The research question that the paper investigates is whether the usage of state of the art algorithms for point clouds registration solves the problem of multi-scale vision-based point clouds registration in mixed aerial and underwater environments. This paper reports very preliminary results on the data we have been able to procure, in the context of a coral reef restoration project nearby Magoodhoo Island (Maldives). The results obtained by exploiting state of the art algorithms are promising, considering that those data presents hard samples, in particular for their multi-scale nature (noise in captured 3D points increases with depth). However, further investigation on larger data-sets is needed to confirm the overall applicability of the current algorithms to this problem.
Di Lauro, F., Fallati, L., Fontana, S., Savini, A., Sorrenti, D. (2024). Automatic Alignment of Multi-scale Aerial and Underwater Photogrammetric Point Clouds: A Case Study in the Maldivian Coral Reef. In Image Analysis and Processing - ICIAP 2023 Workshops Udine, Italy, September 11–15, 2023, Proceedings, Part I (pp.442-453). Springer Science and Business Media Deutschland GmbH [10.1007/978-3-031-51023-6_37].
Automatic Alignment of Multi-scale Aerial and Underwater Photogrammetric Point Clouds: A Case Study in the Maldivian Coral Reef
Di Lauro F.
;Fallati L.;Fontana S.;Savini A.;Sorrenti D. G.
2024
Abstract
The research question that the paper investigates is whether the usage of state of the art algorithms for point clouds registration solves the problem of multi-scale vision-based point clouds registration in mixed aerial and underwater environments. This paper reports very preliminary results on the data we have been able to procure, in the context of a coral reef restoration project nearby Magoodhoo Island (Maldives). The results obtained by exploiting state of the art algorithms are promising, considering that those data presents hard samples, in particular for their multi-scale nature (noise in captured 3D points increases with depth). However, further investigation on larger data-sets is needed to confirm the overall applicability of the current algorithms to this problem.File | Dimensione | Formato | |
---|---|---|---|
Di Lauro-2024-ICIAP 2023-VoR.pdf
Solo gestori archivio
Tipologia di allegato:
Publisher’s Version (Version of Record, VoR)
Licenza:
Tutti i diritti riservati
Dimensione
7.62 MB
Formato
Adobe PDF
|
7.62 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.