A Novel Multi-Sensor Image Matching Algorithm Based on Adaptive Multiscale Structure Orientation

Automatic and reliable multi-sensor image matching is a very challenging task due to the significant nonlinear radiometric differences between multi-sensor images. In this paper, a novel dense descriptor based on adaptive multiscale structure orientation is proposed for capturing the geometrical str...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE access 2019, Vol.7, p.177474-177483
Hauptverfasser: Lu, Jiazhen, Sun, Fangde, Dong, Jing
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Automatic and reliable multi-sensor image matching is a very challenging task due to the significant nonlinear radiometric differences between multi-sensor images. In this paper, a novel dense descriptor based on adaptive multiscale structure orientation is proposed for capturing the geometrical structure information of an image. The dense descriptor of the proposed matching algorithm is not only illumination and contrast invariant but also robust against the image noise. Further, an improved similarity measurement is introduced for adapting the orientation reversal caused by the intensity inversion between multi-sensor images. Based on the robust dense descriptor and the improved similarity measurement, we developed a novel and practical template matching algorithm to match multi-sensor images reliably. We evaluate the proposed matching algorithm by comparing it with other state-of-the-art algorithms. The experimental results show the proposed algorithm has a significant advantage on matching accuracy.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2019.2958658