Practical, Fast and Robust Point Cloud Registration for Scene Stitching and Object Localization

Lei Sun

doi:10.1109/access.2021.3140105

Abstract

3D point cloud registration ranks among the most fundamental problems in remote sensing, photogrammetry, robotics and geometric computer vision. Due to the limited accuracy of 3D feature matching techniques, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">outliers</i> may exist, sometimes even in very large numbers, among the correspondences. Since existing robust solvers may encounter high computational cost or restricted robustness, we propose a novel, fast and highly robust solution, named VOCRA (VOting with Cost function and Rotating Averaging), for the point cloud registration problem with extreme outlier rates. Our first contribution is to employ the Tukey’s Biweight robust cost to introduce a new voting and correspondence sorting technique, which proves to be rather effective in distinguishing true inliers from outliers even with extreme (99%) outlier rates. Our second contribution consists in designing a time-efficient consensus maximization paradigm based on robust rotation averaging, serving to seek inlier candidates among the correspondences. Finally, we apply Graduated Non-Convexity with Tukey’s Biweight (GNC-TB) to estimate the correct transformation with the inlier candidates obtained, which is then used to find the complete inlier set. Both standard benchmarking and realistic experiments with application to two real-data problems are conducted, and we show that our solver VOCRA is robust against over 99% outliers (exceeding traditional GNC by nearly 10% and RANSAC by nearly 4%) and more time-efficient than the state-of-the-art competitors.

Highlights

With the development of the 3D measurement and scanning technologies (e.g. LiDAR scanners, 3D sensors), point cloud registration, which seeks to estimate the best rigid transformation between multiple 3D point clouds or scans, becomes an increasingly important building block in remote sensing, photogrammetry, robotics perception and computer vision, and has found extensive applications in 3D reconstruction [1]–[3], object recognition and localization [4], [5], SLAM [6], medical imaging [7], etc.To address the point cloud registration problem, Iterative Closest Point (ICP) [8] has been a well-known solver, but its downside lies in its high dependence on the initial guess of the rigid transformation
The contributions of this paper include: (a) we introduce the Tukey’s Biweight cost function in combination with the concept of Graduated NonConvexity (GNC) (GNC-TB) and propose a voting technique based on it, which proves to be more effective in extreme-outlier regime than simple 0-1 voting; (b) we present a novel consensus maximization framework using robust rotation averaging to rapidly seek the inlier consensus set; (c) we apply Graduated Non-Convexity with Tukey’s Biweight (GNC-TB) for further robust optimization of the consensus set and use its solution to find the complete inlier set
Where x ∈ K denotes the variables within domian K, pi ↔ qi (i = 1, 2, . . . , N ) is the correspondence, ωi is the weight for the residual error ri(pi, qi, x) w.r.t. this correspondence that can be abbreviated as ri, and is the outlier process corresponding to a certian robust cost function ρ(ri) which serves as a penalty function over weight ωi, we introduce a surrogate function based on GNC, writable as ρμ,ξ that is jointly defined by a controlling parameter μ and the inlier threshold ξ, for function ρ(ri)

Summary

Introduction

To address the point cloud registration problem, Iterative Closest Point (ICP) [8] has been a well-known solver, but its downside lies in its high dependence on the initial guess of the rigid transformation. Correspondence-based registration methods that can be free of initial guess is growing increasingly popular. It consists in first matching keypoints between point clouds to construct putative correspondences and estimating the best transformation using robust estimators. Various robust estimators [13]–[20] are employed to reject outliers, but many of them suffer from issues like high computational cost or limited robustness

Objectives

Methods

Results

Conclusion