Parallel and local feature extraction: a real-time approach to road boundary detection

摘要

Presents a system for the extraction of road boundaries from an image taken in an out-of-town environment. In this application, computational speed and performance play a fundamental role in the selection of the hardware platform and the design of algorithms. The algorithm has been designed to be implemented on a special-purpose mesh-connected SIR ID architecture, PAPRICA, which will be fitted to the vehicle. This presentation focuses on the algorithms and in particular on processing speed.