CN112907461A - Defogging and enhancing method for infrared degraded image in foggy day - Google Patents
Defogging and enhancing method for infrared degraded image in foggy day Download PDFInfo
- Publication number
- CN112907461A CN112907461A CN202110100817.6A CN202110100817A CN112907461A CN 112907461 A CN112907461 A CN 112907461A CN 202110100817 A CN202110100817 A CN 202110100817A CN 112907461 A CN112907461 A CN 112907461A
- Authority
- CN
- China
- Prior art keywords
- image
- value
- pixel
- super
- block
- 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 40
- 230000002708 enhancing effect Effects 0.000 title claims description 6
- 238000002834 transmittance Methods 0.000 claims abstract description 12
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 5
- 230000011218 segmentation Effects 0.000 claims description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000010845 search algorithm Methods 0.000 claims description 4
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 claims 1
- 238000003384 imaging method Methods 0.000 abstract description 7
- 238000012545 processing Methods 0.000 abstract description 4
- 230000000007 visual effect Effects 0.000 abstract description 4
- 238000011156 evaluation Methods 0.000 abstract 1
- 238000003709 image segmentation Methods 0.000 abstract 1
- 230000001788 irregular Effects 0.000 abstract 1
- 239000011159 matrix material Substances 0.000 abstract 1
- 238000006731 degradation reaction Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000015556 catabolic process Effects 0.000 description 3
- 125000001475 halogen functional group Chemical group 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000003331 infrared imaging Methods 0.000 description 1
- 238000005293 physical law Methods 0.000 description 1
- 230000010287 polarization Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- 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
-
- 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
- G06T2207/30192—Weather; Meteorology
-
- 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
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a defogging enhancement method for an infrared foggy degraded image. The image defogging method and the device realize image defogging processing based on the irregular local area information and the atmospheric physical model. According to the complexity of an infrared image scene, the number of image super pixels and the boundary compactness are preset, and simple linear iterative clustering is used for realizing image segmentation. And obtaining the global atmospheric light value A by utilizing an improved quadtree decomposition automatic search method. And in the obtained super-pixel blocks, analyzing a visual visibility evaluation method and an upper and lower limit constraint relation of information truncation according to the value of a pixel matrix in each super-pixel block to obtain the optimal transmittance t'. And inverting the fog-free image J according to the obtained input image I, the atmospheric light value A and the optimal transmissivity t'. According to the method, the optimal parameters of the atmospheric physical model are calculated through image local information, adaptability to different fog concentrations is achieved, infrared image defogging inversion is achieved, the structure is simple, implementation is easy, and the infrared foggy day imaging quality is effectively improved.
Description
The technical field is as follows:
the invention belongs to the technical field of image processing, mainly comprises a degraded image enhancement algorithm for a single-waveband imaging system in a haze day, and is particularly suitable for enhancing the overall brightness, low contrast and local blurring of an image caused by an infrared remote sensing image in the haze day, reducing the influence of haze on the imaging system and realizing the improvement of image quality.
Background art:
in the imaging process of an outdoor remote optical system in haze weather, an infrared imaging system is often influenced by scattering, absorption and reflection effects generated by suspended particles in the atmosphere, so that the phenomena of high overall brightness value, low contrast, reduced dynamic range, reduced definition, blurring and the like caused by degradation of an observed image occur, and the influence degree of the degradation on the image is enhanced along with the increase of the distance between a target and observation equipment. The problem of image degradation results in the inability to obtain clear and stable high quality images or sequences, and the inability to effectively work with subsequent algorithms of identification, tracking, segmentation, and the like. Meanwhile, with the rapid development of automatic driving and auxiliary driving at present, a new requirement is provided for the imaging quality in haze days. Defogging techniques can currently be divided into two broad categories: an enhancement method based on image processing and an enhancement method based on image restoration.
