CN113538374A - Infrared image blur correction method for high-speed moving object - Google Patents
Infrared image blur correction method for high-speed moving object Download PDFInfo
- Publication number
- CN113538374A CN113538374A CN202110799635.2A CN202110799635A CN113538374A CN 113538374 A CN113538374 A CN 113538374A CN 202110799635 A CN202110799635 A CN 202110799635A CN 113538374 A CN113538374 A CN 113538374A
- Authority
- CN
- China
- Prior art keywords
- image
- fuzzy
- prior
- degradation
- moving object
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000012937 correction Methods 0.000 title claims abstract description 26
- 230000015556 catabolic process Effects 0.000 claims abstract description 33
- 238000006731 degradation reaction Methods 0.000 claims abstract description 33
- 230000003287 optical effect Effects 0.000 claims abstract description 20
- 238000005457 optimization Methods 0.000 claims abstract description 7
- 230000006870 function Effects 0.000 claims description 44
- 238000013441 quality evaluation Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 4
- 238000002474 experimental method Methods 0.000 claims description 3
- 239000012530 fluid Substances 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000010187 selection method Methods 0.000 claims description 3
- 230000006872 improvement Effects 0.000 claims description 2
- 238000012545 processing Methods 0.000 claims description 2
- 230000005540 biological transmission Effects 0.000 description 3
- 238000001914 filtration Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000012634 optical imaging Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 240000004282 Grewia occidentalis Species 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003702 image correction Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000035939 shock Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G06T5/73—
-
- G06T5/80—
-
- 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
- G06T2207/10048—Infrared image
Abstract
The invention discloses an infrared image blur correction method for a high-speed moving object, which comprises the following specific steps: synchronously acquiring the degraded image and the high-speed motion state parameters corresponding to the current degraded image; selecting a priori degradation function from a priori degradation function library according to the high-speed motion state parameters; performing characteristic salient region optimization on the degraded image; defining a minimized cost function of the pneumatic optical effect correction based on prior information constraint; solving fuzzy kernels under different scales by utilizing a pyramid principle, and constraining each layer of estimation results through a priori fuzzy kernel to obtain estimation fuzzy kernels under the image scale; obtaining a corrected image through a non-blind image restoration algorithm according to the estimated degradation fuzzy kernel; evaluating the estimation quality of the fuzzy core, and updating the prior fuzzy core library. The method is based on the prior knowledge of the pneumatic theoretical model and the test data, and combines the pyramid principle to realize the intelligent correction of the pneumatic optical distortion image.
Description
Technical Field
The invention belongs to the crossing technical field of combination of pneumatic optics, aerospace science and technology and information processing, and particularly relates to an infrared image fuzzy correction method for a high-speed moving object.
Background
The pneumatic optical effect is a cross discipline. When an aircraft carrying an optical imaging system flies at high speed in the atmosphere, an optical hood of the head of the aircraft and the atmosphere have violent interaction to form multiple complex flow field structures such as shock waves, expansion waves, turbulent flow boundary layers and the like, so that aerodynamic heat, thermal radiation and optical image transmission interference effects are caused to the optical imaging detection system, imaging blurring, offset and shaking are caused, and the effect is called as the aerodynamic optical effect. The higher the speed of the aircraft is, the more serious the aerodynamic optical effect is, the non-uniformity of the refractive index of the light transmission medium is caused by the complex flow field around the optical window, and the effects of wavefront distortion, jitter, offset and the like can be caused during light transmission, so that the imaging quality can be seriously reduced, and the distorted fuzzy image can be received by the optical system. Therefore, the research on how to realize the correction of the airborne aerodynamic degradation image quality has very important value.
Conventional digital image correction algorithms correct for the known degradation function by determining the point spread function or its parameters and then restoring the image using methods such as inverse filtering and wiener filtering. However, in a complex flow field caused by the pneumatic optical effect, the point spread function of the complex flow field cannot be predicted in advance and is randomly changed, and the optical transfer function of the complex flow field is difficult to determine, so that the current pneumatic optical effect correction technology for the image mainly utilizes only priori knowledge to carry out a blind convolution algorithm, and has the defects of poor applicability, poor adaptive capacity, difficult stability guarantee, generally complex iterative computation and long time consumption.
