RAUM-VO: Rotational Adjusted Unsupervised Monocular Visual Odometry

Unsupervised learning for monocular camera motion and 3D scene understanding has gained popularity over traditional methods, which rely on epipolar geometry or non-linear optimization. Notably, deep learning can overcome many issues of monocular vision, such as perceptual aliasing, low-textured area...

Full description

Saved in:
Bibliographic Details
Published in:Sensors (Basel, Switzerland) Switzerland), 2022-03, Vol.22 (7), p.2651
Main Authors: Cimarelli, Claudio, Bavle, Hriday, Sanchez-Lopez, Jose Luis, Voos, Holger
Format: Article
Language:English
Subjects:
Cameras
Constraint modelling
Deep learning
depth estimation
Geometry
Global positioning systems
GPS
Localization
Mapping
Methods
Monocular vision
Motion
Motion simulation
Optimization
Pose estimation
Rotation
Scene analysis
Three dimensional motion
unsupervised learning
Video data
visual odometry
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Unsupervised learning for monocular camera motion and 3D scene understanding has gained popularity over traditional methods, which rely on epipolar geometry or non-linear optimization. Notably, deep learning can overcome many issues of monocular vision, such as perceptual aliasing, low-textured areas, scale drift, and degenerate motions. In addition, concerning supervised learning, we can fully leverage video stream data without the need for depth or motion labels. However, in this work, we note that rotational motion can limit the accuracy of the unsupervised pose networks more than the translational component. Therefore, we present RAUM-VO, an approach based on a model-free epipolar constraint for frame-to-frame motion estimation (F2F) to adjust the rotation during training and online inference. To this end, we match 2D keypoints between consecutive frames using pre-trained deep networks, Superpoint and Superglue, while training a network for depth and pose estimation using an unsupervised training protocol. Then, we adjust the predicted rotation with the motion estimated by F2F using the 2D matches and initializing the solver with the pose network prediction. Ultimately, RAUM-VO shows a considerable accuracy improvement compared to other unsupervised pose networks on the KITTI dataset, while reducing the complexity of other hybrid or traditional approaches and achieving comparable state-of-the-art results.
ISSN:1424-8220
1424-8220
DOI:10.3390/s22072651