scholarly journals Fast Aerial Image Geolocalization Using the Projective-Invariant Contour Feature

2021 ◽  
Vol 13 (3) ◽  
pp. 490
Author(s):  
Yongfei Li ◽  
Shicheng Wang ◽  
Hao He ◽  
Deyu Meng ◽  
Dongfang Yang
Keyword(s):  
Feature Matching ◽  
Projective Transformation ◽  
Aerial Image ◽  
Geometric Feature ◽  
Point Set Registration ◽  
Projective Invariant ◽  
Geometric Consistency ◽  
Local Point ◽  
Contour Feature ◽  
Point Set

We address the problem of aerial image geolocalization over an area as large as a whole city through road network matching, which is modeled as a 2D point set registration problem under the 2D projective transformation and solved in a two-stage manner. In the first stage, all the potential transformations aligning the query road point set to the reference road point set are found by local point feature matching. A local geometric feature, called the Projective-Invariant Contour Feature (PICF), which consists of a road intersection and the closest points to it in each direction, is specifically designed. We prove that the proposed PICF is equivariant under the 2D projective transformation group. We then encode the PICF with a projective-invariant descriptor to enable the fast search of potential correspondences. The bad correspondences are then removed by a geometric consistency check with the graph-cut algorithm effectively. In the second stage, a flexible strategy is developed to recover the homography transformation with all the PICF correspondences with the Random Sample Consensus (RANSAC) method or to recover the transformation with only one correspondence and then refine it with the local-to-global Iterative Closest Point (ICP) algorithm when only a few correspondences exist. The strategy makes our method efficient to deal with both scenes where roads are sparse and scenes where roads are dense. The refined transformations are then verified with alignment accuracy to determine whether they are accepted as correct. Experimental results show that our method runs faster and greatly improves the recall compared with the state-of-the-art methods.

scholarly journals Information-Theoretic Directly Manipulated Free-Form Deformation Labeled Point-Set Registration

2010 ◽  
Author(s):  
Nicholas J. Tustison ◽  
Suyash Awate ◽  
James Gee
Keyword(s):  
Spline Approximation ◽  
Transformation Model ◽  
Free Form ◽  
Theoretic Approach ◽  
Cardinality Constraints ◽  
Information Theoretic ◽  
Point Set Registration ◽  
Local Point ◽  
Free Form Deformation ◽  
Point Set

Our previous contributions to the ITK community include a generalized B-spline approximation scheme as well as a generalized information-theoretic measure for assessing point-set correspondence known as the Jensen-Havrda-Charvat-Tsallis (JHCT) divergence. In this submission, we combine these two contributions for the registration of labeled point-sets. The transformation model which uses the former contribution is denoted as directly manipulated free-form deformation (DMFFD) and has been used for image registration. The information-theoretic approach described not only eliminates exact cardinality constraints which plague exact landmark matching algorithms, but it also incorporates the local point-set structure into the similarity measure calculation. Although theoretical discussion of these two components is deferred to other venues, the implementation details given in this submission should be adequate for those wishing to use our algorithm. Visualization of results is aided by another of our previous contributions. Additionally, we provide the rudimentary command line parsing classes used in our testing routines which were written in the ITK style and also available to use consistent with the open-source paradigm.

Multi-View Image Color Correction Using 3D Point Set Registration

2021 ◽  
Author(s):  
Hyeonwoo Jeong ◽  
Byunghyun Yoon ◽  
Honggu Jeong ◽  
Kang-Sun Choi
Keyword(s):  
Color Correction ◽  
Point Set Registration ◽  
Point Set

A robust non-rigid point set registration method based on inhomogeneous Gaussian mixture models

2017 ◽  
Vol 34 (10) ◽  
pp. 1399-1414 ◽  
Author(s):  
Wanxia Deng ◽  
Huanxin Zou ◽  
Fang Guo ◽  
Lin Lei ◽  
Shilin Zhou ◽  
...  
Keyword(s):  
Mixture Models ◽  
Gaussian Mixture Models ◽  
Gaussian Mixture ◽  
Registration Method ◽  
Point Set Registration ◽  
Point Set

scholarly journals Fast Gravitational Approach for Rigid Point Set Registration with Ordinary Differential Equations

IEEE Access ◽  
2021 ◽  
pp. 1-1
Author(s):  
Sk Aziz Ali ◽  
Kerem Kahraman ◽  
Christian Theobalt ◽  
Didier Stricker ◽  
Vladislav Golyanik
Keyword(s):  
Differential Equations ◽  
Ordinary Differential Equations ◽  
Point Set Registration ◽  
Point Set

Point set registration for assembly feature pose estimation using simulated annealing nested Gauss-Newton optimization

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Kunyong Chen ◽  
Yong Zhao ◽  
Jiaxiang Wang ◽  
Hongwen Xing ◽  
Zhengjian Dong
Keyword(s):  
Simulated Annealing ◽  
Pose Estimation ◽  
Distance Metric ◽  
Implicit Representation ◽  
Registration Method ◽  
Content Type ◽  
Point Set Registration ◽  
Searching Strategy ◽  
Global Robustness ◽  
Point Set

Purpose This paper aims to propose a fast and robust 3D point set registration method for pose estimation of assembly features with few distinctive local features in the manufacturing process. Design/methodology/approach The distance between the two 3D objects is analytically approximated by the implicit representation of the target model. Specifically, the implicit B-spline surface is adopted as an interface to derive the distance metric. With the distance metric, the point set registration problem is formulated into an unconstrained nonlinear least-squares optimization problem. Simulated annealing nested Gauss-Newton method is designed to solve the non-convex problem. This integration of gradient-based optimization and heuristic searching strategy guarantees both global robustness and sufficient efficiency. Findings The proposed method improves the registration efficiency while maintaining high accuracy compared with several commonly used approaches. Convergence can be guaranteed even with critical initial poses or in partial overlapping conditions. The multiple flanges pose estimation experiment validates the effectiveness of the proposed method in real-world applications. Originality/value The proposed registration method is much more efficient because no feature estimation or point-wise correspondences update are performed. At each iteration of the Gauss–Newton optimization, the poses are updated in a singularity-free format without taking the derivatives of a bunch of scalar trigonometric functions. The advantage of the simulated annealing searching strategy is combined to improve global robustness. The implementation is relatively straightforward, which can be easily integrated to realize automatic pose estimation to guide the assembly process.

Sign in / Sign up

Export Citation Format

Share Document