Model Quality Aware RANSAC: A Robust Camera Motion Estimator

TL;DR

This paper introduces Model Quality Aware RANSAC, a new robust camera motion estimation method that significantly reduces failure rates by incorporating model-inlier consistency and inlier set quality tests, outperforming traditional RANSAC.

Contribution

The paper presents a novel RCME algorithm that improves robustness in camera motion estimation by integrating model-sample consistency and inlier set quality verification.

Findings

Failure rate reduced from 1.41% to 0.02% in indoor environments.

Consistent reduction in failure rates across multiple datasets.

Outperforms traditional RANSAC-based methods.

Abstract

Robust estimation of camera motion under the presence of outlier noise is a fundamental problem in robotics and computer vision. Despite existing efforts that focus on detecting motion and scene degeneracies, the best existing approach that builds on Random Consensus Sampling (RANSAC) still has non-negligible failure rate. Since a single failure can lead to the failure of the entire visual simultaneous localization and mapping, it is important to further improve robust estimation algorithm. We propose a new robust camera motion estimator (RCME) by incorporating two main changes: model-sample consistence test at model instantiation step and inlier set quality test that verifies model-inlier consistence using differential entropy. We have implemented our RCME algorithm and tested it under many public datasets. The results have shown consistent reduction in failure rate when comparing to RANSAC-based Gold Standard approach. More specifically, the overall failure rate for indoor environments has reduced from 1.41% to 0.02%.