Stereo DSO: Large-Scale Direct Sparse Visual Odometry with Stereo Cameras
Rui Wang,Martin Schworer,Daniel Cremers +2 more
- pp 3923-3931
TLDR
Stereo Direct Sparse Odometry (Stereo DSO) as discussed by the authors integrates constraints from static stereo into the bundle adjustment pipeline of temporal multi-view stereo to improve tracking accuracy and robustness.Abstract:
We propose Stereo Direct Sparse Odometry (Stereo DSO) as a novel method for highly accurate real-time visual odometry estimation of large-scale environments from stereo cameras. It jointly optimizes for all the model parameters within the active window, including the intrinsic/extrinsic camera parameters of all keyframes and the depth values of all selected pixels. In particular, we propose a novel approach to integrate constraints from static stereo into the bundle adjustment pipeline of temporal multi-view stereo. Real-time optimization is realized by sampling pixels uniformly from image regions with sufficient intensity gradient. Fixed-baseline stereo resolves scale drift. It also reduces the sensitivities to large optical flow and to rolling shutter effect which are known shortcomings of direct image alignment methods. Quantitative evaluation demonstrates that the proposed Stereo DSO outperforms existing state-of-the-art visual odometry methods both in terms of tracking accuracy and robustness. Moreover, our method delivers a more precise metric 3D reconstruction than previous dense/semi-dense direct approaches while providing a higher reconstruction density than feature-based methods.read more
Citations
More filters
Journal ArticleDOI
ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM
TL;DR: This article presents ORB-SLAM3, the first system able to perform visual, visual-inertial and multimap SLAM with monocular, stereo and RGB-D cameras, using pin-hole and fisheye lens models, resulting in real-time robust operation in small and large, indoor and outdoor environments.
Book ChapterDOI
Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometry
TL;DR: The Deep Virtual Stereo Odometry incorporates deep depth predictions into Direct Sparse Odometry (DSO) as direct virtual stereo measurements and designs a novel deep network that refines predicted depth from a single image in a two-stage process.
Proceedings ArticleDOI
The TUM VI Benchmark for Evaluating Visual-Inertial Odometry
TL;DR: The TUM VI dataset as mentioned in this paper is a dataset with a diverse set of sequences in different scenes for evaluating visual-inertial (VI) odometry and SLAM methods in domains such as augmented reality or robotics.
Proceedings ArticleDOI
The TUM VI Benchmark for Evaluating Visual-Inertial Odometry
TL;DR: The TUM VI dataset as discussed by the authors is a dataset with a diverse set of sequences in different scenes for evaluating visual-inertial (VI) odometry and SLAM methods in domains such as augmented reality or robotics.
Proceedings ArticleDOI
LDSO: Direct Sparse Odometry with Loop Closure
TL;DR: In this paper, an extension of Direct Sparse Odometry (DSO) to a monocular visual SLAM system with loop closure detection and pose-graph optimization is presented, which can utilize any image pixel with sufficient intensity gradient, which makes it robust even in featureless areas.
References
More filters
Journal ArticleDOI
Keyframe-based visual-inertial odometry using nonlinear optimization
TL;DR: This work forms a rigorously probabilistic cost function that combines reprojection errors of landmarks and inertial terms and compares the performance to an implementation of a state-of-the-art stochastic cloning sliding-window filter.
Proceedings ArticleDOI
Dense visual SLAM for RGB-D cameras
TL;DR: This paper proposes a dense visual SLAM method for RGB-D cameras that minimizes both the photometric and the depth error over all pixels, and proposes an entropy-based similarity measure for keyframe selection and loop closure detection.
Journal ArticleDOI
Inverse Depth Parametrization for Monocular SLAM
TL;DR: A new parametrization for point features within monocular simultaneous localization and mapping (SLAM) that permits efficient and accurate representation of uncertainty during undelayed initialization and beyond, all within the standard extended Kalman filter (EKF).
Proceedings ArticleDOI
Robust odometry estimation for RGB-D cameras
TL;DR: This work registers two consecutive RGB-D frames directly upon each other by minimizing the photometric error using non-linear minimization in combination with a coarse-to-fine scheme, and proposes to use a robust error function that reduces the influence of large residuals.
Proceedings ArticleDOI
Semi-dense Visual Odometry for a Monocular Camera
TL;DR: A fundamentally novel approach to real-time visual odometry for a monocular camera that allows to benefit from the simplicity and accuracy of dense tracking - which does not depend on visual features - while running in real- time on a CPU.