The defogging method based on image enhancement starts from the characteristic of low contrast of a foggy image, and improves the visual quality through various filtering and linear nonlinear stretching transformation on the contrast of the image, and the mainstream methods comprise histogram equalization, a filtering method, wavelet change, a Retinex algorithm, an atmospheric modulation transfer function method and the like. These methods have achieved good results to some extent, but also have many problems. For targets with uneven illumination or complex distance change, halo phenomenon and blocking effect are easily caused, the method has poor universality and the problem of large calculated amount generally exists, and the defogged image does not accord with the actual physical law to a certain extent only from the perspective of vision.
The method based on image restoration starts from a physical process under the image quality caused by haze weather, and achieves the aim of defogging by inverting a physical degradation process. Obtaining an atmospheric physical scattering model according to atmospheric particle optical basic research, and solving the optimal parameters of the atmospheric physical scattering model to invert the fog-free image. Based on this, the method aims to find the optimal parameters of the model, so that additional prior information besides the image is mostly required to be provided, for example, the depth information of the scene or additional means for obtaining depth auxiliary information, fog concentration information or scene polarization information, etc. The defogging method based only on the image information is rapidly developed due to the difficulty in acquiring additional information and the complexity in operation. The dark channel method is statistical prior information provided by the method of Hommin, and becomes the most effective defogging prior information at present, but because the partitioning is unreasonable, the dark channel method is easy to generate halo and block effects, and a large amount of calculation is needed for eliminating the block effects. However, the dark channel method is obtained by counting a large amount of color image three-channel information, and is not suitable for a single-band infrared image, so that an effective constraint condition needs to be searched to guide the physical restoration process of the infrared degraded image.
The invention content is as follows:
in order to overcome the defects of the prior art, the invention provides an infrared fog degraded image defogging and enhancing method. The method is based on the image restoration method, eliminates the artifact phenomenon by replacing rectangular segmentation with superpixel segmentation, guides the physical restoration process by upper and lower limit constraints, and has small calculated amount and obvious improvement on imaging quality.
The above purpose of the invention is realized by the following technical scheme:
a defogging and enhancing method for an infrared foggy degraded image is characterized in that after the image is segmented by a superpixel segmentation algorithm, the optimal parameters of an atmospheric physical model inversion equation are obtained by combining an improved quadtree decomposition search algorithm and upper and lower limit constraints, so that the image is reconstructed, and the method comprises the following steps:
(1) the simple linear iterative clustering segmentation algorithm needs to give the number k of super pixel blocks and the boundary compactness m in advance, and the number k of the super pixel blocks and the boundary compactness m are set to be 40-80 and 30-50 respectively;
(2) initializing a clustering center according to a formula (1) and the number k of superpixels, calculating an initialized superpixel clustering center interval S, and uniformly distributing the initialized clustering centers on the infrared image according to the interval S. In order to avoid that the clustering center falls on the edge of the image so that the point cannot form a closed connected domain with the surrounding area, taking the minimum gradient value point in the neighborhood range of the initial clustering center point 3x3 as an initial clustering center;
wherein N is the number of total pixel points of the image, k is the number of super pixels,
a downward rounding operation for discarding decimal;
(3) combining an infrared image brightness domain l and a spatial domain (x, y) into a three-dimensional spatial domain V ═ l, x, y]TAnd D is defined as the distance between the pixel point and the clustering center in the three-dimensional space. According to the formulas (2), (3) and (4), the distance D between the pixel point belonging to the superpixel block of the cluster center that minimizes D and the cluster center is calculated. The farther the clustering center is away from the pixel point, the probability of the super-pixel block belonging to the clustering center is sharply reduced, and in order to increase the operation speed, the range of 2S multiplied by 2S of the pixel point neighborhood is taken as a search domain. Updating the clustering centers after all the image pixel points are clustered, taking the center point of each clustering block as a new clustering center, and obtaining a super-pixel image with accurate segmentation through four iterations;