Disclosure of Invention
In order to overcome the problems, the invention provides an infrared image blur correction method for a high-speed moving object.
The technical scheme adopted by the invention is as follows:
an infrared image blur correction method facing a high-speed moving object comprises the following steps:
the method comprises the following steps: synchronously acquiring the degraded image and the high-speed motion state parameters corresponding to the current degraded image;
step two: selecting an initialization fuzzy core from a degradation function library according to the high-speed motion state parameters;
step three: the characteristic salient region is preferably performed on the degraded image:
step four: defining a minimized cost function for aerodynamic-optical effect correction based on a priori information constraint:
step five: solving fuzzy kernels under different scales by utilizing a pyramid principle, and constraining each layer of estimation results through a priori fuzzy kernel to obtain estimation fuzzy kernels under the image scale;
step six: obtaining a corrected image through a non-blind image restoration algorithm according to the estimated degradation fuzzy kernel;
step seven: evaluating the quality of the degraded image and the corrected image, updating the prior degraded function library when the image quality improvement value is greater than a threshold value, otherwise increasing the iteration times of the pyramid solution in the step five, and re-executing the processing process from the step two to the step six.
The method for generating the prior degradation function library in the step two specifically comprises the following steps:
firstly, obtaining an intensity parameter sigma of the pneumatic optical effect under typical high-speed motion state parameters by methods of fluid modeling and wind tunnel experimentt；
Obtaining an intensity parameter sigma by a fitting methodtContinuous mapping relation with high-speed motion state parameters, wherein the fitting method comprises polynomial fitting, Gaussian fitting and least square fitting;
establishing a pneumatic optical effect continuous degradation function model:
wherein, ω isiAs a weight parameter, σtAs intensity parameter, xiAnd yiAn offset control parameter;
and setting n groups of typical high-speed motion state parameters to input into the degradation function model to obtain n degradation functions to form a prior degradation function library.
The method for initializing fuzzy core selection in the second step specifically comprises the following steps:
reading high-speed motion state parameters carried by an input degraded image, including speed;
and (3) solving a minimized loss function or a nonlinear regression method through linear weighting, and selecting a fuzzy kernel corresponding to the closest state parameter from the prior fuzzy kernel library.
The image characteristic salient region optimization method in the step three adopts a salient edge-based optimization method, and selects an image region with the maximum local gradient sum as an image characteristic salient region by calculating the local sum of an image gradient matrix; or adopting a salient region automatic selection method based on the CRF learning framework.
The method for constructing the cost function based on the prior in the fourth step comprises the following steps: and establishing a cost function based on prior knowledge, converting the estimation problem of the fuzzy kernel into a solution optimization problem, and adding a regularization constraint term to the image and the fuzzy kernel based on the characteristic of sparsity.
The prior fuzzy kernel constraint method in the fifth step comprises the following steps: adding constraint to the estimation process of the fuzzy core by using the prior fuzzy core; the fuzzy kernel prior term is
Through the L2 regularization constraint term, the sparsity of residual errors between the fuzzy kernel estimation and the prior fuzzy kernel is guaranteed, and the accuracy of the fuzzy kernel estimation is improved.
And in the sixth step, the non-blind image restoration method is a Lucy-based method or a super-Laplace prior constraint-based method.
And the quality evaluation method in the step seven is to use an image quality evaluation function to calculate the images before and after correction, wherein the image quality evaluation function comprises PSNR, SSIM or GMG.
The method for updating the prior degradation function library in the seventh step is a linear weighting method, and the updated prior degradation function is as follows:
PSFi'＝θ1·PSFi+θ2·PSFnew
wherein, PSFiBeing the original a priori degradation function, PSFnewFor the current estimated degradation blur kernel, parameter θ1、θ2Respectively, the weights of the two.
The invention has the following advantages:
1. compared with the traditional regularization method, the prior information is fully utilized, the precision of fuzzy kernel estimation is improved, and the problems of artifacts and ringing are solved;
2. the method can be used for carrying out real-time correction on the pneumatic optical effect in a high-speed motion state.
Drawings
FIG. 1 is a flow chart of an infrared image blur correction method for a high-speed moving object according to the present invention.
Detailed Description
The present invention will be further described below, but the present invention is not limited to these.
