Abstract
This paper presents an underwater warp estimation approach based on generalized regression neural network (GRNN). The GRNN, with its function approximation feature, is employed for a-priori estimation of the upcoming warped frames using history of the previous frames. An optical flow technique is employed for determining the dense motion fields of the captured frames with respect to the first frame. The proposed method is independent of the pixel-oscillatory model. It also considers the interdependence of the pixels with their neighborhood. Simulation experiments demonstrate that the proposed method is capable of estimating the upcoming frames with small errors.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Hou, W.: A simple underwater imaging model. Optics Letters 34(17), 2688–2690 (2009)
Kanaev, A.V., Hou, W., Woods, S., Smith, L.N.: Restoration of turbulence degraded underwater images. Optical Engineering 51(5) (2012)
Boffety, M., Galland, F., Allais, A.-G.: Influence of polarization filtering on image registration precision in underwater conditions. Optics Letters 37(15), 3273–3275 (2012)
Wang, G., Zheng, B., Sun, F.F.: Estimation-based approach for underwater image restoration. Optics Letters 36(13), 2384–2386 (2011)
Wen, Z., Lambert, A., Fraser, D., Li, H.: Bispectral analysis and recovery of images distorted by a moving water surface. Applied Optics 49(33), 6376–6384 (2010)
Tahtali, M.: Imaging techniques through the atmosphere. The University of New South Wales (2007)
Tahtali, M., Lambert, A.J., Fraser, D.: Progressive restoration of nonuniformly warped images by shiftmap prediction using Kalman filter. In: Proc. Signal Recovery and Synthesis (2007)
Mao, Y., Gilles, J.: Non rigid geometric distortions correction-application to atmospheric turbulence stabilization. Inverse Problems and Imaging 6(3), 531–546 (2012)
Tahtali, M., Lambert, A.J.: Statistical turbulence approach to the covariance matrices in the shiftmap prediction using Kalman filter. In: Proc. OSA Optics and Photonics Technical Digest (2009)
Tahtali, M., Lambert, A., Fraser, D.: Self-tuning Kalman filter estimation of atmospheric warp. In: Proc. SPIE, vol. 7076 (2008)
Kallapur, A., Tahtali, M., Petersen, I.: A pixel-wise robust extended Kalman filter for restoration of geometrically warped anisoplanatic images. In: Proc. IEEE International Conference on Control Applications, pp. 280–285 (2010)
Egmont-Petersen, M., de Ridder, D., Handels, H.: Image processing with neural networks-a review. Pattern Recognition 35, 2279–2301 (2002)
Specht, D.F.: A general regression neural network. IEEE Transactions on Neural Networks 2(6), 568–576 (1991)
Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High accuracy optical flow estimation based on a theory for warping. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3024, pp. 25–36. Springer, Heidelberg (2004)
Liu, C.: Beyond pixels: Exploring new representations and applications for motion analysis. Massachusetts Institute of Technology (2009)
Halder, K.K., Tahtali, M., Anavatti, S.G.: An improved restoration method for non-uniformly warped images using optical flow technique. In: Proc. DICTA (2013)
Black, M.J., Anandan, P.: The robust estimation of multiple motions: Parametric and piecewise-smooth flow fields. Computer Vision and Image Understanding 63(1), 75–104 (1996)
Jwo, D.-J., Lai, C.-C.: Neural network-based GPS GDOP approximation and classification. GPS Solutions 11(1), 51–60 (2007)
Halder, K.K., Tahtali, M., Anavatti, S.G.: A new pixel shiftmap prediction method based on generalized regression neural network. In: Proc. IEEE ISSPIT (2013)
Tian, Y., Narasimhan, S.G.: Seeing through water: image restoration using model-based tracking. In: Proc. ICCV, pp. 2303–2310 (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Halder, K.K., Tahtali, M., Anavatti, S.G. (2014). An Artificial Neural Network Approach for Underwater Warp Prediction. In: Likas, A., Blekas, K., Kalles, D. (eds) Artificial Intelligence: Methods and Applications. SETN 2014. Lecture Notes in Computer Science(), vol 8445. Springer, Cham. https://doi.org/10.1007/978-3-319-07064-3_31
Download citation
DOI: https://doi.org/10.1007/978-3-319-07064-3_31
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-07063-6
Online ISBN: 978-3-319-07064-3
eBook Packages: Computer ScienceComputer Science (R0)