Probabilistic Semi-Dense Mapping from Highly Accurate Feature-Based Monocular SLAM

@inproceedings{MurArtal2015ProbabilisticSM,
  title={Probabilistic Semi-Dense Mapping from Highly Accurate Feature-Based Monocular SLAM},
  author={Raul Mur-Artal and Juan D. Tard{\'o}s},
  booktitle={Robotics: Science and Systems},
  year={2015}
}
In the last years several direct (i.e. featureless) monocular SLAM approaches have appeared showing impressive semi-dense or dense scene reconstructions. These works have questioned the need of features, in which consolidated SLAM techniques of the last decade were based. In this paper we present a novel feature-based monocular SLAM system that is more robust, gives more accurate camera poses, and obtains comparable or better semi-dense reconstructions than the current state of the art. Our… 

Figures and Tables from this paper

Real-time Omnidirectional Visual SLAM with Semi-Dense Mapping
TLDR
Both accuracies of camera tracking and estimated depth map of the proposed SLAM system are evaluated using real-world data and CG rendered data where the ground truth of the depth map is available.
ORB-SLAM based semi-dense mapping with monocular camera
  • Boshi Wang, Haiying Wang, Yuan Yu, Limin Zong
  • Computer Science
    2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC)
  • 2017
TLDR
This paper combines the advantages of direct method and indirect method, to accomplish semi-dense mapping based on ORB-SLAM, and proposes modified bilateral filter to smooth depth estimation.
SE-SLAM: Semi-Dense Structured Edge-Based Monocular SLAM
TLDR
An edge-based monocular SLAM system (SE-SLAM) is proposed as a middle point: edges present good localization as point features, while enabling a structural semidense map reconstruction, and state of the art non-linear optimization is needed to optimize the full semi-dense output.
ORB-SLAM: A Versatile and Accurate Monocular SLAM System
TLDR
A survival of the fittest strategy that selects the points and keyframes of the reconstruction leads to excellent robustness and generates a compact and trackable map that only grows if the scene content changes, allowing lifelong operation.
Feature based simultaneous localization and semi-dense mapping with monocular camera
  • Xiansong Xu, Hanqi Fan
  • Computer Science
    2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)
  • 2016
TLDR
This paper using feature-based tracking method plus depth update and propagation's mechanism achieved a higher-quality tracking and semi-dense mapping in real time and has a higher accuracy.
Visual-inertial direct SLAM
TLDR
This paper proposes for the first time a direct, tightly-coupled formulation for the combination of visual and inertial data and evaluates the algorithm in several real sequences with ground truth trajectory data, showing a state-of-the-art performance.
Combining Feature-Based and Direct Methods for Semi-dense Real-Time Stereo Visual Odometry
TLDR
A two-layer approach for visual odometry with stereo cameras, which runs in real-time and combines feature-based matching with semi-dense direct image alignment, which is faster than state-of-the-art methods without losing accuracy.
Loosely-Coupled Semi-Direct Monocular SLAM
TLDR
A novel semi-direct approach for monocular simultaneous localization and mapping (SLAM) that combines the complementary strengths of direct and feature-based methods and outperforms the state-of-the-art monocular odometry and SLAM systems in terms of overall accuracy and robustness.
Incremental 3D Line Segment Extraction from Semi-dense SLAM
TLDR
3D line segments are proposed to simplify the point clouds generated by semi-dense SLAM by using a novel incremental approach for 3D line segment extraction and it is demonstrated that these line segments greatly improve the quality of 3D surface reconstruction compared to a feature point based baseline.
...
...

References

SHOWING 1-10 OF 25 REFERENCES
LSD-SLAM: Large-Scale Direct Monocular SLAM
TLDR
A novel direct tracking method which operates on \(\mathfrak{sim}(3)\), thereby explicitly detecting scale-drift, and an elegant probabilistic solution to include the effect of noisy depth values into tracking are introduced.
ORB-SLAM: A Versatile and Accurate Monocular SLAM System
TLDR
A survival of the fittest strategy that selects the points and keyframes of the reconstruction leads to excellent robustness and generates a compact and trackable map that only grows if the scene content changes, allowing lifelong operation.
Semi-dense Visual Odometry for a Monocular Camera
We propose a fundamentally novel approach to real-time visual odometry for a monocular camera. It allows to benefit from the simplicity and accuracy of dense tracking - which does not depend on
Appearance-based Active, Monocular, Dense Reconstruction for Micro Aerial Vehicles
TLDR
This work introduces a novel formulation of the measurement uncertainty that accounts for the scene appearance, the scene depth and the vehicle pose, and chooses motion trajectories that minimize perceptual ambiguities inferred by the texture in the scene.
Scale Drift-Aware Large Scale Monocular SLAM
TLDR
This paper describes a new near real-time visual SLAM system which adopts the continuous keyframe optimisation approach of the best current stereo systems, but accounts for the additional challenges presented by monocular input and presents a new pose-graph optimisation technique which allows for the efficient correction of rotation, translation and scale drift at loop closures.
Double window optimisation for constant time visual SLAM
We present a novel and general optimisation framework for visual SLAM, which scales for both local, highly accurate reconstruction and large-scale motion with long loop closures. We take a two-level
Live dense reconstruction with a single moving camera
TLDR
This work takes point-based real-time structure from motion (SFM) as a starting point, generating accurate 3D camera pose estimates and a sparse point cloud and warp the base mesh into highly accurate depth maps based on view-predictive optical flow and a constrained scene flow update.
Fast relocalisation and loop closing in keyframe-based SLAM
TLDR
A relocalisation method for keyframe-based SLAM that can deal with severe viewpoint change, at frame-rate, in maps containing thousands of keyframes, and permits the interoperability between cameras, allowing a camera to relocalise in a map built by a different camera.
MonoSLAM: Real-Time Single Camera SLAM
TLDR
The first successful application of the SLAM methodology from mobile robotics to the "pure vision" domain of a single uncontrolled camera, achieving real time but drift-free performance inaccessible to structure from motion approaches is presented.
REMODE: Probabilistic, monocular dense reconstruction in real time
TLDR
This work proposes a novel approach to depth map computation that combines Bayesian estimation and recent development on convex optimization for image processing, and demonstrates that this method outperforms state-of-the-art techniques in terms of accuracy.
...
...