Combined person classification with airborne optical sectioning

Indrajit Kurmi, David C. Schedl, Oliver Bimber

Research output: Contribution to journalArticlepeer-review

Abstract

Fully autonomous drones have been demonstrated to find lost or injured persons under strongly occluding forest canopy. Airborne optical sectioning (AOS), a novel synthetic aperture imaging technique, together with deep-learning-based classification enables high detection rates under realistic search-and-rescue conditions. We demonstrate that false detections can be significantly suppressed and true detections boosted by combining classifications from multiple AOS—rather than single—integral images. This improves classification rates especially in the presence of occlusion. To make this possible, we modified the AOS imaging process to support large overlaps between subsequent integrals, enabling real-time and on-board scanning and processing of groundspeeds up to 10 m/s.

Original languageEnglish
Article number3804
JournalScientific Reports
Volume12
Issue number1
DOIs
Publication statusPublished - Dec 2022
Externally publishedYes

Keywords

  • Forests
  • Histological Techniques
  • Humans
  • Optical Imaging
  • Optical Phenomena

Fingerprint

Dive into the research topics of 'Combined person classification with airborne optical sectioning'. Together they form a unique fingerprint.

Cite this