wherein d issFor distance in space dimension, i.e. difference in coordinates, dlIs the luminance dimension distance i.e. the gray value difference,(xi,yi) And (x)j,yj) Coordinates of image pixel points and cluster center points, liAnd ljRespectively taking gray values of pixel points and a clustering central point;
(4) an improved quadtree decomposition search algorithm is used for solving the atmospheric light value A, and the specific algorithm content is that a regular rectangular quartering method is replaced by a quartering method based on a superpixel block. Firstly, after the image superpixel is divided, numbering each superpixel block, and marking each pixel point with a corresponding superpixel block number label. Then, the image is divided into four equal parts, the four parts are averaged, the part with the largest average value is taken to count the label numbers appearing on the contained pixel points, and the pixels corresponding to the counted label numbers form a new sub-block. The newly composed subblock coordinate regions are then divided into four equal parts. This process is repeated until the block with the largest average contains only one tag number. And (4) averaging the gray values of the pixels of the superpixel block corresponding to the label number according to a formula (5) to obtain the global atmospheric light value A. Sometimes, the iteration process sinks into the partial loop under a special condition that after multiple iterations, the number of superpixel blocks contained in a newly constructed subblock is less than or equal to four, so that when the new subblock is divided into four equal parts, the tag number appearing in the region with the largest statistical average value is equal to the tag number of the new subblock, the next subblock is constructed and is consistent with the atomic block, so that the next subblock is sunk into the partial loop, and the local loop can also be used as an iteration termination condition. At this time, because the number of the superpixel blocks contained in the subblocks is small, calculating the average value of all the superpixel blocks in the subblocks according to the formula (5), and selecting the maximum value as the global atmospheric light value A;
wherein I (x, y) represents the gray value at the coordinate point (x, y) in the superpixel block omega, and n is the total pixel number in the superpixel block omega;
(5) due to poor nonuniformity of the infrared image, in order to avoid that the maximum gray value point and the minimum gray value point of each super-pixel block are right located at a blind pixel, the gray values of the super-pixel block pixel points are sorted from small to large, and according to formulas (6) and (7), the average value of the first 5% gray value and the second 5% gray value is calculated as the minimum maximum value of the super-pixel blocks and is recorded as min _ m and max _ m:
wherein Ω _ min and Ω _ max are sets of pixels corresponding to the first 5% gray value and the second 5% gray value of the superpixel block Ω, respectively, and n is the number of total pixels in the superpixel block;
(6) the Mean-square Error (MSE) is an effective parameter for measuring the image quality, can be calculated by formula (8), and accords with the visual characteristics of human eyes, and a higher MSE value means that the image has higher contrast. It can be inferred from equation (8) that the value of MSE is inversely related to the transmittance t, with smaller t yielding higher values of MSE. For infrared images, the gray value of an image pixel point is easier to generate a data truncation phenomenon due to smaller t, so that information loss is caused, and a loss value caused by data truncation is defined as CLOSSNamely, formula (9):
wherein
The gray level average value of the pixel points of the original image is obtained. To prevent information loss, C should be satisfiedLOSSIs less than or equal to zero. Number of occurrencesThe value of the transmittance at which the MSE value is large while being lost is the optimum transmittance t'. Derivation of equation (9) yields upper and lower bounds constraints that prevent information loss, so that the value of the optimal transmittance of a super-pixel block can be obtained from equation (10):
where ω is a constant controlling the degree of defogging set to 0.95;
(7) obtaining the optimal atmospheric light value and transmittance through the steps (4) and (6), and calculating to obtain a defogged reconstructed image J according to an atmospheric physical model inversion formula (11);
j (x) and I (x) are pixel points of the reconstructed image and the original image respectively, and t' (x) is the optimal transmittance value of the corresponding super-pixel block;
compared with the prior art, the invention has the beneficial effects that:
1) extra information except the infrared image does not need to be obtained, only single-frame information is needed, multi-frame information is not needed, the defogging process is easy to realize, and the transmittance value can be automatically adjusted in a self-adaptive mode according to the far and near degree of the target and the haze concentration;
2) through superpixel segmentation, halo phenomenon and block effect can be avoided, imaging quality is more natural, and the method better accords with human visual characteristics.
