texture-based forest cover classification using random forests and ensemble margin - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

texture-based forest cover classification using random forests and ensemble margin

Résumé

This work investigates the discriminative power of wavelet decomposition based texture features in forest cover classification. Our texture features are used as inputs in a random forests classifier. The performances of this tree-based ensemble classifier are assessed by classification accuracy as well as classification confidence provided by an unsupervised version of ensemble margin. The effectiveness of the proposed texture based multiple classifier system is demonstrated in performing mapping of very high resolution forest imagery. Traditional grey level co-occurrence matrix derived texture features are also evaluated through our ensemble classification framework for comparison.
Fichier principal
Vignette du fichier
Boukir15_IGARSS.pdf (3.18 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01188174 , version 1 (28-08-2015)

Identifiants

  • HAL Id : hal-01188174 , version 1

Citer

Samia Boukir, Olivier Regniers, Li Guo, Lionel Bombrun, Chrisitan Germain. texture-based forest cover classification using random forests and ensemble margin. IEEE International Geoscience and Remote Sensing Symposium 2015, 2015, Milan, Italy. pp.3072-3075. ⟨hal-01188174⟩
99 Consultations
390 Téléchargements

Partager

Gmail Facebook X LinkedIn More