CN112465881B - Improved robust point registration method and system - Google Patents
Improved robust point registration method and system Download PDFInfo
- Publication number
- CN112465881B CN112465881B CN202011254115.5A CN202011254115A CN112465881B CN 112465881 B CN112465881 B CN 112465881B CN 202011254115 A CN202011254115 A CN 202011254115A CN 112465881 B CN112465881 B CN 112465881B
- Authority
- CN
- China
- Prior art keywords
- point
- probability
- registration
- model
- points
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000004590 computer program Methods 0.000 claims description 13
- 238000003860 storage Methods 0.000 claims description 10
- 239000013598 vector Substances 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 abstract description 15
- 230000002159 abnormal effect Effects 0.000 abstract description 4
- 230000006870 function Effects 0.000 description 16
- 238000010586 diagram Methods 0.000 description 6
- 238000013507 mapping Methods 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 238000009827 uniform distribution Methods 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/35—Determination of transform parameters for the alignment of images, i.e. image registration using statistical methods
-
- 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
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2210/00—Indexing scheme for image generation or computer graphics
- G06T2210/44—Morphing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an improved robust point registration method and system in the technical field of image registration, which maintain the correspondence consistency between local point sets while registering an integral point set, improve the accuracy of point set registration and improve the robustness of an algorithm when abnormal points exist. Comprising the following steps: a. giving two point sets, initializing registration model parameters and giving an initial value; b. solving prior probability of matching consistency between local point pairs in two point sets based on a point local structure maintaining theory; c. further solving posterior probability based on the mixed probability model and the prior probability obtained in the step b; d. c, further solving deformation parameters of the registration model based on the posterior probability obtained in the step c; e. rearranging the points in the two point sets based on the deformation parameters obtained in the step d; f. repeating the steps b-e until the registration model converges, and outputting the corresponding relation between the two point sets.
Description
Technical Field
The invention belongs to the technical field of image registration, and particularly relates to an improved robust point registration method and system.
Background
Image registration technology is a very important research topic in the field of computer vision and image processing. And many research achievements have been widely applied to a plurality of important fields such as pattern recognition, medical image processing, digital media and the like. The technique can be roughly classified into a gray scale registration algorithm and a point registration algorithm according to registration objects. The point registration algorithm can effectively reduce the complexity of the algorithm, has the advantage of real-time performance, can be applied to practical industrial level, and is a hot spot for current industry research. In recent years, a number of related technical documents have been proposed, and the technical lines are classified into the following two main categories: one is a graph-based matching method; another class is classification methods based on probabilistic models. The first class of methods converts the point registration problem into a map matching problem. The matching probability among all the neighborhood points is counted when the point neighbor relation is calculated, and a large amount of redundant information is contained, so that the accuracy of registration is reduced. The second type of method employs a simplified registration probability model to affect the accuracy and robustness of the algorithm.
Disclosure of Invention
In order to solve the defects in the prior art, the invention provides an improved robust point registration method and system, which maintain the correspondence consistency between local point sets while registering the whole point set, improve the accuracy of point set registration and improve the robustness of an algorithm when abnormal points exist.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows: an improved robust point registration method, comprising: a. giving two point sets, initializing registration model parameters and giving an initial value; b. solving prior probability of matching consistency between local point pairs in two point sets based on a point local structure maintaining theory; c. further solving posterior probability based on the mixed probability model and the prior probability obtained in the step b; d. c, further solving deformation parameters of the registration model based on the posterior probability obtained in the step c; e. rearranging the points in the two point sets based on the deformation parameters obtained in the step d; f. repeating the steps b-e until the registration model converges, and outputting the corresponding relation between the two point sets.
Further, the joint probability density function of the hybrid probability model is:
Wherein, Is a model parameter, parameter/>Representing the probability that the i-th point belongs to the j-th gaussian component.
Further, in the step b, the prior probability of matching consistency between local point pairs in two point sets is solved by the following formula:
Wherein, Representation/>For/>Neighborhood points of/> Is the number of neighborhood points.
Further, in the step c, the posterior probability is solved by the following formula:
wherein U is a uniform distribution.
