CN111489319A - Infrared image enhancement method based on multi-scale bilateral filtering and visual saliency - Google Patents
Infrared image enhancement method based on multi-scale bilateral filtering and visual saliency Download PDFInfo
- Publication number
- CN111489319A CN111489319A CN202010307466.1A CN202010307466A CN111489319A CN 111489319 A CN111489319 A CN 111489319A CN 202010307466 A CN202010307466 A CN 202010307466A CN 111489319 A CN111489319 A CN 111489319A
- Authority
- CN
- China
- Prior art keywords
- image
- infrared image
- infrared
- filtering
- visual saliency
- 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
- 238000001914 filtration Methods 0.000 title claims abstract description 42
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000000007 visual effect Effects 0.000 title claims abstract description 27
- 230000002146 bilateral effect Effects 0.000 title claims abstract description 26
- 230000010287 polarization Effects 0.000 claims abstract description 30
- 230000004927 fusion Effects 0.000 claims abstract description 10
- 238000004458 analytical method Methods 0.000 claims abstract description 6
- 238000000605 extraction Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract 1
- 238000012545 processing Methods 0.000 description 18
- 238000003384 imaging method Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000005855 radiation Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000003331 infrared imaging Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000028161 membrane depolarization Effects 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000004377 microelectronic Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 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
- G06T5/20—Image enhancement or restoration by the use of local operators
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20028—Bilateral filtering
Abstract
The invention discloses an infrared image enhancement method based on multi-scale bilateral filtering and visual saliency. In addition, a visual saliency analysis method is adopted to extract a saliency region of an original image, the saliency region is subjected to weighted fusion with a background layer of the image, and then the background layer and a detail layer subjected to denoising are subjected to weighted fusion to obtain an enhanced image. The method is simultaneously suitable for the infrared intensity image and the infrared polarization degree image, has good effects on the aspects of improving the contrast of the image and removing the blur, and ensures that the image details are clearer.
Description
Technical Field
The invention relates to the technical field of infrared image processing, in particular to an infrared image enhancement method based on multi-scale bilateral filtering and visual saliency.
Background
Traditional infrared imaging utilizes the radiation difference of a target and a background to detect, and only can acquire the intensity information of a scene. However, the object produces infrared polarization information during the process of transmitting, scattering, reflecting and transmitting electromagnetic waves. The infrared polarization imaging technology can not only detect infrared intensity information of a scene, but also detect infrared polarization information. The technology can well distinguish the target and the background with the same thermal radiation but different polarization characteristics, can make up the defects in the traditional infrared imaging, and the infrared polarization imaging technology becomes the third imaging detection technology which is subsequent to the traditional intensity detection and spectrum detection, thereby being concerned by the academic and industrial fields
There are several detection modes for infrared polarization imaging, including time-sharing, amplitude-dividing, aperture-dividing and focal plane polarization imaging modes. The first three imaging modes have certain defects more or less, the time-sharing polarization imaging system is only suitable for static scenes through a mechanical rotary structure, and fixed noise is introduced due to mechanical shaking; the amplitude-division type polarization imaging system divides incident light into a plurality of light paths, the structure is large and complex, errors are easy to occur in light path alignment, and the problem of low signal-to-noise ratio is caused; the aperture-splitting polarization imaging system separates polarization components by using separate apertures, and projects the polarization components to different areas of a focal plane, so that the image distortion problem can be caused due to parallax, and the resolution can be reduced; with the development of microelectronic technology and MEMS technology, the uncooled infrared focus-separating planar polarization imaging system based on sub-wavelength metal grating uses a composite super pixel structure, which is a research hotspot due to its high integration level, miniaturization, and ability to effectively extract the polarization characteristics of the target. The system can simultaneously detect infrared intensity information in different polarization directions, can output 14bit original intensity data, and can also obtain images of polarization degree and polarization angle by performing depolarization processing on the infrared intensity data by using a Stokes representation method. However, infrared radiation and transmission characteristics in different environments cause the problems of low signal-to-noise ratio, weak detail blurring, low contrast and the like of an infrared image and infrared polarization degree, and a proper image enhancement method for solving the problems does not exist at present.
