A real-time, robust and versatile visual-SLAM framework based on deep learning networks

TL;DR

This paper presents a versatile deep learning-based visual SLAM system that enhances robustness and accuracy in challenging environments, supporting multiple configurations and outperforming traditional methods.

Contribution

Introduces a hybrid visual SLAM framework integrating deep learning for feature extraction and matching, adaptable to various sensor setups and environments.

Findings

Outperforms traditional SLAM in accuracy and robustness

Effective in low-light, dynamic, and weak-texture scenarios

Supports multiple sensor configurations

Abstract

This paper explores how deep learning techniques can improve visual-based SLAM performance in challenging environments. By combining deep feature extraction and deep matching methods, we introduce a versatile hybrid visual SLAM system designed to enhance adaptability in challenging scenarios, such as low-light conditions, dynamic lighting, weak-texture areas, and severe jitter. Our system supports multiple modes, including monocular, stereo, monocular-inertial, and stereo-inertial configurations. We also perform analysis how to combine visual SLAM with deep learning methods to enlighten other researches. Through extensive experiments on both public datasets and self-sampled data, we demonstrate the superiority of the SL-SLAM system over traditional approaches. The experimental results show that SL-SLAM outperforms state-of-the-art SLAM algorithms in terms of localization accuracy and tracking robustness. For the benefit of community, we make public the source code at https://github.com/zzzzxxxx111/SLslam.