Appearance and Geometry Fusion for Enhanced Dense 3D Alignment (original) (raw)

3D Point Set Registration based on Hierarchical Descriptors

Journal of WSCG

Registering partial point clouds is crucial in numerous applications in the field of robotics, vision, and graphics. For arbitrary configurations, the registration problem requires an initial global alignment, which is computationally expensive and often still requires refinement. In this paper, we propose a pair-wise global registration method that combines the fast convergence made possible by global hierarchical surface descriptors with the arbitrarily fine sampling enabled by continuous surface representations. Registration is performed by matching descriptors of increasing resolution – which the continuous surfaces allow us to choose arbitrarily high – while restricting the search space according to the hierarchy. We evaluated our method on a large set of pair-wise registration problems, demonstrating very competitive registration accuracy that often makes subsequent refinement with a local method unnecessary.

Loosely Distinctive Features for Robust Surface Alignment

2010

Many successful feature detectors and descriptors exist for 2D intensity images. However, obtaining the same effectiveness in the domain of 3D objects has proven to be a more elusive goal. In fact, the smoothness often found in surfaces and the lack of texture information on the range images produced by conventional 3D scanners hinder both the localization of interesting points and the distinctiveness of their characterization in terms of descriptors. To overcome these limitations several approaches have been suggested, ranging from the simple enlargement of the area over which the descriptors are computed to the reliance on external texture information. In this paper we offer a change in perspective, where a game-theoretic matching technique that exploits global geometric consistency allows to obtain an extremely robust surface registration even when coupled with simple surface features exhibiting very low distinctiveness. In order to assess the performance of the whole approach we compare it with state-of-the-art alignment pipelines. Furthermore, we show that using the novel feature points with well-known alternative non-global matching techniques leads to poorer results.

Registration with the Point Cloud Library A Modular Framework for Aligning in 3-D

—Registration is an important step when processing 3D point clouds. Applications for registration range from object modeling and tracking to simultaneous localization and mapping. This article presents the open-source Point Cloud Library (PCL) and the tools therein available for the task of point cloud registration. PCL incorporates methods for the initial alignment of point clouds using a variety of local shape feature descriptors as well as for refining initial alignments using different variants of the well-known Iterative Closest Point (ICP) algorithm. The article provides an overview on registration algorithms, usage examples of their PCL implementations, and tips for their application. Since the choice and parameterization of the right algorithm for a particular type of data is one of the biggest problems in 3D point cloud registration, we present three complete examples of data (and applications) and the respective registration pipeline in PCL. These examples include dense RGB-D point clouds acquired by consumer color and depth cameras, high-resolution laser scans from commercial 3D scanners, and low-resolution sparse point clouds captured by a custom lightweight 3D scanner on a micro aerial vehicle.

3D Registration of Multi-modal Data Using Surface Fitting

The registration of two 3D point clouds is an essential step in many applications. The objective of our work is to estimate the best geometric transformation to merge two point clouds obtained from different sensors. In this paper, we present a new approach for feature extraction which is distinguished by the nature of the extracted signature of each point. The descriptor we propose is invariant to rotation and overcomes the problem of multiresolution. To validate our approach, we have tested on synthetic data and we have applied to heterogeneous real data.

A novel approach to automatic registration of point clouds

2007 IEEE International Geoscience and Remote Sensing Symposium, 2007

For the 3D reconstruction inside historic buildings, we need a marker-free automatic registration approach to align different views together, because GPS does not work indoors and markers are not allowed to paste on the walls. This paper presents an automatic matching process, which employs a novel algorithm, Dynamic Matching Tree technique, for a fast and stable coarse-matching to achieve the automatic pre-alignment of two point clouds and uses modified ICP to do a fine matching efficiently. The whole process can be divided in the following stages: preprocessing, 2-View matching and N-View matching. To validate our method, various experiments has been done on reconstruction of historic sites and industrial objects.

Point Cloud Registration Based on Image Correspondences

International Journal of Heritage in the Digital Era, 2013

Since the early '80s, when Digital Photogrammetry was in its infancy, important progress has been made in the area of automations using the most common photogrammetric procedures. The main objective of this paper is the full automation of 3D Point Cloud Registration process. In particular, an alternative registration method is being presented, based on corresponding points, which are detected on overlapping images that come with each scan using a structured light scanner. The algorithm detects corresponding points applying Feature Based Matching techniques. These are then interpolated directly to any given texture map, thereby the transition to correspondent 3D vertices is achieved. Finally, the algorithm computes the 3D Rigid Body transformation, which is applied to the 3D point clouds, in order to transform one scan's reference system into the other. Experimental results obtained by the proposed method are presented, evaluated and compared with those obtained by standard ICP implementation.

Multi-view alignment with database of features for an improved usage of high-end 3D scanners

EURASIP Journal on Advances in Signal Processing, 2012

The usability of high-precision and high-resolution 3D scanners is of crucial importance due to the increasing demand of 3D data in both professional and general-purpose applications. Simplified, intuitive and rapid object modeling requires effective and automated alignment pipelines capable to trace back each independently acquired range image of the scanned object into a common reference system. To this end, we propose a reliable and fast feature-based multiple-view alignment pipeline that allows interactive registration of multiple views according to an unchained acquisition procedure. A robust alignment of each new view is estimated with respect to the previously aligned data through fast extraction, representation and matching of feature points detected in overlapping areas from different views. The proposed pipeline guarantees a highly reliable alignment of dense range image datasets on a variety of objects in few seconds per million of points.

Generation and weighting of 3D point correspondences for improved registration of RGB-D data

ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, 2013

Registration of RGB-D data using visual features is often influenced by errors in the transformation of visual features to 3D space as well as the random error of individual 3D points. In a long sequence, these errors accumulate and lead to inaccurate and deformed point clouds, particularly in situations where loop closing is not feasible. We present an epipolar search method for accurate transformation of the keypoints from 2D to 3D space, and define weights for the 3D points based on the theoretical random error of depth measurements. Our results show that the epipolar search method results in more accurate 3D correspondences. We also demonstrate that weighting the 3D points improves the accuracy of sensor pose estimates along the trajectory.

Vote based correspondence for 3D point-set registration

Given two views of a static scene, estimation of correspondences between them is required for various computer vision tasks, such as 3D reconstruction and registration, motion and structure estimation, and object recognition. Without loss of generality, this paper treats the correspondence-estimation problem in the context of feature-based rangescan registration of widely separated views and presents a novel approach to obtain globally consistent set of correspondences. In this paper, we define the notion of a weak feature, and follow the approach that avoids early commitment to the "best" match. It instead considers multiple candidate matches for each feature, and eventually models and solves correspondence-estimation as an optimization problem viz. weighted bipartite matching. We focus on developing a robust approach that succeeds in the presence of significant noise and sparsity in the input.

Feature-based three-dimensional registration for repetitive geometry in machine vision

Journal of information technology & software engineering, 2016

As an important step in three-dimensional (3D) machine vision, 3D registration is a process of aligning two or multiple 3D point clouds that are collected from different perspectives together into a complete one. The most popular approach to register point clouds is to minimize the difference between these point clouds iteratively by Iterative Closest Point (ICP) algorithm. However, ICP does not work well for repetitive geometries. To solve this problem, a feature-based 3D registration algorithm is proposed to align the point clouds that are generated by vision-based 3D reconstruction. By utilizing texture information of the object and the robustness of image features, 3D correspondences can be retrieved so that the 3D registration of two point clouds is to solve a rigid transformation. The comparison of our method and different ICP algorithms demonstrates that our proposed algorithm is more accurate, efficient and robust for repetitive geometry registration. Moreover, this method c...