MSCS-ICP: point cloud registration method using multi-view spatial coordinate system–ICP

Point cloud registration plays a crucial role in mobile robot localization, map building and 3D model reconstruction. However, it remains challenged by issues such as compromised accuracy and sluggish efficiency, posing significant obstacles in achieving precise and timely alignments. Therefore, we propose a lightweight and fast point cloud registration method. Firstly, we mesh the 3D point cloud, compared with the traditional gridded point cloud method, it achieves initial point cloud registration by preserving the curvature characteristics of the internal point cloud, and utilizing the spatial relationship between grid cells and the quantitative relationship between the internal point cloud. Moreover, we adopt an iterative nearest point (ICP) based on KD-Tree to realize the fine registration. So, our method does not necessitate intricate feature analysis and data training, and is resilient to similar transformations, non-uniform densities and noise. Finally, we conduct point cloud registration experiments using multiple publicly available point cloud datasets and compare them with several point cloud registration methods. The results demonstrate it is able to accomplish the point cloud registration quickly and exhibit high accuracy. More importantly, it maintains its efficacy and robustness even in the presence of noisy and defective point clouds.

Section: Introduction and Related Workmentioning

confidence: 99%

A fast point cloud registration method based on spatial relations and features

Liao,

Zhang,

Zhao

et al. 2024

A method for extracting and screening main feature points based on salient geometric characteristics and NAD features

Wang,

Ren,

Dai

2024

Point cloud alignment is an important task in the field of industrial automation and computer vision recognition. Aiming at the lack of robustness of traditional alignment algorithms in the face of cylindrical objects such as motors or highly symmetric objects, which in turn is prone to poor alignment accuracy or even alignment failure, a method of extracting and screening main feature points based on salient geometric properties is proposed to provide high-precision inputs for point cloud alignment and to improve the position estimation accuracy of symmetric targets. The salient geometric planes and curved surfaces in the target are utilized as the basis of feature point selection to extract more robust main feature points; and different feature descriptors are adopted to describe the feature points based on the target characteristics, which greatly preserves the original main contour and geometric information. A local feature descriptor NAD (Normalized Angle Descriptor) is designed based on the normal vector, normal angle and Euclidean distance of the point cloud, which is able to effectively remove the incorrect correspondences due to symmetry and feature similarity. Finally, the algorithm for obtaining the global maximum consensus set (GROR) based on the node and edge reliability of the correspondence graph is used to complete the coarse registration, and the Iterative Closest Point (ICP) algorithm is utilized to complete the fine registration. Experimental results on motor point clouds taken from different viewpoints show that the proposed registration strategy is visually and numerically superior to existing state-of-the-art methods, especially when there is only a single-frame point cloud of the target.

MAFNet: a two-stage multiple attention fusion network for partial-to-partial point cloud registration

Chen,

Luo,

Ren

et al. 2024

3D point cloud registration is a critical technology in the fields of visual measurement and robot automation processing. In actual large-scale industrial production, the accuracy of point cloud registration directly affects the quality of automated welding processes. However, most existing methods are confronted with serious challenges such as the failure of partial-to-partial point cloud model registration when facing robot automatic processing guidance and error analysis work. Therefore, this paper proposes a novel two-stage network architecture for point cloud registration, which aims at robot pose adjustment and visual guidance in the field of automated welding by using 3D point cloud data. Specifically, we propose a neighborhood-based multi-head attention module in the coarse registration stage. The neighborhood information of each point can be aggregated through focusing on different weight coefficients of multi-head inputs. Then the spatial structure features which is used to establish the overlapping constraint of point clouds are obtained based on above neighborhood information. In the fine registration stage, we propose the similarity matching removal module based on multiple attention fusion features to explore deeper features from different aspects. By using deep fusion features to guide the similarity calculation, the interference of non-overlapping points is removed to achieve the finer registration. Eventually, we compare and analyze the proposed method with the SOTA ones through several error metrics and overlap estimation experiments based on the ModelNet40 dataset. The test results indicate that our method, relative to other mainstream techniques, achieves lower error rates and the most superior accuracy of 98.61% and recall of 98.37%. To demonstrate the generalization performance of proposed algorithm, extensive experiments on the Stanford 3D Scanning Repository, 7-Scenes and our own scanning dataset using partially overlapping point clouds individually under clean and noisy conditions show the validity and reliability of our proposed registration network.