Latest Past Events

ExCom/AdCom Meeting

Room: 5th Floor Board Room, Bldg: GTRI Conference Center

Bimonthly Administrative Meeting Agenda: 6:00 Dinner 6:30 Meeting Location: Room: 5th Floor Board Room Bldg: GTRI Conference Center 250 14th St NW Atlanta, Georgia 30318

IEEE Atlanta PES Meeting/Luncheon: Battery Storage Research in Georgia

Room: Auditorium, Bldg: Georgia Transmission Corporation

Come and learn about a joint Southern Company and EPRI research project on battery storage that is currently ongoing. Speaker(s): Haile Gashaw, Location: Room: Auditorium Bldg: Georgia Transmission Corporation 2100 East Exchange Place Tucker, Georgia

High Resolution Optical and SAR Satellite Image Processing for Disaster Management Using Hierarchical MRFs

Room: Auditorium , Bldg: Technology Square Research Building (TSRB)

The IEEE Signal Processing Society Chapter of Atlanta is honored to host IEEE Distinguished Lecturer Dr. Josiane Zerubia from INRIA, France . This meeting is part of the annual Signal Provessing Seminar Series. Abstract: In this talk, we describe a novel classification approach for multi-resolution, multi-sensor (optical and synthetic aperture radar (SAR)) and/or multi-band images. This challenging image processing problem is of great importance for various remote sensing monitoring applications and has been scarcely addressed so far. To deal with this classification problem, we propose a two-step explicit statistical model. We first design a model for the multi-variate joint class-conditional statistics of the co-registered input images at each resolution. We then plug the estimated joint probability density functions into a hierarchical Markovian model based on a quad-tree structure, where each tree-scale corresponds to the different input image resolutions and to the corresponding multi-scale decimated wavelet transforms, thus preventing a strong re-sampling of the initial images. To obtain the classification map, we resort to an estimator of the marginal posterior mode. We integrate a prior update in this model in order to improve the robustness of the proposed classifier against noise and speckle. The resulting classification performance is illustrated on several remote sensing multi-resolution datasets including very high resolution and multi-sensor images acquired by COSMO-SkyMed and GeoEye-1 satellites Speaker(s): Josiane Zerubia, Location: Room: Auditorium Bldg: Technology Square Research Building (TSRB) 85 Fifth Street NW Atlanta, Georgia 30308