Real-Time Intensity-Image Reconstruction for Event Cameras Using Manifold Regularisation

Christian Reinbacher, Gottfried Graber, Thomas Pock

Publikation: KonferenzbeitragPaperBegutachtung

Abstract

Event cameras or neuromorphic cameras mimic the human perception system as they measure the per-pixel intensity change rather than the actual intensity level. In contrast to traditional cameras, such cameras capture new information about the scene at MHz frequency in the form of sparse events. The high temporal resolution comes at the cost of losing the familiar per-pixel intensity information. In this work we propose a variational model that accurately models the behaviour of event cameras, enabling reconstruction of intensity images with arbitrary frame rate in real-time. Our method is formulated on a per-event-basis, where we explicitly incorporate information about the asynchronous nature of events via an event manifold induced by the relative timestamps of events. In our experiments we verify that solving the variational model on the manifold produces high-quality images without explicitly estimating optical flow.
Originalspracheenglisch
PublikationsstatusElektronische Veröffentlichung vor Drucklegung. - 23 Sept. 2016
Veranstaltung2016 British Machine Vision Conference: BMVC 2016 - York, Großbritannien / Vereinigtes Königreich
Dauer: 19 Sept. 201622 Sept. 2016

Konferenz

Konferenz2016 British Machine Vision Conference
Land/GebietGroßbritannien / Vereinigtes Königreich
OrtYork
Zeitraum19/09/1622/09/16

Fingerprint

Untersuchen Sie die Forschungsthemen von „Real-Time Intensity-Image Reconstruction for Event Cameras Using Manifold Regularisation“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren