Abstract
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.
Similar content being viewed by others
References
Adrian RJ, Westerweel J (2011) Particle image velocimetry. Cambridge University Press, Cambridge
Astarita T (2007) Analysis of weighting windows for image deformation methods in PIV. Exp Fluids 43(6):859–872
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):80–97
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 2758–2766
Eckstein A, Vlachos PP (2009) Assessment of advanced windowing techniques for digital particle image velocimetry (DPIV). Meas Sci Technol 20(7):075,402
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. http://ieeexplore.ieee.org/document/7780828/
Goodfellow I, Bengio Y, Courville A (2016) Deep learning, http://www.deeplearningbook.org, book in preparation for MIT Press
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):159–166
Grant I, Pan XJ (1997) The use of neural techniques in PIV and PTV. Meas Sci Technol 8(12):1399–1405
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):3656–3663
Hart DP (2000) PIV error correction. Exp Fluids 29(1):13–22
He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition. CoRR abs/1512.03385, http://arxiv.org/abs/1512.03385
Kimura I, Susaki Y, Kiyohara R, Kaga A, Kuroe Y (2002) Gradient-based PIV using neural networks. J Vis 5(4):363–370
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks pp 1097–1105
Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324
Lecun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444
Liang D, Jiang C, Li Y (2003) Cellular neural network to detect spurious vectors in PIV data. Exp Fluids 34(1):52–62
Lin M, Chen Q, Yan S (2013) Network in network. CoRR abs/1312.4400, URL http://arxiv.org/abs/1312.4400
Luo W, Schwing AG, Urtasun R (2016) Efficient deep learning for stereo matching pp 5695–5703
Miao S, Wang ZJ, Liao R (2016) A cnn regression approach for real-time 2d/3d registration. IEEE Trans Med Imaging 35(5):1352–1363
Okamoto K, Nishio S, Saga T, Kobayashi T (2000) Standard images for particle-image velocimetry. Meas Sci Technol 11(6):685
Raffel M, Willert C, Wereley S, Kompenhans J (2007) Particle image velocimetry: a practical guide. Springer, Berlin
Scarano F (2001) Iterative image deformation methods in PIV. Meas Sci Technol 13(1):R1
Scarano F (2003) Theory of non-isotropic spatial resolution in PIV. Exp Fluids 35(3):268–277
Schrijer F, Scarano F (2008) Effect of predictor-corrector filtering on the stability and spatial resolution of iterative PIV interrogation. Exp fluids 45(5):927–941
Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. International conference on learning representations. https://arxiv.org/abs/1409.1556
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 3476–3483
Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2015) Rethinking the inception architecture for computer vision pp 2818–2826
Thielicke W, Stamhuis E (2014) PIVlab-towards user-friendly, affordable and accurate digital particle image velocimetry in MATLAB. J Open Res Soft 2(1). https://openresearchsoftware.metajnl.com/articles/10.5334/jors.bl/
Vedaldi A, Lenc K (2015) Matconvnet – convolutional neural networks for matlab. In: Proceeding of the ACM Int. Conf. on Multimedia
Wereley ST, Meinhart CD (2001) Second-order accurate particle image velocimetry. Exp Fluids 31(3):258–268
Westerweel J, Scarano F (2005) Universal outlier detection for PIV data. Exp Fluids 39(6):1096–1100
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):20–28
Willert CE, Gharib M (1997) The interaction of spatially modulated vortex pairs with free surfaces. J Fluid Mech 345:227–250
Zagoruyko S, Komodakis N (2015) Learning to compare image patches via convolutional neural networks pp 4353–4361
Zbontar J, Lecun Y (2015) Computing the stereo matching cost with a convolutional neural network pp 1592–1599
Zbontar J, Lecun Y (2016) Stereo matching by training a convolutional neural network to compare image patches. J Mach Learning Res 17(65):2287–2318
Zhao L, Jia K (2015) Deep adaptive log-demons: diffeomorphic image registration with very large deformations. Comput Math Methods Med 836(202–836):202
Acknowledgements
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).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Lee, Y., Yang, H. & Yin, Z. PIV-DCNN: cascaded deep convolutional neural networks for particle image velocimetry. Exp Fluids 58, 171 (2017). https://doi.org/10.1007/s00348-017-2456-1
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s00348-017-2456-1