Event Location: NSH 1305
Bio: Harpreet S. Sawhney is the Technical Director of Vision & Learning Technologies at SRI-Sarnoff in Princeton, NJ. Harpreet received his Ph.D. in Computer Science (Computer Vision) in 1992 from the University of Massachusetts, Amherst. His areas of interest are Object/Event Recognition, Motion Video Analysis, 3D Modeling, Immersive Telepresence, Video Enhancement and Indexing, and Statistical Data Mining. Harpreet was one of the key technical contributors to two Sarnoff spin-offs, VideoBrush and Lifeclips. Between 1992 and 1995, he led video indexing research at the IBM Almaden Research Center in San Jose, CA. Dr. Sawhney has been an Associate Editor for the IEEE T-PAMI. He has published over 90 papers and holds 34 patents.

Abstract: Video cameras are no longer being used only in their traditional role of providing “viewable pixels”, but are rapidly becoming sources of intelligent information about the world. More recently 3D cameras/sensors are being developed to directly provide 3D measurements of objects and scenes. Appearance and geometry of objects and scenes, and the temporal dynamics of objects are the key information bearing sources for deriving visual intelligence. This talk will highlight sensor data analysis techniques for creating intelligent representations from 2D and 3D sensors. Intelligent sensor data analytics can be performed for mobile as well as widely distributed static sensor platforms. Applications ranging from 3D video manipulation, 3D situational awareness, and sensor-guided training to video/3D object recognition and fingerprinting will be used to illustrate the work.