BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250626T233528Z
LOCATION:B302-B305
DTSTART;TZID=America/New_York:20241120T100000
DTEND;TZID=America/New_York:20241120T170000
UID:submissions.supercomputing.org_SC24_sess533_post172@linklings.com
SUMMARY:Neural Network Optimization and Performance Analysis for Real-Time
  Object Detection at the Edge
DESCRIPTION:Animesh Ghose (Brookhaven National Laboratory, Carnegie Mellon
  University)\n\nReal-time object detection is an important and computation
 ally intensive task that is gaining more attention in the field of autonom
 ous systems. Recently, a novel object detection algorithm called RT-DETR h
 as emerged, demonstrating superior speed compared to the popular YOLO seri
 es. In recent years, many edge devices optimized for artificial intelligen
 ce have been developed, allowing for faster model inference. Our study use
 s NVIDIA TensorRT to optimize models in the task of object tracking and de
 tection on NVIDIA’s Orin device. Our best resulting model is the FP16 mode
 l with DLA with an average inference time of 19.9416 milliseconds and thro
 ughput of 50.1465 (frames) per second. This is a five-fold improvement com
 pared with the standard unoptimized Pytorch FP32 model, with practically n
 o accuracy sacrifice. Our study shows that applying TensorRT and quantizat
 ion on object tracking and detection on NVIDIA’s Orin device is effective 
 in reducing prediction time, allowing for faster detection.\n\nRegistratio
 n Category: Tech Program Reg Pass, Exhibits Reg Pass\n\nSession Chairs: Ay
 esha Afzal (Friedrich-Alexander University, Erlangen-Nuremberg; Erlangen N
 ational High Performance Computing Center); Sally Ellingson (University of
  Kentucky); and Alan Sussman (University of Maryland)\n\n
END:VEVENT
END:VCALENDAR