3) The invention has less input parameters, only the segmentation stage needs to input the parameters, the improved quadtree decomposition search algorithm can automatically obtain the global atmospheric light value and the upper and lower limit constraint optimal transmissivity, and the defogging reconstruction process can be realized without human intervention.
Drawings
FIG. 1 is a block diagram of an implementation flow of the present invention;
fig. 2 is an original infrared image of a haze day as an input image in the present invention.
Fig. 3 is an output image, i.e., a defogged reconstructed image, according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described in detail below with reference to the accompanying drawings in the embodiments of the present invention. Several parameters are involved that need to be adjusted for a particular processing environment to achieve good performance.
The test picture used by the invention is obtained by shooting by a 640 multiplied by 512 short-wave infrared camera developed by Shanghai technical and physical research institute of Chinese academy of sciences.
Simulation environment: matlab2018 b;
and (3) testing an image: the short wave infrared image has the size of 640 multiplied by 512, and the scene is an urban building;
for the test image, the number of super pixels k is set to 60, the boundary closeness m is set to 40, and the defogging degree control constant ω is set to 0.95 in the defogging step (6).
Claims (1)
1. An infrared fog degraded image defogging and enhancing method is characterized by comprising the following steps:
(1) presetting a super pixel number k and super pixel segmentation boundary compactness m in a simple linear iterative clustering super pixel segmentation algorithm, wherein the super pixel number k is set to be 40-80, and the compactness m is set to be 30-50;
(2) initializing a clustering center according to the number k of the super pixels, wherein the initial clustering center is uniformly distributed in the image according to the size S of an interval grid, in order to avoid the situation that the initial clustering center is just positioned at the edge of the image, taking a pixel point with the minimum gradient value in the neighborhood of an initial center point 3x3 as the initial clustering center, and the size of the grid S is as follows:
wherein N is the number of total pixel points of the image, k is the number of super pixels,
abandoning decimal rounding-down operation;
(3) combining one-dimensional brightness dimension l and two-dimensional space dimension (x, y) of the infrared image into a three-dimensional space domain V ═ l, x, y]TDefining D as the distance between a pixel point and a clustering center in a three-dimensional space, classifying the pixel point into a superpixel block which enables D to be minimum in the clustering process, updating the clustering center after all image pixel points are classified, obtaining a superpixel graph with accurate segmentation through four iterations, and limiting a classification search domain of the pixel point into a range of neighborhood 2S multiplied by 2S around the pixel point to avoid overlarge calculated amount:
wherein d issFor distance in space dimension, i.e. difference in coordinates, dlIs the difference in luminance dimension, i.e. gray value, (x)i,yi) And (x)j,yj) Coordinates of image pixel points and cluster center points, liAnd ljRespectively taking gray values of pixel points and a clustering central point;
(4) using an improved quadtree decomposition search algorithm based on the superpixel block, obtaining a final superpixel block when an iteration termination condition is met, and calculating an average value re _ m of the superpixel block to be an optimal global atmospheric light value A;
wherein I (x, y) represents the gray value at the coordinate point (x, y) in the superpixel block omega, and n is the total pixel number in the superpixel block omega;
