Deep learning approach for flow visualization in background-oriented schlieren
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916979056574464 |
|---|---|
| author | Ram, Viren S. de Rubeis, Tullio Ambrosini, Dario Gannavarpu, Rajshekhar |
| author_facet | Ram, Viren S. de Rubeis, Tullio Ambrosini, Dario Gannavarpu, Rajshekhar |
| contents | Diffractive optical element based background oriented schlieren (BOS) is a popular technique for quantitative flow visualization. This technique relies on encoding spatial density variations of the test medium in the form of an optical fringe pattern; and hence, its accuracy is directly influenced by the quality of fringe pattern demodulation. We introduce a robust deep learning assisted subspace method which enables reliable fringe pattern demodulation even in the presence of severe noise and uneven fringe distortions in recorded BOS fringe patterns. The method's effectiveness to handle fringe pattern artifacts is demonstrated via rigorous numerical simulations. Furthermore, the method's practical applicability is experimentally validated using real-world BOS images obtained from a liquid diffusion process. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_25201 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Deep learning approach for flow visualization in background-oriented schlieren Ram, Viren S. de Rubeis, Tullio Ambrosini, Dario Gannavarpu, Rajshekhar Image and Video Processing Diffractive optical element based background oriented schlieren (BOS) is a popular technique for quantitative flow visualization. This technique relies on encoding spatial density variations of the test medium in the form of an optical fringe pattern; and hence, its accuracy is directly influenced by the quality of fringe pattern demodulation. We introduce a robust deep learning assisted subspace method which enables reliable fringe pattern demodulation even in the presence of severe noise and uneven fringe distortions in recorded BOS fringe patterns. The method's effectiveness to handle fringe pattern artifacts is demonstrated via rigorous numerical simulations. Furthermore, the method's practical applicability is experimentally validated using real-world BOS images obtained from a liquid diffusion process. |
| title | Deep learning approach for flow visualization in background-oriented schlieren |
| topic | Image and Video Processing |
| url | https://arxiv.org/abs/2509.25201 |