BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//euroscipy-2025//speaker//CLXJRK
BEGIN:VTIMEZONE
TZID:Europe/Warsaw
BEGIN:DAYLIGHT
DTSTART:20240820T000000
TZNAME:CEST
TZOFFSETFROM:+0200
TZOFFSETTO:+0200
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20241027T030000
RDATE:20251026T030000
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20250330T030000
RDATE:20260329T030000
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:Python Framework for Large-Scale Radar Data Generation and Visuali
 zation - Manuel Jürgensen
DTSTART;TZID=Europe/Warsaw:20250820T114000
DTEND;TZID=Europe/Warsaw:20250820T120000
DTSTAMP:20260911T011442Z
UID:pretalx-euroscipy-2025-ELXEN7@pretalx.com
DESCRIPTION:The application of machine learning in automotive radar system
 s presents severe challenges\, particularly due to the limited availabilit
 y of raw radar data tailored to specific radar configurations and annotate
 d datasets. In this presentation\, we introduce a novel Python-based frame
 work designed to address these challenges by enabling large-scale radar da
 ta generation and visualization.\n\nOur framework leverages existing radar
  detections from production systems\, accumulating radar detections over m
 ultiple cycles to enhance resolution and minimize feature fluctuation. The
 se accumulated features\, referred to as pseudo scatter points\, are treat
 ed as scatter centers to generate raw spectra for virtual radar systems wi
 th arbitrary antenna arrangements. This approach incorporates clutter in t
 he simulation to achieve more representative results.\n\nKey features of o
 ur framework include:\n\n- GPU Acceleration: Utilizes GPU acceleration to 
 handle the computational demands of large-scale radar data generation effi
 ciently.\n- Inbuilt Visualizer: Provides an inbuilt visualizer for radar d
 ata\, facilitating real-time analysis and debugging.\n- Specialized Data c
 lass: Implements a specialized data class to streamline the process of rad
 ar data generation and processing.
LOCATION:Room 1.20 (Ground Floor\, Shannon)
URL:https://pretalx.com/euroscipy-2025/talk/ELXEN7/
END:VEVENT
END:VCALENDAR
