Registration of multi-spectral satellite images with scale-restricted SURF

Abstract

Multi-spectral images acquired from different viewpoints and positions are required to be registered for various applications. Registration is generally achieved by feature extraction followed by matching of these features. In this paper, registration of multispectral satellite images using Speeded Up Robust Features (SURF) method is examined. The performance of SURF for registration of high resolution satellite images captured at different bands is evaluated. Scale Restriction (SR) method is adapted to SURF to improve multispectral image registration performance. Matching performance between different bands using SURF, U-SURF, and SURF with SR and U-SURF with SR is tested and robustness of these with respect to orientation and scale is evaluated.