CN105321172A - SAR, infrared and visible light image fusion method - Google Patents
SAR, infrared and visible light image fusion method Download PDFInfo
- Publication number
- CN105321172A CN105321172A CN201510547150.9A CN201510547150A CN105321172A CN 105321172 A CN105321172 A CN 105321172A CN 201510547150 A CN201510547150 A CN 201510547150A CN 105321172 A CN105321172 A CN 105321172A
- Authority
- CN
- China
- Prior art keywords
- image
- infrared
- fusion
- sar
- value
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration by the use of more than one image, e.g. averaging, subtraction
-
- 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
- G06T2207/20048—Transform domain processing
- G06T2207/20064—Wavelet transform [DWT]
-
- 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
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Abstract
The present invention discloses an SAR, infrared and visible light image fusion method. The method comprises the following steps: step 1, acquiring original SAR, infrared and visible light images separately for a same target scene; step 2, de-noising the acquired original infrared and visible light images, and performing de-speckling treatment on the original SAR image; and step 3, carrying out registration and fusion of the SAR, infrared and visible light images by using a mutual information based registration method and a wavelet transformation based fusion method. By adopting the method disclosed by the present invention, the SAR, infrared and visible light images are fused; the properties of a multi-source image sensor are organically combined; the potential of a variety of image data is fully tapped; and the accuracy and efficiency of remote sensing interpretation and information extraction are improved.
Description
Technical field
The invention belongs to technical field of image processing, relate to a kind of image registration and image interfusion method, especially relate to a kind of method of SAR, infrared, visual image fusion.
Background technology
Along with the fast development of space technology and the continuous appearance of novel sensor, people can obtain the data such as a large amount of different spatial resolutions, different time resolution, the SAR of different spectral resolution, infrared, visible ray, thus constitute the multi-level Remote Sensing image set for global change research due, gis database renewal, environmental monitoring, resource exploration, Disaster Assessment and the aspect such as control, Military Application.In order to make full use of all kinds of sensor informations from different sensors, overcoming remote sensing image information and extracting the deficiency with decipher single piece of information source, multi-sensor information fusion technology is that the fusion utilization of multi-source remote sensing information provides a main solution route.So-called information fusion, refer under certain criterion, the information from multiple sensor carried out at many levels, many-sided, multi-level process with comprehensive, thus acquisition more reliably, more accurately, abundanter information.
SAR belongs to active microwave imaging sensor, and penetrability is good, has ability that is round-the-clock, round-the-clock earth observation, mainly according to the imaging of the characteristic such as Permittivity of ground materials and surfaceness; Infrared image sensor is mainly according to the thermal radiation property imaging of object; Visible light image sensor is mainly according to the spectral reflection characteristic imaging of object.Thus, under normal circumstances, the atural object profile of SAR image is clear, and contrast, structural information are relatively good, has abundant texture information; Infrared image gives target well and there is characteristic and position characteristic, but object edge is fuzzy; And visible images contains abundant object spectrum information, the environmental information in scene can be described well.Therefore, adopt image fusion technology the characteristic of multi-source image sensor organically to be combined, the potentiality of multiple view data can be given full play to, improve precision and the efficiency of remote Sensing Interpretation and information extraction.
Summary of the invention
The object of this invention is to provide a kind of method of SAR, infrared, visual image fusion, the method not only obtains the fused images with superior quality, also has higher fusion speed simultaneously.
The technical solution adopted for the present invention to solve the technical problems is as follows:
A method for SAR, infrared, visual image fusion, comprises the following steps:
Step one, for same target scene, gather former SAR, infrared, visible images respectively.
Step 2, the former infrared and visible images collected is carried out to denoising, falls spot process to former SAR image:
(1) propose a kind of new ADAPTIVE MIXED noise filtering method and respectively denoising carried out to the former infrared and visible images collected:
If be g containing noisy image, its size is P × Q pixel, and filtering output image is f.From left to right filtering is from top to bottom carried out to Noise image.
1) detection noise type
First, centered by pixel (i, j) in noise image g, selected pixels is 3 × 3 window S
pq, obtain the variance of pixel in spectral window:
In formula,
i (i, j) represents the gray-scale value at point (i, j) place.
Threshold value is made to be T
1, it arranges the linear function that territory is spectral window average gray value m, i.e. T
1=-k × m+b, gets k=0.15 here, b=80.
Judge σ
2with T
1magnitude relationship: work as σ
2> T
1time, then think the pollution being subject to salt-pepper noise in this spectral window, to perform in step (2) 1.; Work as σ
2< T
1time, then think the pollution being subject to Gaussian noise in this spectral window, to perform in step (2) 2..
