Monocular Visual-Inertial SLAM: Continuous Preintegration and Reliable Initialization
In this paper, we propose a new visual-inertial Simultaneous Localization and Mapping (SLAM) algorithm. With the tightly coupled sensor fusion of a global shutter monocular camera and a low-cost Inertial Measurement Unit (IMU), this algorithm is able to achieve robust and real-time estimates of the...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2017-11-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/17/11/2613 |
id |
doaj-b96a6289c14449b99865b97aa0d7fb53 |
---|---|
record_format |
Article |
spelling |
doaj-b96a6289c14449b99865b97aa0d7fb532020-11-24T21:21:45ZengMDPI AGSensors1424-82202017-11-011711261310.3390/s17112613s17112613Monocular Visual-Inertial SLAM: Continuous Preintegration and Reliable InitializationYi Liu0Zhong Chen1Wenjuan Zheng2Hao Wang3Jianguo Liu4National Key Laboratory of Science and Technology on Multi-Spectral Information Processing, School of Automation, Huazhong University of Science and Technology, Wuhan 430074, ChinaNational Key Laboratory of Science and Technology on Multi-Spectral Information Processing, School of Automation, Huazhong University of Science and Technology, Wuhan 430074, ChinaBeijing Aerospace Automatic Control Institute, Beijing 100854, ChinaBeijing Aerospace Automatic Control Institute, Beijing 100854, ChinaNational Key Laboratory of Science and Technology on Multi-Spectral Information Processing, School of Automation, Huazhong University of Science and Technology, Wuhan 430074, ChinaIn this paper, we propose a new visual-inertial Simultaneous Localization and Mapping (SLAM) algorithm. With the tightly coupled sensor fusion of a global shutter monocular camera and a low-cost Inertial Measurement Unit (IMU), this algorithm is able to achieve robust and real-time estimates of the sensor poses in unknown environment. To address the real-time visual-inertial fusion problem, we present a parallel framework with a novel IMU initialization method. Our algorithm also benefits from the novel IMU factor, the continuous preintegration method, the vision factor of directional error, the separability trick and the robust initialization criterion which can efficiently output reliable estimates in real-time on modern Central Processing Unit (CPU). Tremendous experiments also validate the proposed algorithm and prove it is comparable to the state-of-art method.https://www.mdpi.com/1424-8220/17/11/2613sensor fusionSLAMcomputer visioninertial navigationtightly coupled |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yi Liu Zhong Chen Wenjuan Zheng Hao Wang Jianguo Liu |
spellingShingle |
Yi Liu Zhong Chen Wenjuan Zheng Hao Wang Jianguo Liu Monocular Visual-Inertial SLAM: Continuous Preintegration and Reliable Initialization Sensors sensor fusion SLAM computer vision inertial navigation tightly coupled |
author_facet |
Yi Liu Zhong Chen Wenjuan Zheng Hao Wang Jianguo Liu |
author_sort |
Yi Liu |
title |
Monocular Visual-Inertial SLAM: Continuous Preintegration and Reliable Initialization |
title_short |
Monocular Visual-Inertial SLAM: Continuous Preintegration and Reliable Initialization |
title_full |
Monocular Visual-Inertial SLAM: Continuous Preintegration and Reliable Initialization |
title_fullStr |
Monocular Visual-Inertial SLAM: Continuous Preintegration and Reliable Initialization |
title_full_unstemmed |
Monocular Visual-Inertial SLAM: Continuous Preintegration and Reliable Initialization |
title_sort |
monocular visual-inertial slam: continuous preintegration and reliable initialization |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2017-11-01 |
description |
In this paper, we propose a new visual-inertial Simultaneous Localization and Mapping (SLAM) algorithm. With the tightly coupled sensor fusion of a global shutter monocular camera and a low-cost Inertial Measurement Unit (IMU), this algorithm is able to achieve robust and real-time estimates of the sensor poses in unknown environment. To address the real-time visual-inertial fusion problem, we present a parallel framework with a novel IMU initialization method. Our algorithm also benefits from the novel IMU factor, the continuous preintegration method, the vision factor of directional error, the separability trick and the robust initialization criterion which can efficiently output reliable estimates in real-time on modern Central Processing Unit (CPU). Tremendous experiments also validate the proposed algorithm and prove it is comparable to the state-of-art method. |
topic |
sensor fusion SLAM computer vision inertial navigation tightly coupled |
url |
https://www.mdpi.com/1424-8220/17/11/2613 |
work_keys_str_mv |
AT yiliu monocularvisualinertialslamcontinuouspreintegrationandreliableinitialization AT zhongchen monocularvisualinertialslamcontinuouspreintegrationandreliableinitialization AT wenjuanzheng monocularvisualinertialslamcontinuouspreintegrationandreliableinitialization AT haowang monocularvisualinertialslamcontinuouspreintegrationandreliableinitialization AT jianguoliu monocularvisualinertialslamcontinuouspreintegrationandreliableinitialization |
_version_ |
1725998511760080896 |