HOG-Dot: A Parallel Kernel-Based Gradient Extraction for Embedded Image Processing

Luca Maggiani 1, 2 Cédric Bourrasset 2 Matteo Petracca 3 François Berry 2 Paolo Pagano 3 Claudio Salvadori 1
1 Scuola Superiore Sant'Anna [Pisa]
2 IP - Institut Pascal
3 CNIT c/o Dept. of Electronics & Telecommunications
Abstract : In this paper we propose HOG-Dot, a method for the direct computation of the polar image gradients coordinates from the pixels values. The proposed algorithm, to be used as the first step of the Histogram of Oriented Gradient (HOG) pipeline, approximates the exact gradient with its projection onto a versor chosen among the projection plane set. Instead of non linear computations, the HOG-Dot method exploits linear operations while introducing a bounded approximation error with respect to other HOG approaches, thus resulting a more suitable solution for embedded devices. Concerning the state of the art, it also achieves improved accuracy with the mathematical spatial gradient formulation.
Type de document :
Article dans une revue
IEEE Signal Processing Letters, Institute of Electrical and Electronics Engineers, 2015, 〈10.1109/LSP.2015.2463092〉
Liste complète des métadonnées

Littérature citée [9 références]  Voir  Masquer  Télécharger
https://hal.archives-ouvertes.fr/hal-01220417
Contributeur : Luca Maggiani <>
Soumis le : lundi 26 octobre 2015 - 12:20:32
Dernière modification le : mardi 11 septembre 2018 - 16:56:02
Document(s) archivé(s) le : vendredi 28 avril 2017 - 08:21:44

Fichier

HOG-Dot.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

INSTITUT_PASCAL | PRES_CLERMONT | ACL-SPI | SIGMA-CLERMONT

Citation

Luca Maggiani, Cédric Bourrasset, Matteo Petracca, François Berry, Paolo Pagano, et al.. HOG-Dot: A Parallel Kernel-Based Gradient Extraction for Embedded Image Processing. IEEE Signal Processing Letters, Institute of Electrical and Electronics Engineers, 2015, 〈10.1109/LSP.2015.2463092〉. 〈hal-01220417〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

179

Téléchargements de fichiers

277

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD