Fast and Accurate Gaussian Pyramid Construction by Extended Box Filtering

Silvère Konlambigue (1, 2) , Jean-Baptiste Pothin , Paul Honeine (1) , Abdelaziz Bensrhair (2)

1 DocApp - LITIS - Equipe Apprentissage
2 STI - LITIS - Equipe Systèmes de Transport Intelligent

Gaussian Pyramid (GP) is one of the most important representations in computer vision. However, the computation of GP is still challenging for real-time applications. In this paper, we propose a novel approach by investigating the extended box filters for an efficient Gaussian approximation. Taking advantages of the cascade configuration, tiny kernels and memory cache, we develop a fast and suitable algorithm for embedded systems, typically smartphones. Experiments with Android NDK show a 5x speed up compared to an optimized CPU-version of the Gaussian smoothing.

Mots clés: machine learning; computer vision

Domaines: Apprentissage [cs.LG]; Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]; Vision par ordinateur et reconnaissance de formes [cs.CV]

Silvère Konlambigue, Jean-Baptiste Pothin, Paul Honeine, Abdelaziz Bensrhair. Fast and Accurate Gaussian Pyramid Construction by Extended Box Filtering. Proc. 25rd European Conference on Signal Processing (EUSIPCO), 2018, Rome, Italy. pp.400-404, ⟨10.23919/EUSIPCO.2018.8553321⟩. ⟨hal-01965908⟩