H.1.2 Integrated Transputer Systems (2ndgeneration)  

In the European EUREKA-project Prometheus (1987 – 1994), the system architecture developed with the BVV’s at UniBwM has been transferred to ‘Transputer’ systems (details on the system may be found in five contributions to the [International Symposium on ‘Intelligent Vehicles’, 1994 in Paris])


Bifocal vision to the front (in front of the rear view mirror, see left) and rear (hanging under the roof in the center of the window).



H.1.2a. Functional architecture

  • Structured according to classes of objects and tasks;

  • communication bandwidth such that full images could be transferred at video rate (lower bar left).

  • More than five dozen processors of different types (16 to 32 bits) allowed realizing the architecture shown in the two figures:

    a) The upper one emphasizing the perceptual and behavioral tasks to be solved,


 

    b) the lower one shows details of the image sequence processing architecture on a 'transputer network' (at 12.5 Hz, every second video frame).

H.1.2b. Realization on transputer network (adapted to BVV2 system architecture)

  • Bifocal vision systems were installed for the front and the rear hemisphere (top left).

  • Four links each to neighbors in a network;

  • the dynamic data base separates the (lower) data-intensive image processing part from the (upper) cognitive part oriented according to physical objects.

  • Data rates are reduced by 2 to 3 orders of magnitude; for physical objects, time histories may be stored for situation assessment (SA).

  • The objects perceived were painted as overlays on the monitor screens for easy checking of image sequence understanding.



video 18 TwofoldAutonLaneChangeParis 1994

References (in temporal order)

Behringer R (1994). Road Recognition from Multifocal Vision. In Masaki (ed.): Proc. of Int. Symp. on Intelligent Vehicles '94, Paris, pp 302-307

Dickmanns ED, Behringer R, Dickmanns D, Hildebrandt T, Maurer M, Thomanek F, Schiehlen J  (1994).  The Seeing Passenger Car 'VaMoRs-P'. In Masaki (ed): Proc. of Int. Symp. on Intelligent Vehicles '94, Paris, pp 68-73

v. Holt V (1994). Tracking and Classification of Overtaking Vehicles on Autobahnen. Int. Symp. on Intelligent Vehicles '94, Paris, pp 314-319

Schiehlen J, Dickmanns ED (1994).  A Camera Platform for Intelligent Vehicles. In Masaki (ed): Proc. of Int. Symp. on Intelligent Vehicles '94, Paris, pp 393-398

Thomanek F, Dickmanns ED, Dickmanns D (1994).  Multiple Object Recognition and Scene Interpretation for Autonomous Road Vehicle Guidance. In Masaki (ed): Proc. of Int. Symp. on Intelligent Vehicles '94, Paris, Oct. 1994, 231-236

Schiehlen J (1995). Kameraplattformen fuer aktiv sehende Fahrzeuge. Dissertation UniBwM / LRT. Also as Fortschrittsberichte VDI Verlag, Reihe 8, Nr. 514

Behringer R (1996). Visuelle Erkennung und Interpretation des Fahrspurverlaufes durch Rechnersehen für ein autonomes Straßenfahrzeug. Dissertation UniBwM / LRT; also: Fortschrittberichte VDI, Reihe 12, Nr. 310

Thomanek F (1996). Visuelle Erkennung und Zustandsschätzung von mehreren Straßenfahrzeugen zur autonomen Fahrzeugführung. Dissertation UniBwM / LRT; also as Fortschrittsberichte VDI Verlag, Reihe 12, Nr. 272

Dickmanns D (1997). Rahmensystem für visuelle Wahrnehmung veränderlicher Szenen durch Computer. Dissertation UniBwM / INF; also Shaker Verlag, Aachen, 1998

v. Holt V (2004). Integrale Multisensorielle Fahrumgebungserfassung nach dem 4-D Ansatz. Dissertation UniBwM / LRT LRT