2) filtering algorithm
1. filtering algorithm is polluted by salt-pepper noise
A, first, obtain gray scale maximal value max and minimum value min in spectral window, then the gray-scale value g (i, j) of pixel each in spectral window (i, j ∈ filter window S
pq) compare with maximal value and minimum value, remove the pixel that those equal maximal value or minimum value.
If residual pixel is non-vanishing in b spectral window, then obtain the mean value M of residual pixel, and calculate the absolute value d=|M-g (i, j) of the difference of mean pixel gray-scale value and spectral window mid point grey scale pixel value |.By the threshold value T of this absolute value and setting
1compare, if d > is T
1, then residual pixel average M is exported; If d < is T
1, then output filtering window mid point grey scale pixel value g (i, j).
If residual pixel is zero in c spectral window, then expands filter window and be of a size of 5 × 5, and repeat above-mentioned steps a, b, if residual pixel is still zero, then image exports and is:
2. filtering algorithm is polluted by Gaussian noise
A, first calculate the gradient absolute value of pixel in spectral window:
td＝|g(i-1，j)+g(i，j-1)+g(i，j+1)+g(i+1，j)-4g(i，j)|(3)。
If b gradient absolute value td is greater than a certain given threshold value T
2(T
2=-k × m+b, m is spectral window average gray value, gets k=0.3, b=160 here), then directly export preimage element; Otherwise, output filtering window grey scale pixel value average.
3) step 1 is repeated) and 2), until complete the filtering process of all pixels, finally obtain except the image after making an uproar.
(2) utilization falls spot process based on the SAR image denoising method of rarefaction representation to the former SAR image collected, and its concrete steps are as follows:
A, non local filtering process is carried out to former SAR image, obtain low-frequency image f
lowpass;
B, deduct non local filtering process by former SAR image after the low-frequency image f that obtains
lowpassobtain the high frequency imaging of Noise and part edge texture;
C, dividing processing is carried out to the high frequency imaging that upper step obtains, adopt shearing wave to extract linear target image C wherein, adopt small echo to extract point target image P wherein;
D, by low-frequency image f obtained above
lowpassbe weighted fusion with linear target image C, point target image P, obtain final image f
fusion.Detailed process is:
f
fusion＝αf
lowpass+βP+γC(4)，
In formula, f
fusionfor Weighted Fusion gained image; f
lowpassfor non local filtering gained low-frequency image part; P is the point target image extracted from high frequency imaging; C is the linear target image extracted from high frequency imaging; α, β, γ are weighting coefficient, alpha+beta+γ=1, and the determination of weighting coefficient needs to determine according to the feature of target in image.
Step 3, utilize the method for registering based on mutual information and the fusion method based on wavelet transformation that SAR, infrared, visible images are carried out registration fusion:
(1) SAR image after process and visible images are carried out registration fusion, obtain registration fused images C
1, its concrete steps are as follows:
A, the two width images preparing to carry out registration fusion are set to benchmark image A and floating image B respectively;
B, in floating image B, choose that total part of two width images, as matching template image B
1;
C, setting initial point, generally from the starting point of the upper left corner, by matching template B
1slide in benchmark image A and calculate the region association relationship between two width images;
The search strategy of d, employing genetic algorithm, by comparing the size of gradient association relationship, constantly changes spatial alternation coordinate, until find the global optimum of region association relationship, and exports corresponding position, namely obtains optimum registration parameter;
E, utilize wavelet transformation to be merged by two width images after registration, obtain last registration fused images.
(2) infrared image after process and visible images are carried out registration fusion, obtain registration fused images C
2, concrete steps are with a ~ e in (1).
(3) by obtain SAR, visible ray registration fused images C
1with registration fused images C that is infrared, visible ray
2carry out registration fusion, obtain fused images C
3, concrete steps are with a ~ e in (1).
The present invention compared with prior art, has the following advantages:
The first, SAR, infrared, visible images merge by the present invention, the characteristic of multi-source image sensor are organically combined, have given full play to the potentiality of multiple view data, improve precision and the efficiency of remote Sensing Interpretation and information extraction.
Second, the method of the SAR proposed in the present invention, infrared, visual image fusion, the fused images with superior quality can not only be obtained, also there is higher fusion speed, thus have broad application prospects in the military affairs such as night vision reconnaissance, remote sensing, medical science, safety monitoring and civil field.
