Summary: SEGMENTATION AND CLASSIFICATION OF HYPERSPECTRAL DATA USING
WATERSHED
Yuliya Tarabalka1,2
, Jocelyn Chanussot1
, Jon Atli Benediktsson2
, Jesus Angulo3
, and Mathieu Fauvel1,2
1
GIPSA-Lab, Grenoble Institute of Technology, France
2
University of Iceland, Reykjavik, Iceland
3
Paris School of Mines, Paris, France
e-mail: yuliya.tarabalka@gipsa-lab.inpg.fr
ABSTRACT
The paper presents a new segmentation and classi cation
scheme to analyze hyperspectral (HS) data. The Robust
Color Morphological Gradient of the HS image is computed,
and the watershed transformation is applied to the obtained
gradient. After the pixel-wise Support Vector Machines clas-

Source: Angulo,Jesús - Centre de Morphologie Mathématique, Ecole des Mines de Paris

Collections: Computer Technologies and Information Sciences