A multi-FPGA distributed embedded system for the emulation of Multi-Layer CNNs in real time video applications

Abstract

This paper describes the design and the implementation of an embedded system based on multiple FPGAs that can be used to process real time video streams in standalone mode for applications that require the use of large Multi-Layer CNNs (ML-CNNs). The system processes video in progressive mode and provides a standard VGA output format. The main features of the system are determined by using a distributed computing architecture, based on Independent Hardware Modules (IHM), which facilitate system expansion and adaptation to new applications. Each IHM is composed by an FPGA board that can hold one or more CNN layers. The total computing capacity of the system is determined by the number of IHM used and the amount of resources available in the FPGAs. Our architecture supports traditional cloned templates, but also the (simultaneous) use of time-variant and space-variant templates.