Deep-learning optical flow for measuring velocity fields from experimental data

Journal Article · 18 September 2024 · Soft Matter

DOI: https://doi.org/10.1039/D4SM00483C · OSTI ID:2439304

Tran, Phu N.  ^[1]; Ray, Sattvic ^[2]; Lemma, Linnea ^[3]; Li, Yunrui  ^[4]; Sweeney, Reef ^[2]; Baskaran, Aparna  ^[1]; Dogic, Zvonimir  ^[5]; Hong, Pengyu  ^[4]; Hagan, Michael F.  ^[1]

---

1. Department of Physics, Brandeis University, Waltham, MA 02453, USA
2. Department of Physics, University of California at Santa Barbara, Santa Barbara, CA 93106, USA
3. Department of Physics, Brandeis University, Waltham, MA 02453, USA, Department of Physics, University of California at Santa Barbara, Santa Barbara, CA 93106, USA
4. Department of Computer Science, Brandeis University, Waltham, MA 02453, USA
5. Department of Physics, Brandeis University, Waltham, MA 02453, USA, Department of Physics, University of California at Santa Barbara, Santa Barbara, CA 93106, USA, Biomolecular and Engineering Science, University of California at Santa Barbara, Santa Barbara, CA 93106, USA

Deep learning-based optical flow (DLOF) extracts features in video frames with deep convolutional neural networks to estimate the inter-frame motions of objects. DLOF computes velocity fields more accurately than PIV for densely labeled systems.

• Research Organization: Brandeis University, Waltham, MA (United States)
• Sponsoring Organization: National Science Foundation (NSF); USDOE
• Grant/Contract Number: SC0022291
• OSTI ID: 2439304
• Journal Information: Soft Matter, Journal Name: Soft Matter Journal Issue: 36 Vol. 20; ISSN SMOABF; ISSN 1744-683X
• Publisher: Royal Society of Chemistry (RSC)Copyright Statement
• Country of Publication: United Kingdom
• Language: English