"FUSION FOR CLASSES IN DIFFICULTY" FOR ACCURATE AND SPEED TROPICAL RAINFORESTS CLASSIFICATION - Archive ouverte HAL
Conference Papers Year : 2011

"FUSION FOR CLASSES IN DIFFICULTY" FOR ACCURATE AND SPEED TROPICAL RAINFORESTS CLASSIFICATION

Robin Pouteau
  • Function : Author
  • PersonId : 1168503
Benoit Stoll

Abstract

The accuracy of rainforests classification is generally improved by the input of multisensory data since complex vegetation type identification benefits from complementary information. However, in some cases, multisource fusion can also deteriorate accuracy when irrelevant sources are added. Thus, we introduce a fusion method for classes "in difficulty". Our method outperforms the classical global approach consisting in performing fusion for all classes. Moreover, the fusion processing time can significantly decrease when several classes are put aside. This operational method can be used effectively to enhance accuracy and processing speed when analyzing the wealth of information available from remote sensing products.
Fichier principal
Vignette du fichier
IGARSS 2011 submitted.pdf (624.42 Ko) Télécharger le fichier

Dates and versions

hal-03791074 , version 1 (13-06-2023)

Identifiers

Cite

Robin Pouteau, Benoit Stoll. "FUSION FOR CLASSES IN DIFFICULTY" FOR ACCURATE AND SPEED TROPICAL RAINFORESTS CLASSIFICATION. IEEE International Geoscience and Remote Sensing Symposium, IGARSS'11, Jul 2011, Vancouver, Canada. ⟨10.1109/IGARSS.2011.6049236⟩. ⟨hal-03791074⟩

Collections

UPF
8 View
21 Download

Altmetric

Share

More