Online learning of patch perspective rectification for efficient object detection

For a large class of applications, there is time to train the system. In this paper, we propose a learning-based approach to patch perspective rectification, and show that it is both faster and more reliable than state-of-the-art ad hoc affine region detection methods. Our method performs in three s...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Hinterstoisser, S., Benhimane, S., Navab, N., Fua, P., Lepetit, V.
Format:	Tagungsbericht
Sprache:	eng
Schlagworte:	Application software Computer science Computer vision Detectors Image recognition Laboratories Object detection Robustness Testing
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!