CN113628262A - Aircraft skin detection method based on contour feature constraint registration - Google Patents

Aircraft skin detection method based on contour feature constraint registration Download PDF

Info

Publication number
CN113628262A
CN113628262A CN202110941410.6A CN202110941410A CN113628262A CN 113628262 A CN113628262 A CN 113628262A CN 202110941410 A CN202110941410 A CN 202110941410A CN 113628262 A CN113628262 A CN 113628262A
Authority
CN
China
Prior art keywords
point
contour
points
feature
registration
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
Application number
CN202110941410.6A
Other languages
Chinese (zh)
Inventor
崔海华
田威
胡广露
廖文和
张益华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing University of Aeronautics and Astronautics
Original Assignee
Nanjing University of Aeronautics and Astronautics
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Nanjing University of Aeronautics and Astronautics filed Critical Nanjing University of Aeronautics and Astronautics
Priority to CN202110941410.6A priority Critical patent/CN113628262A/en
Publication of CN113628262A publication Critical patent/CN113628262A/en
Pending legal-status Critical Current

Links

Images

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
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/12—Edge-based segmentation
    • 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
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • 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
    • G06T2207/10028—Range image; Depth image; 3D point clouds
    • 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
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30164—Workpiece; Machine component

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Image Analysis (AREA)

Abstract

The invention discloses an aircraft skin detection method based on contour feature constraint registration, which comprises the following steps: acquiring measurement data of an aircraft skin and a CAD model point set; extracting a point cloud boundary to obtain an outline point cloud of an aircraft skin, and dispersing the skin outline point cloud in the CAD model independently to obtain a corresponding point set; calculating C kappa characteristic points on the contour based on curvature mean square error, and clustering the characteristic points based on Euclidean distance; introducing distance features on the basis of the fast point feature histogram, providing an FPFH-d feature point description algorithm, and calculating corresponding points in a skin measurement data contour point set and a CAD data contour point set; and solving an initial registration matrix of the skin measurement data contour point set and the CAD data contour point set according to corresponding points on the contour, solving an optimal spatial transformation matrix by taking contour characteristic point registration as constraint, and calculating the deformation according to the root mean square error of a registration result. The method can effectively solve the problem that the accurate registration of the aircraft skin cannot be realized due to few surface features.

