Header

UZH-Logo

Maintenance Infos

Low-latency visual odometry using event-based feature tracks


Kueng, Beat; Müggler, Elias; Gallego Bonet, Guillermo; Scaramuzza, Davide (2016). Low-latency visual odometry using event-based feature tracks. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Daejeon, Korea, 9 October 2016 - 14 October 2016, 1-8.

Abstract

New vision sensors, such as the Dynamic and Active-pixel Vision sensor (DAVIS), incorporate a conventional camera and an event-based sensor in the same pixel array. These sensors have great potential for robotics because they allow us to combine the benefits of conventional cameras with those of event-based sensors: low latency, high temporal resolution, and high dynamic range. However, new algorithms are required to exploit the sensor characteristics and cope with its unconventional output, which consists of a stream of asynchronous brightness changes (called “events”) and synchronous grayscale frames. In this paper, we present a lowlatency visual odometry algorithm for the DAVIS sensor using event-based feature tracks. Features are first detected in the grayscale frames and then tracked asynchronously using the stream of events. The features are then fed to an event-based visual odometry algorithm that tightly interleaves robust pose optimization and probabilistic mapping. We show that our method successfully tracks the 6-DOF motion of the sensor in natural scenes. This is the first work on event-based visual odometry with the DAVIS sensor using feature tracks.

Abstract

New vision sensors, such as the Dynamic and Active-pixel Vision sensor (DAVIS), incorporate a conventional camera and an event-based sensor in the same pixel array. These sensors have great potential for robotics because they allow us to combine the benefits of conventional cameras with those of event-based sensors: low latency, high temporal resolution, and high dynamic range. However, new algorithms are required to exploit the sensor characteristics and cope with its unconventional output, which consists of a stream of asynchronous brightness changes (called “events”) and synchronous grayscale frames. In this paper, we present a lowlatency visual odometry algorithm for the DAVIS sensor using event-based feature tracks. Features are first detected in the grayscale frames and then tracked asynchronously using the stream of events. The features are then fed to an event-based visual odometry algorithm that tightly interleaves robust pose optimization and probabilistic mapping. We show that our method successfully tracks the 6-DOF motion of the sensor in natural scenes. This is the first work on event-based visual odometry with the DAVIS sensor using feature tracks.

Statistics

Citations

Downloads

26 downloads since deposited on 12 Aug 2016
18 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:03 Faculty of Economics > Department of Informatics
Dewey Decimal Classification:000 Computer science, knowledge & systems
Language:English
Event End Date:14 October 2016
Deposited On:12 Aug 2016 08:51
Last Modified:08 Dec 2017 20:09
Publisher:Institute of Electrical and Electronics Engineers (IEEE)
Free access at:Official URL. An embargo period may apply.
Official URL:http://rpg.ifi.uzh.ch/docs/IROS16_Kueng.pdf
Related URLs:http://www.iros2016.org/ (Organisation)
http://rpg.ifi.uzh.ch/research_dvs.html (Author)
Other Identification Number:merlin-id:13507

Download

Download PDF  'Low-latency visual odometry using event-based feature tracks'.
Preview
Content: Accepted Version
Filetype: PDF
Size: 1MB