Further, in said step d, model deformation parameters of the hybrid probability model are solved by the following formula:
Where G is a Gaussian basis function, W is a deformation parameter, Is the variance of the gaussian component of the model.
An improved robust point registration system, comprising: the first module is used for giving two point sets, initializing registration model parameters and giving an initial value; the second module is used for solving the prior probability of the matching consistency between the local point pairs in the two point sets based on the point local structure maintaining theory; the third module is used for further solving the posterior probability based on the mixed probability model and the prior probability acquired by the second module; a fourth module, configured to further solve a deformation parameter of the registration model based on the posterior probability acquired by the third module; a fifth module for rearranging the points in the two point sets based on the deformation parameters acquired by the fourth module; and a sixth module, configured to output a correspondence between the two point sets after convergence of the registration model.
A computer readable storage medium comprising a stored computer program, wherein the computer program, when run by a processor, controls a device on which the storage medium resides to perform the improved robust point registration method as described before.
Compared with the prior art, the invention has the beneficial effects that: according to the consistency of registration relation between two local point sets, the prior probability of matching between the local point pairs is calculated; then, calculating parameters of the Gaussian mixture model by a maximum posterior probability estimation method, and completing registration between point sets; the method has the advantages that when the whole point set is registered, the correspondence consistency between the local point sets is maintained, the accuracy of point set registration is improved, and meanwhile, the robustness of an algorithm when abnormal points exist is improved.
Detailed Description
The following examples are only for more clearly illustrating the technical aspects of the present invention, and are not intended to limit the scope of the present invention.
Embodiment one: an improved robust point registration method, comprising: a. giving two point sets, initializing registration model parameters and giving an initial value; b. solving prior probability of matching consistency between local point pairs in two point sets based on a point local structure maintaining theory; c. further solving posterior probability based on the mixed probability model and the prior probability obtained in the step b; d. c, further solving deformation parameters of the registration model based on the posterior probability obtained in the step c; e. rearranging the points in the two point sets based on the deformation parameters obtained in the step d; f. repeating the steps b-e until the registration model converges, and outputting the corresponding relation between the two point sets.
1) Given two point sets, and initializing registration model parameters and giving initial values
Given two point setsAnd/>Here, theAnd/>Is a 2-dimensional vector, i.e., the coordinates of the point. And may be extended to higher dimensional vectors. N and L are the number of points of the two point sets.
The point matching is to find a matching function f: A mapping relationship is established between two sets of points.
Representing deformation parameters of the registration model. And finally obtaining the one-to-one correspondence between the two point sets under the registration model.
When the number of the two point concentration points is unequal or abnormal points exist in the point concentration, a one-to-one correspondence cannot be formed. At this time, a pseudo point is added to each of the two point setsPoints represent these unmatched or outliers, which would correspond to pseudo-points/>
When the two point sets are deformed non-rigidly, the distance between the points can be varied arbitrarily. However, the point and its neighborhood remain in a relatively fixed relationship. I.e. the local neighborhood relationship or topology of the points remains stable under non-rigid deformations.