Examples
At the early stage, the strength parameter of the pneumatic optical effect in a typical flight state is obtained by a method of fluid modeling and wind tunnel experiment; and then, obtaining a continuous mapping relation between the flight parameters of the aircraft and the degradation function by establishing a mathematical model to obtain a pneumatic optical effect degradation model, and setting a group of typical flight parameter inputs to obtain a degradation function library. Synchronously acquiring a degraded image and aircraft flight parameters corresponding to the current degraded image, wherein a degradation function with the closest flight state is selected from a fuzzy kernel library according to the aircraft flight parameters corresponding to the input degraded image to be processed; meanwhile, for the input original degraded image, local gradient sum is obtained, the maximum element value of the gradient and the matrix is found out, the x and y coordinates in the gradient and the matrix are limited, and the maximum area coordinate value is not more than the size of the image, so that the area coordinate is obtained; and (4) rounding the coordinate value to obtain the four-corner coordinates of the final salient region, and intercepting the characteristic salient region from the original degraded image according to the coordinates. For the extracted characteristic significance region of the blurred image, defining a minimized cost function of the pneumatic optical effect correction based on prior information constraint:
where x represents a sharp image, y represents a blurred image, k represents a point spread function PSF, and γ, α, and λ are regularization constraint strength parameters. The first term is a likelihood term that preserves the similarity of x k to the observed data y. The second and third terms are intensity prior constraints, represented by l2 and l0 norm regularization terms, respectively, to preserve the sparsity of the blur kernel and the image. The fourth term is gradient prior constraint, which is used to ensure the sparsity of image gradient. The last term is the prior fuzzy constraint, the fuzzy kernel prior term is
Through the L2 regularization constraint term, the sparsity of residual errors between the fuzzy kernel estimation and the prior fuzzy kernel is guaranteed, and the accuracy of the fuzzy kernel estimation is improved. In the iteration process, firstly, an image multi-resolution pyramid is established, a fuzzy kernel and a fuzzy image are subjected to down-sampling, and x and k are alternately and iteratively updated from a topmost image x with the lowest resolution and a fuzzy kernel k. And constraining each layer of estimation result through the prior fuzzy core to obtain an estimation fuzzy core under the image scale of the layer, restoring the fuzzy image by using the estimation fuzzy core k, performing up-sampling on the restored image to obtain a potential intermediate image x of the next layer of the multi-resolution pyramid, and iterating until the finest resolution level is obtained. And obtaining a corrected image through a super-Laplace non-blind image restoration algorithm according to the estimated degraded fuzzy kernel. The image before and after correction is calculated using an image quality evaluation function such as PSNR, SSIM, or GMG. And when the result is improved by more than 85%, updating the prior degradation function according to a linear weighting method:
PSFi'＝θ1·PSFi+θ2·PSFnew
wherein, PSFiBeing the original a priori degradation function, PSFnewFor the current estimated degraded fuzzy kernel, the weight parameter θ1、θ2Set to 0.3 and 0.7, respectively. Otherwise, the iteration times are increased, and the whole correction process is carried out again.
It is noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention.
Claims (7)
1. An infrared image blur correction method for a high-speed moving object is characterized in that: the method comprises the following steps:
the method comprises the following steps: synchronously acquiring the degraded image and the high-speed motion state parameters corresponding to the current degraded image;
step two: selecting an initialization fuzzy core from a degradation function library according to the high-speed motion state parameters;
the generation method of the prior degradation function library specifically comprises the following steps:
firstly, obtaining an intensity parameter sigma of the pneumatic optical effect under typical high-speed motion state parameters by methods of fluid modeling and wind tunnel experimentt；
Obtaining an intensity parameter sigma by a fitting methodtContinuous mapping relation with high-speed motion state parameters, wherein the fitting method comprises polynomial fitting, Gaussian fitting and least square fitting;
establishing a pneumatic optical effect continuous degradation function model:
wherein, ω isiAs a weight parameter, σtAs intensity parameter, xiAnd yiAn offset control parameter;
setting n groups of typical high-speed motion state parameters to input into a degradation function model to obtain n degradation functions to form a prior degradation function library;
the initialization fuzzy core selection method specifically comprises the following steps:
reading high-speed motion state parameters carried by an input degraded image, including speed;
solving a minimum loss function or a nonlinear regression method through linear weighting, and selecting a fuzzy kernel corresponding to the closest state parameter from a fuzzy kernel library;
step three: the characteristic salient region is preferably performed on the degraded image:
step four: defining a minimized cost function for aerodynamic-optical effect correction based on a priori information constraint:
step five: solving fuzzy kernels under different scales by utilizing a pyramid principle, and constraining each layer of estimation results through a priori fuzzy kernel to obtain estimation fuzzy kernels under the image scale;
step six: obtaining a corrected image through a non-blind image restoration algorithm according to the estimated degradation fuzzy kernel;
step seven: evaluating the quality of the degraded image and the corrected image, updating the prior degraded function library when the image quality improvement value is greater than a threshold value, otherwise increasing the iteration times of the pyramid solution in the step five, and re-executing the processing process from the step two to the step six.