Description

Aircraft skin detection method based on contour feature constraint registration
Technical Field
The invention relates to the technical field of aircraft skin detection, in particular to an aircraft skin detection method based on contour feature constraint registration.
Background
The aircraft skin part is an important component of the aerodynamic shape of the aircraft and has the characteristics of large size and easy deformation. The processing quality of the skin parts directly influences the overall assembly precision of the airplane, and the accurate detection of the skin parts has important significance for airplane manufacturing. With the development of optical measurement equipment, surface three-dimensional data of a measured part can be rapidly acquired, the process of comparing the measured data of the skin with a theoretical model is used for detecting the manufacturing error of the skin, the measured point cloud is converted into a model coordinate system by unifying the coordinate systems of the measured point cloud and the design model, the corresponding relation between the measured point cloud and the model data is determined, and the distance between the measured point cloud and the model data is calculated to be the offset of the measured object and the design model. The overall manufacturing error condition of the aircraft skin can be obtained by aligning the aircraft skin measurement point cloud and the model data, and the detection result can be used for performing operations such as skin profile correction, so that the accurate alignment of the aircraft skin measurement point cloud and the model data is a key technology in the aircraft skin detection.
Although a point cloud registration technology is studied in detail, a weak texture point cloud registration method, particularly a registration method of thin-wall parts like smooth and non-porous characteristic aircraft skins, is still deficient. Feature points are generally used as registration constraints in the registration process, but registration dislocation still exists because the aircraft skin features are few. The existing method cannot well solve the problem of accurate registration of the imperforate weak texture aircraft skin, the corresponding relation cannot be effectively distinguished in a smooth area of a molded surface, and the wrong corresponding relation can cause the calculation error of the manufacturing error of the aircraft skin, so that the false detection of the aircraft skin is caused.
Disclosure of Invention
The invention aims to solve the technical problem that an aircraft skin detection method based on contour feature constraint registration is provided, and the problem that the aircraft skin cannot be accurately registered due to few surface features can be effectively solved.
In order to solve the technical problem, the invention provides an aircraft skin detection method based on contour feature constraint registration, which comprises the following steps:
(1) acquiring measurement data of an aircraft skin and a CAD model point set;
(2) extracting a point cloud boundary to obtain an outline point cloud of an aircraft skin, and dispersing the skin outline point cloud in the CAD model independently to obtain a corresponding point set;
(3) calculating C kappa characteristic points on the contour based on curvature mean square error, and clustering the characteristic points based on Euclidean distance;
(4) introducing distance features on the basis of the fast point feature histogram, providing an FPFH-d feature point description algorithm, and calculating corresponding points in a skin measurement data contour point set and a CAD data contour point set;
(5) and solving an initial registration matrix of the skin measurement data contour point set and the CAD data contour point set according to corresponding points on the contour, solving an optimal spatial transformation matrix by taking contour characteristic point registration as constraint, and calculating the deformation according to the root mean square error of a registration result.
Preferably, the step (3) of calculating the C κ feature point on the contour based on the curvature mean square error includes the steps of:
(31) estimating the normal and curvature of discrete point in the point cloud by principal component analysis method, and using a certain discrete point P in the point cloudaConstructing a covariance matrix of the neighborhood points by using n three-dimensional points of a certain number:
Figure BDA0003215012920000021
in the formula piIs PaThe three-dimensional coordinates of the ith point in the neighborhood,
Figure BDA0003215012920000022
the gravity center coordinates of the neighborhood points are obtained, n is the number of the neighborhood points, and in actual calculation, n is determined according to the local point cloud density;
(32) let λ (i ═ 1,2,3), ui(i is 1,2,3) is the eigenvalue and corresponding eigenvector of the covariance matrix C, then PaThe curvature of the point is
Figure BDA0003215012920000023
(33) Calculating the mean square error of curvature k of each point in the neighborhood ki
Figure BDA0003215012920000024
Since E (ρ) is a description of the change in curvature of the point cloud of neighboring points, when P isiPoint and PaWhen the relative position of the point in the neighborhood is not changed, kiThe value is unchanged, so the method of discrete point description using neighborhood curvature mean square error has rotation invariance.
Preferably, in the step (3), clustering the feature points based on the euclidean distance includes the steps of:
(34) selecting a seed point p from the C kappa characteristic point set1Searching for p using kd-Tree1N points in a certain neighborhood are stored as a set of region points (p)1,p2,...,pn)；
(35) Set of points in region (P \ P)1,p2,...,pn) In the seed selection point pn+1Continuing with step (34);
(36) when the region point set is not increased any more, the clustering is considered to be completed;
(37) and selecting the point with the maximum kappa value in each region point set as the characteristic point of the C kappa of the region.
Preferably, in the step (4), the distance feature is introduced on the basis of the fast point feature histogram, an FPFH-d feature point description algorithm is proposed, and the calculation of the corresponding point of the skin measurement data contour point set and the CAD data contour point set specifically includes the following steps:
