Real-Time Recognition and Visual Control:
Image Understanding Research at Rochester

Randal C. Nelson and Christopher M. Brown
Department of Computer Science
University of Rochester
Rochester, NY 14627

Abstract: Real-time vision for the control of actions, real-time control of vision processing, learning, and high- and low-level perception continue to be central themes at Rochester. We continue to integrate vision into behaving robotic systems. This document briefly describes recent work in a number of areas, including deictic visuo-motor control, non-holonomic dynamics and control, curvilinear feature extraction, visually guided manipulation and assembly, memory-based recognition, control of complex maniplators, affine representation for virtual reality, filter-based recognition and monitoring, and selective perception.