Systolic Array Architecture for Early Vision Processing
Jean-Didier Legat, J.P. Cornil, DAMIEN MACQ, Michel Verleysen · Digital Access to Libraries (Université catholique de Louvain (UCL), l'Université de Namur (UNamur) and the Université Saint-Louis (USL-B)) · 1991
This paper describes the architecture and the implementation of a systolic processor dedicated to motion estimation which is one of the most important task in early vision processing. The input image is scanned by a standard video camera with 256 grey levels. Motion computing is based on the optical flow determination. An algorithm to detect multi-motion is proposed and is implemented in real-time in a systolic array.