Accelerating SIFT on parallel architectures

Seth Warn, Wesley Emeneker, Jackson D. Cothren, Amy W. Apon

Abstract: SIFT is a widely-used algorithm that extracts features from images; using it to extract information from hundreds of terabytes of aerial and satellite photographs requires parallelization in order to be feasible. We explore accelerating an existing serial SIFT implementation with OpenMP parallelization and GPU execution.