Aswin C Sankaranarayanan,  (University of Maryland, College Park, USA): “Robust and Efficient Inference of Scene and Object Motion in Multi-Camera Systems,” 2009.  Advised by Prof. Rama Chellappa Multi-camera systems have the ability to overcome some of the fundamental limitations of single camera based systems. Having multiple view points of a scene goes a long way in limiting the influence of field of view, occlusion, blur and poor resolution of an individual camera.  This dissertation addresses robust and efficient inference of object motion and scene in multi-camera and multi-sensor systems. In particular, the dissertation covers all three aspects of the information processing pipeline in such systems: sensing (wherein it proposes parsimonious methods to only sense information of interest), inference (for robust estimation) and processing (with computational efficiency). Click here to access the thesis or contact the author.