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:20260730T152728Z
LOCATION:Mtg Room 201A
DTSTART;TZID=America/Los_Angeles:20260728T163000
DTEND;TZID=America/Los_Angeles:20260728T170000
UID:dac_DAC 2026_sess254_SSSN118@linklings.com
SUMMARY:A Quantitative Approach to Exploring Novel Image Sensor Architectu
 res Towards Autonomous Edge Machine Vision
DESCRIPTION:Xuan Zhang (Northeastern University)\n\nAutonomous edge machin
 e vision requires image sensor architectures that simultaneously advance i
 nference autonomy and energy autonomy. This paper introduces a quantitativ
 e modeling framework that spans conventional CMOS imagers and emerging des
 igns—event-based/DVS sensors, coded-exposure sensors, and self-powered sen
 sors with energy-harvesting pixels. We unify optical, circuit, and algorit
 hmic modeling in a single analytical flow to capture how architectural cho
 ices in pixel structures, readout pipelines, compressive acquisition, and 
 hybrid imaging–harvesting mechanisms propagate to power, latency, noise, a
 nd task-level vision performance. Extending first-principles models of sel
 f-powered vision systems, the framework also evaluates when energy-harvest
 ing pixels provide system-level advantages over external solar harvesting,
  particularly in long-lived and hard-to-maintain deployments. By enabling 
 rapid, physically grounded exploration and comparative analyses, our resul
 ts reveal key trade-offs that determine when unconventional sensor archite
 ctures meaningfully enhance edge intelligence. This framework offers a pri
 ncipled foundation for designing next-generation energy-aware, autonomous 
 machine vision systems.\n\nTopics: Systems\n\nSession Chairs: Shaahin Angi
 zi (New Jersey Institute of Technology), Gourav Datta (Case Western Reserv
 e University), and Peter Beerel (University of Southern California)\n\n
END:VEVENT
END:VCALENDAR