Object-oriented SLAM using Quadrics and Symmetry Properties for Indoor
Environments
Z. Liao, W. Wang, X. Qi, X. Zhang, L. Xue, J. Jiao, and R. Wei. (2020)cite arxiv:2004.05303Comment: Submission to IROS 2020. Video: https://youtu.be/u9zRBp4TPIs. Code: https://github.com/XunshanMan/Object-oriented-SLAM.
Abstract
Aiming at the application environment of indoor mobile robots, this paper
proposes a sparse object-level SLAM algorithm based on an RGB-D camera. A
quadric representation is used as a landmark to compactly model objects,
including their position, orientation, and occupied space. The state-of-art
quadric-based SLAM algorithm faces the observability problem caused by the
limited perspective under the plane trajectory of the mobile robot. To solve
the problem, the proposed algorithm fuses both object detection and point cloud
data to estimate the quadric parameters. It finishes the quadric initialization
based on a single frame of RGB-D data, which significantly reduces the
requirements for perspective changes. As objects are often observed locally,
the proposed algorithm uses the symmetrical properties of indoor artificial
objects to estimate the occluded parts to obtain more accurate quadric
parameters. 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. Finally, we made available an opensource implementation to
replicate the experiments.
%0 Generic
%1 liao2020objectoriented
%A Liao, Ziwei
%A Wang, Wei
%A Qi, Xianyu
%A Zhang, Xiaoyu
%A Xue, Lin
%A Jiao, Jianzhen
%A Wei, Ran
%D 2020
%K 3d_reconstruction object_oriented slam
%T Object-oriented SLAM using Quadrics and Symmetry Properties for Indoor
Environments
%U http://arxiv.org/abs/2004.05303
%X Aiming at the application environment of indoor mobile robots, this paper
proposes a sparse object-level SLAM algorithm based on an RGB-D camera. A
quadric representation is used as a landmark to compactly model objects,
including their position, orientation, and occupied space. The state-of-art
quadric-based SLAM algorithm faces the observability problem caused by the
limited perspective under the plane trajectory of the mobile robot. To solve
the problem, the proposed algorithm fuses both object detection and point cloud
data to estimate the quadric parameters. It finishes the quadric initialization
based on a single frame of RGB-D data, which significantly reduces the
requirements for perspective changes. As objects are often observed locally,
the proposed algorithm uses the symmetrical properties of indoor artificial
objects to estimate the occluded parts to obtain more accurate quadric
parameters. 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. Finally, we made available an opensource implementation to
replicate the experiments.
@misc{liao2020objectoriented,
abstract = {Aiming at the application environment of indoor mobile robots, this paper
proposes a sparse object-level SLAM algorithm based on an RGB-D camera. A
quadric representation is used as a landmark to compactly model objects,
including their position, orientation, and occupied space. The state-of-art
quadric-based SLAM algorithm faces the observability problem caused by the
limited perspective under the plane trajectory of the mobile robot. To solve
the problem, the proposed algorithm fuses both object detection and point cloud
data to estimate the quadric parameters. It finishes the quadric initialization
based on a single frame of RGB-D data, which significantly reduces the
requirements for perspective changes. As objects are often observed locally,
the proposed algorithm uses the symmetrical properties of indoor artificial
objects to estimate the occluded parts to obtain more accurate quadric
parameters. 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. Finally, we made available an opensource implementation to
replicate the experiments.},
added-at = {2021-06-24T11:18:16.000+0200},
author = {Liao, Ziwei and Wang, Wei and Qi, Xianyu and Zhang, Xiaoyu and Xue, Lin and Jiao, Jianzhen and Wei, Ran},
biburl = {https://www.bibsonomy.org/bibtex/27f93964dc2093e8ab404ed9909888e16/shuncheng.wu},
description = {2004.05303.pdf},
interhash = {484b4e8163414de344070d1de4734bab},
intrahash = {7f93964dc2093e8ab404ed9909888e16},
keywords = {3d_reconstruction object_oriented slam},
note = {cite arxiv:2004.05303Comment: Submission to IROS 2020. Video: https://youtu.be/u9zRBp4TPIs. Code: https://github.com/XunshanMan/Object-oriented-SLAM},
timestamp = {2021-06-24T11:18:16.000+0200},
title = {Object-oriented SLAM using Quadrics and Symmetry Properties for Indoor
Environments},
url = {http://arxiv.org/abs/2004.05303},
year = 2020
}