Accelerating SIFT on parallel architectures

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.

• Type: Conference
• Year: 2009
• Where: CLUSTER
• Authors: Seth Warn, Wesley Emeneker, Jackson Cothren, Amy W. Apon
• Keywords: CLUSTER 2009, Cluster Computing, OpenMP Parallelization, Photographs Requires Parallelization, Serial Sift Implementation