Interactive Design of Object Classifiers in Remote Sensing - ONERA - Office national d'études et de recherches aérospatiales Access content directly
Conference Papers Year : 2014

Interactive Design of Object Classifiers in Remote Sensing


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.
Fichier principal
Vignette du fichier
DTIM14028.1403167682.pdf (1.9 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01070388 , version 1 (01-10-2014)


  • 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⟩


142 View
385 Download


Gmail Facebook X LinkedIn More