Surface Estimation for Multiple Misaligned Point Sets

@article{Wiens2019SurfaceEF,
  title={Surface Estimation for Multiple Misaligned Point Sets},
  author={A. Wiens and W. Kleiber and K. Barnhart and Dylan Sain},
  journal={Mathematical Geosciences},
  year={2019},
  volume={52},
  pages={527-542}
}
Two common tasks when processing point cloud data sets are surface estimation and point cloud registration. In this paper, a statistical approach is developed to solve both of these problems simultaneously. In particular, a surface is estimated from a pair of unregistered three-dimensional scans of the same spatial region. In this method, one point cloud defines the fixed coordinate system, and a rigid transformation is applied to the second cloud. Observations from both scans are considered a… Expand

Figures and Tables from this paper

Nonrigid Registration Using Gaussian Processes and Local Likelihood Estimation
TLDR
The nonrigid registration method is applied to a pair of massive remote sensing elevation data sets exhibiting complex geological terrain, with improved accuracy and uncertainty quantification in a cross validation study versus two rigid registration methods. Expand
Fusing tie points' RGB and thermal information for mapping large areas based on aerial images: A study of fusion performance under different flight configurations and experimental conditions
TLDR
How different flight configurations affect the results of the proposed data fusion approach is evaluated, and it is demonstrated that pixels in the thermal images' central area can more accurately represent thermal information than pixels around the image edges for tie point data fusion. Expand
Modeling Nonstationary and Asymmetric Multivariate Spatial Covariances via Deformations
TLDR
This article proposes modeling the warping function as a composition of a number of simple injective warping functions in a deep-learning framework that establishes the types of warpings that allow for symmetry and asymmetry, and uses likelihood-based methods for inference that are computationally efficient. Expand

References

SHOWING 1-10 OF 42 REFERENCES
Point Set Registration: Coherent Point Drift
  • A. Myronenko, Xubo B. Song
  • Mathematics, Computer Science
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2010
TLDR
A probabilistic method, called the Coherent Point Drift (CPD) algorithm, is introduced for both rigid and nonrigid point set registration and a fast algorithm is introduced that reduces the method computation complexity to linear. Expand
Registration of 3D Point Clouds and Meshes: A Survey from Rigid to Nonrigid
TLDR
This study serves to give a comprehensive survey of both types of registration, focusing on three-dimensional point clouds and meshes, and shows how overfitting arises in nonrigid registration and the reasons for increasing interest in intrinsic techniques. Expand
Assessing geoaccuracy of structure from motion point clouds from long-range image collections
TLDR
This work presents a method of analyzing the georegistration error from SfM derived point clouds that have been transformed to a fixed Earth-based coordinate system. Expand
A Method for Registration of 3-D Shapes
  • P. Besl, N. McKay
  • Computer Science, Mathematics
  • IEEE Trans. Pattern Anal. Mach. Intell.
  • 1992
TLDR
A general-purpose, representation-independent method for the accurate and computationally efficient registration of 3-D shapes including free-form curves and surfaces based on the iterative closest point (ICP) algorithm. Expand
Nonlinear Geospatial Frame Transformations in the Presence of Noisy Data
  • C. Kotsakis
  • Computer Science
  • Mathematical Geosciences
  • 2018
TLDR
An extended least squares framework for geospatial frame transformation problems with nonlinear models in the presence of noisy data is presented and the expected improvement in the statistical accuracy of the transformed coordinates under the proposed stacking approach is demonstrated. Expand
A robust algorithm for point set registration using mixture of Gaussians
  • B. Jian, B. Vemuri
  • Computer Science, Medicine
  • Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1
  • 2005
TLDR
A novel and robust approach to the point set registration problem in the presence of large amounts of noise and outliers is proposed, which derives a closed-form expression for the L/sub 2/distance between two Gaussian mixtures, which leads to a computationally efficient registration algorithm. Expand
Registration of RGB and Thermal Point Clouds Generated by Structure From Motion
TLDR
This paper presents an automated method to obtain a 3D model fusing data from a visible and a thermal camera using a variant of the Iterative Closest Point optimization. Expand
‘Structure-from-Motion’ photogrammetry: A low-cost, effective tool for geoscience applications
Abstract High-resolution topographic surveying is traditionally associated with high capital and logistical costs, so that data acquisition is often passed on to specialist third party organisations.Expand
Assessing the Accuracy of Georeferenced Point Clouds Produced via Multi-View Stereopsis from Unmanned Aerial Vehicle (UAV) Imagery
TLDR
It is concluded that sub-decimetre terrain change (in this case coastal erosion) can be monitored and UAV-based image capture provides the spatial and temporal resolution required to map and monitor natural landscapes. Expand
A Correlation-Based Approach to Robust Point Set Registration
TLDR
The point set registration problem is defined as finding the maximum kernel correlation configuration of the the two point sets to be registered, and the new registration method has intuitive interpretations, simple to implement algorithm and easy to prove convergence property. Expand
...
1
2
3
4
5
...