Deep-learning Optical Flow Outperforms PIV in Obtaining Velocity Fields from Active Nematics
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909183591317504 |
|---|---|
| author | Tran, Phu N. Ray, Sattvic Lemma, Linnea Li, Yunrui Sweeney, Reef Baskaran, Aparna Dogic, Zvonimir Hong, Pengyu Hagan, Michael F. |
| author_facet | Tran, Phu N. Ray, Sattvic Lemma, Linnea Li, Yunrui Sweeney, Reef Baskaran, Aparna Dogic, Zvonimir Hong, Pengyu Hagan, Michael F. |
| contents | Deep learning-based optical flow (DLOF) extracts features in adjacent video frames with deep convolutional neural networks. It uses those features to estimate the inter-frame motions of objects at the pixel level. In this article, we evaluate the ability of optical flow to quantify the spontaneous flows of MT-based active nematics under different labeling conditions. We compare DLOF against the commonly used technique, particle imaging velocimetry (PIV). We obtain flow velocity ground truths either by performing semi-automated particle tracking on samples with sparsely labeled filaments, or from passive tracer beads. We find that DLOF produces significantly more accurate velocity fields than PIV for densely labeled samples. We show that the breakdown of PIV arises because the algorithm cannot reliably distinguish contrast variations at high densities, particularly in directions parallel to the nematic director. DLOF overcomes this limitation. For sparsely labeled samples, DLOF and PIV produce results with similar accuracy, but DLOF gives higher-resolution fields. Our work establishes DLOF as a versatile tool for measuring fluid flows in a broad class of active, soft, and biophysical systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_15497 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Deep-learning Optical Flow Outperforms PIV in Obtaining Velocity Fields from Active Nematics Tran, Phu N. Ray, Sattvic Lemma, Linnea Li, Yunrui Sweeney, Reef Baskaran, Aparna Dogic, Zvonimir Hong, Pengyu Hagan, Michael F. Soft Condensed Matter Machine Learning Deep learning-based optical flow (DLOF) extracts features in adjacent video frames with deep convolutional neural networks. It uses those features to estimate the inter-frame motions of objects at the pixel level. In this article, we evaluate the ability of optical flow to quantify the spontaneous flows of MT-based active nematics under different labeling conditions. We compare DLOF against the commonly used technique, particle imaging velocimetry (PIV). We obtain flow velocity ground truths either by performing semi-automated particle tracking on samples with sparsely labeled filaments, or from passive tracer beads. We find that DLOF produces significantly more accurate velocity fields than PIV for densely labeled samples. We show that the breakdown of PIV arises because the algorithm cannot reliably distinguish contrast variations at high densities, particularly in directions parallel to the nematic director. DLOF overcomes this limitation. For sparsely labeled samples, DLOF and PIV produce results with similar accuracy, but DLOF gives higher-resolution fields. Our work establishes DLOF as a versatile tool for measuring fluid flows in a broad class of active, soft, and biophysical systems. |
| title | Deep-learning Optical Flow Outperforms PIV in Obtaining Velocity Fields from Active Nematics |
| topic | Soft Condensed Matter Machine Learning |
| url | https://arxiv.org/abs/2404.15497 |