CN107169947A - A kind of image co-registration experimental method of feature based point location and rim detection - Google Patents
A kind of image co-registration experimental method of feature based point location and rim detection Download PDFInfo
- Publication number
- CN107169947A CN107169947A CN201710281370.0A CN201710281370A CN107169947A CN 107169947 A CN107169947 A CN 107169947A CN 201710281370 A CN201710281370 A CN 201710281370A CN 107169947 A CN107169947 A CN 107169947A
- Authority
- CN
- China
- Prior art keywords
- image
- ultraviolet
- infrared
- registration
- rim detection
- 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
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
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—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
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Abstract
The present invention relates to a kind of feature based point location and the image co-registration experimental method of rim detection, this method comprises the following steps：(1) experimental provision, including infrared camera and ultraviolet-cameras are built, described infrared camera is parallel with ultraviolet-cameras optical axis；(2) four corner points that fluorescent tube is positioned over into ultraviolet-cameras visual field carry out positioning feature point and obtain image co-registration parameter；(3) infrared image and ultraviolet image are shot and is pre-processed respectively；(4) fusion parameters obtained using step (2) are merged to infrared image and ultraviolet image.Compared with prior art, image syncretizing effect of the present invention is good.
Description
Technical field
The present invention relates to a kind of image interfusion method, more particularly, to a kind of feature based point location and the figure of rim detection
As fusion experiment method.
Background technology
Image procossing refers to carry out image sequence of operations to the technology accomplished the end in view, particularly may be divided into simulation
Image procossing and Digital Image Processing.Image co-registration is a main branch of image procossing, is regarded in target identification, robot
There is huge application prospect in terms of feel, space flight, remote sensing.The method of image co-registration is a lot, simplest image interfusion method
It is the original image method of average based on pixel, the fused images that this method can be obscured very much.Nineteen eighty-three Burt, P was carried
Go out Multiresolution Decompositions Approach, based on the pyramidal fusion methods of Laplacian for example Laplacian pyramids, morphology pyramid,
Grad pyramid etc. continuously emerges.In the 1990s, the proposition of wavelet transformation, is widely applied in image procossing,
Also it is successfully applied in image co-registration.
At present, be directed to both at home and abroad multi-band image fusion research focus primarily upon LONG WAVE INFRARED-medium-wave infrared, it is red
The fields such as outside-visible ray, ultraviolet-visible light, the system detected both at home and abroad using infrared and UV signal to shelf depreciation
The detection of the two independent aspects of ultraviolet imagery and infrared detection is only realized, how to the energy profile of day blind ultra-violet (UV) band
Picture and LONG WAVE INFRARED thermal profile picture are merged, and are a difficult points in current research.
The content of the invention
It is an object of the present invention to overcome the above-mentioned drawbacks of the prior art and provide a kind of distinguished point based is fixed
Position and the image co-registration experimental method of rim detection.
The purpose of the present invention can be achieved through the following technical solutions：
A kind of image co-registration experimental method of feature based point location and rim detection, this method comprises the following steps：
(1) experimental provision, including infrared camera and ultraviolet-cameras are built, described infrared camera and ultraviolet-cameras optical axis are flat
OK；
(2) four corner points that fluorescent tube is positioned over into ultraviolet-cameras visual field carry out positioning feature point and obtain image co-registration
Parameter；
(3) infrared image and ultraviolet image are shot and is pre-processed respectively；
(4) fusion parameters obtained using step (2) are merged to infrared image and ultraviolet image.
Step (2) image co-registration parameter includes image co-registration pantograph ratio and image co-registration translational movement.
