MSFD: Multi-Scale Segmentation-Based Feature Detection for Wide-Baseline Scene Reconstruction

A common problem in wide-baseline matching is the sparse and non-uniform distribution of correspondences when using conventional detectors, such as SIFT, SURF, FAST, A-KAZE, and MSER. In this paper, we introduce a novel segmentation-based feature detector (SFD) that produces an increased number of a...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on image processing 2019-03, Vol.28 (3), p.1118-1132
Hauptverfasser:	Mustafa, Armin, Kim, Hansung, Hilton, Adrian
Format:	Artikel
Sprache:	eng
Schlagworte:	Cameras Clustering Detectors Feature detection Feature extraction Image detection Image reconstruction Image segmentation Matching Performance evaluation Robustness segmentation sparse reconstruction
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!