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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [26 references]  Display  Hide  Download

https://hal-onera.archives-ouvertes.fr/hal-01070388
Contributor : Véronique Soullier <>
Submitted on : Wednesday, October 1, 2014 - 11:14:09 AM
Last modification on : Tuesday, March 26, 2019 - 2:24:42 PM
Long-term archiving on : Friday, January 2, 2015 - 10:47:00 AM

File

DTIM14028.1403167682.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01070388, version 1

Collections

Citation

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

Share

Metrics

Record views

256

Files downloads

479