Step (2) is specially：
(21) fluorescent tube is respectively placed in 4 corner points of ultraviolet-cameras visual field, respectively by infrared camera and ultraviolet
Camera shoots corresponding infrared image and ultraviolet image for features localization；
(22) 4 infrared images and 4 ultraviolet images are overlapped to the first infrared figure for obtaining including 4 luminous points respectively
Picture and the first ultraviolet image containing 4 hot spots；
(23) the first infrared image and the first ultraviolet image edge are overlapped and be placed in the same coordinate system；
(24) 4 spot center points in the first ultraviolet image are subjected to line the first rectangle of formation, and obtain rectangle
4 luminous points of the first infrared image are carried out line the second rectangle of formation by center point coordinate P1, and the second rectangular central point is sat
It is designated as P2；
(25) it is S1 to calculate the first rectangular area, and the second rectangular area is S2, then obtains image co-registration contracting
Put than for S1/S2；
(26) reduced by the first ultraviolet image using image center as scaling center and by image co-registration pantograph ratio or
Amplification obtains the second ultraviolet image, and the second ultraviolet image includes 4 luminous points, and 4 spot sizes and the first infrared image
Middle spot size is equal；
(27) 4 luminous points in the second ultraviolet image are subjected to line the 3rd rectangle of formation, obtained in the 3rd rectangle
Heart point coordinates P3；
(28) the second ultraviolet image is carried out into the 3rd rectangular central point of translation to be moved to and the second rectangular central point weight
Close and complete alignment；
(29) translational movement is calculated according to center point coordinate P1 and center point coordinate P3, regard the translational movement as described figure
As fusion translational movement.
Infrared images pre-processing includes in step (3)：
(310) infrared image is filtered and smoothly obtains the first pretreatment infrared image；
(311) grayvalue transition pre-processed first in infrared image is temperature value；
(312) the first pretreatment infrared image is carried out by pseudo-color enhancement according to temperature value and obtains Infrared False color image.
Ultraviolet image pretreatment includes in step (3)：
(320) ultraviolet image is filtered and smoothing processing obtains the first pretreatment ultraviolet image；
(321) rim detection is carried out to the first pretreatment ultraviolet image and obtains the first energy area for pre-processing ultraviolet image
Obtain the second pretreatment ultraviolet image；
(322) from second pretreatment ultraviolet image in extract energy area image, and then by energy area image with it is infrared
Pseudo- color image is merged.
Rim detection uses the Wavelet Edge Detection algorithm based on Canny criterions in step (321).
Image co-registration is carried out using the image interfusion method based on Wavelet Edge Detection in step (4).
Compared with prior art, the invention has the advantages that：
(1) present invention realizes merging for infrared band and ultraviolet band multi-sensor image, combines both imagings
Advantage, demarcation fusion parameters are carried out by way of positioning feature point to infrared camera and ultraviolet-cameras, so that fusion knot
Fruit is more accurate；
(2) present invention carries out image co-registration using the image interfusion method based on Wavelet Edge Detection, suppressing noise
Meanwhile, it can effectively retain edge details, while the image co-registration based on marginal information can preferably keep the space of image
Resolving power, reflects the infrared and respective main information of ultraviolet image.
Brief description of the drawings
Fig. 1 is the FB(flow block) of the image co-registration experimental method of feature based point location of the present invention and rim detection.
Embodiment
The present invention is described in detail with specific embodiment below in conjunction with the accompanying drawings.
Embodiment
As shown in figure 1, a kind of image co-registration experimental method of feature based point location and rim detection, this method is included such as
Lower step：
(1) experimental provision, including infrared camera and ultraviolet-cameras are built, described infrared camera and ultraviolet-cameras optical axis are flat
OK；
(2) four corner points that fluorescent tube is positioned over into ultraviolet-cameras visual field carry out positioning feature point and obtain image co-registration
Parameter；
(3) infrared image and ultraviolet image are shot and is pre-processed respectively；
(4) fusion parameters obtained using step (2) are merged to infrared image and ultraviolet image.
Step (2) image co-registration parameter includes image co-registration pantograph ratio and image co-registration translational movement.
