Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2509.14442 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918143336644608 |
|---|---|
| author | Teh, Arjun Ali, Wael H. Rapp, Joshua Mansour, Hassan |
| author_facet | Teh, Arjun Ali, Wael H. Rapp, Joshua Mansour, Hassan |
| contents | We develop a framework for non-invasive volumetric indoor airflow estimation from a single viewpoint using background-oriented schlieren (BOS) measurements and physics-informed reconstruction. Our framework utilizes a light projector that projects a pattern onto a target back-wall and a camera that observes small distortions in the light pattern. While the single-view BOS tomography problem is severely ill-posed, our proposed framework addresses this using: (1) improved ray tracing, (2) a physics-based light rendering approach and loss formulation, and (3) a physics-based regularization using a physics-informed neural network (PINN) to ensure that the reconstructed airflow is consistent with the governing equations for buoyancy-driven flows. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_14442 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Indoor Airflow Imaging Using Physics-Informed Background-Oriented Schlieren Tomography Teh, Arjun Ali, Wael H. Rapp, Joshua Mansour, Hassan Signal Processing Machine Learning We develop a framework for non-invasive volumetric indoor airflow estimation from a single viewpoint using background-oriented schlieren (BOS) measurements and physics-informed reconstruction. Our framework utilizes a light projector that projects a pattern onto a target back-wall and a camera that observes small distortions in the light pattern. While the single-view BOS tomography problem is severely ill-posed, our proposed framework addresses this using: (1) improved ray tracing, (2) a physics-based light rendering approach and loss formulation, and (3) a physics-based regularization using a physics-informed neural network (PINN) to ensure that the reconstructed airflow is consistent with the governing equations for buoyancy-driven flows. |
| title | Indoor Airflow Imaging Using Physics-Informed Background-Oriented Schlieren Tomography |
| topic | Signal Processing Machine Learning |
| url | https://arxiv.org/abs/2509.14442 |