CN109741376A - It is a kind of based on improve RANSAC algorithm in, LONG WAVE INFRARED method for registering images - Google Patents
It is a kind of based on improve RANSAC algorithm in, LONG WAVE INFRARED method for registering images Download PDFInfo
- Publication number
- CN109741376A CN109741376A CN201811373319.3A CN201811373319A CN109741376A CN 109741376 A CN109741376 A CN 109741376A CN 201811373319 A CN201811373319 A CN 201811373319A CN 109741376 A CN109741376 A CN 109741376A
- Authority
- CN
- China
- Prior art keywords
- image
- long wave
- wave infrared
- characteristic point
- ransac algorithm
- 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
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000012216 screening Methods 0.000 claims abstract description 15
- 238000001514 detection method Methods 0.000 claims abstract description 9
- 238000000605 extraction Methods 0.000 claims abstract description 8
- 239000011159 matrix material Substances 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 4
- 238000003331 infrared imaging Methods 0.000 abstract 1
- 230000008859 change Effects 0.000 description 3
- 230000006872 improvement Effects 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The invention belongs to technical field of image processing, and in particular to it is a kind of especially suitable in/long wave dual-band infrared imaging system based on improve RANSAC algorithm in, LONG WAVE INFRARED method for registering images.This method mainly include Image Acquisition, feature point extraction, subregion screen for the first time, five steps of the postsearch screening of RANSAC algorithm and image registration.The present invention is during characteristic point is chosen, it is introduced into the detection of Harris Corner Detection Algorithm, the matching characteristic point in long wave image, using area dividing method screens matching characteristic point for the first time, guarantee that characteristic point is uniformly distributed in the picture, then postsearch screening is carried out using RANSAC algorithm, error hiding characteristic point pair can be effectively removed, effectively promotion quality of match.
Description
Technical field
The invention belongs to technical field of image processing, and in particular to one kind especially suitable in/long wave dual-band infrared at
As system based on improve in RANSAC algorithm, LONG WAVE INFRARED method for registering images.
Background technique
Image registration techniques are to develop extremely rapid one of image processing techniques, fast and accurately image registration in recent years
Method is conducive to the further research to subsequent image fusion treatment technology.
Method for registering images is divided into three classes: the image registration based on gray scale, the image registration based on feature and based on become
Change the image registration in domain.Wherein, the method for registering images based on feature is current most study, most widely used method for registering.
Method for registering images based on feature has greatly reduced using information such as invariant features, such as point, line or edge in image and is
Calculation amount, so that registration Algorithm calculates comparatively fast, and the registration Algorithm robustness based on feature is high, by variation of image grayscale shadow
Sound is smaller.But there is also disadvantages for the method for registering based on feature: the selection precision of characteristic point is affected to registration Algorithm, if
There is error in the selection of characteristic point pair, can reduce the precision of registration parameter, causes the blurring of image border, influences subsequent figure
As processing;Characteristic point is to must be evenly distributed at each position in image, and otherwise registration will appear error.
Summary of the invention
(1) technical problems to be solved
The present invention propose it is a kind of based on improve RANSAC algorithm in, LONG WAVE INFRARED method for registering images, with solve how
Improving operational speed improves the technical issues of registration accuracy.
(2) technical solution
In order to solve the above-mentioned technical problem, the present invention propose it is a kind of based on improve RANSAC algorithm in, LONG WAVE INFRARED figure
As method for registering;It is characterized in that, method includes the following steps:
S1, Image Acquisition: respectively acquisition in, LONG WAVE INFRARED image, using medium-wave infrared image as benchmark image, long wave is red
Outer image is as image subject to registration;
S2, feature point extraction: using Harris Corner Detection Algorithm, centering, LONG WAVE INFRARED image progress characteristic point are mentioned respectively
It takes;
S3, subregion are screened for the first time: LONG WAVE INFRARED image uniform being divided into the identical muti-piece region of size, respectively every
The characteristic point of identical quantity is selected in block region, is then found in the medium-wave infrared image as benchmark image and LONG WAVE INFRARED
The corresponding match point of the characteristic point of image, forms matched characteristic point pair;
S4, RANSAC algorithm postsearch screening: using RANSAC algorithm to the characteristic point after first screening to the secondary sieve of progress
Choosing removes error hiding characteristic point pair;
S5, image registration: being registrated according to the result of RANSAC algorithm postsearch screening, obtains finally being registrated image.
Further, in step S3, long wave image is divided into 3 × 3 pieces, then randomly chooses two spies in every piece of region
Point is levied, match point corresponding with them is then found in the medium-wave infrared image as benchmark image, is thus obtained 18 pairs
The match point being evenly distributed.
Further, it in step S4, obtains indicating that registration front and back image coordinate is converted by RANSAC algorithm postsearch screening
The homography matrix of relationship;It in the step S5, is registrated using the homography matrix, obtains finally being registrated image.
