Perceptual Computing in general and Computer Vision in particular have great potentials to change the way we interact with computers and how machines such as robots perceive the world. Over the last three decades significant progress has been made in computer vision. Today it is possible to use image information for quality control and domain specific problems such as face recognition, recovery of CAD models for well-defined objects and basic visual surveillance. Robustness of perception and vision algorithms however is a notorious problem and one of the major bottlenecks for industrial applications. At the same time there is little doubt that in the next decades small and inexpensive sensors will be developed and embedded in many devices. Our hypothesis is that the integration of multiple features and sensors facilitates robustness in environments of realistic complexity.
The computer vision and machine learning department was founded by Bernt Schiele in 2010 and currently consists of six research groups headed by Jonas Fischer, Margret Keuper, Jan Eric Lenssen, Gerard Pons-Moll, Paul Swoboda, and Bernt Schiele.