Robust Point Cloud Registration Framework Based on Deep Graph Matching.

Point cloud registration is a fundamental problem in 3D computer vision. Outdoor LiDAR point clouds are typically large-scale and complexly distributed, which makes the registration challenging. In this paper, we propose an efficient hierarchical network named HRegNet for large-scale out-door LiDAR point cloud registration. Instead of using all points in the point clouds, HRegNet performs registration on hierarchically extracted keypoints and descriptors. The overall framework combines the reliable features in deeper layer and the precise position information in shallower layers to achieve robust and precise registration. We present a correspondence network to generate correct and accurate keypoints correspondences. Moreover, bilateral consensus and neighborhood consensus are introduced for keypoints matching and novel similarity features are designed to in-corporate them into the correspondence network, which significantly improves the registration performance. Besides, the whole network is also highly efficient since only a small number of keypoints are used for registration. Extensive experiments are conducted on two large-scale outdoor LiDAR point cloud datasets to demonstrate the high accuracy and efficiency of the proposed HRegNet. The project website is https://ispc-group.github.io/hregnet.

This paper reports a novel mutual information (MI) based algorithm for automatic registration of unstructured 3D point clouds comprised of co-registered 3D lidar and camera imagery. The proposed method provides a robust and principled framework for fusing the complementary information obtained from these two different sensing modalities. High-dimensional features are extracted from a training set of textured point clouds (scans) and hierarchical k-means clustering is used to quantize these features into a set of codewords. Using this codebook, any new scan can be represented as a collection of codewords. Under the correct rigid-body transformation aligning two overlapping scans, the MI between the codewords present in the scans is maximized. We apply a James-Stein-type shrinkage estimator to estimate the true MI from the marginal and joint histograms of the codewords extracted from the scans. Experimental results using scans obtained by a vehicle equipped with a 3D laser scanner and an omnidirectional camera are used to validate the robustness of the proposed algorithm over a wide range of initial conditions. We also show that the proposed method works well with 3D data alone.

Coded light measurement is an important method of non-contact optical measurement. Because of the camera view limitations, it was hard to complete the measurement of the whole surface at a time. Then it needs registration of 3D point clouds. The registration of point clouds can reflect the 3D surface of the object to be measured, which can achieve the full range of requirements. According to the encoded optical 3D measurement system has been built in laboratory, exploring a method which is high accurate and high speed to reach a full range measurement to industrial parts. This paper describes the color target cube. According to the existing method of coordinate transformation (the Nearest Point Iterative Method), Evaluating the registration accuracy. The registration method based on auxiliary three-dimensional targets was been validated, which has its own rationality.

Graph and hypergraph matching are fundamental problems in computer vision, which have been receiving a steadily growing attention in the last two decades due to the recent modern algorithms and models that are both fast and accurate. Graph and hypergraph matching are successful in tackling many real-world tasks that require 2D and 3D feature matching and alignment. Matching is a general problem in vision and graphs have always been quintessential for modeling information that has both local and longer range connections. Therefore, graph matching will continue to influence computer vision and robotics research, crossing over many different mathematical and computational models, including Bayesian networks, conditional and Markov random fields, spectral graph models, and, more recently, deep neural networks. While graph matching is limited to using pairwise relationships, hypergraph matching permits the use of relationships between sets of features of any order. Consequently, it carries the promise to make matching more robust to changes in scale, deformations, and outliers. In this chapter, we present several key ideas, computational models, and optimization methods that introduced in the literature the possibility to learn graph and hypergraph matching in a semi-supervised or even completely unsupervised fashion. We start by describing two methods for solving graph and hypergraph matching based on spectral matching and integer projected fixed point methods, introduced in Chap. 1. Then, based on the same intuition (also discussed in Chap. 1) that correct assignments form a strong cluster of agreements, we follow up by introducing the main approach to learning as it applies to graph and hypergraph matching, as well as the more general Maximum A Posteriori (MAP) inference problem in probabilistic graphical models (MRFs and CRFs). In the last part of the chapter, we demonstrate experimentally the effectiveness of the algorithms presented and, whenever possible, provide extensive comparisons to other top published methods. Moreover, we show that our learning approach is general and can significantly boost the performance of different state-of-the-art matching algorithms in the literature.

Deep learning based point cloud registration: an overview

Three‐dimensional (3D) point cloud registration is a fundamental key issue in 3D reconstruction, 3D object recognition and augmented reality. In this study, the authors propose a novel local feature descriptor called local angle statistics histogram (LASH) for efficient 3D point cloud registration. LASH forms a description of local shape geometries by encoding their properties on angles between the normal vector of the point and the vector formed by the point and other points in its local neighbourhood. In addition, they propose a 3D point cloud registration algorithm based on LASH. The registration algorithm firstly detects triangle matching points with consistent similarity ratios, and then aggregates each pair of triangular matching points into a set of matching points. They can use these matching sets to calculate multiple transformations between two point clouds. Finally, they use the error function to identify the best transformation and to achieve coarse alignment of the two point clouds. Experiments and comparisons with other global algorithms demonstrate that the proposed approach can be applied to register point clouds with considerable or limited overlaps and is robust to noise.

