Practical object and flow structure segmentation using artificial intelligence
Experiments in Fluids · 2024-08 · 65 (8)
DOI: 10.1007/s00348-024-03852-7 ↗Kurz gefasst
Fachartikel in der Zeitschrift Experiments in Fluids, online erschienen am 30.07.2024. Verfasst von Ali R. Khojasteh und 2 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This paper explores integrating artificial intelligence (AI) segmentation models, particularly the Segment Anything Model (SAM), into fluid mechanics experiments. SAM’s architecture, comprising an image encoder, prompt encoder, and mask decoder, is investigated for its application in detecting and segmenting objects and flow structures. Additionally, we explore the integration of natural language prompts, such as BERT, to enhance SAM’s performance in segmenting specific objects. Through case studies, we found that SAM is robust in object detection in fluid experiments. However, segmentations related to flow properties, such as scalar turbulence and bubbly flows, require fine-tuning. To facilitate the application, we have established a repository ( https://github.com/AliRKhojasteh/Flow_segmentation ) where models and usage examples can be accessed.
Zitieren
APA
Khojasteh, A. R., Water, W. V. D., & Westerweel, J. (2024). Practical object and flow structure segmentation using artificial intelligence. Experiments in Fluids, 65(8). https://doi.org/10.1007/s00348-024-03852-7
Vancouver
Khojasteh AR, Water WVD, Westerweel J. Practical object and flow structure segmentation using artificial intelligence. Experiments in Fluids. 2024;65(8). doi:10.1007/s00348-024-03852-7
BibTeX
@article{Khojasteh2024,
author = {Khojasteh, Ali R. and Water, Willem van de and Westerweel, Jerry},
title = {Practical object and flow structure segmentation using artificial intelligence},
journal = {Experiments in Fluids},
year = {2024},
volume = {65},
number = {8},
doi = {10.1007/s00348-024-03852-7}
}
EUVIMED