(41) constructing an FPFH-d characteristic point descriptor by using the deviation of points in the neighborhood to normal vectors and distance characteristics, wherein a description matrix is T (tau, B), and tau (d)1,d2,..,dk)T，B＝(b1,b2,...,bk)；
(42) Describing the similarity of two point cloud feature points by adopting an integration system, recording the similarity score as s, and if the potential corresponding feature points describe matrixes as T respectively1＝(τ1,B1)，T2＝(τ2,B2) The similarity is as follows:
Figure BDA0003215012920000031
wherein k is1，k2Represents T1，T2Dimension of, delta1Being threshold values of distance features, δ2And counting the score of each characteristic point for the threshold value of the angle characteristic, and considering the corresponding point if the score is greater than the score threshold value.
Preferably, in the step (5), solving the optimal spatial transformation matrix with the registration of the contour feature points as constraints includes the following steps:
(51) setting an objective function to
Figure BDA0003215012920000032
Wherein R isTR＝I；
(52) Order to
Figure BDA0003215012920000033
The SVD of S is decomposed into (U, Σ, V), where UTSV＝Σ；
(53) The spatial transformation matrix is
Figure BDA0003215012920000034
(54) And calculating the manufacturing error amount according to the root mean square error of the whole point cloud.
The invention has the beneficial effects that: (1) the method is suitable for registering the aircraft skin without characteristics such as hole sites on the surface, and can effectively avoid the influence of the skin data surface characteristics on the registration result; (2) the registration of the Mongolian point clouds can be accurately and efficiently realized, and the problem of dislocation in the registration process of the existing method is avoided.
Drawings
FIG. 1 is a schematic flow chart of the method of the present invention.
Detailed Description
As shown in fig. 1, a method for detecting an aircraft skin based on contour feature constraint registration includes the following steps:
s1, obtaining measurement data of the aircraft skin and a CAD model point set;
s2, extracting and obtaining a contour point cloud point set P of the aircraft skin through a point cloud boundary, and independently dispersing a skin contour point cloud point set Q in the CAD model;
and S3, calculating C kappa feature points on the contour based on the curvature mean square error, and clustering the feature points based on Euclidean distance.
The method comprises the following specific steps:
s11, estimating the normal and curvature of the discrete point in the point cloud by using principal component analysis method, and using a certain discrete point P in the point cloudaConstructing a covariance matrix of the neighborhood points by using n three-dimensional points of a certain number:
Figure BDA0003215012920000041
in the formula piIs PaThe three-dimensional coordinates of the ith point in the neighborhood,
Figure BDA0003215012920000044
is the barycentric coordinate of the neighborhood points, n is the number of the neighborhood points, and n is determined according to the local point cloud density in the actual calculation.
S12, λ (i ═ 1,2,3), ui(i-1, 2,3) are eachThe eigenvalues of the covariance matrix C and the corresponding eigenvectors.
Then P isaThe curvature of the point is
Figure BDA0003215012920000042
S13, calculating the curvature mean square error k of each point in the neighborhood ki
Figure BDA0003215012920000043
Since E (ρ) is a description of the change in curvature of the point cloud of neighboring points, when P isiPoint and PaWhen the relative position of the point in the neighborhood is not changed, kiThe value is unchanged, so the method of discrete point description using neighborhood curvature mean square error has rotation invariance.
The clustering of the C kappa characteristic points based on Euclidean distance comprises the following steps:
s11, selecting a seed point p from the Ck characteristic point set1Searching for p using kd-Tree1N points in a certain neighborhood are stored as a set of region points (p)1,p2,...,pn)；
S12, set of points in region (P \ P)1,p2,...,pn) In the seed selection point pn+1Continuing with S11;
and S13, when the region point set is not increased any more, the clustering is considered to be completed.
S14, selecting the point with the maximum kappa value in each region point set as the C kappa characteristic point of the region
S3, introducing distance features on the basis of the fast point feature histogram, providing an FPFH-d feature point description algorithm, and calculating corresponding points in the skin measurement data contour point set and the CAD data contour point set. The method comprises the following steps:
s11, constructing an FPFH-d characteristic point descriptor by using the deviation of the point in the neighborhood to the normal vector and the distance characteristic, wherein the description matrix is T ═ tau, B, and tau ═ d (d)1,d2,..,dk)T，B＝(b1,b2,...,bk)。
And S12, describing the similarity of the two point cloud feature points by adopting an integral system. Marking the similarity score as s, and respectively setting the description matrixes of the potential corresponding characteristic points as T1＝(τ1,B1)，T2＝(τ2,B2). The similarity is as follows:
Figure BDA0003215012920000051
wherein k is1，k2Represents T1，T2Dimension of, delta1Being threshold values of distance features, δ2And counting the score of each characteristic point for the threshold value of the angle characteristic, and considering the corresponding point if the score is greater than the score threshold value.
And S4, solving an initial registration matrix of the skin measurement data contour point set and the CAD data contour point set according to the corresponding points on the contour, and solving an optimal spatial transformation matrix by taking contour feature point registration as constraint. And calculating the deformation according to the root mean square error of the registration result. The method comprises the following steps:
s11, setting the objective function as
Figure BDA0003215012920000052
Wherein R isTR＝I。
S12, order
Figure BDA0003215012920000053
The SVD of S is decomposed into (U, Σ, V), where UTSV＝Σ；
S13, spatial transformation matrix is
Figure BDA0003215012920000054
And S14, calculating the manufacturing error amount according to the root mean square error of the whole point cloud.