Step (2) is specially：
(21) fluorescent tube is respectively placed in 4 corner points of ultraviolet-cameras visual field, respectively by infrared camera and ultraviolet
Camera shoots corresponding infrared image and ultraviolet image for features localization；
(22) 4 infrared images and 4 ultraviolet images are overlapped to the first infrared figure for obtaining including 4 luminous points respectively
Picture and the first ultraviolet image containing 4 hot spots；
(23) the first infrared image and the first ultraviolet image edge are overlapped and be placed in the same coordinate system；
(24) 4 spot center points in the first ultraviolet image are subjected to line the first rectangle of formation, and obtain rectangle
4 luminous points of the first infrared image are carried out line the second rectangle of formation by center point coordinate P1, and the second rectangular central point is sat
It is designated as P2；
(25) it is S1 to calculate the first rectangular area, and the second rectangular area is S2, then obtains image co-registration contracting
Put than for S1/S2；
(26) reduced by the first ultraviolet image using image center as scaling center and by image co-registration pantograph ratio or
Amplification obtains the second ultraviolet image, and the second ultraviolet image includes 4 luminous points, and 4 spot sizes and the first infrared image
Middle spot size is equal；
(27) 4 luminous points in the second ultraviolet image are subjected to line the 3rd rectangle of formation, obtained in the 3rd rectangle
Heart point coordinates P3；
(28) the second ultraviolet image is carried out into the 3rd rectangular central point of translation to be moved to and the second rectangular central point weight
Close and complete alignment；
(29) translational movement is calculated according to center point coordinate P1 and center point coordinate P3, regard the translational movement as described figure
As fusion translational movement, such as P1 point coordinates is (x1, y1), and P2 point coordinates is (x2, y2), then horizontal direction translational movement is x2-x1,
X2-x1 is that timing represents to move to x-axis positive direction, and x2-x1 represents to move to x-axis negative direction when being negative；Vertical direction translational movement
For y2-y1, y2-y1 is that timing represents to move to y-axis positive direction, and y2-y1 represents to move to y-axis negative direction when being negative.
Infrared images pre-processing includes in step (3)：
(310) infrared image is filtered and smoothly obtains the first pretreatment infrared image；
(311) grayvalue transition pre-processed first in infrared image is temperature value；
(312) the first pretreatment infrared image is carried out by pseudo-color enhancement according to temperature value and obtains Infrared False color image.
Ultraviolet image pretreatment includes in step (3)：
(320) ultraviolet image is filtered and smoothing processing obtains the first pretreatment ultraviolet image；
(321) rim detection is carried out to the first pretreatment ultraviolet image and obtains the first energy area for pre-processing ultraviolet image
Obtain the second pretreatment ultraviolet image；
(322) from second pretreatment ultraviolet image in extract energy area image, and then by energy area image with it is infrared
Pseudo- color image is merged.
Rim detection uses the Wavelet Edge Detection algorithm based on Canny criterions in step (321).The step can retain
Large spot region is disturbed filter off simultaneously around, is obtained main discharge area, is shown relatively sharp in fused images.John Canny
Propose three optiaml ciriterions on edge extracting：(1) marginal point of not missing inspection necessary being, does not also assign non-edge point as side
Edge point is detected so that the signal to noise ratio of output is maximum；(2) position of the position of the marginal point detected away from actual edge point is nearest,
So that the image position accuracy of output is high；(3) marginal point of each physical presence and the marginal point detected are to correspond
Relation.Canny edge detection methods utilize the first differential of Gaussian function, can be obtained between noise suppressed and rim detection preferably
Balance.But, using a kind of Gauss wave filters of fixed size, it is evident that can not meet detection has different scale size
Marginal texture requirement, and can just to make up this not enough for the Multi-resolution characteristic of small echo.Therefore, Canny criterions are selected
As the algorithm basis of rim detection, and Wavelet Transformation Algorithm is combined, good Detection results can be reached.
Order, θ (x, y) is two-dimentional smooth function, defines two wavelet functions and is
To Ψ1(x,y)、Ψ2(x, y) carries out two rows and stretched and translation composition basic function：
For two-dimensional function f (x, y), its wavelet transformation can be realized by convolution：
X-direction is：
Y-direction is：
In yardstick 2jOn, the mould of gradient vector is：
Its argument is：
The mould of gradient direction sensing gradient takes the direction of maximum, then, as long as detecting wavelet transformation along gradient direction
The Local modulus maxima of coefficient module, you can obtain the marginal point of image.
Choose two threshold value T1And T2, T1=α T2, wherein 0<α<1.Respectively with the two threshold values to the figure through above-mentioned processing
As carrying out binaryzation.Grad is less than T by we1The gray scale of pixel be set to 0, obtain image 1.Then Grad is less than T1
The gray scale of pixel be set to 0, obtain image 2.Because the threshold value of image 2 is higher, most of noise is eliminated, but also lose simultaneously
Useful marginal information.And the threshold value of image 1 is relatively low, more information is remained.We can based on image 2, with
Image 1 comes the edge of connection figure picture for supplement.
640 × 480 image that camera is gathered is handled using method presented above, first by high threshold and
Low threshold carries out denoising, and Low threshold can retain trickle edge, and high threshold can obtain the edge of denoising, then be connected with edge
Method connection two images obtain last edge image figure.Whole edge inner region is extracted, ultraviolet wastewater as to be fused
Measure area
Image co-registration is carried out using the image interfusion method based on Wavelet Edge Detection in step (4).Two dimensional image is entered
The wavelet decomposition that N layers of row, can obtain 3N+1 different frequency bands, wherein including 3N high frequency band and a low-frequency band.It is high for 3
Frequency subgraph H, V, D, using H, V subgraph, edge image is obtained using the Wavelet Edge Detection method based on Canny criterions.Due to
H, V, D subgraph reflect the high-frequency information of the yardstick hypograph, i.e. marginal portion information, and the center at edge be it is unique,
Still can retain the value of the point of absolute value corresponding with the edge image detected in two images H, V, D subgraph greatly,
Rather than the point at edge then takes two images average value.So, noise can effectively be suppressed while reserved high-frequency information.
In the wavelet transformed domain of image, the amplitude of coefficient represents the severe degree of original image grey scale change under the resolving power, therefore
The Local Extremum of high frequency coefficient represents the marginal point of original image.For low frequency coefficient, using the direct method of average or weighting
Method is merged：
The direct method of average：AF(u, v)=mean { A1(u,v),A2(u, v) },
Weighting method：AF(u, v)=[A1(u,v)+k*A2(u,v)]-|A1(u,v)-k*A2(u, v) | * β,
Wherein k, α, β are weighted factor.
Claims (7)
1. the image co-registration experimental method of a kind of feature based point location and rim detection, it is characterised in that this method is included such as
Lower step：
(1) experimental provision, including infrared camera and ultraviolet-cameras are built, described infrared camera is parallel with ultraviolet-cameras optical axis；
(2) four corner points that fluorescent tube is positioned over into ultraviolet-cameras visual field carry out positioning feature point and obtain image co-registration ginseng
Number；
(3) infrared image and ultraviolet image are shot and is pre-processed respectively；
(4) fusion parameters obtained using step (2) are merged to infrared image and ultraviolet image.
2. the image co-registration experimental method of a kind of feature based point location according to claim 1 and rim detection, step
(2) image co-registration parameter includes image co-registration pantograph ratio and image co-registration translational movement.
3. the image co-registration experimental method of a kind of feature based point location according to claim 2 and rim detection, it is special
Levy and be, step (2) is specially：
(21) fluorescent tube is respectively placed in 4 corner points of ultraviolet-cameras visual field, passes through infrared camera and ultraviolet-cameras respectively
Shoot corresponding infrared image and ultraviolet image for features localization；
(22) 4 infrared images and 4 ultraviolet images are overlapped respectively obtain the first infrared image comprising 4 luminous points with
And the first ultraviolet image containing 4 hot spots；
(23) the first infrared image and the first ultraviolet image edge are overlapped and be placed in the same coordinate system；
(24) 4 spot center points in the first ultraviolet image are subjected to line the first rectangle of formation, and obtain rectangular central
4 luminous points of the first infrared image are carried out line the second rectangle of formation by point coordinates P1, and the second rectangular central point coordinates is
P2；
(25) it is S1 to calculate the first rectangular area, and the second rectangular area is S2, then obtains image co-registration pantograph ratio
For S1/S2；
(26) the first ultraviolet image is zoomed in or out using image center as scaling center and by image co-registration pantograph ratio
The second ultraviolet image is obtained, the second ultraviolet image includes light in 4 luminous points, and 4 spot sizes and the first infrared image
Point is equal in magnitude；
(27) 4 luminous points in the second ultraviolet image are subjected to line the 3rd rectangle of formation, obtain the 3rd rectangular central point
Coordinate P3；
(28) the second ultraviolet image progress the 3rd rectangular central point of translation is moved to and overlapped with the second rectangular central point
Into alignment；
(29) translational movement is calculated according to center point coordinate P1 and center point coordinate P3, melted the translational movement as described image
Close translational movement.
4. the image co-registration experimental method of a kind of feature based point location according to claim 1 and rim detection, it is special
Levy and be, Infrared images pre-processing includes in step (3)：
(310) infrared image is filtered and smoothly obtains the first pretreatment infrared image；
(311) grayvalue transition pre-processed first in infrared image is temperature value；
(312) the first pretreatment infrared image is carried out by pseudo-color enhancement according to temperature value and obtains Infrared False color image.
