Investigation of the Performance of Different Wavelet-Based Fusions of SAR and Optical Images Using Sentinel-1 and Sentinel-2 Datasets

DUYSAK H., YİĞİT E.

International Journal of Engineering and Geosciences, vol.7, no.1, pp.81-90, 2022 (ESCI) identifier identifier identifier

  • Publication Type: Article / Article
  • Volume: 7 Issue: 1
  • Publication Date: 2022
  • Doi Number: 10.26833/ijeg.882589
  • Journal Name: International Journal of Engineering and Geosciences
  • Journal Indexes: Emerging Sources Citation Index (ESCI), Scopus, TR DİZİN (ULAKBİM)
  • Page Numbers: pp.81-90
  • Keywords: Synthetic aperture radar (SAR), Optical, Wavelet, Sentinel
  • Bursa Uludag University Affiliated: Yes

Abstract

In this study, the fusion of optical and synthetic aperture radar images with wavelet transform was investigated. Images are obtained from Sentinel-1 and sentinel-2 satellites. Images were decomposed by wavelet transform. The four main coefficients were obtained for different wavelet packages and up to ten decomposition levels. The coefficients were combined taking the maximum, minimum or mean. 1710 Fused images were obtained for all possible combinations in terms of different wavelet packets, decomposition levels and fusion rules. Fused images were evaluated according to the structural similarity index (SSI). It was seen that the missing regions in the optical images were improved in the fused images with the appropriate wavelet packets and highest SSI.