Claims (5)

1. An aircraft skin detection method based on contour feature constraint registration is characterized by comprising the following steps:
(1) acquiring measurement data of an aircraft skin and a CAD model point set;
(2) extracting a point cloud boundary to obtain an outline point cloud of an aircraft skin, and dispersing the skin outline point cloud in the CAD model independently to obtain a corresponding point set;
(3) calculating C kappa characteristic points on the contour based on curvature mean square error, and clustering the characteristic points based on Euclidean distance;
(4) introducing distance features on the basis of the fast point feature histogram, providing an FPFH-d feature point description algorithm, and calculating corresponding points in a skin measurement data contour point set and a CAD data contour point set;
(5) and solving an initial registration matrix of the skin measurement data contour point set and the CAD data contour point set according to corresponding points on the contour, solving an optimal spatial transformation matrix by taking contour characteristic point registration as constraint, and calculating the deformation according to the root mean square error of a registration result.
2. The aircraft skin detection method based on contour feature constraint registration as claimed in claim 1, wherein in the step (3), calculating the C κ feature point on the contour based on the curvature mean square error comprises the following steps:
(31) estimating the normal and curvature of discrete point in the point cloud by principal component analysis method, and using a certain discrete point P in the point cloudaConstructing a covariance matrix of the neighborhood points by using n three-dimensional points of a certain number:
Figure FDA0003215012910000011
in the formula piIs PaThe three-dimensional coordinates of the ith point in the neighborhood,
Figure FDA0003215012910000012
is the barycentric coordinate of the neighborhood points, n is the number of the neighborhood points, and n is the number of the neighborhood points in the actual calculationDetermining according to the density of the local point cloud;
(32) let λ (i ═ 1,2,3), ui(i is 1,2,3) is the eigenvalue and corresponding eigenvector of the covariance matrix C, then PaThe curvature of the point is
Figure FDA0003215012910000013
(33) Calculating the mean square error of curvature k of each point in the neighborhood ki
Figure FDA0003215012910000014
Since E (ρ) is a description of the change in curvature of the point cloud of neighboring points, when P isiPoint and PaWhen the relative position of the point in the neighborhood is not changed, kiThe value is unchanged.
3. The aircraft skin detection method based on contour feature constraint registration as claimed in claim 1, wherein in the step (3), clustering the feature points based on Euclidean distance comprises the following steps:
(34) selecting a seed point p from the C kappa characteristic point set1Searching for p using kd-Tree1N points in a certain neighborhood are stored as a set of region points (p)1,p2,...,pn)；
(35) Set of points in region (P \ P)1,p2,...,pn) In the seed selection point pn+1Continuing with step (34);
(36) when the region point set is not increased any more, the clustering is considered to be completed;
(37) and selecting the point with the maximum kappa value in each region point set as the characteristic point of the C kappa of the region.
4. The method for detecting aircraft skin based on contour feature constraint registration according to claim 1, wherein in the step (4), the distance feature is introduced on the basis of the fast point feature histogram, an FPFH-d feature point description algorithm is proposed, and the calculation of the corresponding points in the skin measurement data contour point set and the CAD data contour point set specifically comprises the following steps:
(41) constructing an FPFH-d characteristic point descriptor by using the deviation of points in the neighborhood to normal vectors and distance characteristics, wherein a description matrix is T (tau, B), and tau (d)1,d2,..,dk)T，B＝(b1,b2,...,bk)；
(42) Describing the similarity of two point cloud feature points by adopting an integration system, recording the similarity score as s, and if the potential corresponding feature points describe matrixes as T respectively1＝(τ1,B1)，T2＝(τ2,B2) The similarity is as follows:
Figure FDA0003215012910000021
wherein k is1，k2Represents T1，T2Dimension of, delta1Being threshold values of distance features, δ2And counting the score of each characteristic point for the threshold value of the angle characteristic, and considering the corresponding point if the score is greater than the score threshold value.
5. The aircraft skin detection method based on contour feature constraint registration as claimed in claim 1, wherein in the step (5), solving the optimal spatial transformation matrix by taking contour feature point registration as constraint comprises the following steps:
(51) setting an objective function to
Figure FDA0003215012910000022
Wherein R isTR＝I；
(52) Order to
Figure FDA0003215012910000023
The SVD of S is decomposed into (U, Σ, V), where UTSV＝Σ；
(53) The spatial transformation matrix is
R＝VUT,
Figure FDA0003215012910000024
(54) And calculating the manufacturing error amount according to the root mean square error of the whole point cloud.
CN202110941410.6A 2021-08-17 2021-08-17 Aircraft skin detection method based on contour feature constraint registration Pending CN113628262A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110941410.6A CN113628262A (en) 2021-08-17 2021-08-17 Aircraft skin detection method based on contour feature constraint registration

