HD-02: Analysis of remote sensing images using mathematical morphology

Mauro Dalla Mura and Jocelyn Chanussot

Sunday, July 26
13:30 - 17:30


When dealing with remote sensing images, especially those with high spatial resolution, the spatial relations of the pixels in the scene are a fundamental feature that should be taken into account during data analysis. Different approaches exist for modeling spatial information and for exploiting it in the tasks of interest (e.g., classification, object extraction and change detection). Mathematical morphology (MM) provides a sound framework comprising many image analysis tools that can be used for addressing the problem of including spatial feature in the analysis of a remote sensing scene. Some of these tools have become popular and widely used in the remote sensing community. With this tutorial, we want to give an overview of the current trends, recent advances and possible future directions in the context of mathematical morphology and its application in the remote sensing realm.

The tutorial is structured as follows.
At first, a general introduction of mathematical morphology is given, lying down the basis for the subsequent presentation. The main MM operators are then introduced with a review of their large spread in many different remote sensing tasks. The tutorial then proceeds with the presentation of more recent MM tools highlighting their capabilities with respect to conventional filtering techniques. Recent advances in MM are then presented as well as future possible trends in their application for the analysis of remote sensing images. The last part of the tutorial is devoted to the use of MM tools in a specific application: the land-cover classification of hyperspectral images. Here the participants can see the challenges, some possible solutions, corresponding outcomes and comparison over other related approaches when performing an analysis based on MM in this real remote sensing task.


Mauro Dalla Mura obtained in 2011 a joint Ph.D. degree in Information and Communication Technologies (Telecommunications Area) from the University of Trento, Italy and in Electrical and Computer Engineering from the University of Iceland, Iceland. He is currently an Assistant Professor at Grenoble Institute of Technology (Grenoble INP), France. His main research activities are in the fields of remote sensing, image processing and pattern recognition. In particular, his interests include mathematical morphology, classification and multivariate data analysis.
Dr. Dalla Mura was the recipient of the IEEE GRSS Second Prize in the Student Paper Competition of the 2011 IEEE International Geoscience and Remote Sensing Symposium 2011 (Vancouver, CA, July 2011).

Jocelyn Chanussot is with the engineering school on Energy, Water and Environment (ENSE3) of the Grenoble Institute of Technology (Grenoble INP). His research interests include multicomponent image processing, nonlinear filtering, statistical modeling and data fusion in remote sensing. He is a Fellow of the IEEE (2012).
He served as a member of the IEEE GRSS AdCom (2009-2010). Since january 2011, he is the Editor-in-Chief of the IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.