Disclosure of Invention
In order to solve the problems of low signal-to-noise ratio, low contrast ratio and the like of an infrared intensity image and an infrared polarization degree image output by an uncooled infrared focal plane type polarization imaging system, the invention provides an infrared image enhancement method based on multi-scale bilateral filtering and visual saliency.
The invention is realized by the following technical scheme:
an infrared image enhancement method based on multi-scale bilateral filtering and visual saliency comprises the following steps:
step one, inputting an infrared image Iin;
Step two, adopting a multi-scale bilateral filtering method to carry out filtering on the input infrared image IinCarrying out layering treatment, and dividing the layering treatment into a background layer and N detail layers;
step three, inputting the infrared image IinExtracting significant region and determining infrared image IinA region of visual saliency;
step four, filtering the N detail layers obtained in the step two by using Gaussian filter operators with different scales to obtain N high-frequency layers after filtering;
step five, carrying out weighted fusion on the background layer obtained in the step two and the visual saliency area obtained in the step three to obtain a low-frequency layer;
step six, weighting the high-frequency layer obtained in the step four and the low-frequency layer obtained in the step five to obtain an enhanced output image Iout。
The invention utilizes multi-scale Bilateral Filter (MBF) to carry out layering processing on the image, decomposes the image into a background layer and a detail layer and carries out denoising processing on the detail layer. In addition, a Visual Saliency analysis method (VSM) is adopted to extract a Saliency region of the original image, the Saliency region is subjected to weighted fusion with a background layer of the image, and then the background layer and a detail layer subjected to denoising are subjected to weighted fusion to obtain an enhanced image. The image quality can be effectively improved, and the details are enhanced.
Preferably, the inventionThe multi-scale bilateral filtering method adopted in the second step is expressed as uj=MBF(uj-1,σs j-1,σrT) in which u0For an input image IinT is the number of iterations, σsIs a scale factor, σrThe radius of operation is chosen, and each iteration has a scale factor twice that of the previous iteration.
Preferably, in step three of the present invention, a visual saliency analysis method is used to extract a saliency region for the input infrared image IinPixel point I ofpA significance value V (p) ofWherein L is an infrared image IinN is the infrared image IinNumber of pixels of, MjRepresenting an infrared image IinIntensity of the middle pixel point is IjThe number of the pixels.
Preferably, in step four of the present invention, the scale factor σ corresponding to the detail layer of different scales is usedsThe Gaussian filtering method is used for filtering, and the selected filtering area is an eight-neighborhood.
Preferably, in the weighted fusion in step five of the present invention, the significant region obtained in step three is specifically used as the weight of the low frequency layer, and the significant region is multiplied by the background layer obtained in step two to obtain the low frequency layer.
Preferably, in the sixth step of the present invention, N high frequency layers and N low frequency layers are added and then normalized to obtain the output image Iout。
Preferably, the infrared image I of the present inventioninAn infrared intensity image or an infrared polarization image. The invention can carry out image enhancement processing on the infrared light intensity image and the infrared polarization degree image output by the infrared polarization detector.
The invention has the following advantages and beneficial effects:
compared with the existing infrared image enhancement technology, the method can directly carry out image enhancement processing on the infrared intensity image and the infrared polarization degree image, can effectively filter the noise of different scale structures by adopting a multi-scale bilateral filtering method, and enables the image to better accord with the visual characteristics of human eyes by utilizing a visual saliency analysis method.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention. In the drawings:
FIG. 1 is a schematic flow chart of the method of the present invention.
Fig. 2 is an infrared intensity image without enhancement (raw) in the present invention.
FIG. 3 is an intermediate processed image obtained during processing of an infrared intensity image using the present invention.
FIG. 4 is an output image after the infrared intensity image is enhanced by the present invention.
Fig. 5 is an infrared polarization image without enhancement (raw) in the present invention.
Fig. 6 is an output image after enhancement processing by the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to examples and accompanying drawings, and the exemplary embodiments and descriptions thereof are only used for explaining the present invention and are not meant to limit the present invention.
