Aligning 2.5D Scene Fragments with Distinctive Local Geometric Features and Voting-Based Correspondences

Jiaqi Yang, Yang Xiao, Zhiguo Cao

Research output: Contribution to journalArticlepeer-review

37 Scopus citations

Abstract

Aligning 2.5D views has been extensively explored in the past decades, where most prior works have concentrated on object data with complex structures. This paper presents a method to align real-word scene scans with challenging features such as noise, poor geometric information, and highly repeatable patterns. Our method consists of two modules: pairwise and multiview alignments. Key to the proposed pairwise alignment method is the rotational contour signature geometric feature and voting-based correspondence selection algorithm. The former promises strong discriminative power for 2.5D scene data, while the latter affords high-quality correspondences via a voting process for all raw feature matches using L 2 distance and point pair affinity constraints. For the multiview alignment method, we first use a connected graph algorithm to establish the connections of all 2.5D views for coarse merging; then, we propose a shape-growing iterative closest point algorithm for further refinement. Experiments are conducted on scene point cloud datasets addressing both the indoor and outdoor scenarios, whereby we demonstrate that the proposed pairwise alignment method clearly outperforms the state of the art. Moreover, the proposed multiview alignment method manages to put multiple unordered 2.5D scene fragments into a unified coordinate system automatically, accurately, and efficiently.

Original languageEnglish
Article number8307430
Pages (from-to)714-729
Number of pages16
JournalIEEE Transactions on Circuits and Systems for Video Technology
Volume29
Issue number3
DOIs
StatePublished - 2019
Externally publishedYes

Keywords

  • 2.5D scene fragments
  • correspondence selection
  • feature description
  • multi-view alignment
  • pairwise alignment

Fingerprint

Dive into the research topics of 'Aligning 2.5D Scene Fragments with Distinctive Local Geometric Features and Voting-Based Correspondences'. Together they form a unique fingerprint.

Cite this