Self-Supervised Optical Flow Estimation by Projective Bootstrap

Dense optical flow estimation is complex and time consuming, with state-of-the-art methods relying either on large synthetic data sets or on pipelines requiring up to a few minutes per frame pair. In this paper, we address the problem of optical flow estimation in the automotive scenario in a self-s...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on intelligent transportation systems 2019-09, Vol.20 (9), p.3294-3302
Hauptverfasser:	Alletto, Stefano, Abati, Davide, Calderara, Simone, Cucchiara, Rita, Rigazio, Luca
Format:	Artikel
Sprache:	eng
Schlagworte:	Adaptive optics Automotive engineering Cameras Computer architecture Computer vision Datasets Estimation image motion analysis Optical flow (image analysis) Optical imaging Optical sensors Transformations unsupervised learning Warping
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!