BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240626T180033Z
LOCATION:Level 2 Lobby
DTSTART;TZID=America/Los_Angeles:20240625T180000
DTEND;TZID=America/Los_Angeles:20240625T190000
UID:dac_DAC 2024_sess236_RESEARCH1383@linklings.com
SUMMARY:FEI: Fusion Processing of Sensing Energy and Information for Self-
 sustainable Infrared Smart Vision System
DESCRIPTION:Work-in-Progress Poster\n\nXin Hong (Jinan University), Haijin
  Su (Beijing Jiaotong University), Maimaiti Nazhamaiti (Tsinghua Universit
 y), Ce Zhang (Beihang University), Junkai Huang (Jinan University), Yuzhao
  Yang (Guangdong University of Technology), Li Luo (Beijing Jiaotong Unive
 rsity), Qi Wei (Tsinghua University), Zheyu Liu (MakeSens AI), and Fei Qia
 o (Beijing National Research Center for Information Science and Technology
 )\n\nIn the natural world, energy and information are deeply entwined, mut
 ually constraining and complementing each other. To exploit this natural m
 erit, this paper proposes an FEI strategy: Fusion processing of sensing En
 ergy and Information for infrared smart vision system. The proposed Inform
 ation-Power-Coupler (IPCp) takes the ability of simultaneous energy harves
 ting and low power in-pixel computing, which utilizes in-situ coupled ener
 gy to process the containing information on the same focal plane. Furtherm
 ore, a self-adaptive Intelligent-Power-Controller (IPCtrl) is capable of s
 cheduling the harvested energy to complete low-power neural network infere
 nce is introduced. The implementation of (IPC2 ) system utilizes a softwar
 e-hardware co-design strategy to exploit the layer-wise characteristic of 
 the computation process and circuit topology, achieving energy-efficient s
 elf-sustainable fusion processing of sensing energy and information. Simul
 ation results show that the intelligent power controller could supply 594.
 68nW with the power conversion efficiency of 93.38%, when the harvested en
 ergy from the information power coupler is 636.84nW. The performance valid
 ates the self-sustainability of the system with the self-powered image rec
 ognition of a complete network running at 4fps with an accuracy of 99.4%.\
 n\nTopic: AI, Autonomous Systems, Cloud, Design, EDA, Embedded Systems, IP
 , Security
END:VEVENT
END:VCALENDAR