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110941410.6A CN113628262A (en) 2021-08-17 2021-08-17 Aircraft skin detection method based on contour feature constraint registration

Publications (1)

Publication Number Publication Date
CN113628262A true CN113628262A (en) 2021-11-09

Family

ID=78386058

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110941410.6A Pending CN113628262A (en) 2021-08-17 2021-08-17 Aircraft skin detection method based on contour feature constraint registration

Country Status (1)

Country Link
CN (1) CN113628262A (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113837326A (en) * 2021-11-30 2021-12-24 自然资源部第一海洋研究所 Airborne laser sounding data registration method based on characteristic curve
CN114943752A (en) * 2022-05-31 2022-08-26 河南埃尔森智能科技有限公司 Self-adaptive contour template identification and registration method based on curvature feature description
CN115147471A (en) * 2022-06-28 2022-10-04 兰州交通大学 Laser point cloud automatic registration method based on curvature density characteristics
CN115272733A (en) * 2022-07-29 2022-11-01 南京林业大学 Trunk information extraction method based on point cloud data and multi-feature fusion
CN116541638A (en) * 2023-06-30 2023-08-04 南京航空航天大学 Aircraft skin repair processing path calculation method based on tensor voting
WO2023226131A1 (en) * 2022-05-24 2023-11-30 湖南大学 Curved surface skinning three-dimensional data merging method
US11861793B2 (en) 2022-05-24 2024-01-02 Hunan University Method for merging surface skin three-dimensional data
CN117454672A (en) * 2023-12-22 2024-01-26 湖南大学 Robot operation allowance calculation method based on curved surface assembly constraint

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110276790A (en) * 2019-06-28 2019-09-24 易思维（杭州）科技有限公司 Point cloud registration method based on shape constraining
CN112802070A (en) * 2021-01-06 2021-05-14 南京航空航天大学 Aircraft skin local point cloud positioning method based on multi-descriptor voting

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110276790A (en) * 2019-06-28 2019-09-24 易思维（杭州）科技有限公司 Point cloud registration method based on shape constraining
CN112802070A (en) * 2021-01-06 2021-05-14 南京航空航天大学 Aircraft skin local point cloud positioning method based on multi-descriptor voting

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
靳宇婷: "一种基于轮廓特征约束的飞机蒙皮配准方法一种基于轮廓特征约束的飞机蒙皮配准方法", 光学学报, vol. 41, no. 3, 28 February 2021 (2021-02-28), pages 1 - 9 *