3rd, a kind of new ADAPTIVE MIXED noise filtering algorithm is proposed when carrying out denoising to the former visible ray collected and infrared image in the present invention.Medium filtering, mean filter combine with Threshold selection by this algorithm, can not only filtering noise well, and can protect the details of image preferably.
Four, propose a kind of SAR image based on rarefaction representation in the present invention when falling spot process to the SAR image collected and fall spot algorithm, the useful information of image medium-high frequency part can be made full use of, take into account noise suppression effect and grain details reservation.This algorithm is a kind of effectively for the SAR image Speckle Reduction Algorithm of high resolving power, texture-rich.
5th, adopt Wavelet Transform to decompose image in the present invention when carrying out image co-registration.Because in wavelet decomposition process, the data volume of image is constant, the fusion of each layer simultaneously can walk abreast and carry out, and its computing velocitys all and required memory space all have good advantage.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of SAR, infrared, visible light image fusion method;
Fig. 2 falls spot processing flow chart based on the SAR image of rarefaction representation;
Fig. 3 is that process flow diagram is merged in image registration.
Embodiment
Below in conjunction with accompanying drawing, technical scheme of the present invention is further described; but be not limited thereto; everyly technical solution of the present invention modified or equivalent to replace, and not departing from the spirit and scope of technical solution of the present invention, all should be encompassed in protection scope of the present invention.
The invention provides a kind of method of SAR, infrared, visual image fusion, as shown in Figure 1, comprise the following steps:
S1, for same target scene, gather former SAR, infrared, visible images respectively.
S2, the former infrared and visible images collected is carried out to denoising, falls spot process to former SAR image.
S21, propose a kind of new ADAPTIVE MIXED noise filtering method respectively denoising carried out to the former infrared and visible images collected:
If be g containing noisy image, size is P × Q, and filtering exports as f.From left to right filtering is from top to bottom carried out to Noise image.The concrete steps of image denoising process are as follows:
S211, detection noise type
First, centered by pixel (i, j) in noise image g, selected pixels is 3 × 3 window S
pq, obtain the variance of pixel in spectral window:
In formula,
i (i, j) represents the gray-scale value at point (i, j) place.
Threshold value is made to be T
1, it arranges the linear function that territory is spectral window average gray value m, i.e. T
1=-k × m+b, gets k=0.15 here, b=80.
Judge σ
2with T
1magnitude relationship: work as σ
2> T
1time, then think and the pollution being subject to salt-pepper noise in this spectral window perform step S2121; Work as σ
2< T
1time, then think and the pollution being subject to Gaussian noise in this spectral window perform step S2122.
S212, filtering algorithm
S2121 pollutes filtering algorithm by salt-pepper noise
A, first, obtain gray scale maximal value max and minimum value min in spectral window, then the gray-scale value g (i, j) of pixel each in spectral window (i, j ∈ filter window S
pq) compare with maximal value and minimum value, remove the pixel that those equal maximal value or minimum value.
If residual pixel is non-vanishing in b spectral window, then obtain the mean value M of residual pixel, and calculate the absolute value d=|M-g (i, j) of the difference of mean pixel gray-scale value and spectral window mid point grey scale pixel value |.By the threshold value T of this absolute value and setting
1compare, if d > is T
1, then residual pixel average M is exported; If d < is T
1, then output filtering window mid point grey scale pixel value g (i, j).
If residual pixel is zero in c spectral window, then expands filter window and be of a size of 5 × 5, and repeat above-mentioned steps a, b.If residual pixel is still zero, image exports and is:
S2122 pollutes filtering algorithm by Gaussian noise
First the gradient absolute value of pixel in spectral window is calculated:
td＝|g(i-1，j)+g(i，j-1)+g(i，j+1)+g(i+1，j)-4g(i，j)|。
If gradient absolute value td be greater than a certain to threshold value T
2(T
2=-k × m+b, m is spectral window average gray value, gets k=0.3, b=160 here), then directly export preimage element; Otherwise, output filtering window grey scale pixel value average.
S213, repeat above-mentioned steps S211 and S212, until complete the filtering process of all pixels, finally obtain except the image after making an uproar.
