Light-SLAM: A Robust Deep-Learning Visual SLAM System Based on LightGlue under Challenging Lighting Conditions

TL;DR

Light-SLAM introduces a hybrid visual SLAM system utilizing deep learning-based features and traditional geometry methods, achieving improved robustness and accuracy in challenging lighting conditions while maintaining real-time performance.

Contribution

The paper presents a novel hybrid SLAM system combining LightGlue deep features with traditional geometry, enhancing robustness and accuracy in low-light environments.

Findings

Outperforms traditional manual features in low-light conditions

Achieves real-time processing on GPU

Demonstrates superior accuracy and robustness on multiple datasets

Abstract

Simultaneous Localization and Mapping (SLAM) has become a critical technology for intelligent transportation systems and autonomous robots and is widely used in autonomous driving. However, traditional manual feature-based methods in challenging lighting environments make it difficult to ensure robustness and accuracy. Some deep learning-based methods show potential but still have significant drawbacks. To address this problem, we propose a novel hybrid system for visual SLAM based on the LightGlue deep learning network. It uses deep local feature descriptors to replace traditional hand-crafted features and a more efficient and accurate deep network to achieve fast and precise feature matching. Thus, we use the robustness of deep learning to improve the whole system. We have combined traditional geometry-based approaches to introduce a complete visual SLAM system for monocular, binocular, and RGB-D sensors. We thoroughly tested the proposed system on four public datasets: KITTI, EuRoC, TUM, and 4Season, as well as on actual campus scenes. The experimental results show that the proposed method exhibits better accuracy and robustness in adapting to low-light and strongly light-varying environments than traditional manual features and deep learning-based methods. It can also run on GPU in real time.