Fuzzy-based motion estimation for video stabilization using SIFT interest points

In this paper we present a technique which infers interframe motion by tracking SIFT features through consecutive frames: feature points are detected and their stability is evaluated through a combination of geometric error measures and fuzzy logic modelling. Our algorithm does not depend on the point detector adopted prior to SIFT descriptor creation: therefore performance have been evaluated against a wide set of point detection algorithms, in order to investigate how to increase stabilization quality with an appropriate detector.

• Type: Journal
• Year: 2009
• Where: DPHOTO
• Authors: Sebastiano Battiato, Giovanni Gallo, Giovanni Puglisi, Salvatore Scellato
• Keywords: Consecutive Frames, DPHOTO 2009, Geometric Error Measures, Hardware, SIFT Descriptor Creation