2) Based on the point local structure retention theory, solving the prior probability of matching consistency between local point pairs in two point sets
In a point registration algorithm based on a mixed probability model, one point set is used as the centroid of a mixed model component, and the other point set is used as sample data. I.e. find the sample and the mixture model component to which it belongs and establish a correspondence between them. Defining its joint probability density function as:
Wherein, Is a mixed model weight,/>Is a model parameter, and when it is a gaussian mixture model, the function f j () is a gaussian function:
Wherein, Is the Gaussian mean, and is the centroid coordinates of Gaussian components in the Gaussian registration model, namely/>, in the point set Y to be registeredThis takes the point registration problem as a clustering problem for a set of points; /(I)Is a gaussian function variance; wherein, gaussian model parameter/>Can be found by a expectation maximization algorithm. To obtain the corresponding relation between the point sets, a vector/>, is introducedRepresenting a dot/>Mapping to/>Probability of (2); if dot/>Is a dot/>Corresponding points of/>The value is 0 if not; given probability Density function/>The bayesian rule is as follows:
when the parameter is When known, the point/>, can be obtained by solving the following formula from the Bayesian classification ruleCorresponding relation of (3):
When there are no outliers in the point sets and the number of sets of the two point sets is identical, the above model can be solved by the expectation maximization algorithm. Otherwise, outliers can be treated as several erroneous gaussian components, resulting in an incorrect convergence of the expectation maximization algorithm. If a uniform gaussian distribution of components is used. I.e. parameters Is a constant. The hybrid probability model is simplified. So that posterior probability in the desired maximization:
is simplified as follows:
to solve the above problems, the present embodiment defines a new model parameter in the mixed probability model Representing the probability that the i-th point belongs to the j-th gaussian component. Equation (1) can be redefined as:
The above formula defines a more general problem, and therefore Becomes a special case in the formula (7). The following defines the complete data as/>Wherein implicit variable/>Vectors are randomly indicated for lx1. Each component is from the set/>And (3) taking the value. Here/>Is an lx1 vector, where one component takes a value of 1 and the remaining components are zero. Then/>Is a discrete random variable with the value ofThen equation (7) becomes:
Given parameters Can be solved by maximizing a posterior probability estimate to obtain a hybrid model:
Under the probability model framework, the local correspondence consistency of the point set is introduced as the prior probability. Even if the point set is subjected to large-scale inelastic deformation, the local relationship of the point set still maintains strong stability in terms of a local small range of the point set. That is, the local point set neighbor structure cannot be changed at will due to certain physical constraints.
Where N m is the neighborhood of point m, while the neighborhood relationship is symmetric, i.e., if i ε N m, then m ε N i. f (m), f (i) represents a neighborhood system of corresponding points in the two point sets; d (f (m), f (i)) measures the distance between the two neighbor systems; a distance of 1 indicates that the two neighborhood systems match, i.e., the better the neighborhood relationship is maintained; otherwise, 0. The algorithm uses the Euclidean distance between points to describe the neighborhood relationship and its differences between neighbors. In this case, the formula (10) is:
Wherein, As is apparent from the above equation, when the mapping function f achieves an accurate one-to-one correspondence, then the minimum value is zero in equation (11). In order to find the matching consistency probability between the neighborhoods, the embodiment redefines the following neighborhood relation:
I.e. point Is a dot/>One point in the neighborhood then the function d () takes a value of 1, otherwise takes a value of 0. Points are defined hereinIs the neighborhood of the point of departure/>N points nearest to the point are called point/>Where the N value takes 5. According to the above principle of local correspondence consistency, the present embodiment proposes a priori probability of matching between point pairs, and solves the prior probability of matching consistency between local point pairs in two point sets by the following formula:
Wherein, Representation of/>Is/>Neighborhood points of (1), "statistics/>Is/>The number of neighborhood points.Is/>Can be determined by a posterior probability formula (11) of the hybrid model; /(I)Representing the number of all neighborhood points. From the above equation, if a point/>The corresponding points of the neighborhood points in the other point set are all points/>Neighborhood of point of (1)/>, thenMatching with a dot/>The probability of (2) is the largest and the value is 1. Otherwise, the value is between 0 and 1.
3) Further solving posterior probability based on mixed probability model and prior probability obtained in step 2)
Solving the posterior probability of the mixed probability model by the following formula:
Where U is a uniform distribution used to fit outliers in the data. Finally, point location estimation of CPD (Myronenko, 2010) is adopted, Is the initial coordinates, G is a gaussian basis function for regularization constraints, and W is the deformation parameter.
4) Further solving deformation parameters of the registration model based on the posterior probability obtained in the step 3)
Redefined as maximum a posteriori equation (6) based on equation (14):
Obtaining model deformation parameters of the mixed probability model by deriving the formula (15), wherein G is a Gaussian basis function, W is the deformation parameters, Is the variance of the gaussian component of the model.
5) Rearranging the points in the two point sets based on the deformation parameters obtained in step 4)
6) Repeating the steps until the registration model converges, and outputting the corresponding relation between the two point sets.
