Comparison of feature-based algorithms for large-scale satellite image matching

Using different algorithms to extract, describe, and match features requires knowing their capabilities and weaknesses in various applications. Therefore, it is a basic need to evaluate algorithms and understand their performance and characteristics in various applications. In this article, classical local feature extraction and description algorithms for large-scale satellite image matching are discussed. Eight algorithms, SIFT, SURF, MINEIGEN, MSER, HARRIS, FAST, BRISK, and KAZE, have been implemented, and the results of their evaluation and comparison have been presented on two types of satellite images. In previous studies, comparisons have been made between local feature algorithms for satellite image matching. However, the difference between the comparison of algorithms in this article and the previous comparisons is in the type of images used, which both reference and query images are large-scale, and the query image covers a small part of the reference image. The experiments were conducted in three criteria: time, repeatability, and accuracy. The results showed that the fastest algorithm was Surf, and in terms of repeatability and accuracy, Surf and Kaze got the first rank, respectively.