Abstract
Vortex identification methods have been extensively studied in recent years due to their importance in understanding the potential physical mechanism of the flow field. Although demonstrating great success in various scenarios, these methods cannot achieve a compromise between computational speed and accuracy, which restricts their usage in large-scale applications. In specific, local methods provide results rapidly with pool accuracies. By contrast, global methods can obtain reliable results by consuming much more time. To take the advantages of both local and global methods, several methods based on convolutional neural networks are proposed. These methods use local patches around each point and the labels obtained by global methods to train the network. They convert the vortex identification tasks into binary classification problems. In this manner, these methods detect vortices rapidly and robustly. By revisiting these methods, we observe two drawbacks that limit their performance: (i) the large number of parameters and (ii) high computational complexity. To address these issues, we provide a rapid vortex identification method by using a fully convolutional segmentation network in this work. Specifically, we discard the fully connected layers to decrease the number of parameters and design a segmentation network to reduce computational complexity. Intensive experimental results show that the accuracy and recall performance of our method are comparable with those of the global methods. Moreover, the time consumption of our method is less than that of all other methods.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Jeong, J., Hussain, F.: On the identification of a vortex. J. Fluid Mech. 285(1), 69–94 (1995). https://doi.org/10.1017/S0022112095000462
Hunt, J.C.R.: Vorticity and vortex dynamics in complex turbulent flows. Trans. Can. Soc. Mech. Eng. 11(1), 21–35 (1987). https://doi.org/10.1139/tcsme-1987-0004
Chong, M.S., Perry, A.E., Cantwell, B.J.: A general classification of three-dimensional flow fields. Phys. Fluids A 2(5), 765–777 (1990). https://doi.org/10.1063/1.857730
Schafhitzel, T., Vollrath, J., Gois, J., Weiskopf, D., Castelo, A., Ertl, T.: Topology preserving \(\lambda _2\)-based vortex core line detection for flow visualization. Comput. Graph. Forum 27, 1023–1030 (2008). https://doi.org/10.1111/j.1467-8659.2008.01238
Liu, C.Q., Wang, Y.Q., Yang, Y., Duan, Z.W.: New omega vortex identification method. Sci. China Phys. Mech. Astron. 59(8), 684–711 (2016). https://doi.org/10.1007/s11433-016-0022-6
Sadarjoen, A., Post, F.H., Ma, B., Banks, D.C., Pagendarm, H.G.: Selective visualization of vortices in hydrodynamic flows. In: Proceedings of the Visualization, pp. 419–422. IEEE Computer Society, Los Alamitos (2002)
Haller, G., Hadjighasem, A., Farazmand, M., Huhn, F.: Defining coherent vortices objectively from the vorticity. J. Fluid Mech. 795(7), 136–173 (2015). https://doi.org/10.1017/jfm.2016.151
Serra, M., Haller, G.: Objective eulerian coherent structures. Chaos Interdiscipl. J. Nonlinear Sci. 26(5), 95–105 (2016). https://doi.org/10.1063/1.4951720
Simard, P.Y., Steinkraus, D., Platt, J.C.: Best practices for convolutional neural networks applied to visual document analysis. In: International Conference on Document Analysis and Recognition, pp. 958–963. IEEE Computer Society, Los Alamitos (2003). https://doi.org/10.1109/ICDAR.2003.1227801
Zhang, L., Deng, Q., Machiraju, R., Rangarajan, A., Thompson, D., Walters, D.K., Shen, H.: Boosting techniques for physics-based vortex detection. Comput. Graph. Forum 33, 1–12 (2014). https://doi.org/10.1111/cgf.12275
