Combined Person Classification with Airborne Optical Sectioning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2021
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913563926331392 |
|---|---|
| author | Kurmi, Indrajit Schedl, David C. Bimber, Oliver |
| author_facet | Kurmi, Indrajit Schedl, David C. Bimber, Oliver |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2106_10077 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Combined Person Classification with Airborne Optical Sectioning Kurmi, Indrajit Schedl, David C. Bimber, Oliver Computer Vision and Pattern Recognition 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. |
| title | Combined Person Classification with Airborne Optical Sectioning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2106.10077 |