Latest revision as of 10:54, 16 February 2021

Abstract

Event cameras are bio-inspired vision sensors that output pixel-level brightness changes instead of standard intensity frames. These cameras do not suffer from motion blur and have a very high dynamic range, which enables them to provide reliable visual information during high-speed motions or in scenes characterized by high dynamic range. These features, along with a very low power consumption, make event cameras an ideal complement to standard cameras for VR/AR and video game applications. With these applications in mind, this paper tackles the problem of accurate, low-latency tracking of an event camera from an existing photometric depth map (i.e., intensity plus depth information) built via classic dense reconstruction pipelines. Our approach tracks the 6-DOF pose of the event camera upon the arrival of each event, thus virtually eliminating latency. We successfully evaluate the method in both indoor and outdoor scenes and show that---because of the technological advantages of the event camera---our pipeline works in scenes characterized by high-speed motion, which are still unaccessible to standard cameras.

Comment: 12 pages, 13 figures. 2 tables. (in press)

Original document

The different versions of the original document can be found in:

• http://arxiv.org/abs/1607.03468

• http://dx.doi.org/10.5167/uzh-150432

• http://infoscience.epfl.ch/record/232970

• https://www.zora.uzh.ch/149359

• https://www.zora.uzh.ch/id/eprint/150432/1/PAMI17_Gallego.pdf

• http://xplorestaging.ieee.org/ielx7/34/8454009/08094962.pdf?arnumber=8094962,

http://dx.doi.org/10.1109/tpami.2017.2769655

• https://dblp.uni-trier.de/db/journals/pami/pami40.html#GallegoLMRDS18,

https://www.arxiv.org/abs/1607.03468,

https://ieeexplore.ieee.org/document/8094962,

https://www.zora.uzh.ch/id/eprint/150432,

https://www.ncbi.nlm.nih.gov/pubmed/29990121,

http://europepmc.org/abstract/MED/29990121,

https://ui.adsabs.harvard.edu/abs/2016arXiv160703468G/abstract,

https://www.research-collection.ethz.ch/handle/20.500.11850/217074,

https://infoscience.epfl.ch/record/232970,

https://doi.org/10.1109/TPAMI.2017.2769655,

http://ieeexplore.ieee.org/document/8094962,

https://www.arxiv-vanity.com/papers/1607.03468,

https://fr.arxiv.org/abs/1607.03468,

https://128.84.21.199/abs/1607.03468,

https://infosciences.epfl.ch/record/232970?ln=en,

https://academic.microsoft.com/#/detail/2766013930

DOIS: 10.1109/tpami.2017.2769655 10.5167/uzh-150432