(3) beneficial effect
It is proposed by the present invention based on improve in RANSAC algorithm, LONG WAVE INFRARED method for registering images, this method mainly wraps
Include Image Acquisition, feature point extraction, subregion screen for the first time, five steps of the postsearch screening of RANSAC algorithm and image registration.This
Invention is introduced into the detection of Harris Corner Detection Algorithm, the matching characteristic point in long wave image, makes during characteristic point is chosen
Matching characteristic point is screened for the first time with region segmentation method, guarantees that characteristic point is uniformly distributed in the picture, then utilizes
RANSAC algorithm carries out postsearch screening, can effectively remove error hiding characteristic point pair, effectively promotion quality of match.
Detailed description of the invention
Fig. 1 is the method for registering images flow chart of the embodiment of the present invention;
Fig. 2 is the region division schematic diagram of the embodiment of the present invention.
Specific embodiment
To keep the purpose of the present invention, content and advantage clearer, with reference to the accompanying drawings and examples, to tool of the invention
Body embodiment is described in further detail.
The present embodiment propose it is a kind of based on improve RANSAC algorithm in, LONG WAVE INFRARED method for registering images, the registration side
The process of method is as shown in Figure 1, mainly include the following steps:
S1, Image Acquisition: respectively acquisition in, LONG WAVE INFRARED image, using medium-wave infrared image as benchmark image, long wave is red
Outer image is as image subject to registration.
S2, feature point extraction: using Harris Corner Detection Algorithm, centering, LONG WAVE INFRARED image progress characteristic point are mentioned respectively
It takes.
Harris Corner Detection Algorithm is a kind of point feature extraction algorithm, and with calculating, simple, point multiplicity is high and misses
The features such as inspection rate is low, even if image, there are the influence such as grey scale change, rotation, scaling or noise, the extraction of angle steel joint is also ratio
More stable.
It is in one group of square region that Harris Corner Detection Algorithm, which defines the autocorrelation value E (u, v) on any direction,
The summation of image grayscale error, it may be assumed that
Its Taylor expansion is
Wherein, M is 2 × 2 symmetrical matrix
Wherein, u and v is window translational movement, is generated grey scale change E (u, v), and E (u, v) can be approximate as local cross-correlation letter
Number.
F (x, y) is image grayscale, and f (x+u, y+v) is the image grayscale after image translation, and w (x, y) is window function, fx
And fyRespectively gradient value of the image in the direction x, y.
For Gaussian function.
If λ1And λ2For two characteristic values of matrix M, the receptance function R of angle point is calculated:
R=λ1λ2-k(λ1+λ2)2 (4)
In formula, k is constant, generally takes 0.04.
S3, subregion are screened for the first time: LONG WAVE INFRARED image uniform being divided into the identical muti-piece region of size, respectively every
The characteristic point of identical quantity is selected in block region, is then found in the medium-wave infrared image as benchmark image and LONG WAVE INFRARED
The corresponding match point of the characteristic point of image, forms matched characteristic point pair.
When randomly selecting match point, in order to guarantee the accuracy of model parameter, characteristic point is carried out as unit of region
It chooses.Long wave image is divided into 3 × 3 pieces in the present embodiment, as shown in Fig. 2, randomly choosing two spies in every piece of region again
Point is levied, it is possible thereby to avoid because the characteristic point of selection is to excessively concentrating due to the accuracy of affecting parameters.Then as reference map
Match point corresponding with them is found in the medium-wave infrared image of picture, and 18 pairs of relatively uniform match points of distribution are thus obtained,
It is more stable, accurate with 18 pairs of calculated transformation matrixs of match point.
S4, RANSAC algorithm postsearch screening: using RANSAC algorithm to the characteristic point after first screening to the secondary sieve of progress
Choosing removes error hiding characteristic point pair.
The principle of RANSAC algorithm is in alignment to be fitted using given point set.It is randomly selected first in a concentration
Two points, the two points have determined straight line.The number of characteristic point within the scope of this straight line certain distance, as supports
Point set number.RANSAC algorithm so repeats selection n times at random, and then the straight line with maximum support point set number is identified as a little
The fitting of collection.Point within the scope of the error distance of fitting is considered as available point, it is on the contrary then be Null Spot.Its step are as follows:
1, a data point sample is randomly selected from feature point set S, and model of fit is initialized by this subset;
2, according to specific threshold T, the support point set S of "current" model is found outi, set SiIt is exactly the consistent collection of sample, is considered
It is available point;
If 3, set SiSize be more than threshold value Ts, use SiIt reevaluates model and terminates;
If 4, set SiSize be less than threshold value Ts, then a new sample is chosen, above step is repeated;
5, it is attempted by n times, selects maximum consistent collection Si, and estimate new model accordingly, obtain to the end as a result, i.e. single
Answering property matrix H:
S5, image registration: being registrated according to the result of RANSAC algorithm postsearch screening, obtains finally being registrated image.