S22, the SAR image denoising method based on rarefaction representation is utilized to fall spot process to the former SAR image collected.As shown in Figure 2, its concrete steps are as follows:
S221, non local filtering process is carried out to former SAR image, obtain low-frequency image f
lowpass;
S222, deduct non local filtering process by former SAR image after the low-frequency image f that obtains
lowpassobtain the high frequency imaging of Noise and part edge texture;
S223, dividing processing is carried out to the high frequency imaging that upper step obtains, adopt shearing wave to extract linear target image C wherein, adopt small echo to extract point target image P wherein;
S224, by low-frequency image f obtained above
lowpassbe weighted fusion with linear target image C, point target image P, obtain final image f
fusion.Detailed process is:
f
fusion＝αf
lowpass+βP+γC，
In formula, f
fusionfor Weighted Fusion gained image; f
lowpassfor non local filtering gained low-frequency image part; P is the point target image extracted from high frequency imaging; C is the linear target image extracted from high frequency imaging; α, β, γ are weighting coefficient, alpha+beta+γ=1, and the determination of weighting coefficient needs to determine according to the feature of target in image.
S3, utilize the method for registering based on mutual information and the fusion method based on wavelet transformation that SAR, infrared, visible images are carried out registration fusion.
S31, SAR image and visible images are carried out registration fusion, obtain registration fused images C
1.
Image registration merges process flow diagram as shown in Figure 3, and specific algorithm is mainly as follows:
S311, the two width images preparing to carry out registration fusion are set to benchmark image A and floating image B respectively;
S312, in floating image B, choose the part had in two width images, as matching template image B
1;
S313, setting initial point, generally from the starting point of the upper left corner, by matching template B
1slide in benchmark image A and calculate the region association relationship between two width images;
The search strategy of S314, employing genetic algorithm, by comparing the size of gradient association relationship, constantly changes spatial alternation coordinate, until find the global optimum of region mutual information, and exports corresponding position, namely obtains optimum registration parameter;
S315, utilize wavelet transformation to be merged by two width images after registration, obtain last registration fused images.
S32, infrared image and visible images are carried out registration fusion, obtain registration fused images C
2, concrete steps are with the S311-S315 in S31.
S33, by obtain SAR, visible ray registration fused images C
1with registration fused images C that is infrared, visible ray
2carry out registration fusion, obtain fused images C
3, concrete steps are with the S311-S315 in S31.
Claims (9)
1. a method for SAR, infrared, visual image fusion, is characterized in that described method step is as follows:
Step one, for same target scene, gather former SAR, infrared, visible images respectively;
Step 2, the former infrared and visible images collected is carried out to denoising, falls spot process to former SAR image;
Step 3, utilize the method for registering based on mutual information and the fusion method based on wavelet transformation that SAR, infrared, visible images are carried out registration fusion.
2. the method for SAR according to claim 1, infrared, visual image fusion, is characterized in that the concrete steps of described step 2 are as follows:
(1) propose a kind of new ADAPTIVE MIXED noise filtering method and respectively denoising is carried out to the former infrared and visible images collected;
(2) utilization falls spot process based on the SAR image denoising method of rarefaction representation to the former SAR image collected.
3. the method for SAR according to claim 2, infrared, visual image fusion, is characterized in that the concrete steps of described denoising are as follows:
(1) detection noise type
First, centered by pixel (i, j) in noise image g, selected pixels is 3 × 3 window S
pq, obtain the variance of pixel in spectral window:
In formula,
i (i, j) represents the gray-scale value at point (i, j) place;
Threshold value is made to be T
1, work as σ
2> T
1time, then think the pollution being subject to salt-pepper noise in this spectral window, to perform in step (2) 1.; Work as σ
2< T
1time, then think the pollution being subject to Gaussian noise in this spectral window, to perform in step (2) 2.;
(2) filtering algorithm
1. filtering algorithm is polluted by salt-pepper noise
A, first, obtain gray scale maximal value max and minimum value min in spectral window, then the gray-scale value g (i, j) of pixel each in spectral window and maximal value and minimum value are compared, remove the pixel equaling maximal value or minimum value;
If residual pixel is non-vanishing in b spectral window, then obtain the mean value M of residual pixel, and calculate the absolute value d=|M-g (i, j) of the difference of mean pixel gray-scale value and spectral window mid point grey scale pixel value |, by the threshold value T of this absolute value and setting
1compare, if d > is T
1, then residual pixel average M is exported; If d < is T
1, then output filtering window mid point grey scale pixel value g (i, j);
If residual pixel is zero in c spectral window, then expands filter window and be of a size of 5 × 5, and repeat above-mentioned steps a, b, if residual pixel is still zero, then image exports and is:
2. filtering algorithm is polluted by Gaussian noise
A, first calculate the gradient absolute value of pixel in spectral window:
td＝|g(i-1，j)+g(i，j-1)+g(i，j+1)+g(i+1，j)-4g(i，j)|；
If b gradient absolute value is greater than a certain given threshold value T
2, then preimage element is directly exported; Otherwise, output filtering window grey scale pixel value average;
(3) repeat step (1) and (2), until complete the filtering process of all pixels, finally obtain except the image after making an uproar.