Example 1
The embodiment provides an infrared image enhancement method based on multi-scale bilateral filtering and visual saliency, and as shown in fig. 1, the method of the embodiment mainly includes the following steps:
step one, image layering processing: input image IinApplying a Multiscale Bilateral Filter (MBF) method to the input image IinPerforming layering treatment to decompose into a background layerAnd N detail layersWherein the background layer is a low-frequency layer, and the detail layer is a high-frequency layer.
In this embodiment, the calculation formula of the adopted multi-scale bilateral filtering method is as follows:
uj=MBF(uj-1,σs j-1,σrt), u in the formulajWhere j denotes the jth iteration, where u0For an input image IinI.e. u0=IinT is the number of iterations, σsIs a scale factor, σrIs the operating radius. To avoid the algorithm time consumption, a larger scale factor sigma is usually adopteds. The larger the scale factor selected in each iteration is, the two times of the previous iteration is.
For single-step bilateral filtering, the calculation formula is:
wherein (x, y) is the central pixel position, (i, j) is the central pixel point region pixel point position, W(i,j)Representing results after bilateral filtering, ws(i, j) denotes a Gaussian filter, wrAnd (i, j) denotes an edge-preserving filter.
Step two, salient region extraction: input image IinInput image I is subjected to visual saliency analysis (VSM) methodinExtracting salient regions to find an input image IinVisual saliency area (V) ofregion)。
In the present embodiment, for the input image IinPixel point I of gray scale image IpA significance value V (p) of Wherein L is the gray scale number of gray scale image I, N is the number of pixels of gray scale image I, MjRepresenting the intensity of a pixel point in a gray-scale image I as IiThe number of the pixels.
Step three, high-frequency treatment: for the N detail layers obtained in the step oneFiltering by using Gaussian filtering operators with different scales to obtain N high-frequency layers after filtering
Step four, low-frequency processing: for the background layer obtained in the step oneAnd the visually significant region (V) obtained in the second stepregion) Performing weighted fusion to obtain a low frequency layer
In this embodiment, the visually significant region (V) obtained in step tworegion) The weight of the low frequency layer is combined with the background layer obtained in the step oneMultiplying to obtain a low frequency layer
Step five, the high-frequency layer obtained in the step three is usedAnd the low frequency layer obtained in the fourth stepWeighting to obtain enhanced output image Iout。
Example 2
In this embodiment, the infrared image enhancement method proposed in embodiment 1 is adopted to perform enhancement processing on the infrared intensity image (shown in fig. 2), that is, the input image Iin. The specific process is as follows:
step one, image layering processing. Input infrared intensity image IinIs shown byinPerforming hierarchical processing by using a Multiscale Bilateral Filter (MBF) method, and decomposing the Filter into a background layerAnd N detail layersWherein the background layer is a low-frequency layer, and the detail layer is a high-frequency layer;
the calculation formula of the MBF method adopted in this embodiment is as follows: u. ofj=MBF(uj-1,σs j-1,σr,t),u0=IinT is the number of iterations, which is 2, σ in this embodimentsIs a scale factor, σrThe operation area of this embodiment is eight fields. To avoid the algorithm time consumption, a larger scale factor sigma is usually adopteds. The second iteration selects a scale factor twice that of the previous iteration.
For single-step bilateral filtering, the calculation formula is:
wherein (x, y) is the central pixel position, and (i, j) is the central pixel point region pixel position.
The image after the step-one layering process is shown in FIG. 3, in which IbaseAs a background layer, Idetail1,Idetail2Detail layers after two iterations.
And step two, extracting the salient region. Input image IinObject I by Visual SaliencyMap (VSM) methodinExtracting significant region to find IinVisual saliency area (V) ofregion);
For input image IinPixel point I of gray scale image IpA significance value V (p) ofWherein L is the gray scale number of I, N is the number of pixels of I, MjIndicating the intensity of the pixel point in I as IjThe number of the pixels.
The image after the step-one layering process is shown as VSM in FIG. 3
Step three, high-frequency treatment. Filtering the 2 detail layers obtained in the step one by using Gaussian filter operators with different scales to obtain a filtered high-frequency layer image Ihigh1And Ihigh2;
The gaussian filter is calculated as:
For each detail layer of different scale, use the corresponding scale parameter sigmasThe filtering is performed by the gaussian filtering method, and the filtering area usually selected is eight neighborhoods.
