CLEAR: A Consistent Lifting, Embedding, and Alignment Rectification Algorithm for Multiview Data Association

doi:10.1109/TRO.2020.3002432

CLEAR: A Consistent Lifting, Embedding, and Alignment Rectification Algorithm for Multiview Data Association

2020-12-01

15

OA

AI

DOI：10.1109/TRO.2020.3002432

Original

Save

View PDF

Abstract

En 中文

Many robotics applications require alignment and fusion of observations obtained at multiple views to form a global model of the environment. Multiway data association methods provide a mechanism to improve alignment accuracy of pairwise associations and ensure their consistency. However, existing methods that solve this computationally challenging problem are often too slow for real-time applications. Furthermore, some of the existing techniques can violate the cycle consistency principle, thus drastically reducing the fusion accuracy. This article presents the consistent lifting, embedding, and alignment rectification (CLEAR) algorithm to address these issues. By leveraging insights from the multiway matching and spectral graph clustering literature, CLEAR provides cycle-consistent and accurate solutions in a computationally efficient manner. Numerical experiments on both synthetic and real datasets are carried out to demonstrate the scalability and superior performance of our algorithm in real-world problems. This algorithmic framework can provide significant improvement in the accuracy and efficiency of existing discrete assignment problems, which traditionally use pairwise (but potentially inconsistent) correspondences. An implementation of CLEAR is made publicly available online.

Keywords:

Clustering algorithms

Simultaneous localization and mapping

Real-time systems

Noise measurement

Complexity theory

Approximation algorithms

Data association

multi-way matching

simultaneous localization and mapping

CLEAR: A Consistent Lifting, Embedding, and Alignment Rectification Algorithm for Multiview Data Association

Abstract

AI Summary

Journal

Organization