AirSLAM: An Efficient and Illumination-Robust Point-Line Visual SLAM System
arXiv:2408.03520 · doi:10.1109/TRO.2025.3539171
Abstract
In this paper, we present an efficient visual SLAM system designed to tackle both short-term and long-term illumination challenges. Our system adopts a hybrid approach that combines deep learning techniques for feature detection and matching with traditional backend optimization methods. Specifically, we propose a unified convolutional neural network (CNN) that simultaneously extracts keypoints and structural lines. These features are then associated, matched, triangulated, and optimized in a coupled manner. Additionally, we introduce a lightweight relocalization pipeline that reuses the built map, where keypoints, lines, and a structure graph are used to match the query frame with the map. To enhance the applicability of the proposed system to real-world robots, we deploy and accelerate the feature detection and matching networks using C++ and NVIDIA TensorRT. Extensive experiments conducted on various datasets demonstrate that our system outperforms other state-of-the-art visual SLAM systems in illumination-challenging environments. Efficiency evaluations show that our system can run at a rate of 73Hz on a PC and 40Hz on an embedded platform. Our implementation is open-sourced: https://github.com/sair-lab/AirSLAM.
20 pages, 15 figures, 9 tables
References in corpus (15)
- ORB-SLAM: a Versatile and Accurate Monocular SLAM System
- ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras
- VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator
- Generative Adversarial Networks: An Overview
- ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM
- Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age
- On-Manifold Preintegration for Real-Time Visual-Inertial Odometry
- RTAB-Map as an Open-Source Lidar and Visual SLAM Library for Large-Scale and Long-Term Online Operation
- Visual-Inertial Mapping with Non-Linear Factor Recovery
- LIFT-SLAM: a deep-learning feature-based monocular visual SLAM method
- maplab 2.0 -- A Modular and Multi-Modal Mapping Framework
- AirVO: An Illumination-Robust Point-Line Visual Odometry
- Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learning
- Learning Regional Attraction for Line Segment Detection
- Multi-Session Visual SLAM for Illumination Invariant Re-Localization in Indoor Environments