And step four, low-frequency processing. For the background layer (I) obtained in step onebase) Carrying out weighted fusion with the visual saliency region image (VSM) obtained in the step two to obtain a low-frequency layer (I)low);
In this embodiment, VSM is used as the weight value and multiplied by IbaseImage, obtaining a low frequency image Ilow;
Step five, the product obtained in the step threeThe high frequency layer and the low frequency layer obtained in step four are weighted, i.e. Iout=Ihigh1+Ihigh2+IlowObtaining an enhanced output image Iout。
In order to meet the output requirement of the display equipment, the embodiment enhances the image IoutNormalized to a 256 gray scale number.
The image processed in step five is shown in fig. 4.
The infrared polarization degree image is processed in the same flow as the infrared intensity image, namely an input image IinThe infrared polarization degree image in the present embodiment is shown in fig. 5.
The infrared polarization degree enhanced image processed by the invention is shown in fig. 6.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (7)
1. The infrared image enhancement method based on multi-scale bilateral filtering and visual saliency is characterized by comprising the following steps of:
step one, inputting an infrared image Iin;
Step two, adopting a multi-scale bilateral filtering method to carry out filtering on the input infrared image IinCarrying out layering treatment, and dividing the layering treatment into a background layer and N detail layers;
step three, inputting the infrared image IinExtracting significant region and determining infrared image IinA region of visual saliency;
step four, filtering the N detail layers obtained in the step two by using Gaussian filter operators with different scales to obtain N high-frequency layers after filtering;
step five, carrying out weighted fusion on the background layer obtained in the step two and the visual saliency area obtained in the step three to obtain a low-frequency layer;
step six, weighting the high-frequency layer obtained in the step four and the low-frequency layer obtained in the step five to obtain an enhanced output image Iout。
2. The infrared image enhancement method based on multi-scale bilateral filtering and visual saliency characterized in that said step two adopts a multi-scale bilateral filtering method denoted as uj=MBF(uj-1,σs j-1,σrT) in which u0For an input image IinT is the number of iterations, σsIs a scale factor, σrThe radius of operation is chosen, and each iteration has a scale factor twice that of the previous iteration.
3. The infrared image enhancement method based on multi-scale bilateral filtering and visual saliency as claimed in claim 1, characterized in that in step three of the present invention, a visual saliency analysis method is used to perform saliency region extraction for an input infrared image IinPixel point I ofpA significance value V (p) ofWherein L is an infrared image IinN is the infrared image IinNumber of pixels of, MjRepresenting an infrared image IinIntensity of the middle pixel point is IjThe number of the pixels.
4. The infrared image enhancement method based on multi-scale bilateral filtering and visual saliency characterized in that the four steps use the corresponding scale factor σ for detail layers of different scalessThe Gaussian filtering method is used for filtering, and the selected filtering area is an eight-neighborhood.
5. The infrared image enhancement method based on multi-scale bilateral filtering and visual saliency as claimed in claim 1, wherein said weighted fusion in step five specifically uses the saliency region obtained in step three as the weight of the low frequency layer, and multiplies it by the background layer obtained in step two to obtain the low frequency layer.
