CVMay 11, 2017

Challenges in Monocular Visual Odometry: Photometric Calibration, Motion Bias and Rolling Shutter Effect

arXiv:1705.04300v4118 citations
Originality Synthesis-oriented
AI Analysis

This work addresses overlooked challenges in monocular VO/SLAM for researchers and practitioners, offering incremental analysis and guidance.

The paper quantitatively evaluates the impacts of photometric calibration, motion bias, and rolling shutter effect on state-of-the-art monocular visual odometry and SLAM methods, providing practical insights and proposing improvements like a sub-pixel refinement for ORB-SLAM.

Monocular visual odometry (VO) and simultaneous localization and mapping (SLAM) have seen tremendous improvements in accuracy, robustness and efficiency, and have gained increasing popularity over recent years. Nevertheless, not so many discussions have been carried out to reveal the influences of three very influential yet easily overlooked aspects: photometric calibration, motion bias and rolling shutter effect. In this work, we evaluate these three aspects quantitatively on the state of the art of direct, feature-based and semi-direct methods, providing the community with useful practical knowledge both for better applying existing methods and developing new algorithms of VO and SLAM. Conclusions (some of which are counter-intuitive) are drawn with both technical and empirical analyses to all of our experiments. Possible improvements on existing methods are directed or proposed, such as a sub-pixel accuracy refinement of ORB-SLAM which boosts its performance.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes