Signal, Image and Video Processing

, Volume 13, Issue 7, pp 1303–1310 | Cite as

Robust optical flow estimation based on wavelet

  • Jia Zheng
  • Hongyan WangEmail author
  • Bingnan Pei
Original Paper


Concentrating on the issue that the systematic error caused by variation of illumination conditions and sensor noise leads to poor robustness and low accuracy of optical flow calculation, based on the wavelet multi-resolution theory, a robust optical flow estimation method is developed in this paper. With the multi-resolution characteristics of wavelet, the systematic error is incorporated into the calculation of optical flow to improve the robustness and estimation accuracy. In what follows, the total least squares method can be exploited to solve the obtained overdetermined wavelet optical flow equations such that the optical flow vector can be achieved. As compared to the traditional Lucas–Kanade approach, Horn–Schunck method, and the optical flow estimation algorithm in omnidirectional images using wavelet approach, simulation results show that the proposed algorithm can significantly improve the accuracy of optical flow estimation and the robustness of the optical flow field.


Optical flow Wavelet multi-resolution Systematic error Total least squares (TLS) Robustness 



This work is partially supported by the National Natural Science Foundation of China under Grant 61301258 and China Postdoctoral Science Foundation Funded Project under Grant No. 2016M590218.


  1. 1.
    Horn, B.K.P., Schunck, B.G.: Determining optical flow. Artif. Intell. 17(1–3), 185–203 (1981)CrossRefGoogle Scholar
  2. 2.
    Kajo, I., Malik, A.S., Kamel, N.: Motion estimation of crowd flow using optical flow techniques: a review. In: International Conference on Signal Processing and Communication Systems, pp. 1–9. IEEE (2016)Google Scholar
  3. 3.
    Goppert, J., Yantek, S., Hwang, I.: Invariant Kalman filter application to optical flow based visual odometry for UAVs. In: Ninth International Conference on Ubiquitous and Future Networks, pp. 99–104. IEEE, Milan, Italy (2017)Google Scholar
  4. 4.
    Peng, Y., Chen, Z., Wu, Q.M.J., et al.: Traffic flow detection and statistics via improved optical flow and connected region analysis. Signal Image Video Process. 12(1), 99–105 (2018)CrossRefGoogle Scholar
  5. 5.
    Khalid, M., Penard, L., Memin, E.: Application of optical flow for river velocimetry. In: IGARSS 2017—2017 IEEE International Geoscience and Remote Sensing Symposium, pp. 6243–6246. IEEE (2017)Google Scholar
  6. 6.
    Lazcano, V., Molina, M.: Modification of the optical flow Horn–Schunck estimation incorporating exaustive search. In: Electrical, Electronics Engineering, Information and Communication Technologies, pp. 873–878. IEEE (2016)Google Scholar
  7. 7.
    Douini, Y., Riffi, J., Mahraz, A.M., et al.: An image registration algorithm based on phase correlation and the classical Lucas–Kanade technique. Signal Image Video Process. 11(11), 1–8 (2017)Google Scholar
  8. 8.
    Drulea, M., Nedevschi, S.: Total variation regularization of local–global optical flow. In: International IEEE Conference on Intelligent Transportation Systems, pp. 318–323. IEEE, Washington, DC, USA (2011)Google Scholar
  9. 9.
    Douini, Y., Riffi, J., Mahraz, M.A., et al.: Solving sub-pixel image registration problems using phase correlation and Lucas–Kanade optical flow method. In: Intelligent Systems and Computer Vision (2017)Google Scholar
  10. 10.
    Magarey, J., Kingsbury, N.: Motion estimation using a complex-valued wavelet transform. IEEE Trans. Signal Process. 46(4), 1069–1084 (2002)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Dérian, P., Almar, R.: Wavelet-based optical flow estimation of instant surface currents from shore-based and UAV videos. IEEE Trans. Geosci. Remote Sens. 55(10), 5790–5797 (2017)CrossRefGoogle Scholar
  12. 12.
    Afdhal, R., Ejbali, R., Zaied, M., et al.: Emotion recognition using features distances classified by wavelets network and trained by fast wavelets transform. In: International Conference on Hybrid Intelligent Systems, pp. 238–241. IEEE (2015)Google Scholar
  13. 13.
    Demonceaux, C., Kachi-Akkouche, D.: Optical flow estimation in omnidirectional images using wavelet approach. In: Computer Vision and Pattern Recognition Workshop, 2003. CVPRW ‘03. Conference on EEE, Madison, Wisconsin, USA, p. 76 (2003)Google Scholar
  14. 14.
    Niaz, M.T., Imdad, F., Kim, S., et al.: Total least-square-based receiver for asymmetrically clipped optical-orthogonal frequency divisional multiplexing visible light communication system. IET Optoelectron. 11(4), 129–133 (2017)CrossRefGoogle Scholar
  15. 15.
    Wu, H., Chen, S., Zhang, Y., et al.: Robust structured total least squares algorithm for passive location. J. Syst. Eng. Electron. 26(5), 946–953 (2015)CrossRefGoogle Scholar
  16. 16.
    Kukde, R., Manikandan, M.S., Panda, G.: Reduced complexity diffusion filtered x least mean square algorithm for distributed active noise cancellation. Signal Image Video Process. 5, 1–9 (2019)Google Scholar
  17. 17.
    Abatzoglou, T.J., Lam, L.K.: Direction finding using uniform arrays and the constrained total least squares method. In: Conference Record of the Twenty-Fifth Asilomar Conference on Signals, Systems & Computers, pp. 57–578. IEEE (1991)Google Scholar
  18. 18.
    Barron, J.L., Fleet, D.J., Chemin, S.S.: Performance of optical flow techniques. In: Computer Vision and Pattern Recognition, 1992. Proceedings CVPR ‘92. 1992 IEEE Computer Society Conference on, pp. 236–242. IEEE, Champaign, IL, USA (2002)Google Scholar
  19. 19.
    Cella, G.: Thermal noise correlations and subtraction. Phys. Lett. A 382(33), 2269–2274 (2018)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  1. 1.Liaoning Engineering Laboratory of BeiDou High-Precision Location ServiceDalian UniversityDalianChina
  2. 2.Dalian Key Laboratory of Environmental Perception and Intelligent ControlDalian UniversityDalianChina

Personalised recommendations