6. The infrared image enhancement method based on multi-scale bilateral filtering and visual saliency as claimed in claim 1, wherein in said sixth step, N high frequency layers and N low frequency layers are added and then normalized to obtain an output image Iout。
7. The infrared image enhancement method based on multi-scale bilateral filtering and visual saliency characterized in that according to any one of claims 1 to 6, the infrared image I isinAn infrared intensity image or an infrared polarization image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010307466.1A CN111489319A (en) | 2020-04-17 | 2020-04-17 | Infrared image enhancement method based on multi-scale bilateral filtering and visual saliency |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010307466.1A CN111489319A (en) | 2020-04-17 | 2020-04-17 | Infrared image enhancement method based on multi-scale bilateral filtering and visual saliency |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111489319A true CN111489319A (en) | 2020-08-04 |
Family
ID=71798289
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010307466.1A Pending CN111489319A (en) | 2020-04-17 | 2020-04-17 | Infrared image enhancement method based on multi-scale bilateral filtering and visual saliency |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111489319A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112308793A (en) * | 2020-10-21 | 2021-02-02 | 淮阴工学院 | Novel method for enhancing contrast and detail of non-uniform illumination image |
CN113269704A (en) * | 2021-06-29 | 2021-08-17 | 南昌航空大学 | Infrared and visible light image fusion method |
CN114693577A (en) * | 2022-04-20 | 2022-07-01 | 合肥工业大学 | Infrared polarization image fusion method based on Transformer |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102005037A (en) * | 2010-11-12 | 2011-04-06 | 湖南大学 | Multimodality image fusion method combining multi-scale bilateral filtering and direction filtering |
CN103907109A (en) * | 2011-06-27 | 2014-07-02 | 耶路撒冷希伯来大学伊萨姆研究发展有限公司 | Applying rapid numerical approximation of convolutions with filters for image processing purposes |
CN104463822A (en) * | 2014-12-11 | 2015-03-25 | 西安电子科技大学 | Multi-focus image fusing method and device based on multi-scale overall filtering |
CN105844601A (en) * | 2016-05-20 | 2016-08-10 | 中国矿业大学(北京) | Mine image enhancement method based on bilateral filtering and multi-scale Retinex algorithm |
CN106846289A (en) * | 2017-01-17 | 2017-06-13 | 中北大学 | A kind of infrared light intensity and polarization image fusion method based on conspicuousness migration with details classification |
CN108376391A (en) * | 2018-01-29 | 2018-08-07 | 江苏宇特光电科技股份有限公司 | A kind of intelligence infrared image scene Enhancement Method |
CN108492274A (en) * | 2018-04-03 | 2018-09-04 | 中国人民解放军国防科技大学 | Long-wave infrared polarization feature extraction and fusion image enhancement method |
CN109754384A (en) * | 2018-12-18 | 2019-05-14 | 电子科技大学 | A kind of uncooled ir divides the infrared polarization image interfusion method of focal plane arrays (FPA) |
CN109919861A (en) * | 2019-01-29 | 2019-06-21 | 浙江数链科技有限公司 | Infrared image enhancing method, device, computer equipment and storage medium |
CN110175970A (en) * | 2019-05-20 | 2019-08-27 | 桂林电子科技大学 | Based on the infrared and visible light image fusion method for improving FPDE and PCA |
CN110415202A (en) * | 2019-07-31 | 2019-11-05 | 浙江大华技术股份有限公司 | A kind of image interfusion method, device, electronic equipment and storage medium |
CN110619647A (en) * | 2019-09-16 | 2019-12-27 | 中山大学 | Method for positioning fuzzy region of image based on combination of edge point frequency domain and spatial domain characteristics |
-
2020
- 2020-04-17 CN CN202010307466.1A patent/CN111489319A/en active Pending
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102005037A (en) * | 2010-11-12 | 2011-04-06 | 湖南大学 | Multimodality image fusion method combining multi-scale bilateral filtering and direction filtering |
CN103907109A (en) * | 2011-06-27 | 2014-07-02 | 耶路撒冷希伯来大学伊萨姆研究发展有限公司 | Applying rapid numerical approximation of convolutions with filters for image processing purposes |
CN104463822A (en) * | 2014-12-11 | 2015-03-25 | 西安电子科技大学 | Multi-focus image fusing method and device based on multi-scale overall filtering |
CN105844601A (en) * | 2016-05-20 | 2016-08-10 | 中国矿业大学(北京) | Mine image enhancement method based on bilateral filtering and multi-scale Retinex algorithm |
