Indexing of satellite images with different resolutions by wavelet features

Bin Luo (1) , Jean-François Aujol (2) , Yann Gousseau (1) , Saïd Ladjal (1)

1 LTCI - Laboratoire Traitement et Communication de l'Information
2 CMLA - Centre de Mathématiques et de Leurs Applications

As many users of imaging technologies, space agencies are rapidly building up massive image databases. A particularity of these databases is that they are made of images with different but known resolution. In this paper, we introduce a new scheme allowing to index and compare images with different resolution. This scheme relies on a simplified modeling of the acquisition process of satellite images and uses continuous wavelet decompositions. We establish a correspondance between scales that permits to compare wavelet decompositions of images having different resolutions. We validate the approach through several matching and classification experiments, and show that taking the acquisition process into account yields better results than just using scaling properties of wavelet features.

Domaines: Traitement des images [eess.IV]

Bin Luo, Jean-François Aujol, Yann Gousseau, Saïd Ladjal. Indexing of satellite images with different resolutions by wavelet features. IEEE Transactions on Image Processing, 2008, 17 (8), pp.1465-1472. ⟨10.1109/TIP.2008.925367⟩. ⟨hal-00180600⟩