Combining Multiple Resolutions into Hierarchical Representations for kernel-based Image Classification - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

Combining Multiple Resolutions into Hierarchical Representations for kernel-based Image Classification

Yanwei Cui
  • Fonction : Auteur
  • PersonId : 967818
Laëtitia Chapel
Anne Puissant

Résumé

Geographic object-based image analysis (GEOBIA) framework has gained increasing interest recently. Following this popular paradigm, we propose a novel multiscale classification approach operating on a hierarchical image representation built from two images at different resolutions. They capture the same scene with different sensors and are naturally fused together through the hierarchical representation, where coarser levels are built from a Low Spatial Resolution (LSR) or Medium Spatial Resolution (MSR) image while finer levels are generated from a High Spatial Resolution (HSR) or Very High Spatial Resolution (VHSR) image. Such a representation allows one to benefit from the context information thanks to the coarser levels, and subregions spatial arrangement information thanks to the finer levels. Two dedicated structured kernels are then used to perform machine learning directly on the constructed hierarchical representation. This strategy overcomes the limits of conventional GEOBIA classification procedures that can handle only one or very few pre-selected scales. Experiments run on an urban classification task show that the proposed approach can highly improve the classification accuracy w.r.t. conventional approaches working on a single scale.
Fichier principal
Vignette du fichier
geobia2016kernel.pdf (6.8 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01320011 , version 1 (13-11-2019)

Identifiants

  • HAL Id : hal-01320011 , version 1

Citer

Yanwei Cui, Sébastien Lefèvre, Laëtitia Chapel, Anne Puissant. Combining Multiple Resolutions into Hierarchical Representations for kernel-based Image Classification. international Conference on Geographic Object-Based Image Analysis (GEOBIA), 2016, Enschede, Netherlands. ⟨hal-01320011⟩
163 Consultations
28 Téléchargements

Partager

Gmail Facebook X LinkedIn More