Experiments in Fluids

, 58:171 | Cite as

PIV-DCNN: cascaded deep convolutional neural networks for particle image velocimetry

  • Yong Lee
  • Hua Yang
  • Zhouping Yin
Research Article


Velocity estimation (extracting the displacement vector information) from the particle image pairs is of critical importance for particle image velocimetry. This problem is mostly transformed into finding the sub-pixel peak in a correlation map. To address the original displacement extraction problem, we propose a different evaluation scheme (PIV-DCNN) with four-level regression deep convolutional neural networks. At each level, the networks are trained to predict a vector from two input image patches. The low-level network is skilled at large displacement estimation and the high- level networks are devoted to improving the accuracy. Outlier replacement and symmetric window offset operation glue the well- functioning networks in a cascaded manner. Through comparison with the standard PIV methods (one-pass cross-correlation method, three-pass window deformation), the practicability of the proposed PIV-DCNN is verified by the application to a diversity of synthetic and experimental PIV images.



We would like to thank all the professional editor and reviewers for the substantial effort and expertise that contribute to this work. This work was supported by National Natural Science Foundation of China (Grant Nos. 51327801 and 51475193) and the Major Project Foundation of Hubei Province (Grant No. 2016AAA009).


  1. Adrian RJ, Westerweel J (2011) Particle image velocimetry. Cambridge University Press, CambridgeMATHGoogle Scholar
  2. Astarita T (2007) Analysis of weighting windows for image deformation methods in PIV. Exp Fluids 43(6):859–872CrossRefGoogle Scholar
  3. Corpetti T, Heitz D, Arroyo G, Memin E, Santa-Cruz A (2006) Fluid experimental flow estimation based on an optical-flow scheme. Exp fluids 40(1):80–97CrossRefGoogle Scholar
  4. Dosovitskiy A, Fischer P, Ilg E, Hausser P, Hazirbas C, Golkov V, van der Smagt P, Cremers D, Brox T (2015) Flownet: Learning optical flow with convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp 2758–2766Google Scholar
  5. Eckstein A, Vlachos PP (2009) Assessment of advanced windowing techniques for digital particle image velocimetry (DPIV). Meas Sci Technol 20(7):075,402CrossRefGoogle Scholar
  6. Gadot D, Wolf L (2016) Patchbatch: a batch augmented loss for optical flow. Computer Vision and Pattern Recognition (CVPR), 2016 IEEE Conference on 4236–4245.
  7. Goodfellow I, Bengio Y, Courville A (2016) Deep learning,, book in preparation for MIT Press
  8. Grant I, Pan X (1995) An investigation of the performance of multi layer, neural networks applied to the analysis of PIV images. Exp Fluids 19(3):159–166CrossRefGoogle Scholar
  9. Grant I, Pan XJ (1997) The use of neural techniques in PIV and PTV. Meas Sci Technol 8(12):1399–1405CrossRefGoogle Scholar
  10. Grant I, Pan XJ, Romano F, Wang X (1998) Neural-network method applied to the stereo image correspondence problem in three-component particle image velocimetry. Appl Optics 37(17):3656–3663CrossRefGoogle Scholar
  11. Hart DP (2000) PIV error correction. Exp Fluids 29(1):13–22CrossRefGoogle Scholar
  12. He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition. CoRR abs/1512.03385,
  13. Kimura I, Susaki Y, Kiyohara R, Kaga A, Kuroe Y (2002) Gradient-based PIV using neural networks. J Vis 5(4):363–370CrossRefGoogle Scholar
  14. Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks pp 1097–1105Google Scholar
  15. Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324CrossRefGoogle Scholar
  16. Lecun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444CrossRefGoogle Scholar
  17. Liang D, Jiang C, Li Y (2003) Cellular neural network to detect spurious vectors in PIV data. Exp Fluids 34(1):52–62CrossRefGoogle Scholar
  18. Lin M, Chen Q, Yan S (2013) Network in network. CoRR abs/1312.4400, URL Scholar
  19. Luo W, Schwing AG, Urtasun R (2016) Efficient deep learning for stereo matching pp 5695–5703Google Scholar
  20. Miao S, Wang ZJ, Liao R (2016) A cnn regression approach for real-time 2d/3d registration. IEEE Trans Med Imaging 35(5):1352–1363CrossRefGoogle Scholar
  21. Okamoto K, Nishio S, Saga T, Kobayashi T (2000) Standard images for particle-image velocimetry. Meas Sci Technol 11(6):685CrossRefGoogle Scholar
  22. Raffel M, Willert C, Wereley S, Kompenhans J (2007) Particle image velocimetry: a practical guide. Springer, BerlinGoogle Scholar
  23. Scarano F (2001) Iterative image deformation methods in PIV. Meas Sci Technol 13(1):R1CrossRefGoogle Scholar
  24. Scarano F (2003) Theory of non-isotropic spatial resolution in PIV. Exp Fluids 35(3):268–277CrossRefGoogle Scholar
  25. Schrijer F, Scarano F (2008) Effect of predictor-corrector filtering on the stability and spatial resolution of iterative PIV interrogation. Exp fluids 45(5):927–941CrossRefGoogle Scholar
  26. Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. International conference on learning representations.
  27. Sun Y, Wang X, Tang X (2013) Deep convolutional network cascade for facial point detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 3476–3483Google Scholar
  28. Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2015) Rethinking the inception architecture for computer vision pp 2818–2826Google Scholar
  29. Thielicke W, Stamhuis E (2014) PIVlab-towards user-friendly, affordable and accurate digital particle image velocimetry in MATLAB. J Open Res Soft 2(1).
  30. Vedaldi A, Lenc K (2015) Matconvnet – convolutional neural networks for matlab. In: Proceeding of the ACM Int. Conf. on MultimediaGoogle Scholar
  31. Wereley ST, Meinhart CD (2001) Second-order accurate particle image velocimetry. Exp Fluids 31(3):258–268CrossRefGoogle Scholar
  32. Westerweel J, Scarano F (2005) Universal outlier detection for PIV data. Exp Fluids 39(6):1096–1100CrossRefGoogle Scholar
  33. Westerweel J, Dabiri D, Gharib M (1997) The effect of a discrete window offset on the accuracy of cross-correlation analysis of digital PIV recordings. Exp fluids 23(1):20–28CrossRefGoogle Scholar
  34. Willert CE, Gharib M (1997) The interaction of spatially modulated vortex pairs with free surfaces. J Fluid Mech 345:227–250MathSciNetCrossRefGoogle Scholar
  35. Zagoruyko S, Komodakis N (2015) Learning to compare image patches via convolutional neural networks pp 4353–4361Google Scholar
  36. Zbontar J, Lecun Y (2015) Computing the stereo matching cost with a convolutional neural network pp 1592–1599Google Scholar
  37. Zbontar J, Lecun Y (2016) Stereo matching by training a convolutional neural network to compare image patches. J Mach Learning Res 17(65):2287–2318MATHGoogle Scholar
  38. Zhao L, Jia K (2015) Deep adaptive log-demons: diffeomorphic image registration with very large deformations. Comput Math Methods Med 836(202–836):202Google Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2017

Authors and Affiliations

  1. 1.State Key Laboratory of Digital Manufacturing Equipment and TechnologyHuazhong University of Science and TechnologyWuhanChina

Personalised recommendations