Model Quality Aware RANSAC: A Robust Camera Motion Estimator
This addresses a critical issue for robotics and computer vision applications, where failures in visual SLAM can be catastrophic, representing an incremental improvement over existing methods.
The paper tackles the problem of robust camera motion estimation in the presence of outliers, proposing a new estimator that reduces the failure rate from 1.41% to 0.02% in indoor environments compared to a RANSAC-based gold standard.
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%.