A 0.05pJ/Pixel 70fps FHD 1Meps Event-Driven Visual Data Processing Unit
2020 IEEE Symposium on VLSI Circuits(2020)
摘要
An Event-driven visual data Processing Unit (EPU) exploits temporal redundancy in stationary camera video streams to localize motion-based Regions-of-Interest (RoI), saving compute FLOPs and memory bandwidth (BW) for Deep Learning (DL) based object detection. The proposed EPU supports FHD frames at 70fps and can be time-multiplexed across multiple video streams. The EPU pipeline consists of event detection, event clustering, event cluster dilation and RoI extraction and occupies 0.34mm
2
in 10nm CMOS. Frame-based, inter- and intra-frame event-driven power management schemes minimize normalized energy/pixel to 0.05pJ at 0.65V. RoI filtering with an EPU frontend improves the end-to-end (E2E) energy-efficiency of a deep-learning (DL) based vision pipeline by 5X, while improving its throughput by 4.3X.
更多查看译文
关键词
EPU pipeline,event detection,event clustering,event cluster dilation,intra-frame event-driven power management schemes,deep-learning based vision pipeline,stationary camera video streams,FHD frames,event-driven visual data processing unit,motion-based regions-of-interest,deep learning based object detection,RoI extraction,frame-based event-driven power management schemes,end-to-end energy-efficiency
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要