Recent advance in high-accuracy sensors has made point cloud become the main data format to characterize the three-dimensional world. Since the sensor can only scan and capture the 3D data within a limited field of view, an alignment algorithm is needed to generate the complete 3D scene. Point cloud registration is the solution for alignment problem that aims to estimate the transformation matrix between two frames of different point cloud sets. In this paper, we propose a neural network called OLFF-Net to achieve robust registration of 3D point clouds based on overlapped local feature fusion, which focuses on extracting rotational-invariant local features while providing enough information to achieve accurate alignment. Extensive experiments on representative datasets indicate that the framework can largely outperform competing methods with an average improvement of 16.82% in the metrics over the compared methods. More importantly, it shows significant generalization capability and can be widely applied to point cloud data with multiple complex structures.

Because of its high sensitivity to misalignment, precision grinding of free-form surfaces with micron accuracy requires accurate registration of the surface measurement point cloud. Registration of point clouds obtained with a coordinate measuring machine (CMM) is generally an iterative process of finding optimal coordinate transformation between the CMM frame and the model frame of the workpiece by minimizing the point-to-surface distances with probe radius compensation. For free-form surfaces, frequent calculation of point-to-surface distances consumes very much time, and a trade-off has to be made between the efficiency and the accuracy. This paper presents a method for fast registration of free-form surface point clouds based on the point-to-triangle distance which involves only Delaunay triangulation of a two-dimensional dataset, and the surface normal is quickly calculated from cross product. Probe radius compensation is realized by registering the probe center points with the offset surface. We prove that it is equivalent to registering the probe contact points with the nominal surface through theoretical analysis. The registration problem is then formulated as sequential linear least-square problems with properly defined ball constraints. To validate the method, numerical simulations are presented to show the accuracy of the point-to-triangle distance. The registration algorithm also shows excellent robustness against misalignment of tens of millimeters/degrees. Finally measurement, registration, and grinding of a free-form optical surface are experimentally demonstrated. The surface error obtained after registration is used for compensatory grinding which reduces it to micron level.

Rotation search and point cloud registration are two fundamental problems in robotics, geometric vision, and remote sensing, which aim to estimate the rotation and transformation between the 3D vector sets and point clouds, respectively. Due to the presence of outliers (probably in very large numbers) among the putative vector or point correspondences in real-world applications, robust estimation is of great importance. In this paper, we present Inlier searching using COmpatible Structures (ICOS), a novel, efficient, and highly robust solver for both the correspondence-based rotation search and point cloud registration problems. Specifically, we (i) propose and construct a series of compatible structures for the two problems, based on which various invariants can be established, and (ii) design time-efficient frameworks to filter out outliers and seek inliers from the invariant-constrained random sampling based on the compatible structures proposed. In this manner, even with extreme outlier ratios, inliers can be effectively sifted out and collected for solving the optimal rotation and transformation, leading to our robust solver ICOS. Through plentiful experiments over standard datasets, we demonstrated that: (i) our solver ICOS is fast, accurate, and robust against over 95% outliers with nearly a 100% recall ratio of inliers for rotation search and both known-scale and unknown-scale registration, outperforming other state-of-the-art methods, and (ii) ICOS is practical for use in real-world application problems including 2D image stitching and 3D object localization.

Point cloud registration is a fundamental problem in robotics, critical for tasks such as localization and mapping. Most approaches to this problem use feature-based techniques. However, these approaches have issues when dealing with unstructured environments where meaningful features are difficult to extract. Recently, an innovative global point cloud registration algorithm, PHASER, which does not rely on geometric features or point correspondences, has been introduced. It leverages Fourier transforms to identify the optimal rigid transform that maximizes cross-correlation between source and target point clouds. PHASER can also incorporate additional data channels, like LiDAR intensity, to enhance registration results. Because it does not rely on local features and because of its ability to exploit additional data, PHASER is particularly useful when dealing with very noisy point clouds or with many outliers. For this reason, we propose an extension to PHASER that considers multiple plausible rototranslation hypotheses. Our extended approach outperforms the original PHASER algorithm, especially in challenging scenarios where point clouds are widely separated. We validate its effectiveness on the DARPA SubT, and the Newer College datasets, showcasing its potential for improving registration accuracy in complex environments.

The present work proposes a new method Reg3DFacePtCd for registration of point clouds. The key contribution of the present method is that an unknown face in 3D point cloud form is given to the system and is registered to the already existing known 3D face point clouds using a fast 3D face registration method. The novelty of the present technique is that at first the alignment and registration parameters are found out by initially registering eight key points of the unknown source model to that of the known model. Next, the rest of the point clouds of the unknown model are registered to that of the known model using the same parameters found as above. The main method used for alignment is iterative closest point (ICP) using point-based technique followed by registration in the least squares sense. Mainly there are two significant contributions. Firstly, we have developed a new mathematical model facial landmark point based model across poses to obtain the target or the known model to which all the unknown models will be registered. Secondly, a novel way to accelerate point cloud matching by reducing the number of points has been proposed. Using a small number of points necessarily would speed up the registration process but may inculcate errors. So, to determine the registration quality of the fundamental eight key points on which the entire registration process is based, a new robust metric namely ICV (ICP certainty vector) consisting of several key components have been used. Finally, we have addressed several important face registration issues like pre-processing, convergence and quality of registration of the entire facial point cloud based on the eight key points. Extensive experimentation on Frav3D, GavabDB, and the Bosphorus databases on a high-performance computing environment show the novelty and robustness of the method.

