CN104463823A - Compressed sensing remote sensing image reconstruction algorithm based on gradient information of reference image - Google Patents
Compressed sensing remote sensing image reconstruction algorithm based on gradient information of reference image Download PDFInfo
- Publication number
- CN104463823A CN104463823A CN201410852665.5A CN201410852665A CN104463823A CN 104463823 A CN104463823 A CN 104463823A CN 201410852665 A CN201410852665 A CN 201410852665A CN 104463823 A CN104463823 A CN 104463823A
- Authority
- CN
- China
- Prior art keywords
- image
- target image
- gradient information
- sparse
- constraint
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Abstract
The invention discloses a compressed sensing remote sensing image reconstruction algorithm based on gradient information of a reference image. The compressed sensing remote sensing image reconstruction algorithm includes the steps that an initial value is set for the sparse coefficient of a pre-allocated target image, and a sparse constraint of the target image is set; the sparse coefficient of the pre-allocated reference image matched with the target image is calculated, and a sparse constraint of the reference image is set; gradient information of the target image and the gradient information of the reference image are calculated according to the sparse coefficient and the sparse constraint of the target image and the sparse coefficient and the sparse constraint of the reference image; a unit vector perpendicular to the gradient information of the reference image is set according to the gradient information of the reference image; based on the steps, a constraint item is constructed and added into the target image for reconstruction; based on a pre-allocated optimization method, a pre-allocated signal of the target image is reconstructed. The compressed sensing remote sensing image reconstruction algorithm has the advantages that the gradient information of the reference image serves as constraint information and is added into the reconstruction process of the target image, and the image reconstruction accuracy is improved.
Description
Technical field
The present invention relates to a kind of based on the compressed sensing remote sensing images reconstruction algorithm with reference to image gradient information.
Background technology
In remote sensing image application, the same area comprises the image of multi-source, multidate usually, although the spectrum between these images is different, but there is very large similarity in its grain direction, therefore need structure one to punish bound term, carry out the process of reconstruction of constrained objective image with the gradient information with reference to image.
For the problem in correlation technique, at present effective solution is not yet proposed.
Summary of the invention
The object of this invention is to provide a kind of based on the compressed sensing remote sensing images reconstruction algorithm with reference to image gradient information, with reference to the gradient information of image as constraint information, add the process of reconstruction of target image, improve the reconstruction precision of image.
The object of the invention is to be achieved through the following technical solutions:
Based on the compressed sensing remote sensing images reconstruction algorithm with reference to image gradient information, comprise the following steps:
Step 1: initial value is arranged to the sparse coefficient of pre-configured target image, and the sparse constraint of Offered target image; Calculate the sparse coefficient of the pre-configured reference image matched with target image, and the sparse constraint with reference to image is set;
Step 2: calculate described target image and the gradient information with reference to image according to the sparse coefficient of target image and sparse constraint and with reference to the sparse coefficient of image and sparse constraint;
Step 3: according to the described gradient information with reference to image, arranges a vector of unit length perpendicular with the gradient information of described reference image;
Step 4: according to step 1 to step 3, builds the bound term matched with target image, bound term is joined in target image and rebuild;
Step 5: based on pre-configured optimization method, enters to rebuild to the pre-configured signal of target image.
Further, in steps of 5, pre-configured optimization method comprises conjugate gradient Conjunction Gradient optimization method and division Donald Bragg graceful Bregman Split optimization method.
Beneficial effect of the present invention is: with reference to the gradient information of image as constraint information, add the process of reconstruction of target image, effectively raise the reconstruction precision of image.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is a kind of process flow diagram based on the compressed sensing remote sensing images reconstruction algorithm with reference to image gradient information according to the embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, the every other embodiment that those of ordinary skill in the art obtain, all belongs to the scope of protection of the invention.
