GPU Acceleration of Eff2 Descriptors using CUDA

Kristleifur Daðason 1 Ársaell Þór Jóhannsson 1 Herwig Lejsek 1, * Björn Þór Jónsson 2 Laurent Amsaleg 2, 3
* Corresponding author
3 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : Video analysis using local descriptors requires a high-throughput descriptor creation process. This speed can be obtained from modern GPUs. In this paper, we adapt the computation of the Eff2 descriptors, a SIFT variant, to the GPU. We compare our GPU-Eff descriptors to SiftGPU and show that while both variants yield similar results, the GPU-Eff descriptors require significantly less processing time.
Document type :
Conference papers
Complete list of metadatas

https://hal.inria.fr/inria-00560190
Contributor : Patrick Gros <>
Submitted on : Thursday, January 27, 2011 - 3:40:07 PM
Last modification on : Friday, August 23, 2019 - 3:08:02 PM

Identifiers

Citation

Kristleifur Daðason, Ársaell Þór Jóhannsson, Herwig Lejsek, Björn Þór Jónsson, Laurent Amsaleg. GPU Acceleration of Eff2 Descriptors using CUDA. ACM International Conference on Multimedia, Oct 2010, Florence, Italy. ⟨10.1145/1873951.1874178⟩. ⟨inria-00560190⟩

Share

Metrics

Record views

210