(5) arranging the gray values corresponding to the pixel points in each super pixel block from small to large, calculating the average value of the gray values of the front 5% and the rear 5% in each block as the minimum value and the maximum value of the super pixel block, and respectively recording the average value as min _ m and max _ m:
wherein Ω _ min and Ω _ max are sets of pixels corresponding to the first 5% gray value and the second 5% gray value of the superpixel block Ω, respectively, and n is the number of total pixels in the superpixel block;
(6) to obtain a higher mean square error value CMSEEquation (8) and prevent the occurrence of information truncation CLOSSThe formula (9), the upper and lower limit constraints of the transmittance can be obtained; by using the maximum and minimum mean values max _ m and min _ m of the superpixel block, the optimal transmittance value t' of the superpixel block can be obtained according to the upper and lower limit constraint formula (10):
wherein
Is the average value of gray levels of pixels in the original image, and omega is the normal value for controlling the defogging degreeNumber, set to 0.95;
(7) and (3) calculating an inversion formula (11) of the atmospheric physical model by using the obtained global atmospheric light value A and the optimal transmittance t' of each superpixel block, and obtaining a defogged reconstructed image:
wherein J (x) and I (x) are pixel points of the reconstructed image and the original image respectively, and t' (x) is the optimal transmittance value of the corresponding super-pixel block.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110100817.6A CN112907461B (en) | 2021-01-26 | 2021-01-26 | Defogging enhancement method for infrared foggy-day degraded image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110100817.6A CN112907461B (en) | 2021-01-26 | 2021-01-26 | Defogging enhancement method for infrared foggy-day degraded image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112907461A true CN112907461A (en) | 2021-06-04 |
| CN112907461B CN112907461B (en) | 2023-05-05 |
Family
ID=76119218
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110100817.6A Active CN112907461B (en) | 2021-01-26 | 2021-01-26 | Defogging enhancement method for infrared foggy-day degraded image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112907461B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114549336A (en) * | 2021-11-25 | 2022-05-27 | 湖南科技大学 | Unsupervised image defogging method |
| CN115063404A (en) * | 2022-07-27 | 2022-09-16 | 建首(山东)钢材加工有限公司 | Weathering resistant steel weld joint quality detection method based on X-ray flaw detection |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104794688A (en) * | 2015-03-12 | 2015-07-22 | 北京航空航天大学 | Single image defogging method and device based on depth information separation sky region |
| CN108596849A (en) * | 2018-04-23 | 2018-09-28 | 南京邮电大学 | A kind of single image to the fog method based on sky areas segmentation |
| CN110428371A (en) * | 2019-07-03 | 2019-11-08 | 深圳大学 | Image defogging method, system, storage medium and electronic equipment based on super-pixel segmentation |
| CN111325688A (en) * | 2020-02-18 | 2020-06-23 | 长安大学 | Unmanned aerial vehicle image defogging method fusing morphological clustering and optimizing atmospheric light |
| CN111598788A (en) * | 2020-04-08 | 2020-08-28 | 西安理工大学 | Single image defogging method based on quadtree decomposition and non-local prior |
| CN111667433A (en) * | 2020-06-09 | 2020-09-15 | 中国电子科技集团公司第五十四研究所 | Unmanned aerial vehicle image defogging method based on simple linear iterative clustering optimization |
| CN111899198A (en) * | 2020-08-06 | 2020-11-06 | 北京科技大学 | Defogging method and device for marine image |
-
2021
- 2021-01-26 CN CN202110100817.6A patent/CN112907461B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104794688A (en) * | 2015-03-12 | 2015-07-22 | 北京航空航天大学 | Single image defogging method and device based on depth information separation sky region |
| CN108596849A (en) * | 2018-04-23 | 2018-09-28 | 南京邮电大学 | A kind of single image to the fog method based on sky areas segmentation |
| CN110428371A (en) * | 2019-07-03 | 2019-11-08 | 深圳大学 | Image defogging method, system, storage medium and electronic equipment based on super-pixel segmentation |