CN106846289A (en) * | 2017-01-17 | 2017-06-13 | 中北大学 | A kind of infrared light intensity and polarization image fusion method based on conspicuousness migration with details classification |
WO2019144581A1 (en) * | 2018-01-29 | 2019-08-01 | 江苏宇特光电科技股份有限公司 | Smart infrared image scene enhancement method |
CN108376391A (en) * | 2018-01-29 | 2018-08-07 | 江苏宇特光电科技股份有限公司 | A kind of intelligence infrared image scene Enhancement Method |
CN108492274A (en) * | 2018-04-03 | 2018-09-04 | 中国人民解放军国防科技大学 | Long-wave infrared polarization feature extraction and fusion image enhancement method |
CN109754384A (en) * | 2018-12-18 | 2019-05-14 | 电子科技大学 | A kind of uncooled ir divides the infrared polarization image interfusion method of focal plane arrays (FPA) |
CN109919861A (en) * | 2019-01-29 | 2019-06-21 | 浙江数链科技有限公司 | Infrared image enhancing method, device, computer equipment and storage medium |
CN110175970A (en) * | 2019-05-20 | 2019-08-27 | 桂林电子科技大学 | Based on the infrared and visible light image fusion method for improving FPDE and PCA |
CN110415202A (en) * | 2019-07-31 | 2019-11-05 | 浙江大华技术股份有限公司 | A kind of image interfusion method, device, electronic equipment and storage medium |
CN110619647A (en) * | 2019-09-16 | 2019-12-27 | 中山大学 | Method for positioning fuzzy region of image based on combination of edge point frequency domain and spatial domain characteristics |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112308793A (en) * | 2020-10-21 | 2021-02-02 | 淮阴工学院 | Novel method for enhancing contrast and detail of non-uniform illumination image |
CN113269704A (en) * | 2021-06-29 | 2021-08-17 | 南昌航空大学 | Infrared and visible light image fusion method |
CN113269704B (en) * | 2021-06-29 | 2022-07-29 | 南昌航空大学 | Infrared and visible light image fusion method |
CN114693577A (en) * | 2022-04-20 | 2022-07-01 | 合肥工业大学 | Infrared polarization image fusion method based on Transformer |
CN114693577B (en) * | 2022-04-20 | 2023-08-11 | 合肥工业大学 | Infrared polarized image fusion method based on Transformer |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Chen et al. | Robust image and video dehazing with visual artifact suppression via gradient residual minimization | |
CN101860667B (en) | Method of quickly eliminating composite noise in images | |
CN111489319A (en) | Infrared image enhancement method based on multi-scale bilateral filtering and visual saliency | |
CN110097634B (en) | Self-adaptive multi-scale three-dimensional ghost imaging method | |
Biradar et al. | A novel image inpainting technique based on median diffusion | |
Singh et al. | Weighted least squares based detail enhanced exposure fusion | |
KR102195047B1 (en) | Method and apparatus for enhancing quality of 3D image | |
Liu et al. | Infrared and visible image fusion and denoising via ℓ2− ℓp norm minimization | |
CN115880177A (en) | Full-resolution low-illumination image enhancement method for aggregating context and enhancing details | |
Dou et al. | Anti-forensics of diffusion-based image inpainting | |
CN105608674B (en) | A kind of image enchancing method based on image registration, interpolation and denoising | |
Guo et al. | Haze removal for single image: A comprehensive review | |
US20180033156A1 (en) | Method and device for filtering texture, using patch shift | |
CN116433496A (en) | Image denoising method, device and storage medium | |
Hung et al. | Moran’s I for impulse noise detection and removal in color images | |
Wang et al. | A bilateral filtering based ringing elimination approach for motion-blurred restoration image | |
Wang et al. | Kernel optimization for blind motion deblurring with image edge prior | |
CN116579959A (en) | Fusion imaging method and device for hyperspectral image | |
Zhang et al. | A new image filtering method: Nonlocal image guided averaging | |
JP4405407B2 (en) | Defect inspection equipment | |
Yao et al. | A multi-expose fusion image dehazing based on scene depth information | |
Wu et al. | Learning to joint remosaic and denoise in quad bayer cfa via universal multi-scale channel attention network | |
Holla et al. | EFID: edge-focused image denoising using a convolutional neural network | |
Singh et al. | Multifocus and multiexposure techniques | |
Quan | Quality evaluation method of agricultural product packaging image based on structural similarity and MTF |
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 |