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113837326A (en) * 2021-11-30 2021-12-24 自然资源部第一海洋研究所 Airborne laser sounding data registration method based on characteristic curve
WO2023226131A1 (en) * 2022-05-24 2023-11-30 湖南大学 Curved surface skinning three-dimensional data merging method
US11861793B2 (en) 2022-05-24 2024-01-02 Hunan University Method for merging surface skin three-dimensional data
CN114943752A (en) * 2022-05-31 2022-08-26 河南埃尔森智能科技有限公司 Self-adaptive contour template identification and registration method based on curvature feature description
CN114943752B (en) * 2022-05-31 2024-03-29 河南埃尔森智能科技有限公司 Self-adaptive contour template identification registration method based on curvature feature description
CN115147471A (en) * 2022-06-28 2022-10-04 兰州交通大学 Laser point cloud automatic registration method based on curvature density characteristics
CN115272733A (en) * 2022-07-29 2022-11-01 南京林业大学 Trunk information extraction method based on point cloud data and multi-feature fusion
CN115272733B (en) * 2022-07-29 2024-02-23 南京林业大学 Trunk information extraction method based on point cloud data and multi-feature fusion
CN116541638A (en) * 2023-06-30 2023-08-04 南京航空航天大学 Aircraft skin repair processing path calculation method based on tensor voting
CN116541638B (en) * 2023-06-30 2023-09-12 南京航空航天大学 Aircraft skin repair processing path calculation method based on tensor voting
CN117454672A (en) * 2023-12-22 2024-01-26 湖南大学 Robot operation allowance calculation method based on curved surface assembly constraint
CN117454672B (en) * 2023-12-22 2024-04-12 湖南大学 Robot operation allowance calculation method based on curved surface assembly constraint

Similar Documents

Publication Publication Date Title
CN113628262A (en) Aircraft skin detection method based on contour feature constraint registration
CN110335297B (en) Point cloud registration method based on feature extraction
CN109493372B (en) Rapid global optimization registration method for product point cloud data with large data volume and few characteristics
Jordan et al. A quantitative evaluation of surface normal estimation in point clouds
CN104121902B (en) Implementation method of indoor robot visual odometer based on Xtion camera
CN109147040B (en) Template-based human point cloud hole repairing method
CN113327275B (en) Point cloud double-view-angle fine registration method based on multi-constraint point to local curved surface projection
CN112381862B (en) Full-automatic registration method and device for CAD (computer-aided design) model and triangular mesh
CN111145129A (en) Point cloud denoising method based on hyper-voxels
CN109270079B (en) Workpiece surface defect accurate detection method based on point cloud model
CN114037706A (en) Precast beam segment surface flatness detection method based on three-dimensional point cloud model
Dong et al. Application of local-feature-based 3D point cloud stitching method of low-overlap point cloud to aero-engine blade measurement
KR100828412B1 (en) 3d face recognition method using multiple point signature
CN115082472A (en) Quality detection method and system for hub mold casting molding product
CN114840925A (en) Method for registering vehicle body part measurement data to integral CAD model
WO2018131163A1 (en) Information processing device, database generation device, method, and program, and storage medium
CN110942077A (en) Feature line extraction method based on weight local change degree and L1 median optimization
Liu et al. Robust 3-d object recognition via view-specific constraint
CN116721144A (en) Cone hole size measurement method based on point cloud slicing
CN115082547B (en) Profile measuring method based on point cloud data and storage medium
CN111652801B (en) Accurate point cloud splicing method
KR100596559B1 (en) Method of Error Compensated Singular Value Decomposition Based Head Pose Estimation for 3D Face Recognition
CN115147471A (en) Laser point cloud automatic registration method based on curvature density characteristics
CN115797414A (en) Complex curved surface measurement point cloud data registration method considering measuring head radius
CN115496784A (en) Point cloud registration method based on normalized four-dimensional feature vector

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