2. The infrared image blur correction method for a high-speed moving object according to claim 1, characterized in that: the image characteristic salient region optimization method in the third step adopts a salient edge optimization-based method, and selects an image region with the maximum local gradient sum as an image characteristic salient region by calculating the local sum of an image gradient matrix; or adopting a salient region automatic selection method based on the CRF learning framework.
3. The infrared image blur correction method for a high-speed moving object according to claim 1, characterized in that: the method for constructing the cost function based on prior in the fourth step comprises the following steps: and establishing a cost function based on prior knowledge, converting the estimation problem of the fuzzy kernel into a solution optimization problem, and adding a regularization constraint term to the image and the fuzzy kernel based on the characteristic of sparsity.
4. The infrared image blur correction method for a high-speed moving object according to claim 1, characterized in that:the prior fuzzy kernel constraint method in the fifth step comprises the following steps: adding constraint to the estimation process of the fuzzy core by using the prior fuzzy core; the fuzzy kernel prior term is
5. The infrared image blur correction method for a high-speed moving object according to claim 1, characterized in that: and in the sixth step, the non-blind image restoration method is a Lucy-based method or a super-Laplace prior constraint-based method.
6. The infrared image blur correction method for a high-speed moving object according to claim 1, characterized in that: the quality evaluation method in the seventh step is to use an image quality evaluation function to calculate the images before and after correction, wherein the image quality evaluation function comprises PSNR, SSIM or GMG.
7. The infrared image blur correction method for a high-speed moving object according to claim 1, characterized in that: the method for updating the prior degradation function library in the seventh step is a linear weighting method, and the updated prior degradation function is as follows:
PSFi'＝θ1·PSFi+θ2·PSFnew
wherein, PSFiBeing the original a priori degradation function, PSFnewFor the current estimated degradation blur kernel, parameter θ1、θ2Respectively, the weights of the two.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110799635.2A CN113538374B (en) | 2021-07-15 | 2021-07-15 | Infrared image blurring correction method for high-speed moving object |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110799635.2A CN113538374B (en) | 2021-07-15 | 2021-07-15 | Infrared image blurring correction method for high-speed moving object |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113538374A true CN113538374A (en) | 2021-10-22 |
| CN113538374B CN113538374B (en) | 2023-11-28 |
Family
ID=78099397
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110799635.2A Active CN113538374B (en) | 2021-07-15 | 2021-07-15 | Infrared image blurring correction method for high-speed moving object |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113538374B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113793284A (en) * | 2021-11-17 | 2021-12-14 | 武汉工程大学 | Image restoration method for nonuniform blocking of aerodynamic optical effect space-variant blurred image |
| CN113962908A (en) * | 2021-12-21 | 2022-01-21 | 武汉工程大学 | Pneumatic optical effect large-view-field degraded image point-by-point correction restoration method and system |
| CN114529481A (en) * | 2022-04-21 | 2022-05-24 | 武汉工程大学 | Pneumatic optical thermal radiation effect correction method, device, equipment and storage medium |
| CN114663304A (en) * | 2022-03-16 | 2022-06-24 | 中国科学院光电技术研究所 | Sparse prior-based optical synthetic aperture system imaging enhancement method |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070286514A1 (en) * | 2006-06-08 | 2007-12-13 | Michael Scott Brown | Minimizing image blur in an image projected onto a display surface by a projector |
| CN101236650A (en) * | 2008-01-24 | 2008-08-06 | 上海交通大学 | Real time rotating blurred image restoration method based on gradient loading optimization |
| US20090179995A1 (en) * | 2008-01-16 | 2009-07-16 | Sanyo Electric Co., Ltd. | Image Shooting Apparatus and Blur Correction Method |
| US20150161771A1 (en) * | 2013-12-11 | 2015-06-11 | Canon Kabushiki Kaisha | Image processing method, image processing apparatus, image capturing apparatus and non-transitory computer-readable storage medium |
| CN106920220A (en) * | 2017-02-24 | 2017-07-04 | 西北工业大学 | Based on the turbulent flow method for blindly restoring image that dark primary and alternating direction multiplier method optimize |
| CN107742278A (en) * | 2017-10-25 | 2018-02-27 | 重庆邮电大学 | With reference to L0The motion blur image blind restoration method of norm and space scale information |
| CN108830802A (en) * | 2018-05-16 | 2018-11-16 | 浙江大学 | A kind of image fuzzy core estimation method based on short exposure image gradient guiding |
| WO2018227882A1 (en) * | 2017-06-15 | 2018-12-20 | 北京大学深圳研究生院 | A priori constraint and outlier suppression based image deblurring method |
| CN109919871A (en) * | 2019-03-05 | 2019-06-21 | 重庆大学 | Fuzzy core estimation method based on image and fuzzy core mixed constraints |
| CN110852973A (en) * | 2019-11-12 | 2020-02-28 | 华中科技大学 | Nonlinear restoration method and system for pulse noise blurred image |
| CN112132758A (en) * | 2020-08-05 | 2020-12-25 | 浙江工业大学 | Image restoration method based on asymmetric optical system point spread function model |
-
2021
- 2021-07-15 CN CN202110799635.2A patent/CN113538374B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070286514A1 (en) * | 2006-06-08 | 2007-12-13 | Michael Scott Brown | Minimizing image blur in an image projected onto a display surface by a projector |
| US20090179995A1 (en) * | 2008-01-16 | 2009-07-16 | Sanyo Electric Co., Ltd. | Image Shooting Apparatus and Blur Correction Method |
| CN101236650A (en) * | 2008-01-24 | 2008-08-06 | 上海交通大学 | Real time rotating blurred image restoration method based on gradient loading optimization |
| US20150161771A1 (en) * | 2013-12-11 | 2015-06-11 | Canon Kabushiki Kaisha | Image processing method, image processing apparatus, image capturing apparatus and non-transitory computer-readable storage medium |
| CN106920220A (en) * | 2017-02-24 | 2017-07-04 | 西北工业大学 | Based on the turbulent flow method for blindly restoring image that dark primary and alternating direction multiplier method optimize |
| WO2018227882A1 (en) * | 2017-06-15 | 2018-12-20 | 北京大学深圳研究生院 | A priori constraint and outlier suppression based image deblurring method |
| CN107742278A (en) * | 2017-10-25 | 2018-02-27 | 重庆邮电大学 | With reference to L0The motion blur image blind restoration method of norm and space scale information |
| CN108830802A (en) * | 2018-05-16 | 2018-11-16 | 浙江大学 | A kind of image fuzzy core estimation method based on short exposure image gradient guiding |
| CN109919871A (en) * | 2019-03-05 | 2019-06-21 | 重庆大学 | Fuzzy core estimation method based on image and fuzzy core mixed constraints |
| CN110852973A (en) * | 2019-11-12 | 2020-02-28 | 华中科技大学 | Nonlinear restoration method and system for pulse noise blurred image |
| CN112132758A (en) * | 2020-08-05 | 2020-12-25 | 浙江工业大学 | Image restoration method based on asymmetric optical system point spread function model |
Non-Patent Citations (7)
| Title |
|---|
| MINGZUO JIANG ET.AL: "A new type of fuzzy systems using pyramid membership functions (PMFs) and approximation properties", 《SOFT COMPUTING》 * |
| SHUANGLIANG CAO ET.AL: "Dynamic PET Image Reconstruction Incorporating Multiscale Superpixel Clusters", 《IEEE ACCESS》, no. 09 * |
| 南一冰;高昆;倪国强;: "基于波段选择估计PSF的高光谱图像运动模糊盲校正方法", 红外与毫米波学报, no. 06 * |
| 张姣;李俊山;杨亚威;: "结合仿射变换和多层B样条配准的湍流畸变图像校正", 光学精密工程, no. 03 * |
