Efficient registration of multi-view point sets by K-means clustering

DOI10.1016/J.INS.2019.03.024zbMATH Open1451.68293OpenAlexW2766534319WikidataQ128224126 ScholiaQ128224126MaRDI QIDQ2215151FDOQ2215151

Authors Jihua Zhu, Zutao Jiang, Georgios Evangelidis, Changqing Zhang, Shanmin Pang, Zhongyu Li 

Publication date 10 December 2020

Published in Information Sciences (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1710.05193

zbMATH Keywords

point setsK-means clusteringiterative closest pointmulti-view registration

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Machine vision and scene understanding (68T45)

Abstract: Generally, there are three main factors that determine the practical usability of registration, i.e., accuracy, robustness, and efficiency. In real-time applications, efficiency and robustness are more important. To promote these two abilities, we cast the multi-view registration into a clustering task. All the centroids are uniformly sampled from the initially aligned point sets involved in the multi-view registration, which makes it rather efficient and effective for the clustering. Then, each point is assigned to a single cluster and each cluster centroid is updated accordingly. Subsequently, the shape comprised by all cluster centroids is used to sequentially estimate the rigid transformation for each point set. For accuracy and stability, clustering and transformation estimation are alternately and iteratively applied to all point sets. We tested our proposed approach on several benchmark datasets and compared it with state-of-the-art approaches. Experimental results validate its efficiency and robustness for the registration of multi-view point sets.

Recommendations

• Simultaneous Registration of Multiple Corresponding Point Sets
• Clustering as an approach to 3D reconstruction problem
• Point cloud registration using virtual interest points from Macaulay's resultant of quadric surfaces
• A robust estimation technique for 3D point cloud registration
• A Coarse to Fine 3D Registration Method Based on Robust Fuzzy Clustering

Cites work

• Accurate integration of multi-view range images using \(k\)-means clustering
• Fast Descriptors and Correspondence Propagation for Robust Global Point Cloud Registration
• On Averaging Multiview Relations for 3D Scan Registration
• Pattern recognition and machine learning.

Cited in

(8)

• Simultaneous learning coefficient matrix and affinity graph for multiple kernel clustering
• Accurate integration of multi-view range images using \(k\)-means clustering
• Point cloud registration using virtual interest points from Macaulay's resultant of quadric surfaces
• Automatic multi-view point cloud merging algorithm used in structure light measure system
• D3Former: jointly learning repeatable dense detectors and feature-enhanced descriptors via saliency-guided transformer
• Clustering as an approach to 3D reconstruction problem
• Efficient object recognition under cluttered scenes via descriptor-based matching and single point voting
• Low-rank local tangent space embedding for subspace clustering

Describes a project that uses

Uses Software

• Go-ICP
• PRMLT
• BundleFusion

This page was built for publication: Efficient registration of multi-view point sets by K-means clustering

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2215151)