As shown in Figure 1, a kind of compressed sensing remote sensing images reconstruction algorithm based on reference image gradient information according to the embodiment of the present invention, comprises the following steps:
Step 1: initial value is arranged to the sparse coefficient of pre-configured target image, and the sparse constraint of Offered target image; Calculate the sparse coefficient of the pre-configured reference image matched with target image, and the sparse constraint with reference to image is set;
Step 2: calculate described target image and the gradient information with reference to image according to the sparse coefficient of target image and sparse constraint and with reference to the sparse coefficient of image and sparse constraint;
Step 3: according to the described gradient information with reference to image, arranges a vector of unit length perpendicular with the gradient information of described reference image;
Step 4: according to step 1 to step 3, builds the bound term matched with target image, bound term is joined in target image and rebuild;
Step 5: based on pre-configured optimization method, enters to rebuild to the pre-configured signal of target image.
In steps of 5, pre-configured optimization method comprises conjugate gradient Conjunction Gradient optimization method and division Donald Bragg graceful Bregman Split optimization method.
During embody rule,
1) initial value of given target image sparse coefficient
, setting sparse constraint
;
2) gradient information of computing reference image
;
3) one is arranged perpendicular to the vector of unit length with reference to image gradient:;
4) by 1)-3) build bound term
, and added the process of reconstruction of target image, such objective function becomes:
5) signal reconstruction is carried out based on optimization methods such as the optimization method of pre-configured conjugate gradient Conjunction Gradient or the optimization methods of the graceful Bregman Split of division Donald Bragg.
In sum, by means of technique scheme of the present invention, by the gradient information with reference to image as constraint information, add the process of reconstruction of target image, effectively raise the reconstruction precision of image, tremendous contribution has been made to the process of image data.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (2)
1., based on the compressed sensing remote sensing images reconstruction algorithm with reference to image gradient information, it is characterized in that, comprise the following steps:
Step 1: initial value is arranged to the sparse coefficient of pre-configured target image, and the sparse constraint of Offered target image; Calculate the sparse coefficient of the pre-configured reference image matched with target image, and the sparse constraint with reference to image is set;
Step 2: calculate described target image and the gradient information with reference to image according to the sparse coefficient of target image and sparse constraint and with reference to the sparse coefficient of image and sparse constraint;
Step 3: according to the described gradient information with reference to image, arranges a vector of unit length perpendicular with the gradient information of described reference image;
Step 4: according to step 1 to step 3, builds the bound term matched with target image, bound term is joined in target image and rebuild;
Step 5: based on pre-configured optimization method, enters to rebuild to the pre-configured signal of target image.
2. according to claim 1 based on the compressed sensing remote sensing images reconstruction algorithm with reference to image gradient information, it is characterized in that, in steps of 5, pre-configured optimization method comprises conjugate gradient Conjunction Gradient optimization method and division Donald Bragg graceful Bregman Split optimization method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410852665.5A CN104463823A (en) | 2014-12-31 | 2014-12-31 | Compressed sensing remote sensing image reconstruction algorithm based on gradient information of reference image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410852665.5A CN104463823A (en) | 2014-12-31 | 2014-12-31 | Compressed sensing remote sensing image reconstruction algorithm based on gradient information of reference image |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104463823A true CN104463823A (en) | 2015-03-25 |
Family
ID=52909810
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410852665.5A Pending CN104463823A (en) | 2014-12-31 | 2014-12-31 | Compressed sensing remote sensing image reconstruction algorithm based on gradient information of reference image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104463823A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105551000A (en) * | 2015-12-11 | 2016-05-04 | 中国科学院遥感与数字地球研究所 | Remote sensing image reconstruction method based on reference image structure constraint and non-convex low rank constraint |
