LIFT-SLAM: a deep-learning feature-based monocular visual SLAM method

TL;DR

LIFT-SLAM integrates deep learning-based feature descriptors with traditional geometry-based monocular visual SLAM to improve robustness and performance, demonstrating comparable results to state-of-the-art methods on standard datasets.

Contribution

The paper introduces LIFT-SLAM, a novel VSLAM system combining deep learning features with classical methods, enhancing robustness without extensive parameter tuning.

Findings

Achieved results comparable to state-of-the-art on KITTI and Euroc datasets.

Enhanced robustness to sensor noise through deep learning features.

Implemented adaptive parameter tuning to improve generalization.

Abstract

The Simultaneous Localization and Mapping (SLAM) problem addresses the possibility of a robot to localize itself in an unknown environment and simultaneously build a consistent map of this environment. Recently, cameras have been successfully used to get the environment's features to perform SLAM, which is referred to as visual SLAM (VSLAM). However, classical VSLAM algorithms can be easily induced to fail when either the motion of the robot or the environment is too challenging. Although new approaches based on Deep Neural Networks (DNNs) have achieved promising results in VSLAM, they still are unable to outperform traditional methods. To leverage the robustness of deep learning to enhance traditional VSLAM systems, we propose to combine the potential of deep learning-based feature descriptors with the traditional geometry-based VSLAM, building a new VSLAM system called LIFT-SLAM. Experiments conducted on KITTI and Euroc datasets show that deep learning can be used to improve the performance of traditional VSLAM systems, as the proposed approach was able to achieve results comparable to the state-of-the-art while being robust to sensorial noise. We enhance the proposed VSLAM pipeline by avoiding parameter tuning for specific datasets with an adaptive approach while evaluating how transfer learning can affect the quality of the features extracted.