5. the image co-registration experimental method of a kind of feature based point location according to claim 1 and rim detection, it is special
Levy and be, ultraviolet image pretreatment includes in step (3)：
(320) ultraviolet image is filtered and smoothing processing obtains the first pretreatment ultraviolet image；
(321) energy area that rim detection acquisition the first pretreatment ultraviolet image is carried out to the first pretreatment ultraviolet image is obtained
Second pretreatment ultraviolet image；
(322) energy area image is extracted from the second pretreatment ultraviolet image, and then by energy area image and infrared false colour
Coloured picture picture is merged.
6. the image co-registration experimental method of a kind of feature based point location according to claim 5 and rim detection, it is special
Levy and be, rim detection uses the Wavelet Edge Detection algorithm based on Canny criterions in step (321).
7. the image co-registration experimental method of a kind of feature based point location according to claim 1 and rim detection, it is special
Levy and be, image co-registration is carried out using the image interfusion method based on Wavelet Edge Detection in step (4).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710281370.0A CN107169947B (en) | 2017-04-26 | 2017-04-26 | Image fusion experimental method based on feature point positioning and edge detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710281370.0A CN107169947B (en) | 2017-04-26 | 2017-04-26 | Image fusion experimental method based on feature point positioning and edge detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107169947A true CN107169947A (en) | 2017-09-15 |
| CN107169947B CN107169947B (en) | 2021-02-12 |
Family
ID=59813237
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710281370.0A Active CN107169947B (en) | 2017-04-26 | 2017-04-26 | Image fusion experimental method based on feature point positioning and edge detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107169947B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109060308A (en) * | 2018-06-04 | 2018-12-21 | 北京理工大学 | Time delay measurement device and method for image fusion system |
| CN109102669A (en) * | 2018-09-06 | 2018-12-28 | 广东电网有限责任公司 | A kind of transformer substation auxiliary facility detection control method and its device |
| CN110728703A (en) * | 2019-09-16 | 2020-01-24 | 东南大学 | Registration and fusion method of visible light image and solar blind ultraviolet light image |
| CN110850244A (en) * | 2019-11-11 | 2020-02-28 | 国网湖南省电力有限公司 | Local discharge defect time domain map diagnosis method, system and medium based on deep learning |
| CN111462032A (en) * | 2020-03-31 | 2020-07-28 | 北方夜视技术股份有限公司 | Method for fusing uncooled infrared image and solar blind ultraviolet image and application |
| CN111736040A (en) * | 2020-05-21 | 2020-10-02 | 南京工程学院 | Weak electric leakage detection method based on single-pixel imaging system |
| CN112819739A (en) * | 2021-01-28 | 2021-05-18 | 浙江祺跃科技有限公司 | Scanning electron microscope image processing method and system |
| US20220319011A1 (en) * | 2020-06-08 | 2022-10-06 | Shanghai Jiaotong University | Heterogeneous Image Registration Method and System |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102789640A (en) * | 2012-07-16 | 2012-11-21 | 中国科学院自动化研究所 | Method for fusing visible light full-color image and infrared remote sensing image |
| US20130083959A1 (en) * | 2011-09-29 | 2013-04-04 | The Boeing Company | Multi-Modal Sensor Fusion |
| CN103487729A (en) * | 2013-09-06 | 2014-01-01 | 广东电网公司电力科学研究院 | Electrical equipment defect detection method based on fusion of ultraviolet video and infrared video |
-
2017
- 2017-04-26 CN CN201710281370.0A patent/CN107169947B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130083959A1 (en) * | 2011-09-29 | 2013-04-04 | The Boeing Company | Multi-Modal Sensor Fusion |
| CN102789640A (en) * | 2012-07-16 | 2012-11-21 | 中国科学院自动化研究所 | Method for fusing visible light full-color image and infrared remote sensing image |
| CN103487729A (en) * | 2013-09-06 | 2014-01-01 | 广东电网公司电力科学研究院 | Electrical equipment defect detection method based on fusion of ultraviolet video and infrared video |
Non-Patent Citations (2)
| Title |
|---|
| 姚敏 等: "一种基于图像融合的红外图像预处理算法", 《红外技术》 * |
| 黄克明 等: "基于DSP的多源图像融合系统", 《兵工自动化》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109060308A (en) * | 2018-06-04 | 2018-12-21 | 北京理工大学 | Time delay measurement device and method for image fusion system |