4. the method for SAR according to claim 3, infrared, visual image fusion, is characterized in that in described step (1), threshold value T
1=-k × m+b, m is spectral window average gray value, k=0.15, b=80.
5. the method for SAR according to claim 3, infrared, visual image fusion, in it is characterized in that described step is 2., threshold value T
2=-k × m+b, m is spectral window average gray value, k=0.3, b=160.
6. the method for SAR according to claim 2, infrared, visual image fusion, the concrete steps of falling spot process described in it is characterized in that are as follows:
A, non local filtering process is carried out to former SAR image, obtain low-frequency image f
lowpass;
B, deduct non local filtering process by former SAR image after the low-frequency image f that obtains
lowpassobtain the high frequency imaging of Noise and part edge texture;
C, dividing processing is carried out to the high frequency imaging that upper step obtains, adopt shearing wave to extract linear target image C wherein, adopt small echo to extract point target image P wherein;
D, by low-frequency image f obtained above
lowpassbe weighted fusion with linear target image C, point target image P, obtain final image f
fusion.
7. the method for SAR according to claim 6, infrared, visual image fusion, is characterized in that the detailed process of described steps d is:
f
fusion＝αf
lowpass+βP+γC，
In formula, f
fusionfor Weighted Fusion gained image; f
lowpassfor non local filtering gained low-frequency image part; P is the point target image extracted from high frequency imaging; C is the linear target image extracted from high frequency imaging; α, β, γ are weighting coefficient, alpha+beta+γ=1.
8. the method for SAR according to claim 1, infrared, visual image fusion, is characterized in that the concrete steps of described step 3 are as follows:
(1) SAR image after process and visible images are carried out registration fusion, obtain registration fused images C
1;
(2) infrared image after process and visible images are carried out registration fusion, obtain registration fused images C
2;
(3) by obtain SAR, visible ray registration fused images C
1with registration fused images C that is infrared, visible ray
2carry out registration fusion, obtain fused images C
3.
9. the method for SAR according to claim 7, infrared, visual image fusion, is characterized in that the concrete steps of described step (1) are as follows:
A, the two width images preparing to carry out registration fusion are set to benchmark image A and floating image B respectively;
B, in floating image B, choose the part had in two width images, as matching template image B
1;
C, setting initial point, generally from the starting point of the upper left corner, by matching template B
1slide in benchmark image A and calculate the region association relationship between two width images;
The search strategy of d, employing genetic algorithm, by comparing the size of gradient association relationship, constantly changes spatial alternation coordinate, until find the global optimum of region association relationship, and exports corresponding position, namely obtains optimum registration parameter;
E, utilize wavelet transformation to be merged by two width images after registration, obtain last registration fused images.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510547150.9A CN105321172A (en) | 2015-08-31 | 2015-08-31 | SAR, infrared and visible light image fusion method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510547150.9A CN105321172A (en) | 2015-08-31 | 2015-08-31 | SAR, infrared and visible light image fusion method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105321172A true CN105321172A (en) | 2016-02-10 |
Family
ID=55248487
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510547150.9A Pending CN105321172A (en) | 2015-08-31 | 2015-08-31 | SAR, infrared and visible light image fusion method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105321172A (en) |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105809649A (en) * | 2016-03-03 | 2016-07-27 | 西安电子科技大学 | Variation multi-scale decomposing based SAR image and visible light image integration method |
| CN106296624A (en) * | 2015-06-11 | 2017-01-04 | 联想(北京)有限公司 | A kind of image interfusion method and device |
