<title>VaMoRs-P: an advanced platform for visual autonomous road vehicle guidance</title>

Abstract

A sedan Mercedes 500 SEL has been equipped with active bifocal vision systems. Road and object recognition is performed both in a look-ahead and in a look-back region; this allows to servo-maintain an internal representation of the entire situation around in the vehicle using the 4D approach to dynamic machine vision. Obstacles are detected and tracked both in the forward and in the backward viewing range up to about 100 meters distance; up to 5 objects may be tracked in parallel in each hemisphere. A fixation type viewing direction control with the capability of saccadic shifts for attention focusing has been developed. The overall system comprises about 5 dozen transputers T-222 (16-bit, for image processing and communication) and T-800 (32-bit, for number crunching and knowledge processing) plus a PC as transputer host. A description of the parallel processing architecture is given allowing frequent data driven bottom-up and model driven top-down integration steps for efficient and robust object tracking (4D approach).