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 SSSUP - Scuola Universitaria Superiore Sant'Anna [Pisa]
2 IP - Institut Pascal
3 CNIT c/o Dept. of Electronics & Telecommunications

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.

Domaines: Traitement du signal et de l'image [eess.SP]

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, 2015, ⟨10.1109/LSP.2015.2463092⟩. ⟨hal-01220417⟩