Header

UZH-Logo

Maintenance Infos

SVO: Semi-Direct Visual Odometry for Monocular and Multi-Camera Systems


Forster, Christian; Zhang, Zichao; Gassner, Michael; Werlberger, Manuel; Scaramuzza, Davide (2016). SVO: Semi-Direct Visual Odometry for Monocular and Multi-Camera Systems. IEEE Transactions on Robotics:1-18.

Abstract

Direct methods for Visual Odometry (VO) have gained popularity due to their capability to exploit information from all intensity gradients in the image. However, low computational speed as well as missing guarantees for optimality and consistency are limiting factors of direct methods, where established feature-based methods instead succeed at. Based on these considerations, we propose a Semi-direct VO (SVO) that uses direct methods to track and triangulate pixels that are characterized by high image gradients but relies on proven feature-based methods for joint optimization of structure and motion. Together with a robust probabilistic depth estimation algorithm, this enables us to efficiently track pixels lying on weak corners and edges in environments with little or high-frequency texture. We further demonstrate that the algorithm can easily be extended to multiple cameras, to track edges, to include motion priors, and to enable the use of very large field of view cameras, such as fisheye and catadioptric ones. Experimental evaluation on benchmark datasets shows that the algorithm is significantly faster than the state of the art while achieving highly competitive accuracy.

Abstract

Direct methods for Visual Odometry (VO) have gained popularity due to their capability to exploit information from all intensity gradients in the image. However, low computational speed as well as missing guarantees for optimality and consistency are limiting factors of direct methods, where established feature-based methods instead succeed at. Based on these considerations, we propose a Semi-direct VO (SVO) that uses direct methods to track and triangulate pixels that are characterized by high image gradients but relies on proven feature-based methods for joint optimization of structure and motion. Together with a robust probabilistic depth estimation algorithm, this enables us to efficiently track pixels lying on weak corners and edges in environments with little or high-frequency texture. We further demonstrate that the algorithm can easily be extended to multiple cameras, to track edges, to include motion priors, and to enable the use of very large field of view cameras, such as fisheye and catadioptric ones. Experimental evaluation on benchmark datasets shows that the algorithm is significantly faster than the state of the art while achieving highly competitive accuracy.

Statistics

Downloads

451 downloads since deposited on 24 Nov 2016
294 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:03 Faculty of Economics > Department of Informatics
Dewey Decimal Classification:000 Computer science, knowledge & systems
Language:English
Date:23 November 2016
Deposited On:24 Nov 2016 14:52
Last Modified:02 Feb 2018 10:48
Publisher:Institute of Electrical and Electronics Engineers
ISSN:1552-3098
OA Status:Green
Free access at:Official URL. An embargo period may apply.
Official URL:http://rpg.ifi.uzh.ch/docs/TRO16_Forster-SVO.pdf
Other Identification Number:merlin-id:14067

Download

Download PDF  'SVO: Semi-Direct Visual Odometry for Monocular and Multi-Camera Systems'.
Preview
Content: Published Version
Filetype: PDF
Size: 1MB