CN105741240A (en) * | 2016-01-18 | 2016-07-06 | 中国科学院遥感与数字地球研究所 | Remote sensing image reconstruction method based on reference image texture constraint and non-convex low-rank constraint |
CN106023274A (en) * | 2016-01-16 | 2016-10-12 | 中国科学院遥感与数字地球研究所 | Compressed sensing image reconstruction method combining with expert field filter sparse constraint |
-
2014
- 2014-12-31 CN CN201410852665.5A patent/CN104463823A/en active Pending
Non-Patent Citations (4)
Title |
---|
HAO GENG等: "COMPRESSED SENSING BASED REMOTE SENSING IMAGE RECONSTRUCTION USING AN AUXILIARY IMAGE AS PRIORS", 《2014 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM(IGARSS)》 * |
LIZHE WANG等: "Compressed Sensing of a Remote Sensing Image Based on the Priors of the Reference Image", 《HTTP://IEEEXPLORE.IEEE.ORG/DOCUMENT/6919260》 * |
PENG LIU等: "COMPRESSIVE SENSING OF MULTISPECTRAL IMAGE BASED ON PCA AND BREGMAN SPLIT", 《2013 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM(IGARSS)》 * |
PENG LIU等: "Compressive Sensing of Noisy Multispectral Images", 《IEEE GEOSCIENCE AND REMOTE SENSING LETTERS》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105551000A (en) * | 2015-12-11 | 2016-05-04 | 中国科学院遥感与数字地球研究所 | Remote sensing image reconstruction method based on reference image structure constraint and non-convex low rank constraint |
CN105551000B (en) * | 2015-12-11 | 2019-09-20 | 中国科学院遥感与数字地球研究所 | Remote sensing images method for reconstructing based on the constraint of reference image and the constraint of non-convex low-rank |
CN106023274A (en) * | 2016-01-16 | 2016-10-12 | 中国科学院遥感与数字地球研究所 | Compressed sensing image reconstruction method combining with expert field filter sparse constraint |
CN106023274B (en) * | 2016-01-16 | 2019-03-15 | 中国科学院遥感与数字地球研究所 | A kind of compressed sensing image rebuilding method of combination expert filter sparse constraint |
CN105741240A (en) * | 2016-01-18 | 2016-07-06 | 中国科学院遥感与数字地球研究所 | Remote sensing image reconstruction method based on reference image texture constraint and non-convex low-rank constraint |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Ahmad et al. | Existence of solutions for nonlinear fractional q-difference integral equations with two fractional orders and nonlocal four-point boundary conditions | |
US20200334819A1 (en) | Image segmentation apparatus, method and relevant computing device | |
D’Odorico et al. | Asymptotic freedom in Hořava-Lifshitz gravity | |
WO2019120320A3 (en) | System and method for parallel-processing blockchain transactions | |
EP4336411A3 (en) | Performing kernel striding in hardware | |
Tang et al. | Depth recovery and refinement from a single image using defocus cues | |
CN104463823A (en) | Compressed sensing remote sensing image reconstruction algorithm based on gradient information of reference image | |
JP2017188137A5 (en) | ||
Hecht et al. | Incompressible limit of a mechanical model for tissue growth with non-overlapping constraint | |
PH12016501202A1 (en) | Discovering a business relationship network, and assessing a relevance of a relationship | |
KR20190041921A (en) | Method and device for performing activation and convolution operation at the same time, learning method and learning device for the same | |
IN2014MU03392A (en) | ||
WO2014152313A3 (en) | Method and system for recording information about rendered assets | |
EP2759948A3 (en) | Panoptic visualization of elements of a complex system using localization of a point on a physical instance of the complex system | |
Komori et al. | Strong first order S-ROCK methods for stochastic differential equations | |
CN104239280A (en) | Method for quickly solving nodal impedance matrix of power system | |
US11470298B2 (en) | Method and apparatus with updating of algorithm for generating disparity image | |
WO2019008343A3 (en) | A computer-implemented system that enables the deployment of configurable and customizable financial services | |
CN104657944A (en) | Compressed sensing remote sensing image reconstruction method based on reference image texture constraints | |
WO2021060875A3 (en) | Patent network establishment guide system and method using big data technique | |
CN104049949A (en) | Peephole optimization method based on BSWAP instruction | |
Li et al. | Plant identification based on multi-branch convolutional neural network with attention | |
Eskandari et al. | Inter-scale dependency modeling for skin lesion segmentation with transformer-based networks | |
CN104182930A (en) | Size pretreatment method of SIFT (Scale Invariant Feature Transform) image fast matching | |
Pandit | 3D pathfinding and collision avoidance using uneven search-space quantization and visual cone search |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150325 |