| CN109102669A (en) * | 2018-09-06 | 2018-12-28 | 广东电网有限责任公司 | A kind of transformer substation auxiliary facility detection control method and its device |
| CN110728703A (en) * | 2019-09-16 | 2020-01-24 | 东南大学 | Registration and fusion method of visible light image and solar blind ultraviolet light image |
| CN110850244A (en) * | 2019-11-11 | 2020-02-28 | 国网湖南省电力有限公司 | Local discharge defect time domain map diagnosis method, system and medium based on deep learning |
| CN110850244B (en) * | 2019-11-11 | 2022-03-11 | 国网湖南省电力有限公司 | Local discharge defect time domain map diagnosis method, system and medium based on deep learning |
| CN111462032A (en) * | 2020-03-31 | 2020-07-28 | 北方夜视技术股份有限公司 | Method for fusing uncooled infrared image and solar blind ultraviolet image and application |
| CN111462032B (en) * | 2020-03-31 | 2023-03-31 | 北方夜视技术股份有限公司 | Method for fusing uncooled infrared image and solar blind ultraviolet image and application |
| CN111736040A (en) * | 2020-05-21 | 2020-10-02 | 南京工程学院 | Weak electric leakage detection method based on single-pixel imaging system |
| CN111736040B (en) * | 2020-05-21 | 2023-01-24 | 南京工程学院 | Weak electric leakage detection method based on single-pixel imaging system |
| US20220319011A1 (en) * | 2020-06-08 | 2022-10-06 | Shanghai Jiaotong University | Heterogeneous Image Registration Method and System |
| CN112819739A (en) * | 2021-01-28 | 2021-05-18 | 浙江祺跃科技有限公司 | Scanning electron microscope image processing method and system |
| CN112819739B (en) * | 2021-01-28 | 2024-03-01 | 浙江祺跃科技有限公司 | Image processing method and system for scanning electron microscope |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107169947B (en) | 2021-02-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107169947A (en) | A kind of image co-registration experimental method of feature based point location and rim detection | |
| CN107578418B (en) | Indoor scene contour detection method fusing color and depth information | |
| CN108596849B (en) | Single image defogging method based on sky region segmentation | |
| CN105354865B (en) | The automatic cloud detection method of optic of multispectral remote sensing satellite image and system | |
| CN103927741B (en) | SAR image synthesis method for enhancing target characteristics | |
| CN111080724A (en) | Infrared and visible light fusion method | |
| CN102567979B (en) | Vehicle-mounted infrared night vision system and multi-source images fusing method thereof | |
| CN102436652B (en) | Automatic registering method of multisource remote sensing images | |
| CN105701483B (en) | A kind of urban border extracting method of fusion Multi-spectral Remote Sensing Data and night lights remotely-sensed data | |
| CN105139367A (en) | Visible-light polarization image fusion method based on non-subsampled shearlets | |
| CN105184779A (en) | Rapid-feature-pyramid-based multi-dimensioned tracking method of vehicle | |
| CN106846289A (en) | A kind of infrared light intensity and polarization image fusion method based on conspicuousness migration with details classification | |
| CN107563405A (en) | Garage automatic Pilot semantic objects recognition methods based on multiresolution neutral net | |
| Bhatnagar et al. | An image fusion framework based on human visual system in framelet domain | |
| CN102663760A (en) | Location and segmentation method for windshield area of vehicle in images | |
| CN105405138B (en) | Waterborne target tracking based on conspicuousness detection | |
| CN112184604A (en) | Color image enhancement method based on image fusion | |
| Luo et al. | Infrared and visible image fusion based on visibility enhancement and hybrid multiscale decomposition | |
| Kong et al. | Infrared and visible image fusion using structure-transferring fusion method | |
| CN106228541A (en) | The method and device of screen location in vision-based detection | |
| CN101799915B (en) | Bicolor medium wave infrared image fusion method | |
| CN110414308A (en) | A kind of target identification method for dynamic foreign matter on transmission line of electricity | |
| CN109559273A (en) | A kind of quick joining method towards vehicle base map picture | |
| CN115689960A (en) | Illumination self-adaptive infrared and visible light image fusion method in night scene | |
| CN111311503A (en) | Night low-brightness image enhancement system |
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 |