Comparison of classical and machine learning algorithms for feature point extraction in rugged terrain images for application in SLAM algorithms

P. A. Ukhov, M. B. Bulakina, S. S. Krylov

Moscow Aviation Institute (National Research University)

Abstract: The paper proposes a metric for evaluating the performance of feature point extraction algorithms in rough terrain conditions with no clearly defined landmarks or corners. Various feature point detection algorithms are compared for subsequent integration into a SLAM algorithm on board an unmanned aerial vehicle (UAV). The proposed metric, along with other algorithm parameters, is evaluated through experiments conducted in a controlled environment. The advantages of algorithms based on machine learning models are demonstrated.

Keywords: feature point detection algorithms, SLAM, SIFT, LightGlue, SURF, ORB, SuperPoint, R2D2, machine learning

DOI: 10.15514/ISPRAS-2025-37(6)-24