The more stable the local relationship of points is in the non-rigid point registration process, the higher the accuracy and robustness of the algorithm is. Therefore, in the global point registration technology based on the mixed model, the key points are to maintain the corresponding consistency relation between the local point pairs in the registration process. Meanwhile, as the displacement change of the non-rigid deformation point can be arbitrary and the local corresponding relation is relatively stable, the local corresponding relation of the point set can be kept stable, and the shape characteristics of the point set are ensured. Finally, the integral corresponding relation between the registration point sets is maintained in the registration process. How to quantify correspondence between pairs of points becomes a key technique therein.
The local corresponding relation of the points is considered, and the corresponding relation between the local points is used as the prior probability of point registration. A local correspondence consistency probability calculation method is provided, and the definition is shown in formula 10. The method is based on priori knowledge of structural stability between the neighborhood points of the point sets, the global probability of matching between the two point sets is guided through the local consistency local matching probability, and finally registration model parameters are obtained through maximum posterior probability estimation, which is shown in a formula (15). In the point registration process, the correspondence consistency between the points and the neighborhood points is always maintained. The accuracy and the robustness of the algorithm are improved.
Embodiment two:
Based on the improved robust point registration method of embodiment one, the present embodiment provides an improved robust point registration system, comprising: the first module is used for giving two point sets, initializing registration model parameters and giving an initial value; the second module is used for solving the prior probability of the matching consistency between the local point pairs in the two point sets based on the point local structure maintaining theory; the third module is used for further solving the posterior probability based on the mixed probability model and the prior probability acquired by the second module; a fourth module, configured to further solve a deformation parameter of the registration model based on the posterior probability acquired by the third module; a fifth module for rearranging the points in the two point sets based on the deformation parameters acquired by the fourth module; and a sixth module, configured to output a correspondence between the two point sets after convergence of the registration model.
Embodiment III:
based on the improved robust point registration method of embodiment one, this embodiment provides a computer readable storage medium comprising a stored computer program, wherein the device in which the storage medium is controlled to perform the improved robust point registration method of embodiment one when the computer program is run by a processor.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Claims (3)
1. An improved robust point registration method, applied to image registration technology, is characterized by comprising the following steps:
a. given two point sets And/> And/>Is a two-dimensional vector, i.e., the coordinates of a point; n and L are the number of points of the two point sets, and initialize the registration model parameters and give an initial value;
b. solving prior probability of matching consistency between local point pairs in two point sets based on a point local structure maintaining theory;
c. Further solving posterior probability based on the mixed probability model and the prior probability obtained in the step b;
d. c, further solving deformation parameters of the registration model based on the posterior probability obtained in the step c;
e. Rearranging the points in the two point sets based on the deformation parameters obtained in the step d;
f. repeating the steps b-e until the registration model converges, and outputting the corresponding relation between the two point sets;
Wherein, the joint probability density function of the mixed probability model is:
Wherein, Is a model parameter, parameter/>Representing the probability that the i-th point belongs to the j-th gaussian component; the function f j () is a gaussian function;
In the step b, the prior probability of matching consistency between local point pairs in two point sets is solved by the following formula:
Wherein, Representation/>For/>Neighborhood points of/> The number of all neighborhood points; /(I)Representation of/>Is/>Neighborhood points of (1), "statistics/>Is/>The number of neighborhood points; Is/> Global corresponding points of (a); if dot/>The corresponding points of the neighborhood points in the other point set are all points/>Neighborhood of point of (1)/>, thenMatching with a dot/>The probability of (2) is maximum, and the value is 1; otherwise, the value is between 0 and 1;
In the step c, the posterior probability is solved by the following formula:
Wherein U is uniformly distributed; is the Gaussian mean of the j-th component,/> Y is an initial coordinate, G is a Gaussian basis function, and W is a deformation parameter; /(I)Is a gaussian function variance;
In said step d, model deformation parameters of the hybrid probability model are solved by the following formula:
2. An improved robust point registration system based on the improved robust point registration method of claim 1, comprising:
the first module is used for giving two point sets, initializing registration model parameters and giving an initial value;
the second module is used for solving the prior probability of the matching consistency between the local point pairs in the two point sets based on the point local structure maintaining theory;
The third module is used for further solving the posterior probability based on the mixed probability model and the prior probability acquired by the second module;
A fourth module, configured to further solve a deformation parameter of the registration model based on the posterior probability acquired by the third module;
a fifth module for rearranging the points in the two point sets based on the deformation parameters acquired by the fourth module;
and a sixth module, configured to output a correspondence between the two point sets after convergence of the registration model.