Biswas, A., Thompson, D., He, W., Deng, Q., Chen, C.-M., Shen, H.-W., Machiraju, R., Rangarajan, A.: An uncertainty-driven approach to vortex analysis using oracle consensus and spatial proximity. In: IEEE Pacific Visualization Symposium, pp. 1–8. IEEE Computer Society, Los Alamitos (2015). https://doi.org/10.1109/PACIFICVIS.2015.715638
Liang, D., Yueqing, W., Yang, L., Fang, W., Sikun, L., Jie, L.: A CNN-based vortex identification method. J. Vis. (2018). https://doi.org/10.1007/s12650-018-0523-1
Lguensat, R., Sun, M., Fablet, R., Mason, E., Tandeo, P., Chen, G.: Eddynet: a deep neural network for pixel-wise classification of oceanic eddies. Comput. Vis. Pattern Recognit. (2017)
Ströfer, C.M., Wu, J., Xiao, H., Paterson, E.: Data-driven, physics-based feature extraction from fluid flow fields. Fluid Dyn. (2018)
Franz, K., Roscher, R., Milioto, A., Wenzel, S., Kusche, J.: Ocean eddy identification and tracking using neural networks. In: IGARSS 2018-2018 IEEE International Geoscience and Remote Sensing Symposium, IEEE, pp. 6887–6890 (2018)
Epps, B.: Review of vortex identification methods. In: 55th AIAA Aerospace Sciences Meeting, p. 0989 (2017)
Günther, T., Theiselr, H.: The state of the art in vortex extraction. Comput. Graph. Forum 1, 1–24 (2018). https://doi.org/10.1111/cgf.13319
Serra, M., Haller, G.: Efficient computation of null-geodesic with applications to coherent vortex detection. Proc. R. Soc. A: Math. Phys. Eng. Sci. 473, 1–18 (2016). https://doi.org/10.1098/rspa.2016.0807
Bin, T., Yi, L.: CNN-based flow field feature visualization method. Int. J. Perform. Eng. 14(3), 434 (2018)
Rajendran, V., Kelly, K.Y., Leonardi, E., Menzies, K.: Vortex detection on unsteady CFD simulations using recurrent neural networks. In: 2018 Fluid Dynamics Conference, p. 3724 (2018)
Lguensat, R., Sun, M., Fablet, R., Tandeo, P., Mason, E., Chen, G.: EddyNet: A deep neural network for pixel-wise classification of oceanic eddies. In: IGARSS 2018-2018 IEEE International Geoscience and Remote Sensing Symposium, IEEE, pp. 1764–1767 (2018)
Ströfer, C.M., Wu, J.-L., Xiao, H., Paterson, E.: Data-driven, physics-based feature extraction from fluid flow fields using convolutional neural networks. Commun. Comput. Phys. 25, 625–650 (2019)
Kim, B., Günther, T.: Robust reference frame extraction from unsteady 2d vector fields with convolutional neural networks. arXiv preprint arXiv:1903.10255
Ali, A., Sinan, K., Yusuf, S.: Deep 3d semantic scene extrapolation. Vis. Comput. 35(2), 271–279 (2019). https://doi.org/10.1007/s00371-018-1586-7
Xu, X., Liu, C., Zheng, Y.: 3d tooth segmentation and labeling using deep convolutional neural networks. IEEE Trans. Vis. Comput. Graph. (TVCG) 25(7), 2336–2348 (2019)
Zhenyu, S., Shiqing, X., Xin, X., Ligang, L., Ladislav, K.: Detecting 3d points of interest using multiple features and stacked auto-encoder. IEEE Trans. Vis. Comput. Graph. (TVCG) 25(7), 2583–2596 (2019)
Shixia, L., Jiannan, X., Junlin, L., Xiting, W., Jing, W., Jun, Z.: Visual diagnosis of tree boosting methods. IEEE Trans. Vis. Comput. Graph. (TVCG) 24(1), 163–173 (2018)
Ho, T.K.: Random decision forest. In: Proceedings of the 3rd International Conference on Document Analysis and Recognition, pp. 278–282 (1995)
Freund, Y., Schapire, R.E.: A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci. 55(1), 119–139 (1997). https://doi.org/10.1006/jcss.1997.1504
Acknowledgements
This work was supported by the National Natural Science Foundation of China (61806205).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Wang, Y., Deng, L., Yang, Z. et al. A rapid vortex identification method using fully convolutional segmentation network. Vis Comput 37, 261–273 (2021). https://doi.org/10.1007/s00371-020-01797-6
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-020-01797-6