Pose-invariant matching for non-rigid 3D models using Isomap

Hairong Jin; Haichao Huang; Zhiqiang Wang; Yuqing Xie; Xinyue Zhou; Liming Huang; Zhouzhenyan Hong

doi:10.1371/journal.pone.0264192

Pose-invariant matching for non-rigid 3D models using Isomap

PLoS One. 2022 Mar 16;17(3):e0264192. doi: 10.1371/journal.pone.0264192. eCollection 2022.

Authors

Hairong Jin¹, Haichao Huang², Zhiqiang Wang², Yuqing Xie², Xinyue Zhou³, Liming Huang⁴, Zhouzhenyan Hong²

Affiliations

¹ Polytechnic Institute, Zhejiang University, Ningbo, Zhejiang, China.
² State Grid Zhejiang Electric Power Corporation Information & Telecommunication Branch, Hangzhou, Zhejiang, China.
³ State Grid Hangzhou Power Supply Company, Hangzhou, Zhejiang, China.
⁴ Zhejiang Huayun information technology co., ltd, Hangzhou, Zhejiang, China.

Abstract

The wide usage of 3D mesh models greatly increases the importance of an effective matching algorithm for them. In this paper, we propose a novel 3D model matching algorithm. Firstly, vertices on the input 3D mesh models are mapped to 1D space by employing Isomap. A pose-invariant feature set is then constructed from the vertices in 1D space. Finally, the similarity between any two 3D models can be computed by comparing their feature sets. Experimental results show that the algorithm is not only invariant to translation, rotation, scaling, but also invariant to different poses of 3D models. Additionally, the algorithm is robust to noise.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Algorithms*
Rotation

Grants and funding

Hairong Jin is funded by the Ningbo Major Special Projects of the “Science and Technology Innovation 2025” [Grant No. 2020Z005, 2020Z007]. Haichao Huang is funded the Science Foundation of State Grid, China [Grant Number 5211XT190033]. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. The funders do have roles in the study design, data collection and analysis, decision to publish, or preparation of our manuscript. In detail, the Science Foundation of State Grid, China [Grant No. 5211XT190033] has contributed to study design. The Ningbo Major Special Project of the “Science and Technology Innovation 2025” [Grant No. 2020Z005] has contributed to data collection and analysis. The Ningbo Major Special Project of the “Science and Technology Innovation 2025” [Grant No. 2020Z007] has contributed to the preparation of our manuscript.