A CMOS imager with focal-plane computation for feature detection

Feature detection and tracking is a fundamental problem in computer vision research. By detecting and tracking features in an image sequence it is possible to recover information about both the motion of the viewer and the structure of the environment. We designed, fabricated and tested a CMOS imager with analog VLSI focal-plane computation for feature detection. The chip implements a feature detection algorithm that is suitable for integration in a compact analog VLSI chip. We review the algorithm, its analog VLSI implementation and experimental results from the chip.