REMOT: A Hardware-Software Architecture for Attention-Guided Multi-Object Tracking with Dynamic Vision Sensors on FPGAs
softwareposted on 2021-12-29, 10:04 authored by Yizhao GaoYizhao Gao, Song WangSong Wang, Hayden Kwok Hay SoHayden Kwok Hay So
This repository serves as the official code release of the paper "REMOT: A Hardware-Software Architecture for Attention-Guided Multi-Object Tracking with Dynamic Vision Sensors on FPGAs" (FPGA'22).
REMOT is a hardware/software architecture for Multi-Object Tracking using Dynamic Vision Sensors on FPGA. It's designed around the concept of an attention unit (AU). Each AU will only pay attention to a specific region of interest, which is designed to changed as the object moves. In REMOT, a layer of parallel AUs is implemented on FPGA to collectively process the stream of asynchronous events from a DVS.
Link to our paper: https://casr.eee.hku.hk/publication/remot-fpga22
Link to github repo: https://github.com/CASR-HKU/REMOT-FPGA-22