Adaptive parameter tuning for morphological segmentation of building facade images

Abstract : We present an adaptive method to segment Haussmannian facades from street level images. Our approach assumes that images are rectified, cropped and their elements are aligned in a pseudo-regular structure. It is based on the accumulation of directional color gradients, combined with morphological filters in order to deal with textured facades. We propose an automatic parametrization of three filters included in the process: opening filter of size n op, alternate sequential filter (ASF) of size n, and H-minima filter with contrast threshold h. This automatic selection offers robustness to noise, image resolution changes, shadows and textures. Quantitative and qualitative results are reported on a public annotated database, validating the good performances of our approach.
Type de document :
Communication dans un congrès
20th European Signal Processing Conference EUSIPCO 2012, Aug 2012, Bucarest, Romania. EURASIP, pp.2268-2272, 2012
Liste complète des métadonnées

https://hal-mines-paristech.archives-ouvertes.fr/hal-00834430
Contributeur : Bibliothèque Mines Paristech <>
Soumis le : samedi 15 juin 2013 - 08:15:35
Dernière modification le : vendredi 27 octobre 2017 - 17:36:02

Identifiants

  • HAL Id : hal-00834430, version 1

Collections

Citation

Andrés Serna, Jorge Hernandez, Beatriz Marcotegui. Adaptive parameter tuning for morphological segmentation of building facade images. 20th European Signal Processing Conference EUSIPCO 2012, Aug 2012, Bucarest, Romania. EURASIP, pp.2268-2272, 2012. 〈hal-00834430〉

Partager

Métriques

Consultations de la notice

75