H-matrix illustrates registration front and back image coordinate transformation relation, can obtain images after registration according to matrix multiplication accordingly
Each corresponding registration of coordinate points (m, n) before image corresponding coordinate (X, Y), as shown in formula (5).
Under normal circumstances, the value of X and Y is not integer, it is assumed that X=x+p, Y=y+q, wherein x, y indicate integer part,
P and q indicates fractional part, so the pixel value of the position (m, n) can be obtained in images after registration such as according to bilinear interpolation algorithm
Shown in formula (6).
G ' (m, n)=G (X, Y)=(1-p) * (1-q) * G (x, y)+p* (1-q) * G (x+1, y)+(1-p) * q*G (x, y+1)
+p*q*G(x+1,y+1) (6)
Wherein, G indicates that the image grayscale before registration, G ' indicate the image grayscale after registration.
According to above-mentioned steps, the pixel value of each pixel is calculated, obtains finally being registrated image.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, without departing from the technical principles of the invention, several improvement and deformations can also be made, these improvement and deformations
Also it should be regarded as protection scope of the present invention.
Claims (3)
1. it is a kind of based on improve RANSAC algorithm in, LONG WAVE INFRARED method for registering images;It is characterized in that, the method includes
Following steps:
S1, Image Acquisition: respectively acquisition in, LONG WAVE INFRARED image, using medium-wave infrared image as benchmark image, LONG WAVE INFRARED figure
As being used as image subject to registration;
S2, feature point extraction: feature point extraction is carried out using the centering of Harris Corner Detection Algorithm difference, LONG WAVE INFRARED image;
S3, subregion are screened for the first time: LONG WAVE INFRARED image uniform being divided into the identical muti-piece region of size, respectively in every piece of area
The characteristic point of identical quantity is selected in domain, is then found in the medium-wave infrared image as benchmark image and LONG WAVE INFRARED image
The corresponding match point of characteristic point, form matched characteristic point pair;
S4, RANSAC algorithm postsearch screening: the characteristic point after first screening is gone to postsearch screening is carried out using RANSAC algorithm
Except error hiding characteristic point pair;
S5, image registration: being registrated according to the result of RANSAC algorithm postsearch screening, obtains finally being registrated image.
2. method for registering as described in claim 1, which is characterized in that in the step S3, long wave image is divided into 3 × 3
Block, then in every piece of region randomly choose two characteristic points, then found in the medium-wave infrared image as benchmark image and
Thus 18 pairs of match points being evenly distributed are obtained in their corresponding match points.
3. method for registering as described in claim 1, which is characterized in that in the step S4, pass through the secondary sieve of RANSAC algorithm
Choosing obtains indicating the homography matrix of registration front and back image coordinate transformation relation;In the step S5, the homography square is utilized
Battle array is registrated, and obtains finally being registrated image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811373319.3A CN109741376A (en) | 2018-11-19 | 2018-11-19 | It is a kind of based on improve RANSAC algorithm in, LONG WAVE INFRARED method for registering images |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811373319.3A CN109741376A (en) | 2018-11-19 | 2018-11-19 | It is a kind of based on improve RANSAC algorithm in, LONG WAVE INFRARED method for registering images |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109741376A true CN109741376A (en) | 2019-05-10 |
Family
ID=66355659
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811373319.3A Pending CN109741376A (en) | 2018-11-19 | 2018-11-19 | It is a kind of based on improve RANSAC algorithm in, LONG WAVE INFRARED method for registering images |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109741376A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110163273A (en) * | 2019-05-14 | 2019-08-23 | 西安文理学院 | It is a kind of that genic image matching method is had based on RANSAC algorithm |
CN111311658A (en) * | 2020-04-02 | 2020-06-19 | 烟台艾睿光电科技有限公司 | Image registration method of dual-light imaging system and related device |
CN111667517A (en) * | 2020-06-05 | 2020-09-15 | 北京环境特性研究所 | Infrared polarization information fusion method and device based on wavelet packet transformation |
CN112837335A (en) * | 2021-01-27 | 2021-05-25 | 上海航天控制技术研究所 | Medium-long wave infrared composite anti-interference method |
CN116309741A (en) * | 2023-05-22 | 2023-06-23 | 中南大学 | TVDS image registration method, segmentation method, device and medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130004035A1 (en) * | 2011-06-30 | 2013-01-03 | National Taiwan University | Longitudinal Image Registration Algorithm For Infrared Images For Chemotherapy Response Monitoring And Early Detection Of Breast Cancers |