| CN111325688A (en) * | 2020-02-18 | 2020-06-23 | 长安大学 | Unmanned aerial vehicle image defogging method fusing morphological clustering and optimizing atmospheric light |
| CN111598788A (en) * | 2020-04-08 | 2020-08-28 | 西安理工大学 | Single image defogging method based on quadtree decomposition and non-local prior |
| CN111667433A (en) * | 2020-06-09 | 2020-09-15 | 中国电子科技集团公司第五十四研究所 | Unmanned aerial vehicle image defogging method based on simple linear iterative clustering optimization |
| CN111899198A (en) * | 2020-08-06 | 2020-11-06 | 北京科技大学 | Defogging method and device for marine image |
Non-Patent Citations (4)
| Title |
|---|
| RADHAKRISHNA ACHANTA 等: "SLIC Superpixels Compared to State-of-the-Art Superpixel Methods", 《IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE》 * |
| 杨龙 等: "基于超像素分割的红外图像细节增强算法", 《红外》 * |
| 郑良缘 等: "基于超像素分割的图像去雾算法", 《重庆理工大学学报（自然科学）》 * |
| 陈永 等: "基于超像素分割和暗亮通道结合的单幅图像去雾", 《激光与光电子学进展》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114549336A (en) * | 2021-11-25 | 2022-05-27 | 湖南科技大学 | Unsupervised image defogging method |
| CN114549336B (en) * | 2021-11-25 | 2024-05-03 | 湖南科技大学 | Unsupervised image defogging method |
| CN115063404A (en) * | 2022-07-27 | 2022-09-16 | 建首(山东)钢材加工有限公司 | Weathering resistant steel weld joint quality detection method based on X-ray flaw detection |
| CN115063404B (en) * | 2022-07-27 | 2022-11-08 | 建首(山东)钢材加工有限公司 | Weathering resistant steel weld joint quality detection method based on X-ray flaw detection |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112907461B (en) | 2023-05-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Huang et al. | An efficient visibility enhancement algorithm for road scenes captured by intelligent transportation systems | |
| Ju et al. | Single image dehazing via an improved atmospheric scattering model | |
| CN107301623B (en) | Traffic image defogging method and system based on dark channel and image segmentation | |
| Gao et al. | Sand-dust image restoration based on reversing the blue channel prior | |
| CN111667433B (en) | Unmanned aerial vehicle image defogging method based on simple linear iterative clustering optimization | |
| CN109389569B (en) | Monitoring video real-time defogging method based on improved DehazeNet | |
| CN105447825B (en) | Image defogging method and its system | |
| CN112907461A (en) | Defogging and enhancing method for infrared degraded image in foggy day | |
| CN110827218A (en) | Airborne image defogging method based on image HSV transmissivity weighted correction | |
| CN111598814B (en) | Single image defogging method based on extreme scattering channel | |
| CN110349113B (en) | Adaptive image defogging method based on dark primary color priori improvement | |
| CN109949239B (en) | Self-adaptive sharpening method suitable for multi-concentration multi-scene haze image | |
| CN105023246B (en) | A kind of image enchancing method based on contrast and structural similarity | |
| CN106023118A (en) | Image defogging method and realization method on FPGA | |
| CN107085830B (en) | Single image defogging method based on propagation filtering | |
| CN109345479B (en) | Real-time preprocessing method and storage medium for video monitoring data | |
| Fu et al. | Scene-awareness based single image dehazing technique via automatic estimation of sky area | |
| Khan et al. | Recent advancement in haze removal approaches | |
| Pandey et al. | A fast and effective vision enhancement method for single foggy image | |
| Zhen et al. | Single Image Defogging Algorithm based on Dark Channel Priority. | |
| CN117611501A (en) | Low-illumination image enhancement method, device, equipment and readable storage medium | |
| Trongtirakul et al. | Transmission map optimization for single image dehazing | |
| CN112598777B (en) | Haze fusion method based on dark channel prior | |
| Chengtao et al. | Improved dark channel prior dehazing approach using adaptive factor | |
| Xu | Novel Image Dehazing Algorithm Using Scene Segmentation and Open Channel 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 |