| CN106407900A (en) * | 2016-08-31 | 2017-02-15 | 上海交通大学 | Multi-source aerial photo-based abnormal scene identification method |
| CN107918929A (en) * | 2016-10-08 | 2018-04-17 | 杭州海康威视数字技术股份有限公司 | A kind of image interfusion method, apparatus and system |
| CN108022230A (en) * | 2017-12-22 | 2018-05-11 | 青岛大学附属医院 | The more phase CT image fusion systems of kidney |
| CN108510532A (en) * | 2018-03-30 | 2018-09-07 | 西安电子科技大学 | Optics and SAR image registration method based on depth convolution GAN |
| CN108520494A (en) * | 2018-04-04 | 2018-09-11 | 西安电子科技大学 | SAR image based on structural condition mutual information and visible light image registration method |
| CN108564606A (en) * | 2018-03-30 | 2018-09-21 | 西安电子科技大学 | Heterologous image block matching method based on image conversion |
| CN108737728A (en) * | 2018-05-03 | 2018-11-02 | Oppo广东移动通信有限公司 | A kind of image capturing method, terminal and computer storage media |
| CN109584193A (en) * | 2018-10-24 | 2019-04-05 | 航天时代飞鸿技术有限公司 | A kind of unmanned plane based on target preextraction is infrared and visible light image fusion method |
| CN110243769A (en) * | 2019-07-30 | 2019-09-17 | 南阳理工学院 | A kind of the high spectrum sub-pixel target identification system and method for multi-source information auxiliary |
| CN110246164A (en) * | 2019-05-30 | 2019-09-17 | 中国科学院长春光学精密机械与物理研究所 | Visible images and SAR image registration method and system |
| 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 |
| CN110472658A (en) * | 2019-07-05 | 2019-11-19 | 哈尔滨工程大学 | A kind of the level fusion and extracting method of the detection of moving-target multi-source |
| CN110515079A (en) * | 2019-06-04 | 2019-11-29 | 沈阳瑞初科技有限公司 | Merge the visualization fusion method of SAR radar and infrared imagery technique |
| CN110930311A (en) * | 2018-09-19 | 2020-03-27 | 杭州萤石软件有限公司 | Method and device for improving signal-to-noise ratio of infrared image and visible light image fusion |
| CN111522007A (en) * | 2020-07-06 | 2020-08-11 | 航天宏图信息技术股份有限公司 | SAR imaging simulation method and system with real scene and target simulation fused |
| CN111583315A (en) * | 2020-04-23 | 2020-08-25 | 武汉卓目科技有限公司 | Novel visible light image and infrared image registration method and device |
| CN111652809A (en) * | 2019-07-29 | 2020-09-11 | 天津大学 | Infrared image noise suppression method for enhancing details |
| CN112666426A (en) * | 2020-11-13 | 2021-04-16 | 国网江苏省电力有限公司电力科学研究院 | Equipment fault detection method and system based on multispectral three-in-one image |
| CN113076991A (en) * | 2021-03-30 | 2021-07-06 | 中国人民解放军93114部队 | Multi-target information comprehensive processing method and device based on nonlinear integral algorithm |
| CN115687899A (en) * | 2022-09-06 | 2023-02-03 | 东华大学 | Mixed feature selection method based on high-dimensional spinning data |
| CN116977154A (en) * | 2023-09-22 | 2023-10-31 | 南方电网数字电网研究院有限公司 | Visible light image and infrared image fusion storage method, device, equipment and medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102231205A (en) * | 2011-06-24 | 2011-11-02 | 北京戎大时代科技有限公司 | Multimode monitoring device and method |
| CN102353346A (en) * | 2011-06-23 | 2012-02-15 | 东华大学 | Method and system for detection of verticality of CCD installation of laser cutting machine with automatically edge searching performance |
| CN103400357A (en) * | 2013-08-23 | 2013-11-20 | 闽江学院 | Method for removing salt-pepper noises in images |
| CN103444179A (en) * | 2011-01-10 | 2013-12-11 | 三星电子株式会社 | Method and apparatus for removing image blocking artifact by using transformation coefficient |
| US20140254882A1 (en) * | 2013-03-11 | 2014-09-11 | Adobe Systems Incorporated | Optical Flow with Nearest Neighbor Field Fusion |
-
2015
- 2015-08-31 CN CN201510547150.9A patent/CN105321172A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103444179A (en) * | 2011-01-10 | 2013-12-11 | 三星电子株式会社 | Method and apparatus for removing image blocking artifact by using transformation coefficient |
| CN102353346A (en) * | 2011-06-23 | 2012-02-15 | 东华大学 | Method and system for detection of verticality of CCD installation of laser cutting machine with automatically edge searching performance |
| CN102231205A (en) * | 2011-06-24 | 2011-11-02 | 北京戎大时代科技有限公司 | Multimode monitoring device and method |
| US20140254882A1 (en) * | 2013-03-11 | 2014-09-11 | Adobe Systems Incorporated | Optical Flow with Nearest Neighbor Field Fusion |
