Reconfigurable machine vision systems using FPGAs

摘要

FPGAs provide a flexible architecture for implementing many different types of machine vision algorithms. They allow heavily parallel portions of those algorithms to be accelerated and optimized for high specific performance (MIPS:Watt ratio). In comparison to ASICS, FPGAs enable low cost, quick turn prototyping and algorithm development as well as lower production costs for small quantity and one off applications. FPGAs also have the ability to be reprogrammed in flight, allowing them to be configured for different applications as mission needs evolve. JPL has developed a suite of machine vision IP cores to accelerate many common machine vision tasks used in robotic mobility applications. Modules such as stereo correlation for ranging, filtering, optical flow, area based correlation, feature detection, and image homography and rectification allow the real-time processing of image data using much smaller systems with much less power draw then an appropriately sized general purpose processor. These modules, along with a vision processing framework, are being re-cast in a generic plug and play form to allow rapid, low cost configuration, reconfiguration, evolution and adaptation of next generation machine vision systems for mobile robotics.