Dr Roberto Cipolla
Reader in Information Engineering
Department of Engineering
University of Cambridge

Our visual systems allow us to recognize familiar objects in a scene as well as describing qualitatively the position, orientation and three-dimensional shape of unfamiliar ones. Vision is our most powerful sense but it is also our most complicated. What are the complex chain of events that constitute "seeing" and can we make machines that see?

Computer Vision (Computational Vision) is concerned with understanding the principles underlying visual competences in both natural and artificial systems. It analyses vision as a complex information processing task and uses the precise language and methods of computation to propose and test models of visual processing.

In this talk I will describe some of the computational processes involved in making machines that see and will illustrate the talk with realtime demonstrations of machines that can see for:

(4) A vision-based mouse for simpler ways of interacting with computers.

Roberto Cipolla obtained a B.A. (Engineering) from the University of Cambridge in 1984 and an M.S.E. (Electrical Engineering) from the University of Pennsylvania in 1985. From 1985 to 1988 he studied and worked in Japan at the Osaka University of Foreign Studies (Japanese Language) and Electrotechnical Laboratory, Tsukuba (visiting scientist) and he obtained an M.Eng. (Robotics) from the University of Electro-communications in Tokyo in 1988.

In 1991 he was awarded a D.Phil. (Computer Vision) from the University of Oxford and from 1991-92 was a Toshiba Fellow and engineer at the Toshiba Corporation Research and Development Centre in Kawasaki, Japan. He joined the Department of Engineering, University of Cambridge in 1992 as a Lecturer and a Fellow of Jesus College. He became a Reader in Information Engineering in 1997.

His research interests are in computer vision and robotics and include the recovery of motion and 3D shape of visible surfaces from image sequences; visual tracking and navigation; robot hand-eye coordination; algebraic and geometric invariants for object recognition and perceptual grouping; novel man-machine interfaces using visual gestures and visual inspection. He has authored and co-authored more than 100 papers.