Implementation of low level image processing algorithms on a reconfigurable perception system

The development of VLSI technology allows an increase of the computing power of intelligent machines treating complex applications with a low cost. However, in spite of the success which has been achieved in many specific areas, vision problems are often ill defined, ill posed or computationally intractable (A. Rosenfield, 1993). This constrains the designers to limit the domain of applications for applying adequate computer power which can be inefficient if more powerful algorithms against new constraints come into view. We present a low cost perception system that performs a number of algorithms, such as a real time edge detection and motion estimation and high speed image compression. The main robustness features of the system are its flexibility, reconfigurability, extensibility and modularity, making it easily suited to a large field of applications. The design is based on the needs of every level of image processing in communication, power computing, input data flow and storage features.