Deep Direct Visual Odometry

Zhao, C; Tang, Y; Sun, Q; Vasilakos, AV

Deep Direct Visual Odometry

Zhao, C Tang, Y Sun, Q Vasilakos, AV

Permalink

Publisher:: Institute of Electrical and Electronics Engineers
Publication Type:: Journal Article
Citation:: IEEE Transactions on Intelligent Transportation Systems, 2022, 23, (7), pp. 7733-7742
Issue Date:: 2022-01-01

Closed Access

	Filename	Description	Size
	Deep Direct Visual Odometry.pdf	Published version	2.95 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Zhao, C
dc.contributor.author	Tang, Y
dc.contributor.author	Sun, Q
dc.contributor.author	Vasilakos, AV
dc.date.accessioned	2023-03-21T03:17:48Z
dc.date.available	2023-03-21T03:17:48Z
dc.date.issued	2022-01-01
dc.identifier.citation	IEEE Transactions on Intelligent Transportation Systems, 2022, 23, (7), pp. 7733-7742
dc.identifier.issn	1524-9050
dc.identifier.issn	1558-0016
dc.identifier.uri	http://hdl.handle.net/10453/167932
dc.description.abstract	Traditional monocular direct visual odometry (DVO) is one of the most famous methods to estimate the ego-motion of robots and map environments from images simultaneously. However, DVO heavily relies on high-quality images and accurate initial pose estimation during tracking. With the outstanding performance of deep learning, previous works have shown that deep neural networks can effectively learn 6-DoF (Degree of Freedom) poses between frames from monocular image sequences in the unsupervised manner. However, these unsupervised deep learning-based frameworks cannot accurately generate the full trajectory of a long monocular video because of the scale-inconsistency between each pose. To address this problem, we use several geometric constraints to improve the scale-consistency of the pose network, including improving the previous loss function and proposing a novel scale-to-trajectory constraint for unsupervised training. We call the pose network trained by the proposed novel constraint as TrajNet. In addition, a new DVO architecture, called deep direct sparse odometry (DDSO), is proposed to overcome the drawbacks of the previous direct sparse odometry (DSO) framework by embedding TrajNet. Extensive experiments on the KITTI dataset show that the proposed constraints can effectively improve the scale-consistency of TrajNet when compared with previous unsupervised monocular methods, and integration with TrajNet makes the initialization and tracking of DSO more robust and accurate.
dc.language	English
dc.publisher	Institute of Electrical and Electronics Engineers
dc.relation.ispartof	IEEE Transactions on Intelligent Transportation Systems
dc.relation.isbasedon	10.1109/TITS.2021.3071886
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0801 Artificial Intelligence and Image Processing, 0905 Civil Engineering, 1507 Transportation and Freight Services
dc.subject.classification	Logistics & Transportation
dc.title	Deep Direct Visual Odometry
dc.type	Journal Article
utslib.citation.volume	23
utslib.for	0801 Artificial Intelligence and Image Processing
utslib.for	0905 Civil Engineering
utslib.for	1507 Transportation and Freight Services
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2023-03-21T03:17:46Z
pubs.issue	7
pubs.publication-status	Published
pubs.volume	23
utslib.citation.issue	7

Abstract:

Traditional monocular direct visual odometry (DVO) is one of the most famous methods to estimate the ego-motion of robots and map environments from images simultaneously. However, DVO heavily relies on high-quality images and accurate initial pose estimation during tracking. With the outstanding performance of deep learning, previous works have shown that deep neural networks can effectively learn 6-DoF (Degree of Freedom) poses between frames from monocular image sequences in the unsupervised manner. However, these unsupervised deep learning-based frameworks cannot accurately generate the full trajectory of a long monocular video because of the scale-inconsistency between each pose. To address this problem, we use several geometric constraints to improve the scale-consistency of the pose network, including improving the previous loss function and proposing a novel scale-to-trajectory constraint for unsupervised training. We call the pose network trained by the proposed novel constraint as TrajNet. In addition, a new DVO architecture, called deep direct sparse odometry (DDSO), is proposed to overcome the drawbacks of the previous direct sparse odometry (DSO) framework by embedding TrajNet. Extensive experiments on the KITTI dataset show that the proposed constraints can effectively improve the scale-consistency of TrajNet when compared with previous unsupervised monocular methods, and integration with TrajNet makes the initialization and tracking of DSO more robust and accurate.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/167932