Vision Chips with Pixel-parallel Cellular Processor Arrays

Vision chips are microelectronic devices which combine image sensing and processing on a single silicon die. In a way somewhat resembling the vertebrate retina these VLSI chips perform preliminary image processing directly on the sensory plane and are capable of very high processing speed at very low power consumption. This makes them particularly suitable for applications such as autonomous robots and other embedded machine vision systems. This paper discusses the principles of using massively parallel fine-grain SIMD processor arrays for low-level image processing and reviews the design and implementation of vision chips developed at the University of Manchester, including the SCAMP-3 chip, which contains 16,384 processors. Application examples and experimental results are presented.