Abstract
Computer vision requires the processing of large volumes of data and requires parallel architectures and algorithms to be useful in real-time, industrial applica tions. The INSIGHT dataflow language was designed to allow encoding of vision algorithms at all levels of the computer vision paradigm. INSIGHT programs, which are relational in nature, can be translated into a graph structure that represents an architecture for solving a particular vision problem or a configuration of a reconfi gurable computational network. We consider here IN SIGHT programs that produce a parallel net architecture for solving low-, mid-, and high-level vision tasks.

This publication has 13 references indexed in Scilit: