Advertisement

Three-dimensional particle tracking velocimetry using shallow neural network for real-time analysis

  • 101 Accesses

Abstract

Three-dimensional particle tracking velocimetry (3D-PTV) technique is widely used to acquire the complicated trajectories of particles and flow fields. It is known that the accuracy of 3D-PTV depends on the mapping function to reconstruct three-dimensional particles locations. The mapping function becomes more complicated if the number of cameras is increased and there is a liquid–vapor interface, which crucially affect the total computation time. In this paper, using a shallow neural network model, we dramatically decrease the computation time with a high accuracy to successfully reconstruct the three-dimensional particle positions, which can be used for real-time particle detection for 3D-PTV. The developed technique is verified by numerical simulations and applied to measure a complex solutal Marangoni flow patterns inside a binary mixture droplet.

Graphic abstract

This is a preview of subscription content, log in to check access.

Access options

Buy single article

Instant unlimited access to the full article PDF.

US$ 39.95

Price includes VAT for USA

Subscribe to journal

Immediate online access to all issues from 2019. Subscription will auto renew annually.

US$ 199

This is the net price. Taxes to be calculated in checkout.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

References

  1. Adrian RJ, Westerweel J (2011) Particle image velocimetry. Cambridge University Press, Cambridge

  2. Cai S, Zhou S, Xu C, Gao Q (2019a) Dense motion estimation of particle images via a convolutional neural network. Exp Fluids 60(4):73

  3. Cai S, Liang J, Gao Q, Xu C, Wei R (2019b) Particle image velocimetry based on a deep learning motion estimator. IEEE Trans Instrum Meas. https://doi.org/10.1109/TIM.2019.2932649

  4. Chen C, Kim YJ, Ko HS (2011) Three-dimensional tomographic reconstruction of unstable ejection phenomena of droplets for electrohydrodynamic jet. Exp Therm Fluid Sci 35(3):433–441

  5. Christy JR, Hamamoto Y, Sefiane K (2011) Flow transition within an evaporating binary mixture sessile drop. Phys Rev Lett 106(20):205701

  6. de Dios M, Bombardelli FA, García CM, Liscia SO, Lopardo RA, Parravicini JA (2017) Experimental characterization of three-dimensional flow vortical structures in submerged hydraulic jumps. J Hydro-environ Res 15:1–12

  7. Gavin H (2011) The Levenberg-Marquardt method for nonlinear least squares curve-fitting problems. Department of Civil and Environmental Engineering, Duke University, Durham

  8. Géron A (2017) Hands-on machine learning with Scikit-Learn and TensorFlow: concepts, tools, and techniques to build intelligent systems. O’Reilly Media, Inc, Newton

  9. Gim Y, Ko HS (2016) Development of a three-dimensional correction method for optical distortion of flow field inside a liquid droplet. Opt Lett 41(8):1801–1804

  10. Gim Y, Shin DH, Ko HS (2017) Development of limited-view and three-dimensional reconstruction method for analysis of electrohydrodynamic jetting behavior. Opt Express 25(8):9244–9251

  11. Horstmann GM, Schiepel D, Wagner C (2018) Experimental study of the global flow-state transformation in a rectangular Rayleigh-Benard sample. Int J Heat Mass Transf 126:1333–1346

  12. Kang KH, Lee SJ, Lee CM, Kang IS (2004) Quantitative visualization of flow inside an evaporating droplet using the ray tracing method. Meas Sci Technol 15(6):1104

  13. Kim H, Stone HA (2018) Direct measurement of selective evaporation of binary mixture droplets by dissolving materials. J Fluid Mech 850:769–783

  14. Kim H, Große S, Elsinga GE, Westerweel J (2011) Full 3D-3C velocity measurement inside a liquid immersion droplet. Exp Fluids 51(2):395–405

  15. Kim H, Boulogne F, Um E, Jacobi I, Button E, Stone HA (2016) Controlled uniform coating from the interplay of Marangoni flows and surface-adsorbed macromolecules. Phys Rev Lett 116(12):124501

  16. Leonarda C, Vitoantonio B, Lucia C, Giuseppe M (2009) Retinal vessel extraction by a combined neural network–wavelet enhancement method. In: International conference on intelligent computing. Springer, Berlin

  17. Martins FJ, Foucaut JM, Thomas L, Azevedo LF, Stanislas M (2015) Volume reconstruction optimization for tomo-PIV algorithms applied to experimental data. Meas Sci Technol 26(8):085202

  18. Minor G, Djilali N, Sinton D, Oshkai P (2009) Flow within a water droplet subjected to an air stream in a hydrophobic microchannel. Fluid Dyn Res 41(4):045506

  19. Nguyen XH, Lee SH, Ko HS (2012) Comparative study on basis functions for projection matrix of three-dimensional tomographic reconstruction for analysis of droplet behavior from electrohydrodynamic jet. Appl Opt 51(24):5834–5844

  20. Nguyen XH, Lee SH, Ko HS (2013) Analysis of electrohydrodynamic jetting behaviors using three-dimensional shadowgraphic tomography. Appl Opt 52(19):4494–4504

  21. Nicolas F, Todoroff V, Plyer A, Le Besnerais G, Donjat D, Micheli F, Champagnat F, Cornic P, Le Sant Y (2016) A direct approach for instantaneous 3D density field reconstruction from background-oriented schlieren (BOS) measurements. Exp Fluids 57(1):13

  22. Ohmi K, Joshi B, Panday SP (2009) A SOM based stereo pair matching algorithm for 3-D particle tracking velocimetry. In: International conference on intelligent computing. Springer, Berlin, pp 11–20

  23. Panday SP (2016) Stereoscopic correspondence of particles for 3-dimensional particle tracking velocimetry by using genetic algorithm. J Inst Eng 12(1):10–26

  24. Rabault J, Kolaas J, Jensen A (2017) Performing particle image velocimetry using artificial neural networks: a proof-of-concept. Meas Sci Technol 28(12):125301

  25. Scarano F (2012) Tomographic PIV: principles and practice. Meas Sci Technol 24(1):012001

  26. Scharnowski S, Bross M, Kähler CJ (2019) Accurate turbulence level estimations using PIV/PTV. Exp Fluids 60(1):1

  27. Schröder A, Schanz D, Michaelis D, Cierpka C, Scharnowski S, Kähler CJ (2015) Advances of PIV and 4D-PTV” Shake-The-Box” for turbulent flow analysis–the flow over periodic hills. Flow Turbul Combust 95(2–3):193–209

  28. Soloff SM, Adrian RJ, Liu ZC (1997) Distortion compensation for generalized stereoscopic particle image velocimetry. Meas Sci Technol 8(12):1441

  29. Zhang Y, Wang Y, Yang B, He W (2015) A particle tracking velocimetry algorithm based on the Voronoi diagram. Meas Sci Technol 26(7):075302

Download references

Acknowledgements

National Research Foundation of Korea (NRF) (NRF-2019R1A2C2003176 and NRF-2018R1C1B6004190)

Author information

Correspondence to Hyoungsoo Kim or Han Seo Ko.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Gim, Y., Jang, D.K., Sohn, D.K. et al. Three-dimensional particle tracking velocimetry using shallow neural network for real-time analysis. Exp Fluids 61, 26 (2020). https://doi.org/10.1007/s00348-019-2861-8

Download citation