| 张姣;李俊山;隋中山;汪晓建;: "混合正则化约束的湍流退化图像复原算法", 激光与红外, no. 07 * |
| 杨文霞等: "气动光学效应分析与气动模糊图像复原", 《光学学报》, vol. 29, no. 02 * |
| 邹皓: "基于大气湍流相关参数的图像复原方法研究", 《中国优秀硕士学位论文全文数据库（信息科技辑）》, no. 01 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113793284A (en) * | 2021-11-17 | 2021-12-14 | 武汉工程大学 | Image restoration method for nonuniform blocking of aerodynamic optical effect space-variant blurred image |
| CN113962908A (en) * | 2021-12-21 | 2022-01-21 | 武汉工程大学 | Pneumatic optical effect large-view-field degraded image point-by-point correction restoration method and system |
| CN113962908B (en) * | 2021-12-21 | 2022-05-10 | 武汉工程大学 | Pneumatic optical effect large-visual-field degraded image point-by-point correction restoration method and system |
| CN114663304A (en) * | 2022-03-16 | 2022-06-24 | 中国科学院光电技术研究所 | Sparse prior-based optical synthetic aperture system imaging enhancement method |
| CN114663304B (en) * | 2022-03-16 | 2023-09-19 | 中国科学院光电技术研究所 | Sparse prior-based optical synthetic aperture system imaging enhancement method |
| CN114529481A (en) * | 2022-04-21 | 2022-05-24 | 武汉工程大学 | Pneumatic optical thermal radiation effect correction method, device, equipment and storage medium |
| CN114529481B (en) * | 2022-04-21 | 2022-07-26 | 武汉工程大学 | Pneumatic optical thermal radiation effect correction method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113538374B (en) | 2023-11-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113538374B (en) | Infrared image blurring correction method for high-speed moving object | |
| Quan et al. | Self2self with dropout: Learning self-supervised denoising from single image | |
| CN110097519B (en) | Dual-monitoring image defogging method, system, medium and device based on deep learning | |
| Pan et al. | Learning dual convolutional neural networks for low-level vision | |
| CN110232394B (en) | Multi-scale image semantic segmentation method | |
| CN108564549B (en) | Image defogging method based on multi-scale dense connection network | |
| Yin et al. | Highly accurate image reconstruction for multimodal noise suppression using semisupervised learning on big data | |
| CN110796616B (en) | Turbulence degradation image recovery method based on norm constraint and self-adaptive weighted gradient | |
| CN105657402A (en) | Depth map recovery method | |
| CN114418883B (en) | Blind image deblurring method based on depth priori | |
| CN105590304B (en) | Super-resolution image reconstruction method and device | |
| CN106339996B (en) | A kind of Image Blind deblurring method based on super Laplace prior | |
| CN105913392A (en) | Degraded image overall quality improving method in complex environment | |
| CN111738954B (en) | Single-frame turbulence degradation image distortion removal method based on double-layer cavity U-Net model | |
| CN115358953B (en) | Turbulence removing method based on image registration and dynamic target fusion | |
| CN111028265A (en) | Target tracking method for constructing correlation filtering response based on iteration method | |
| CN109767404A (en) | Infrared image deblurring method under a kind of salt-pepper noise | |
| CN114494015A (en) | Image reconstruction method based on blind super-resolution network | |
| CN113538258B (en) | Mask-based image deblurring model and method | |
| CN112085674B (en) | Aerial image deblurring algorithm based on neural network | |
| CN111401209B (en) | Action recognition method based on deep learning | |
| CN116596792B (en) | Inland river foggy scene recovery method, system and equipment for intelligent ship | |
| KR102095444B1 (en) | Method and Apparatus for Removing gain Linearity Noise Based on Deep Learning | |
| CN116843544A (en) | Method, system and equipment for super-resolution reconstruction by introducing hypersonic flow field into convolutional neural network | |
| Cao et al. | Remote sensing image recovery and enhancement by joint blind denoising and dehazing |
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 |