Structure Aware SLAM Using Quadrics and Planes

@inproceedings{Hosseinzadeh2018StructureAS,
  title={Structure Aware SLAM Using Quadrics and Planes},
  author={Mehdi Hosseinzadeh and Yasir Latif and Trung T. Pham and Niko S{\"u}nderhauf and Ian D. Reid},
  booktitle={ACCV},
  year={2018}
}
Simultaneous Localization And Mapping (SLAM) is a fundamental problem in mobile robotics. While point-based SLAM methods provide accurate camera localization, the generated maps lack semantic information. On the other hand, state of the art object detection methods provide rich information about entities present in the scene from a single image. This work marries the two and proposes a method for representing generic objects as quadrics which allows object detections to be seamlessly integrated… 
Real-Time Monocular Object-Model Aware Sparse SLAM
TLDR
This work incorporates a real- time deep-learned object detector to the monocular SLAM framework for representing generic objects as quadrics that permit detections to be seamlessly integrated while allowing the real-time performance.
Monocular Object and Plane SLAM in Structured Environments
TLDR
Experiments show that the monocular simultaneous localization and mapping algorithm can improve camera localization accuracy compared to state-of-the-art SLAM, especially when there is no loop closure, and also generate dense maps robustly in many structured environments.
RGB-D Object SLAM Using Quadrics for Indoor Environments
TLDR
This paper proposes an object-level semantic SLAM algorithm based on RGB-D data, which uses a quadric surface as an object model to compactly represent the object’s position, orientation, and shape, and innovatively applies a nonparametric pose graph to solve data associations in the back end.
S3LAM: Structured Scene SLAM
TLDR
This work proposes a new SLAM system based on ORB-SLAM2 that creates a semantic map made of clusters of points corresponding to objects instances and structures in the scene that improves both camera localization and reconstruction and enables a better understanding of the scene.
An Orientation Factor for Object-Oriented SLAM
TLDR
This work implements the geometric factor for the recently proposed QuadricSLAM that represents landmarks as dual quadrics that probabilistically models the quadrics' major axes to be either perpendicular to or aligned with the direction of gravity, depending on their semantic class.
Simultaneous Localisation and Mapping with Quadric Surfaces
TLDR
A minimal representation for quadric surfaces is introduced and it is shown how this can be included in a least-squares formulation and can be easily extended to include additional constraints on quadrics such as those found in quadrics of revolution.
SO-SLAM: Semantic Object SLAM With Scale Proportional and Symmetrical Texture Constraints
TLDR
This letter proposes a novel monocular Semantic Object SLAM (SO-SLAM) system that addresses the introduction of object spatial constraints and proposes two new methods - a more robust object initialization method and an orientation fine optimization method.
Spatial semantic graph enhanced monocular SLAM System
TLDR
SSG SLAM is presented: a monocular SLAM system based on Spatial Semantic Graph (SSG), leveraging spatial relations to achieve good estimation of objects' poses and new constraints are proposed based on spatial relations.
Object-oriented SLAM using Quadrics and Symmetry Properties for Indoor Environments
TLDR
Experiments have shown that compared with the state-of-art algorithm, especially on the forward trajectory of mobile robots, the proposed algorithm significantly improves the accuracy and convergence speed of quadric reconstruction.
From Points to Planes - Adding Planar Constraints to Monocular SLAM Factor Graphs
TLDR
This paper presents a novel formulation to incorporate plane landmarks and planar constraints to feature- based monocular SLAM, and enforce in-plane points to lie exactly in the plane they belong to, propagating such information to the rest of the states.
...
...

References

SHOWING 1-10 OF 37 REFERENCES
Dual Quadrics from Object Detection BoundingBoxes as Landmark Representations in SLAM
TLDR
This paper demonstrates how to jointly estimate the robot pose and dual quadric parameters in factor graph based SLAM with a general perspective camera, and covers the use-cases of a robot moving with a monocular camera with and without the availability of additional depth information.
Dense planar SLAM
TLDR
This work presents an efficient new real-time approach which densely maps an environment using bounded planes and surfels extracted from depth images (like those produced by RGB-D sensors or dense multi-view stereo reconstruction) to take advantage of the planarity of many parts of real-world scenes.
SLAM++: Simultaneous Localisation and Mapping at the Level of Objects
TLDR
The object graph enables predictions for accurate ICP-based camera to model tracking at each live frame, and efficient active search for new objects in currently undescribed image regions, as well as the generation of an object level scene description with the potential to enable interaction.
PL-SLAM: Real-time monocular visual SLAM with points and lines
TLDR
This paper builds upon ORB-SLAM, presumably the current state-of-the-art solution both in terms of accuracy as efficiency, and extends its formulation to simultaneously handle both point and line correspondences, and demonstrates that the use of lines does not only improve the performance of the original ORB -SLAM solution in poorly textured frames, but also systematically improves it in sequence frames combining points and lines, without compromising the efficiency.
Pop-up SLAM: Semantic monocular plane SLAM for low-texture environments
TLDR
This paper proposes real-time monocular plane SLAM to demonstrate that scene understanding could improve both state estimation and dense mapping especially in low-texture environments.
PL-SLAM: A Stereo SLAM System Through the Combination of Points and Line Segments
TLDR
PL-SLAM is proposed, a stereo visual SLAM system that combines both points and line segments to work robustly in a wider variety of scenarios, particularly in those where point features are scarce or not well-distributed in the image.
Real-Time Model-Based SLAM Using Line Segments
TLDR
A model-based SLAM system that uses 3D line segments as landmarks that is operating in real-time with resilience to partial occlusion and the maps of line segments generated during the SLAM process are physically meaningful and their structure is measured against the true 3D structure of the scene.
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.
Monocular-vision based SLAM using Line Segments
  • T. Lemaire, S. Lacroix
  • Engineering
    Proceedings 2007 IEEE International Conference on Robotics and Automation
  • 2007
TLDR
A landmark initialization method that relies on the Plucker coordinates to represent a 3D line is introduced: a Gaussian sum approximates the feature initial state and is updated as new observations are gathered by the camera.
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.
...
...