Design Details of a Low Cost and High Performance Robotic Vision Architecture

Abstract

The implementation of an advanced real-time, low cost video processing platform capable of supporting a variety of demanding robotic applications is presented. The system is designed as an open project, accessible in full detail and has the potential to grow. It is based on a FPGA plus MCU architecture, allowing the implementation of combined fixed-point and 32-bit floating-point applications with optimized resource allocation. The presented platform is optimally integrated with appropriate controllers, like video-input frame grabbers for multiple camera applications, external SDRAM, as well as USB and VGA interfaces. The processing and interfacing capabilities of the proposed system are illustrated by implementing basic feature extraction and preprocessing tasks, achieving the display of processed video frames at a rate of 30 fps with resolution 640x480. The proposed architecture is evaluated in terms of resource usage, power consumption and cost. Potential applications are also discussed.