Georg Hartmann

Learn More
The recognition of 3-D objects is surely one of the most challenging goals in computer vision. In this paper we present a robot vision system that analyzes its environment by active vision techniques. Therefore, the system is gathering information about an object in the scene by taking multiple views. It is designed as a hybrid system that brings together(More)
The fast simulation of large networks of spiking neurons is a major task for the examination of biology-inspired vision systems. Networks of this type label features by synchronization of spikes and there is strong demand to simulate these eeects in real world environments. As the calculations for one model neuron are complex, the digital simulation of(More)
A chaotic environment can give rise to "flares" if an autocatalytic variable responds in a multiplicative, threshold-type fashion to the environmental forcing. An "economic unit" similarly depends in its growth behavior on the unpredictable (chaotic?) buying habits of its customers, say. It turns out that coupled flare attractors are surprisingly robust in(More)
The labeling of features by synchronization of spikes seems to be a very efficient encoding scheme for a visual system. Simulation of a vision system with millions of pulse-coded model neurons, however, is almost impossible on the base of available processors including parallel processors and neurocomputers. A "one-to-one" silicon implementation of(More)