Tutorial 4 : Image analysis in very high resolution optical remote sensing

Presenter:

Dr. Jocelyn Chanussot, Grenoble Institute of Technology, France

Abstract

Satellite and airborne remote sensing is currently undergoing a technical revolution with the appearance and blooming development of very high resolution sensors. For high resolution remote sensing sensors, resolution can have the following three meanings:

• Spatial resolution: Metric and sub-metric resolutions are currently available for satellite remote sensing. That opens the door for very accurate geometrical analysis of objects present in scenes of study. This is of a great importance in a variety of applications such as the monitoring of urban areas etc.
• Spectral resolution: After decades of use of multispectral remote sensing, most of the major space agencies now have new programs to launch hyperspectral sensors, recording the reflectance information of each point on the ground in hundreds of narrow and contiguous spectral bands. The spectral information is instrumental for the accurate analysis of the physical component present in one scene.
• Temporal resolution: Due to the launch of constellations of satellites and the increasing number of operating systems, the temporal resolution between two acquisitions over a given scene of interest has dramatically decreased. This opens the door to the accurate monitoring of abrupt changes and to efficient response in case of major disasters. Temporal phenomena with longer scales may also be monitored.

The needs for very high resolution remote sensing data grew in parallel to this technical revolution. As a matter of fact, a lot of applications, with an increasing societal impact can now potentially be addressed using remote sensing: urban mapping and urban planning, precision agriculture, disaster management, monitroing and management of the environment, defense related issues etc.

However, in order to fully exploit all the potential offered by the new generations of sensors and to actually face all the applications with a very high societal impact, advanced image processing methods are required. As a matter of fact, most of the traditional processing algorithms fail when the resolution increases significantly. For instance, statistical learning becomes intractable with hyperspectral data because of the dimensionality of the data. Similarly, while it was easy to classify urban versus non urban areas with medium resolution data, very high resolution data enable the accurate classification at the building scale, but this requires to completely redesign the whole processing chain.

This tutorial aims on the one hand at presenting the key challenges arising in very high resolution optical (airborne or satellite) remote sensing, and on the other hand, at covering some recent developments in advanced image processing in relation with these challenges, such as:

• Image pansharpening: fusion of images with different resolutions
• Basics in change detection
• Road network extraction using advanced morphological tools (path operators recently developped by Talbot et al).
• Spectral-spatial analysis of hyperspectral data (extension of marker based segmentation in very high dimensional spaces)
• Segmentation and object recognition using Binary Partition Trees (recent work by Salembier et al).
• Superresolution in hyperspectral imagery.
• Supervised classification and machine learning.
  

Biography of the presenter

Jocelyn Chanussot received the M.Sc. degree in electrical engineering from the Grenoble Institute of Technology (Grenoble INP), Grenoble, France, in 1995, and the Ph.D. degree from Savoie University, Annecy, France, in 1998. In 1999, he was with the Geography Imagery Perception Laboratory for the Delegation Generale de l'Armement (DGA - French National Defense Department). Since 1999, he has been with Grenoble INP, where he was an Assistant Professor from 1999 to 2005, an Associate Professor from 2005 to 2007, and is currently a Professor of signal and image processing. He is currently conducting his research at the Grenoble Images Speech Signals and Automatics Laboratory (GIPSA-Lab). His research interests include image analysis, multicomponent image processing, nonlinear filtering, mathematical morphology, and data fusion in remote sensing and hyperspectral imagery.

Dr. Chanussot is the founding President of IEEE Geoscience and Remote Sensing French chapter (2007-2010) which received the 2010 IEEE GRS-S Chapter Excellence Award « for excellence as a Geoscience and Remote Sensing Society chapter demonstrated by exemplary activities during 2009 ». He was a member of the IEEE Geoscience and Remote Sensing AdCom (2009–2010), in charge of membership development. He was the General Chair of the first IEEE GRSS Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote sensing (WHISPERS). He is the Chair (2009-2011) and was the Cochair (2005-2008) of the GRS Data Fusion Technical Committee. He was a member of the Machine Learning for Signal Processing Technical Committee of the IEEE Signal Processing Society (2006–2008) and the Program Chair of the IEEE International Workshop on Machine Learning for Signal Processing, (2009). He was an Associate Editor for the IEEE Geoscience and Remote Sensing Letters (2005–2007) and for Pattern Recognition (2006–2008). Since 2007, he is an Associate Editor for the IEEE Transactions on Geoscience and Remote Sensing (IEEE TGRS). He was the Guest Editor of various special issues (for IEEE TGRS, the Springer Journal of Signal Processing Systems, IEEE Journal of Selected Topics in Signal Processing). He is the new Editor in Chief of the IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. He edited two books and co-authored more than 40 journal papers and 100 conference papers. He is a Senior Member of the IEEE (2004). More information: http://www.gipsa-lab.grenoble-inp.fr/~jocelyn.chanussot/