN for hyperspectral image super-resolution
CN100514085C (en) Method for enhancing distinguishability cooperated with space-optical spectrum information of high optical spectrum image
Song et al. Spatiotemporal satellite image fusion through one-pair image learning
Xu et al. Sub-pixel mapping based on a MAP model with multiple shifted hyperspectral imagery
CN110046673A (en) No reference tone mapping graph image quality evaluation method based on multi-feature fusion
Song et al. Improving the spatial resolution of landsat TM/ETM+ through fusion with SPOT5 images via learning-based super-resolution
Theiler et al. Local coregistration adjustment for anomalous change detection
CN110415199B (en) Multispectral remote sensing image fusion method and device based on residual learning
CN101916436B (en) Multi-scale spatial projecting and remote sensing image fusing method
CN107464222B (en) Based on tensor space without reference high dynamic range images method for evaluating objective quality
CN108182449A (en) A kind of hyperspectral image classification method
CN110084747A (en) Spatial attraction model sub-pixed mapping localization method under being supported based on panchromatic sharpening technique
CN109191450A (en) A kind of remote sensing image fusion quality evaluating method
Meng et al. A blind full-resolution quality evaluation method for pansharpening
Guerra et al. A computationally efficient algorithm for fusing multispectral and hyperspectral images
Zhou et al. No-reference quality assessment for pansharpened images via opinion-unaware learning
CN105976351A (en) Central offset based three-dimensional image quality evaluation method
CN108921035A (en) Sub-pixed mapping localization method and system based on spatial attraction and pixel concentration class
CN110298883A (en) A kind of remote sensing images sub-pixed mapping localization method based on extension Random Walk Algorithm
Yang et al. FG-GAN: a fine-grained generative adversarial network for unsupervised SAR-to-optical image translation
Li et al. Spatial-temporal super-resolution land cover mapping with a local spatial-temporal dependence model
Eismann Resolution enhancement of hyperspectral imagery using maximum a posteriori estimation with a stochastic mixing model

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