FDMO: Feature Assisted Direct Monocular Odometry

TL;DR

FDMO combines direct and feature-based visual odometry to improve robustness and accuracy, especially in challenging scenarios, by switching between methods based on failure detection and leveraging their respective strengths.

Contribution

The paper introduces FDMO, a novel system that integrates direct and feature-based methods for monocular odometry, enhancing robustness and reducing drift.

Findings

FDMO outperforms DSO and ORB SLAM in accuracy on TumMono and EuroC datasets.

FDMO effectively reduces drift in alignment, rotation, and scale.

The system operates in real time with introduced efficiencies.

Abstract

Visual Odometry (VO) can be categorized as being either direct or feature based. When the system is calibrated photometrically, and images are captured at high rates, direct methods have shown to outperform feature-based ones in terms of accuracy and processing time; they are also more robust to failure in feature-deprived environments. On the downside, Direct methods rely on heuristic motion models to seed the estimation of camera motion between frames; in the event that these models are violated (e.g., erratic motion), Direct methods easily fail. This paper proposes a novel system entitled FDMO (Feature assisted Direct Monocular Odometry), which complements the advantages of both direct and featured based techniques. FDMO bootstraps indirect feature tracking upon the sub-pixel accurate localized direct keyframes only when failure modes (e.g., large baselines) of direct tracking occur. Control returns back to direct odometry when these conditions are no longer violated. Efficiencies are introduced to help FDMO perform in real time. FDMO shows significant drift (alignment, rotation & scale) reduction when compared to DSO & ORB SLAM when evaluated using the TumMono and EuroC datasets.