3. A computer readable storage medium, characterized in that the computer readable storage medium comprises a stored computer program, wherein the computer program, when run by a processor, controls a device in which the storage medium is located to perform the improved robust point registration method of claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011254115.5A CN112465881B (en) | 2020-11-11 | 2020-11-11 | Improved robust point registration method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011254115.5A CN112465881B (en) | 2020-11-11 | 2020-11-11 | Improved robust point registration method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112465881A CN112465881A (en) | 2021-03-09 |
| CN112465881B true CN112465881B (en) | 2024-06-04 |
Family
ID=74826785
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011254115.5A Active CN112465881B (en) | 2020-11-11 | 2020-11-11 | Improved robust point registration method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112465881B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103310219A (en) * | 2012-03-08 | 2013-09-18 | 佳能株式会社 | Method and equipment for precision evaluation of object shape registration, and method and equipment for registration |
| CN103353989A (en) * | 2013-06-18 | 2013-10-16 | 西安电子科技大学 | SAR image change detection method based on priori, fusion gray level and textural feature |
| CN104392458A (en) * | 2014-12-12 | 2015-03-04 | 哈尔滨理工大学 | Image segmentation method based on space limitation neighborhood hybrid model |
| CN105635808A (en) * | 2015-12-31 | 2016-06-01 | 电子科技大学 | Video splicing method based on Bayesian theory |
| CN106485741A (en) * | 2016-10-19 | 2017-03-08 | 哈尔滨工业大学 | A kind of method of the non-firm point set registration retaining partial structurtes |
| CN106530341A (en) * | 2016-11-01 | 2017-03-22 | 成都理工大学 | Point registration algorithm capable of keeping local topology invariance |
| CN109919984A (en) * | 2019-04-15 | 2019-06-21 | 武汉惟景三维科技有限公司 | A kind of point cloud autoegistration method based on local feature description's |
| CN110111250A (en) * | 2019-04-11 | 2019-08-09 | 中国地质大学（武汉） | A kind of automatic panorama unmanned plane image split-joint method and device of robust |
| CN110458874A (en) * | 2019-07-17 | 2019-11-15 | 苏州博芮恩光电科技有限公司 | A kind of image non-rigid registration method and system |
| CN110706191A (en) * | 2019-10-14 | 2020-01-17 | 中国空气动力研究与发展中心超高速空气动力研究所 | High-pressure container detection method based on infrared image splicing fusion algorithm |
| CN110874849A (en) * | 2019-11-08 | 2020-03-10 | 安徽大学 | Non-rigid point set registration method based on local transformation consistency |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1736928A1 (en) * | 2005-06-20 | 2006-12-27 | Mitsubishi Electric Information Technology Centre Europe B.V. | Robust image registration |
| US7583857B2 (en) * | 2005-08-24 | 2009-09-01 | Siemens Medical Solutions Usa, Inc. | System and method for salient region feature based 3D multi modality registration of medical images |
| US10445891B2 (en) * | 2017-11-03 | 2019-10-15 | Canon Medical Systems Corporation | Medical image processing apparatus and method |
-
2020
- 2020-11-11 CN CN202011254115.5A patent/CN112465881B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103310219A (en) * | 2012-03-08 | 2013-09-18 | 佳能株式会社 | Method and equipment for precision evaluation of object shape registration, and method and equipment for registration |
| CN103353989A (en) * | 2013-06-18 | 2013-10-16 | 西安电子科技大学 | SAR image change detection method based on priori, fusion gray level and textural feature |
| CN104392458A (en) * | 2014-12-12 | 2015-03-04 | 哈尔滨理工大学 | Image segmentation method based on space limitation neighborhood hybrid model |
| CN105635808A (en) * | 2015-12-31 | 2016-06-01 | 电子科技大学 | Video splicing method based on Bayesian theory |
| CN106485741A (en) * | 2016-10-19 | 2017-03-08 | 哈尔滨工业大学 | A kind of method of the non-firm point set registration retaining partial structurtes |
| CN106530341A (en) * | 2016-11-01 | 2017-03-22 | 成都理工大学 | Point registration algorithm capable of keeping local topology invariance |
| CN110111250A (en) * | 2019-04-11 | 2019-08-09 | 中国地质大学（武汉） | A kind of automatic panorama unmanned plane image split-joint method and device of robust |
| CN109919984A (en) * | 2019-04-15 | 2019-06-21 | 武汉惟景三维科技有限公司 | A kind of point cloud autoegistration method based on local feature description's |
| CN110458874A (en) * | 2019-07-17 | 2019-11-15 | 苏州博芮恩光电科技有限公司 | A kind of image non-rigid registration method and system |
| CN110706191A (en) * | 2019-10-14 | 2020-01-17 | 中国空气动力研究与发展中心超高速空气动力研究所 | High-pressure container detection method based on infrared image splicing fusion algorithm |
| CN110874849A (en) * | 2019-11-08 | 2020-03-10 | 安徽大学 | Non-rigid point set registration method based on local transformation consistency |
Non-Patent Citations (2)
| Title |
|---|
| 基于特征点的非刚性图像配准算法;谷皓;程远志;;智能计算机与应用;20190501(第03期);全文 * |
| 基于邻域结构和高斯混合模型的非刚性点集配准算法;彭磊;李光耀;肖莽;王刚;谢力;;电子与信息学报(第01期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112465881A (en) | 2021-03-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107123164B (en) | Three-dimensional reconstruction method and system for keeping sharp features | |
| WO2018098891A1 (en) | Stereo matching method and system | |
| CN106530341B (en) | Point registration algorithm for keeping local topology invariance | |
| WO2022077863A1 (en) | Visual positioning method, and method for training related model, related apparatus, and device | |
| CN115222625A (en) | Laser radar point cloud denoising method based on multi-scale noise | |
| CN103366375A (en) | Method for registering image set based on dynamic digraphs | |
| CN111553296B (en) | Two-value neural network stereo vision matching method based on FPGA | |
| CN112634149A (en) | Point cloud denoising method based on graph convolution network | |
| CN112364881B (en) | Advanced sampling consistency image matching method | |
| Zhou et al. | Improvement of normal estimation for point clouds via simplifying surface fitting | |
| CN110334450B (en) | Method for repairing object plane projection error in multi-block structure grid generation | |
| CN110688440A (en) | Map fusion method suitable for less sub-map overlapping parts | |
| CN108846845B (en) | SAR image segmentation method based on thumbnail and hierarchical fuzzy clustering | |
| CN112465881B (en) | Improved robust point registration method and system | |
| CN103325104A (en) | Facial image super-resolution reestablishing method based on iterative sparse representation | |
| CN109887012B (en) | Point cloud registration method combined with self-adaptive search point set | |
| CN106056575A (en) | Image matching method based on object similarity recommended algorithm | |
| CN111401385B (en) | Similarity calculation method for image local topological structure feature descriptors | |
| CN112837420A (en) | Method and system for completing shape of terracotta warriors point cloud based on multi-scale and folding structure | |
| Lee et al. | SAF-Nets: Shape-Adaptive Filter Networks for 3D point cloud processing | |
| CN109785331B (en) | Sonar image segmentation method based on self-adaptive pixel value constraint and MRF | |
| CN111382834B (en) | Confidence degree comparison method and device | |
| CN112738724A (en) | Method, device, equipment and medium for accurately identifying regional target crowd | |
| Lin et al. | Weighted two-dimensional Otsu threshold approached for image segmentation | |
| Jensen et al. | Deep Active Latent Surfaces for Medical Geometries |
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 |