Interactive Design of Object Classifiers in Remote Sensing

Abstract : This paper deals with the interactive design of generic classifiers for aerial images. In many real-life cases, object detectors that work are not available, due to a new geographical context or a need for a type of object unseen before. We propose an approach for on-line learning of such detectors using user interactions. Variants of gradient boosting and support-vector machine classification are proposed to cope with the problems raised by interactivity: unbalanced and par- tially mislabeled training data. We assess our framework for various visual classes (buildings, vegetation, cars, visual changes) on challenging data corresponding to several applications (SAR or optical sensors at various resolutions). We show that our model and algorithms outperform several state-of-the-art baselines for feature extraction and learning in remote sensing.
Type de document :
Communication dans un congrès
ICPR 2014, Aug 2014, STOCKHOLM, Sweden
Liste complète des métadonnées

Littérature citée [26 références]  Voir  Masquer  Télécharger
Contributeur : Véronique Soullier <>
Soumis le : mercredi 1 octobre 2014 - 11:14:09
Dernière modification le : jeudi 15 novembre 2018 - 08:38:45
Document(s) archivé(s) le : vendredi 2 janvier 2015 - 10:47:00


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-01070388, version 1



B. Le Saux. Interactive Design of Object Classifiers in Remote Sensing. ICPR 2014, Aug 2014, STOCKHOLM, Sweden. 〈hal-01070388〉



Consultations de la notice


Téléchargements de fichiers