SIFT and SURF feature analysis in visible and infrared imaging for UAVs

This paper presents an in-depth analysis of the SIFT and SURF feature detection and matching techniques in characterizing natural environments for vision based navigation problems, in particular, the performance of feature extraction algorithms and matching when both visual and infrared data are used. With successful utilization of both feature extraction methods on different characteristic images, performance metrics include processing time, number of detected features and matching rate with RANSAC outlier rejection applied are discussed, with relevant conclusions made.