A comparative evaluation of learned feature descriptors on hybrid monocular visual SLAM methods

TL;DR

This paper compares hybrid monocular VSLAM methods using learned feature descriptors, demonstrating their enhanced robustness across various challenging environments, camera motions, and sensor noise conditions.

Contribution

It provides a systematic evaluation of different learned feature descriptors within hybrid VSLAM frameworks, highlighting their robustness improvements.

Findings

Learned feature descriptors improve VSLAM robustness.

Hybrid methods outperform classical VSLAM in challenging conditions.

Experiments confirm effectiveness on KITTI and Euroc MAV datasets.

Abstract

Classical Visual Simultaneous Localization and Mapping (VSLAM) algorithms can be easily induced to fail when either the robot's motion or the environment is too challenging. The use of Deep Neural Networks to enhance VSLAM algorithms has recently achieved promising results, which we call hybrid methods. In this paper, we compare the performance of hybrid monocular VSLAM methods with different learned feature descriptors. To this end, we propose a set of experiments to evaluate the robustness of the algorithms under different environments, camera motion, and camera sensor noise. Experiments conducted on KITTI and Euroc MAV datasets confirm that learned feature descriptors can create more robust VSLAM systems.