The precise estimation of scale in Structure from Motion (SfM) pipelines holds paramount significance for robotic systems, influencing their navigational capabilities, object manipulation, and decision-making processes. This paper presents an innovative prior-knowledge approach designed to address the challenge of scale ambiguity in monocular robots by strategically utilizing beacons positioned at known locations within the environment. Our methodology integrates well-established optimization techniques into a highly modular pipeline, offering adaptability to a spectrum of use cases and requirements. To validate the effectiveness of our approach, we conducted benchmarking experiments utilizing synthetic data (ICL-NUIM) and simulated data. The evaluation of our method on the ICL-NUIM dataset underscores its capability to correct the scale drift with comparable accuracy. The results highlight the potential of our approach to serve as a robust system across diverse scenarios, showcasing its viability for implementation in real-world applications.
Robust Scale Estimation System for Monocular Mobile Robots Using Beacon-Based Structure from Motion / Iacobelli, E.; Ospizio, L.; Tassone, F. R.; Starczewski, J.; Napoli, C.. - 15165:(2025), pp. 270-284. ( 23rd International Conference on Artificial Intelligence and Soft Computing, ICAISC 2024 Zakopane; pol ) [10.1007/978-3-031-84356-3_22].
Robust Scale Estimation System for Monocular Mobile Robots Using Beacon-Based Structure from Motion
Iacobelli E.Primo
Investigation
;Napoli C.
Ultimo
Supervision
2025
Abstract
The precise estimation of scale in Structure from Motion (SfM) pipelines holds paramount significance for robotic systems, influencing their navigational capabilities, object manipulation, and decision-making processes. This paper presents an innovative prior-knowledge approach designed to address the challenge of scale ambiguity in monocular robots by strategically utilizing beacons positioned at known locations within the environment. Our methodology integrates well-established optimization techniques into a highly modular pipeline, offering adaptability to a spectrum of use cases and requirements. To validate the effectiveness of our approach, we conducted benchmarking experiments utilizing synthetic data (ICL-NUIM) and simulated data. The evaluation of our method on the ICL-NUIM dataset underscores its capability to correct the scale drift with comparable accuracy. The results highlight the potential of our approach to serve as a robust system across diverse scenarios, showcasing its viability for implementation in real-world applications.| File | Dimensione | Formato | |
|---|---|---|---|
|
Iacobelli_Robust-Scale_2025.pdf
solo gestori archivio
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
1.26 MB
Formato
Adobe PDF
|
1.26 MB | Adobe PDF | Contatta l'autore |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.


