Combined person classification with airborne optical sectioning

Indrajit Kurmi, David C. Schedl, Oliver Bimber

Publikation: Beitrag in FachzeitschriftArtikelBegutachtung

7 Zitate (Scopus)

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.

OriginalspracheEnglisch
Aufsatznummer3804
Seiten (von - bis)3804
FachzeitschriftScientific Reports
Jahrgang12
Ausgabenummer1
DOIs
PublikationsstatusVeröffentlicht - 9 März 2022
Extern publiziertJa

Fingerprint

Untersuchen Sie die Forschungsthemen von „Combined person classification with airborne optical sectioning“. Zusammen bilden sie einen einzigartigen Fingerprint.

Zitieren