| CN103400357A (en) * | 2013-08-23 | 2013-11-20 | 闽江学院 | Method for removing salt-pepper noises in images |
Non-Patent Citations (4)
| Title |
|---|
| 张余宽: "基于剪切波的SAR/红外图像融合研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 李师亿: "微光与红外图像融合算法研究与系统设计", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 李龙勋: "基于互信息的异源图像匹配与融合", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 裴璐乾: "SAR、红外、可见光图像配准及融合算法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (38)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106296624A (en) * | 2015-06-11 | 2017-01-04 | 联想(北京)有限公司 | A kind of image interfusion method and device |
| CN106296624B (en) * | 2015-06-11 | 2020-05-26 | 联想(北京)有限公司 | Image fusion method and device |
| CN105809649B (en) * | 2016-03-03 | 2019-03-26 | 西安电子科技大学 | The SAR image and visible light image fusion method decomposed based on variational multiscale |
| CN105809649A (en) * | 2016-03-03 | 2016-07-27 | 西安电子科技大学 | Variation multi-scale decomposing based SAR image and visible light image integration method |
| CN106407900A (en) * | 2016-08-31 | 2017-02-15 | 上海交通大学 | Multi-source aerial photo-based abnormal scene identification method |
| CN106407900B (en) * | 2016-08-31 | 2019-04-19 | 上海交通大学 | Abnormal scene recognition method based on multi-source aerophotograph |
| CN107918929A (en) * | 2016-10-08 | 2018-04-17 | 杭州海康威视数字技术股份有限公司 | A kind of image interfusion method, apparatus and system |
| US10977781B2 (en) | 2016-10-08 | 2021-04-13 | Hangzhou Hikvision Digital Technology Co., Ltd. | Method, device and system for image fusion |
| CN107918929B (en) * | 2016-10-08 | 2019-06-21 | 杭州海康威视数字技术股份有限公司 | A kind of image interfusion method, apparatus and system |
| CN108022230A (en) * | 2017-12-22 | 2018-05-11 | 青岛大学附属医院 | The more phase CT image fusion systems of kidney |
| CN108022230B (en) * | 2017-12-22 | 2020-07-31 | 青岛大学附属医院 | Kidney multi-phase CT image fusion system |
| CN108510532B (en) * | 2018-03-30 | 2022-07-15 | 西安电子科技大学 | Optical and SAR image registration method based on deep convolution GAN |
| CN108564606A (en) * | 2018-03-30 | 2018-09-21 | 西安电子科技大学 | Heterologous image block matching method based on image conversion |
| CN108564606B (en) * | 2018-03-30 | 2022-06-24 | 西安电子科技大学 | Heterogeneous image block matching method based on image conversion |
| CN108510532A (en) * | 2018-03-30 | 2018-09-07 | 西安电子科技大学 | Optics and SAR image registration method based on depth convolution GAN |
| CN108520494B (en) * | 2018-04-04 | 2021-08-06 | 西安电子科技大学 | SAR image and visible light image registration method based on structural condition mutual information |
| CN108520494A (en) * | 2018-04-04 | 2018-09-11 | 西安电子科技大学 | SAR image based on structural condition mutual information and visible light image registration method |
| CN108737728A (en) * | 2018-05-03 | 2018-11-02 | Oppo广东移动通信有限公司 | A kind of image capturing method, terminal and computer storage media |
| CN108737728B (en) * | 2018-05-03 | 2021-06-11 | Oppo广东移动通信有限公司 | Image shooting method, terminal and computer storage medium |
| CN110930311A (en) * | 2018-09-19 | 2020-03-27 | 杭州萤石软件有限公司 | Method and device for improving signal-to-noise ratio of infrared image and visible light image fusion |
| CN110930311B (en) * | 2018-09-19 | 2023-04-25 | 杭州萤石软件有限公司 | Method and device for improving signal-to-noise ratio of infrared image and visible light image fusion |
| CN109584193A (en) * | 2018-10-24 | 2019-04-05 | 航天时代飞鸿技术有限公司 | A kind of unmanned plane based on target preextraction is infrared and visible light image fusion method |
| CN110246164A (en) * | 2019-05-30 | 2019-09-17 | 中国科学院长春光学精密机械与物理研究所 | Visible images and SAR image registration method and system |
| CN110515079A (en) * | 2019-06-04 | 2019-11-29 | 沈阳瑞初科技有限公司 | Merge the visualization fusion method of SAR radar and infrared imagery technique |
| CN110472658A (en) * | 2019-07-05 | 2019-11-19 | 哈尔滨工程大学 | A kind of the level fusion and extracting method of the detection of moving-target multi-source |
| CN110472658B (en) * | 2019-07-05 | 2023-02-14 | 哈尔滨工程大学 | Hierarchical fusion and extraction method for multi-source detection of moving target |
| CN111652809A (en) * | 2019-07-29 | 2020-09-11 | 天津大学 | Infrared image noise suppression method for enhancing details |
| CN110243769A (en) * | 2019-07-30 | 2019-09-17 | 南阳理工学院 | A kind of the high spectrum sub-pixel target identification system and method for multi-source information auxiliary |
