Steffen Schmalz

Learn More
This article describes an architecture for the recognition of three-dimensional objects on the basis of viewer centred representations and temporal associations. Considering evidence from psychophysics, neurophysiology, as well as computer science we have decided to use a viewer centred approach for the representation of three-dimensional objects. Even(More)
This paper introduces the Neural Active Vision System NAVIS. It it able to explore visually its environment, locates interesting 2D and 3D objects and recognizes them under control of several invariance capabilities. Emphasis has been put on the system’s biological plausibility as well as on its computational costs and the integration aspects. The(More)
Object recognition is essential for autonomous vision systems. In order to obtain a size invariant recognition an extremely high number of possible matches has to be considered. One method to avoid a combinatorial explosion is to partition the scene into separate depth planes. Each plane contains less features than the entire image and therefore the number(More)
  • 1