東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Monocular Visual-Inertial Odometry U...

Tian, Yuan.

FindBook

Google Book

Amazon

博客來

Monocular Visual-Inertial Odometry Using Learning-Based Methods.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Monocular Visual-Inertial Odometry Using Learning-Based Methods./
作者:	Tian, Yuan.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2020,
面頁冊數:	167 p.
附註:	Source: Dissertations Abstracts International, Volume: 82-03, Section: B.
Contained By:	Dissertations Abstracts International82-03B.
標題:	Mechanical engineering. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28030970
ISBN:	9798672130613

Monocular Visual-Inertial Odometry Using Learning-Based Methods.
Tian, Yuan.

Monocular Visual-Inertial Odometry Using Learning-Based Methods. - Ann Arbor : ProQuest Dissertations & Theses, 2020 - 167 p.

Source: Dissertations Abstracts International, Volume: 82-03, Section: B.

Thesis (Ph.D.)--Embry-Riddle Aeronautical University, 2020.

This item must not be sold to any third party vendors.

Precise prose information is a fundamental prerequisite for numerous applications in robotics, Artificial Intelligent and mobile computing. Many well-developed algorithms have been established using a single sensor or multiple sensors. Visual Inertial Odometry (VIO) uses images and inertial measurements to estimate the motion and is considered a key technology for GPS-denied localization in the real world and also virtual reality and augmented reality.The study develops three novel learning-based approaches to odometry estimation using a monocular camera and inertial measurement unit. The networks are well-trained on standard datasets, KITTI and EuROC, and a custom dataset using supervised, unsupervised and semi-supervised training methods. Compared to traditional methods, the deep-learning methods presented here do not require precise manual synchronization of the camera and IMU or explicit camera calibration.To the best of our knowledge, the proposed supervised method is a novel end-to-end trainable Visual-Inertial Odometry method with an IMU pre-integration module, that simplifies the network architecture and reduces the computation cost. Meanwhile, the unsupervised Visual-Inertial Odometry method shows its novelty in achieving outstanding accuracy in odometry estimation while training with monocular images and inertial measurements only. Last but not least, the semi-supervised method is the first Visual-Inertial Odometry approach that uses a semi-supervised training technique in the literature, allowing the network to learn from both labeled and unlabeled datasets.Through our qualitative and quantitative experimentation on a wide range of datasets, we conclude that the proposed methods can be used to obtain accurate visual localization information to a wide variety of consumer devices and robotic platforms.

ISBN: 9798672130613Subjects--Topical Terms:

649730
Mechanical engineering.
Subjects--Index Terms:

Visual Inertial Odometry

Monocular Visual-Inertial Odometry Using Learning-Based Methods.
LDR:02964nmm a2200349 4500 001 2281717
005 20210920103350.5
008 220723s2020 ||||||||||||||||| ||eng d
020 $a 9798672130613
035 $a (MiAaPQ)AAI28030970
035 $a AAI28030970
040 $a MiAaPQ $c MiAaPQ
100 1 $a Tian, Yuan. $3 1287310
245 1 0 $a Monocular Visual-Inertial Odometry Using Learning-Based Methods.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2020
300 $a 167 p.
500 $a Source: Dissertations Abstracts International, Volume: 82-03, Section: B.
500 $a Advisor: Compere, Marc.
502 $a Thesis (Ph.D.)--Embry-Riddle Aeronautical University, 2020.
506 $a This item must not be sold to any third party vendors.
520 $a Precise prose information is a fundamental prerequisite for numerous applications in robotics, Artificial Intelligent and mobile computing. Many well-developed algorithms have been established using a single sensor or multiple sensors. Visual Inertial Odometry (VIO) uses images and inertial measurements to estimate the motion and is considered a key technology for GPS-denied localization in the real world and also virtual reality and augmented reality.The study develops three novel learning-based approaches to odometry estimation using a monocular camera and inertial measurement unit. The networks are well-trained on standard datasets, KITTI and EuROC, and a custom dataset using supervised, unsupervised and semi-supervised training methods. Compared to traditional methods, the deep-learning methods presented here do not require precise manual synchronization of the camera and IMU or explicit camera calibration.To the best of our knowledge, the proposed supervised method is a novel end-to-end trainable Visual-Inertial Odometry method with an IMU pre-integration module, that simplifies the network architecture and reduces the computation cost. Meanwhile, the unsupervised Visual-Inertial Odometry method shows its novelty in achieving outstanding accuracy in odometry estimation while training with monocular images and inertial measurements only. Last but not least, the semi-supervised method is the first Visual-Inertial Odometry approach that uses a semi-supervised training technique in the literature, allowing the network to learn from both labeled and unlabeled datasets.Through our qualitative and quantitative experimentation on a wide range of datasets, we conclude that the proposed methods can be used to obtain accurate visual localization information to a wide variety of consumer devices and robotic platforms.
590 $a School code: 1076.
650 4 $a Mechanical engineering. $3 649730
650 4 $a Engineering. $3 586835
650 4 $a Robotics. $3 519753
653 $a Visual Inertial Odometry
653 $a Visual localization information
653 $a Monocular camera
690 $a 0548
690 $a 0537
690 $a 0771
710 2 $a Embry-Riddle Aeronautical University. $b Mechanical Engineering. $3 3550781
773 0 $t Dissertations Abstracts International $g 82-03B.
790 $a 1076
791 $a Ph.D.
792 $a 2020
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28030970