| 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 |
| CN110415202B (en) * | 2019-07-31 | 2022-04-12 | 浙江大华技术股份有限公司 | Image fusion method and device, electronic equipment and storage medium |
| CN111583315A (en) * | 2020-04-23 | 2020-08-25 | 武汉卓目科技有限公司 | Novel visible light image and infrared image registration method and device |
| CN111522007A (en) * | 2020-07-06 | 2020-08-11 | 航天宏图信息技术股份有限公司 | SAR imaging simulation method and system with real scene and target simulation fused |
| CN112666426A (en) * | 2020-11-13 | 2021-04-16 | 国网江苏省电力有限公司电力科学研究院 | Equipment fault detection method and system based on multispectral three-in-one image |
| CN113076991A (en) * | 2021-03-30 | 2021-07-06 | 中国人民解放军93114部队 | Multi-target information comprehensive processing method and device based on nonlinear integral algorithm |
| CN113076991B (en) * | 2021-03-30 | 2024-03-08 | 中国人民解放军93114部队 | Nonlinear integration algorithm-based multi-target information comprehensive processing method and device |
| CN115687899A (en) * | 2022-09-06 | 2023-02-03 | 东华大学 | Mixed feature selection method based on high-dimensional spinning data |
| CN116977154A (en) * | 2023-09-22 | 2023-10-31 | 南方电网数字电网研究院有限公司 | Visible light image and infrared image fusion storage method, device, equipment and medium |
| CN116977154B (en) * | 2023-09-22 | 2024-03-19 | 南方电网数字电网研究院有限公司 | Visible light image and infrared image fusion storage method, device, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105321172A (en) | SAR, infrared and visible light image fusion method | |
| CN111145131B (en) | Infrared and visible light image fusion method based on multiscale generation type countermeasure network | |
| Hall et al. | A multiscale object-specific approach to digital change detection | |
| CN104751478B (en) | Object-oriented building change detection method based on multi-feature fusion | |
| CN103455991B (en) | A kind of multi-focus image fusing method | |
| CN105069769A (en) | Low-light and infrared night vision image fusion method | |
| CN102800074B (en) | Synthetic aperture radar (SAR) image change detection difference chart generation method based on contourlet transform | |
| CN106960442A (en) | Based on the infrared night robot vision wide view-field three-D construction method of monocular | |
| CN104835130A (en) | Multi-exposure image fusion method | |
| Hidayati et al. | Developing an extraction method of urban built-up area based on remote sensing imagery transformation index | |
| CN102800070B (en) | Multi-modality image fusion method based on region and human eye contrast sensitivity characteristic | |
| CN103279935A (en) | Method and system of thermal infrared remote sensing image super-resolution reconstruction based on MAP algorithm | |
| CN109509164A (en) | A kind of Multisensor Image Fusion Scheme and system based on GDGF | |
| CN103745453B (en) | Urban residential areas method based on Google Earth remote sensing image | |
| CN105894513A (en) | Remote sensing image change detection method and remote sensing image change detection system taking into consideration spatial and temporal variations of image objects | |
| CN113298147B (en) | Image fusion method and device based on regional energy and intuitionistic fuzzy set | |
| CN104361571A (en) | Infrared and low-light image fusion method based on marginal information and support degree transformation | |
| Ghanbari et al. | Improved IHS algorithm for fusing high resolution satellite images of urban areas | |
| Zhang | Image Enhancement Method Based on Deep Learning | |
| Rani et al. | An efficient block based feature level image fusion technique using wavelet transform and neural network | |
| CN114092369A (en) | Image fusion method based on visual saliency mapping and least square optimization | |
| Li et al. | Algorithm for relative radiometric consistency process of remote sensing images based on object-oriented smoothing and contourlet transforms | |
| Shakya et al. | Satellite Image Enhancement for Small Particle Observation Using Decorrelation Stretcher | |
| CN103679725B (en) | Based on the blade area automatic retrieval method of straight-line detection and template matches | |
| Rane et al. | Comparative Study of Image Fusion Methods |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160210 |
|
| WD01 | Invention patent application deemed withdrawn after publication |