Fast recursive ensemble convolution of haar-like features

Abstract : Haar-like features are ubiquitous in computer vision, e.g. for Viola and Jones face detection or local descriptors such as Speeded-Up-Robust-Features. They are classically computed in one pass over integral image by reading the values at the feature corners. Here we present a new, general, parsing formalism for convolving them more efficiently. Our method is fully automatic and applicable to an arbitrary set of Haar-like features. The parser reduces the number of memory accesses which are the main computational bottleneck during convolution on modern computer architectures. It first splits the features into simpler kernels. Then it aligns and reuses them where applicable forming an ensemble of recursive convolution trees, which can be computed faster. This is illustrated with experiments, which show a significant speed-up over the classic approach.
Type de document :
Communication dans un congrès
CVPR "12 : IEEE Conference on Computer Vision and Pattern Recognition, Jun 2012, Providence, Rhode Island, United States. IEEE, pp.3689-3696, 2012, <10.1109/CVPR.2012.6248115>
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00819740
Contributeur : Médiathèque Télécom Sudparis & Télécom Ecole de Management <>
Soumis le : jeudi 2 mai 2013 - 10:55:37
Dernière modification le : jeudi 9 février 2017 - 15:20:57
Document(s) archivé(s) le : lundi 19 août 2013 - 11:05:45

Fichier

Wesierski_2012_cvpr.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Daniel Wesierski, Maher Mkhinini, Patrick Horain, Anna Jezierska. Fast recursive ensemble convolution of haar-like features. CVPR "12 : IEEE Conference on Computer Vision and Pattern Recognition, Jun 2012, Providence, Rhode Island, United States. IEEE, pp.3689-3696, 2012, <10.1109/CVPR.2012.6248115>. <hal-00819740>

Partager

Métriques

Consultations de
la notice

167

Téléchargements du document

72