Aligning point cloud views using persistent feature histograms

  title={Aligning point cloud views using persistent feature histograms},
  author={Radu Bogdan Rusu and Nico Blodow and Zolt{\'a}n-Csaba M{\'a}rton and Michael Beetz},
  journal={2008 IEEE/RSJ International Conference on Intelligent Robots and Systems},
  • R. RusuNico Blodow M. Beetz
  • Published 14 October 2008
  • Computer Science
  • 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems
In this paper we investigate the usage of persistent point feature histograms for the problem of aligning point cloud data views into a consistent global model. Given a collection of noisy point clouds, our algorithm estimates a set of robust 16D features which describe the geometry of each point locally. By analyzing the persistence of the features at different scales, we extract an optimal set which best characterizes a given point cloud. The resulted persistent features are used in an… 

Rigid 3D Point Cloud Registration Based on Point Feature Histograms

A dynamic constraint of distance is applied to improve the traditional algorithm of point cloud classification based on point feature histogram to match feature points in different clouds with higher accuracy and efficiency.

Registration of 3D point clouds using a local descriptor based on grid point normal.

Experimental comparisons on two public datasets demonstrate that the GNDAS descriptor has high descriptiveness and strong robustness to noise at low level and varying mesh resolution and the superiority of the registration approach over previous versions in accuracy and efficiency.

Registration of point clouds using sample-sphere and adaptive distance restriction

A novel technique, the sample-sphere method, is proposed to register a pair of point clouds in arbitrary initial positions, which roughly aligns point clouds by matching pairs of triplets of points, which are approximately congruent under rigid transformation.

Point Clouds Registration with Probabilistic Data Association

This work proposes an improvement over the standard ICP data association policy and it is called Probabilistic Data Association, derived applying statistical inference techniques on a fully probabilistic model to deal with the problem of dense-sparse registration.

Automatic Point Cloud Registration for Large Outdoor Scenes Using a Priori Semantic Information

This paper presents a new point cloud registration pipeline for large, outdoor scenes that takes advantage of semantic segmentation, and demonstrates how a priori semantic information improves registration in terms of precision and speed.

Aligning Point Clouds with an Effective Local Feature Descriptor

Validations and comparisons with other point cloud registration algorithms showed that LPFH is low-dimension, efficient, effective and easy to compute.

Robust Kernel-Based Feature Representation for 3d Point Cloud Analysis Via Circular Convolutional Network

A new local feature description method that is robust to rotation and scale variations is presented that showed superior performances when compared to the state-of-the-art methods by reducing 70 % of the rotation and translation errors in the registration task.

A Local Feature Descriptor Based on Rotational Volume for Pairwise Registration of Point Clouds

A novel feature descriptor based on ratio of rotational volume to describe effectively keypoints and an improved coarse-to-fine registration pipeline of point clouds, in which it is proposed to use coarse registration to obtain a good initial transformation matrix and then fine registration based on a modified ICP algorithm to obtain an accurate transformation matrix.

Feature Description with Feature Point Registration Error Using Local and Global Point Cloud Encoders

A feature description method robust to the feature point registration error that consists of a local feature description around the feature points and a global feature description of the entire point cloud and can estimate with higher accuracy in comparison to methods such as FPFH or 3DMatch.



Persistent Point Feature Histograms for 3D Point Clouds

This paper proposes a novel way of characterizing the local geometry of 3D points, using persistent feature histograms, and shows that geometric primitives have unique signatures in this feature space, preserved even in the presence of additive noise.

Automated Registration of Unorganised Point Clouds from Terrestrial Laser Scanners

Laser scanners provide a three-dimensional sampled representation of the surfaces of objects. The spatial resolution of the data is much higher than that of conventional surveying methods. The data

Fully Automatic Registration of 3D Point Clouds

We propose a novel technique for the registration of 3D point clouds which makes very few assumptions: we avoid any manual rough alignment or the use of landmarks, displacement can be arbitrarily

Estimating surface normals in noisy point cloud data

A method based on local least square fitting for estimating the normals at all sample points of a point cloud data (PCD) set, in the presence of noise is described and analyzed.

Efficient variants of the ICP algorithm

  • S. RusinkiewiczM. Levoy
  • Computer Science
    Proceedings Third International Conference on 3-D Digital Imaging and Modeling
  • 2001
An implementation is demonstrated that is able to align two range images in a few tens of milliseconds, assuming a good initial guess, and has potential application to real-time 3D model acquisition and model-based tracking.

Robust global registration

This work presents an algorithm for the automatic alignment of two 3D shapes ( data and model), without any assumptions about their initial positions, and develops a fast branch-and-bound algorithm based on distance matrix comparisons to select the optimal correspondence set and bring the two shapes into a coarse alignment.

ICP Registration Using Invariant Features

Experimental results suggest that using invariant features decreases the probability of being trapped in a local minimum and may be an effective solution for difficult range image registration problems where the scene is very small compared to the model.

Scale selection for classification of point-sampled 3D surfaces

The problem of automatic data-driven scale selection to improve point cloud classification is investigated and the approach is validated with results using data from different sensors in various environments classified into different terrain types.

Registration and integration of textured 3D data

Least squares 3D surface and curve matching