CN104867137A (en) * | 2015-05-08 | 2015-08-26 | 中国科学院苏州生物医学工程技术研究所 | Improved RANSAC algorithm-based image registration method |
CN107301661A (en) * | 2017-07-10 | 2017-10-27 | 中国科学院遥感与数字地球研究所 | High-resolution remote sensing image method for registering based on edge point feature |
CN108335319A (en) * | 2018-02-06 | 2018-07-27 | 中南林业科技大学 | A kind of image angle point matching process based on adaptive threshold and RANSAC |
-
2018
- 2018-11-19 CN CN201811373319.3A patent/CN109741376A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130004035A1 (en) * | 2011-06-30 | 2013-01-03 | National Taiwan University | Longitudinal Image Registration Algorithm For Infrared Images For Chemotherapy Response Monitoring And Early Detection Of Breast Cancers |
CN104867137A (en) * | 2015-05-08 | 2015-08-26 | 中国科学院苏州生物医学工程技术研究所 | Improved RANSAC algorithm-based image registration method |
CN107301661A (en) * | 2017-07-10 | 2017-10-27 | 中国科学院遥感与数字地球研究所 | High-resolution remote sensing image method for registering based on edge point feature |
CN108335319A (en) * | 2018-02-06 | 2018-07-27 | 中南林业科技大学 | A kind of image angle point matching process based on adaptive threshold and RANSAC |
Non-Patent Citations (1)
Title |
---|
姚敏: "基于特征点自动匹配的红外图像配准研究", 《光学与光电技术》 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110163273A (en) * | 2019-05-14 | 2019-08-23 | 西安文理学院 | It is a kind of that genic image matching method is had based on RANSAC algorithm |
CN110163273B (en) * | 2019-05-14 | 2021-02-12 | 西安文理学院 | RANSAC algorithm-based image matching method with genetic factors |
CN111311658A (en) * | 2020-04-02 | 2020-06-19 | 烟台艾睿光电科技有限公司 | Image registration method of dual-light imaging system and related device |
CN111311658B (en) * | 2020-04-02 | 2023-11-07 | 烟台艾睿光电科技有限公司 | Image registration method and related device for dual-light imaging system |
CN111667517A (en) * | 2020-06-05 | 2020-09-15 | 北京环境特性研究所 | Infrared polarization information fusion method and device based on wavelet packet transformation |
CN112837335A (en) * | 2021-01-27 | 2021-05-25 | 上海航天控制技术研究所 | Medium-long wave infrared composite anti-interference method |
CN116309741A (en) * | 2023-05-22 | 2023-06-23 | 中南大学 | TVDS image registration method, segmentation method, device and medium |
CN116309741B (en) * | 2023-05-22 | 2023-08-11 | 中南大学 | TVDS image registration method, segmentation method, device and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109741376A (en) | It is a kind of based on improve RANSAC algorithm in, LONG WAVE INFRARED method for registering images | |
CN107301661B (en) | High-resolution remote sensing image registration method based on edge point features | |
CN109816673B (en) | Non-maximum value inhibition, dynamic threshold value calculation and image edge detection method | |
KR101011515B1 (en) | Method of object recognition in image data using combined edge magnitude and edge direction analysis techniques | |
CN106874949A (en) | A kind of moving platform moving target detecting method and system based on infrared image | |
CN109871938A (en) | A kind of components coding detection method based on convolutional neural networks | |
US20100166257A1 (en) | Method and apparatus for detecting semi-transparencies in video | |
CN104392416B (en) | Video stitching method for sports scene | |
CN106991690A (en) | A kind of video sequence synchronous method based on moving target timing information | |
CN104574419B (en) | Lens distortion parameter calibration method and system | |
CN107462182B (en) | A kind of cross section profile deformation detecting method based on machine vision and red line laser | |
CN108537787B (en) | Quality judgment method for face image | |
CN109801343A (en) | Based on annular artifact bearing calibration, the CT control system for rebuilding front and back image | |
CN110189375A (en) | A kind of images steganalysis method based on monocular vision measurement | |
CN101976436A (en) | Pixel-level multi-focus image fusion method based on correction of differential image | |
CN110335280A (en) | A kind of financial documents image segmentation and antidote based on mobile terminal | |
CN112801141B (en) | Heterogeneous image matching method based on template matching and twin neural network optimization | |
CN104732541A (en) | Method and device for acquiring PET crystal position lookup table | |
CN106340010A (en) | Corner detection method based on second-order contour difference | |
CN105550694A (en) | Method for measurement of fuzzy degree of face image | |
CN105608674B (en) | A kind of image enchancing method based on image registration, interpolation and denoising | |
CN106600615A (en) | Image edge detection algorithm evaluation system and method | |
CN104182931B (en) | Super resolution method and device | |
CN107301628A (en) | Trembled image deblurring method based on trembling as moving the satellite platform of track | |
CN111445510A (en) | Method for detecting straight line in image |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190510 |
|
RJ01 | Rejection of invention patent application after publication |