OpenVSLAM: A Versatile Visual SLAM Framework

• Its framework is intended to let researchers and engineers use and extend visual SLAM more easily than conventional open-source systems designed primarily as standalone programs.Source: §1 · p. 1
• OpenVSLAM packages well-known SLAM approaches into separated components with clear APIs and extensive documentation, including sample code snippets.Source: §1 · p. 1
• OpenVSLAM stores and loads map databases and localizes new images using prebuilt maps.Source: §1 · pp. 1–2
• The framework supports perspective, fisheye, and equirectangular cameras, with nearly the same implementation for perspective and fisheye models.Equirectangular input enables tracking and mapping independent of camera direction.Source: §1 · p. 2
• The project is provided as a community framework so researchers can jointly contribute to its development.Source: §1 · p. 2

• SfM typically reconstructs 3D scenes from an image set prepared in advance using batch processing, whereas visual SLAM processes sequential images in real time.Source: §2.1 · p. 2
• Open-source visual SLAM frameworks mostly handle perspective imagery, motivating OpenVSLAM’s compatibility with various camera models.Source: §2.1 · p. 2
• OpenVSLAM is presented as a novel framework designed to improve usability and extensibility for 3D mapping and localization.Source: §2.1 · p. 2
• Indirect SLAM uses local feature matching, while direct SLAM exploits image brightness information without explicitly extracting keypoints.The passage states that direct methods can operate correctly in more texture-less environments but also notes additional drawbacks.Source: §2.2 · p. 2
• Most visual SLAM frameworks cannot store and load map databases, although prebuilt-map localization is important for practical applications.OpenVSLAM implements map-database input and output functions in response to this gap.Source: §2.2 · p. 2

Module Structure

• The framework uses graph-based indirect SLAM with ORB feature extraction, while its module structure is designed for customizability.Source: §3.1 · p. 3
• OpenVSLAM separates tracking, mapping, and global optimization into modules, with tracking estimating poses and selecting keyframes for downstream processing.The mapping module triangulates new 3D points from inserted keyframes.Source: §3.1 · p. 3

Camera Models

• OpenVSLAM accepts perspective, fisheye, and equirectangular cameras, including monocular, stereo, and RGBD setups for perspective and fisheye models.Source: §3.2 · p. 3
• Users can add camera models such as dual fisheye and catadioptric by implementing classes derived from camera::base.Source: §3.2 · p. 3
• Equirectangular support provides omnidirectional imagery compatibility, which the paper identifies as novel among open-source visual SLAM frameworks.Source: §3.2 · p. 3

Map I/O and Localization

• OpenVSLAM stores and loads maps, supports localization against prebuilt maps, and saves map databases in MessagePack for third-party reuse.Source: §3.3 · p. 3

Evaluation Setup

• Tracking accuracy and tracking times are compared with ORB–SLAM2 on EuRoC MAV and KITTI Odometry datasets containing ground-truth trajectories.Source: §4 · p. 3
• ATE evaluates estimated trajectories after alignment using Sim(3) for monocular sequences and SE(3) for stereo sequences.Source: §4 · p. 3

EuRoC MAV

• OpenVSLAM has comparable tracking accuracy to ORB–SLAM on 11 EuRoC MAV monocular sequences and is more accurate on dark MH_04 and MH_05 scenes.The paper attributes the dark-scene result mainly to robust matching in frame tracking.Source: §4.1 · p. 3
• OpenVSLAM consumes less tracking time than ORB–SLAM on EuRoC MAV MH_02, including later sequence parts.The paper attributes this to optimized ORB extraction and preventing unnecessary local-map enlargement during global-map expansion.Source: §4.1 · pp. 3–4

KITTI Odometry

• OpenVSLAM has comparable tracking accuracy to ORB–SLAM on 11 KITTI Odometry stereo sequences.Source: §4.2 · p. 4, Figure 3 · p. 4
• OpenVSLAM consumes less tracking time than ORB–SLAM on KITTI sequence 05, with a larger difference attributed to larger images and more optimized stereo matching.Source: §4.2 · p. 4, Figure 4 · p. 4

Fisheye Camera

• Outdoor fisheye mapping uses about 6400 frames and preserves elevation differences in the 3D map’s side view.Camera pose tracking also succeeded in high dynamic range scenes.Source: §5.1 · p. 4, Figure 7 · p. 5
• Indoor fisheye mapping uses about 6700 frames, reconstructs the room clearly, and tracks successfully in areas with less common views.Source: §5.1 · p. 4
• The fisheye experiments conclude that visual SLAM is correctly performed both outdoors and indoors.Source: §5.1 · p. 4

Equirectangular Camera

• Outdoor equirectangular mapping uses 15,000 frames at 10.0 FPS, with camera tracking, loop-closing, and global optimization working on a large-scale sequence.Source: §5.2 · p. 4
• Indoor equirectangular mapping uses 1,430 frames at 10.0 FPS and tracks camera poses in texture-less areas through omnidirectional observation.Source: §5.2 · p. 4
• The equirectangular experiments conclude that visual SLAM is correctly performed both outdoors and indoors.Source: §5.2 · p. 4

Conclusion

• OpenVSLAM is designed for usability and extensibility across visual SLAM application scenarios and includes functions useful for research and development.The paper reports benchmark-based quantitative evaluation and experiments with fisheye and equirectangular camera models.Source: §6 · p. 5