Monocular Visual Inertial Odometry using Learning-based Methods

<p>Precise pose 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.</p> <p>This 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.</p> <p>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 VisualInertial Odometry approach that uses a semi-supervised training technique in the literature, allowing the network to learn from both labeled and unlabeled datasets.</p> <p>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.</p>

Name thesis:degree_name

Doctor of Philosophy in Mechanical Engineering

Level thesis:degree_level

Dissertation - Open Access

Discipline thesis:degree_discipline

Mechanical Engineering

Year

2020

Author dc:creator

• Tian, Yuan

• monocular
• inertial
• odometry
• Mechanical Engineering

Repository record dc:identifier

https://commons.erau.edu/edt/527

OAI identifier oai:identifier

oai:commons.erau.edu:edt-1527