Abstract
We present the fusion of an active stereo camera system together with a mobile robot having the capability of orientating and navigating. This performance is achieved by realizing a task-specific hierarchy of visual, biologically motivated information processing modules. The claimed behavioural complexity depends on a task-specific combination of simple but versatile units and additionally from an active vision concept. This concept is able to solve basic vision problems in a much more efficient way than a passive one [5]. We describe the basic ideas how such a hierarchy of capabilities can be achieved. In a second step the structure of the utilized mechanical system and the underlying software concept are presented. Finally, an obstacle detection scheme is presented as a basic module in the field of low-level tasks. It deals as an example of actually developed “evolvable” modules combining biological principles in order to realize a basic task in visually guided behaviour.
This project is supported by the German Fed. Dep. of Research and Technology (BMFT), Grant No. ITR8800K4
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
H.H.Bülthoff, J.J.Little, and T.Poggio. A parallel algorithm for real-time computation of optical flow. Nature, 337: 549, 1989
H.A.Mallot, E.Schulze, and K.Storjohann. Neural Network strategies for robot navigation. In G. Dreyfus and L. Personnaz, editors, nEuro 88, Paris
H.A.Mallot, H.H.Bülthoff, and J.J.Little. Neural Architecture for optical flow computation. Artific. Intell. Memo. 1067, Massachusetts Institute of Technology, 1989
S.Bohrer, H.H.Bülthoff, H.A.Mallot. Adaptation of a parallel correlation-based optical flow scheme. In Proceedings of INNC-90-PARIS, 1990
J.Y.Aloimonos, A.Bandyopadhyay: Active Vision, In Proceedings of ICCV, London, 35:52, 1987
K.Storjohann, E.Schulze, Segmentierung dreidimensionaler Szenen mittels perspektiver Kartierungen, In Proceedings of 10. DAGM-Symposium, Zürich 1988 (Springerverlag)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1990 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Schulze, E.R., Bohrer, S., Dose, M., Fuhrmann, S. (1990). An Active Vision System for Task-Specific Information Processing. In: Großkopf, R.E. (eds) Mustererkennung 1990. Informatik-Fachberichte, vol 254. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-84305-1_8
Download citation
DOI: https://doi.org/10.1007/978-3-642-84305-1_8
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-53172-2
Online ISBN: 978-3-642-84305-1
eBook Packages: Springer Book Archive