The 3D laser scanning technology has been widely adopted in the field of workshop automatic assembly. Among them, the point cloud registration is a crucial part of the 3D data processing. Among the 3D data processing steps, point cloud registration is an important one. However, existing 3D point cloud registration methods have issues such as mismatching of feature point pairs, long registration time, and poor registration accuracy. In this paper, an LM-NDT point cloud registration algorithm based on 3D shape context feature (3DSC) is proposed.Firstly, the key points of the 3D point cloud are extracted through the intrinsic shape signature (ISS) to enhance the registration efficiency. Then, the features of the key points are described by the 3D shape context feature. According to the feature points, the error pair is processed using the median distance method, and the initial transformation matrix is calculated through SVD decomposition. Finally, the alignment is accomplished by the LM-NDT algorithm. Compared with the NDT algorithm, the proposed algorithm is more accurate and robust when the initial pose transformation is more significant. The test results demonstrate that the accuracy of the algorithm in the shoe and sole can reach 0.019cm, which remarkably improves the registration efficiency of the traditional SAC-IA and LM-NDT algorithms and has certain engineering application value.

The iterative closest point (ICP) algorithm is widely used in three-dimensional (3D) point cloud registration, and it is very stable and robust. However, its biggest drawback is being easily trapped in a local optimal solution, which results in the incorrect registration result. Currently, there is neither a clear effective range to define whether the ICP algorithm will fall into a local optimum nor a study providing a comprehensive evaluation of the ICP algorithm. In this paper, we take the overlap ratio, angle, distance, and noise as the influencing factors of ICP and evaluate the validity, robustness, accuracy, and efficiency of point-to-point and point-to-plane ICP by using four datasets. We first analyze the effective ranges of the two ICP algorithms with respect to overlap ratio, angle, and distance and then propose a universal effective range for the three factors. Next, the effect of Gaussian noise on the validity and accuracy of two ICPs is evaluated. We also analyze the factors influencing ICP accuracy and explain their changing rules. We finally study the effect of different parameters on the efficiency. All results are compared by using point-to-point and point-to-plane ICP algorithms. The results show that the overlap ratio has no effect on validity, but it has a significant influence on accuracy. The angle has a great impact on the validity and efficiency of ICP but has no effect on accuracy. The distance only affects validity, has a limited effect on efficiency and no effect on accuracy. Meanwhile, Gaussian noise has a little effect on the validity. In addition, the general effective range of point-to-point ICP is larger than that of point-to-plane ICP, but the point-to-plane ICP algorithm presents a better efficiency. The point-to-point ICP is more robust to Gaussian noise with respect to validity, while the point-to-plane is more resistant in terms of accuracy.

Terrestrial laser scanners have achieved great popularity in the last decade. Their easy on-site application and the possibility of flexible and high quality post processing added to their success in several fields such as architectural, archaeological, and heritage documentation. We present a method for handling the automatic registration of point clouds which are characterized by significant noise level, generally imperfect geometry and occlusions. Hereby we combine and extend already existing and established methods to facilitate the registration of point clouds without prior pre-processing. Our approach consists—similar to other methods—of three steps which are scan analysis, pair-wise registration, and global registration. To handle the abovementioned datasets we propose to use imperfect and subdivided features, and to implement Genetic Algorithms (GAs). At the same time our approach can be seen as extension to already known Genetic Algorithms used for the registration of point clouds. By implementing an adapted version of a Genetic Algorithm in the classical registration process between rough alignment and fine registration, we are able to maintain robustness and computational performance also when registering point clouds of bigger objects characterized by a notably increased number of points, a significant noise level, and occlusions. We show and discuss the successful application of the algorithm on a scene which does not consist of classical geometric primitives such as planes.

Registration of 3D point clouds is an important task for many different applications today, like reverse engineering, medical imaging, remote sensing, robotics and automation in general.In this paper we explore a new algorithm for rough registration by using the genetic algorithm (GA) which has showed acceptable results in a reasonable amount of computational time.The algorithm is based on the Median Squared Error (MSE) as the fitness function for the GA, and a threshold that defines the maximum distance between corresponding pair of points to be considered inliers.One of the contributions in this paper is a new scheme for adaptable boundary constrains in the algorithm, which makes the global minimum detection faster than the traditional GAs implementations.Another contribution is the separation of the chromosome parameter, i.e. for the first steps of the algorithm we have separated the chromosome encoding into two groups; three genes representing the translation vector (Tx, Ty and Tz) and three genes representing the rotation matrices (Rx, Ry and Rz).Finally, experimental results are presented and discussed using this algorithm.