Optimizing SIFT algorithm parameters for better matching UAV and satellite images

Abstract

Abstract Image registration has been increasingly employed in various applications such as target identification, 3D mapping, and motion tracking. The main idea of Image registration is aligning two or more images of the same scene captured from different viewpoints, at different times. Scale-invariant feature transform, SIFT, is considered one of the most robust algorithms used in image registration for extracting and matching features under different conditions. Using SIFT algorithm default parameters in Matching UAV and satellite Images provides unreliable results due to the nature of aerial images because the dynamic range is quite low. The number of extracted features depends on the image content and the selected parameters. In this paper we tuned SIFT parameters to get the best performance with aerial images, to increase the number of features (SM) and the correct match rate (CMR) which increases the efficiency of the process of registration. The algorithm is validated by matching a large number of aerial images taken by mini-UAV with satellite images for the same region.