A Rotation-Invariant Regularization Term for Optical Flow Related Problems

详细信息    查看全文

• 作者：Roberto P. Palomares (17)
  Gloria Haro (17)
  Coloma Ballester (17)
  
  17. DTIC ; Pompeu Fabra University ; 08018 ; Barcelona ; Spain
  
• 刊名：Lecture Notes in Computer Science
• 出版年：2015
• 出版时间：2015
• 年：2015
• 卷：9007
• 期：1
• 页码：304-319
• 全文大小：2,041 KB
• 参考文献：1. Horn, BKP, Schunck, BG (1981) Determining optical flow. Artif. Intell. 17: pp. 185-203 CrossRef
  2. Black, MJ, Anandan, P (1996) The robust estimation of multiple motions: parametric and piecewise-smooth flow fields. Comput. Vis. Image Underst. 63: pp. 75-104 CrossRef
  3. Zimmer, H, Bruhn, A, Weickert, J (2011) Optic flow in harmony. Int. J. Comput. Vis. 93: pp. 368-388 CrossRef
  4. Nagel, HH, Enkelmann, W (1986) An Investigation of smoothness constraints for the estimation of displacement vector fields from image sequences. IEEE Trans. Pattern Anal. Mach. Intell. 8: pp. 565-593 CrossRef
  5. Wedel, A., Cremers D., Pock, T., Bischof, H.: Structure-and motion-adaptative regularization for high accuracy optic flow. In: IEEE 12th International Conference on Computer Vision, pp. 1663鈥?668 (2009)
  6. Werlberger, M., Trobin, W., Pock, T., Wedel, A., Cremers, D., Bischof, H.: Anisotropic Huber-L1 optical flow. In: Proceedings of the British Machine Vision Conference (2009)
  7. Weickert, J, Schn枚rr, C (2001) A theoretical framework for convex regularizers in PDE-based computation of image motion. Int. J. Comput. Vis. 45: pp. 245-264 CrossRef
  8. Trobin, W, Pock, T, Cremers, D, Bischof, H An unbiased second-order prior for high-accuracy motion estimation. In: Rigoll, G eds. (2008) Pattern Recognition. Springer, Heidelberg, pp. 396-405 CrossRef
  9. Rudin, LI, Osher, S, Fatemi, E (1992) Nonlinear total variation based noise removal algorithms. J. Phys. D Appl. Phys. 60: pp. 259-268
  10. Zach, C, Pock, T, Bischof, H A duality based approach for realtime TV-L1 optical flow. In: Hamprecht, FA, Schn枚rr, C, J盲hne, B eds. (2007) Pattern Recognition. Springer, Heidelberg, pp. 214-223 CrossRef
  11. Wedel, A., Pock, T., Braun, J., Franke, U., Cremers, D.: Duality TV-L1 flow with fundamental matrix prior. In: 23rd International Conference Image and Vision Computing, pp. 1鈥?, New Zealand (2008)
  12. Rosman, G, Shem-Tov, S, Bitton, D, Nir, T, Adiv, G, Kimmel, R, Feuer, A, Bruckstein, AM Over-parameterized optical flow using a stereoscopic constraint. In: Bruckstein, AM, Haar Romeny, BM, Bronstein, AM, Bronstein, MM eds. (2012) Scale Space and Variational Methods in Computer Vision. Springer, Heidelberg, pp. 761-772 CrossRef
  13. Kondermann, C, Kondermann, D, Garbe, CS Postprocessing of optical flows via surface measures and motion inpainting. In: Rigoll, G eds. (2008) Pattern Recognition. Springer, Heidelberg, pp. 355-364 CrossRef
  14. Matsushita, Y, Ofek, E, Ge, W, Tang, X, Shum, H-Y (2006) Full-frame video stabilization with motion inpainting. IEEE Trans. Pattern Anal. Mach. Intell. 28: pp. 1150-1163 CrossRef
  15. Shiratori, T, Matsushita, Y.: Video completion by motion field transfer. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 411鈥?18 (2006)
  16. Chorin, AJ, Marsden, JE (1990) A Mathematical Introduction to Fluid Mechanics: Texts in Applied Mathematics. Springer, New York CrossRef
  17. Strekalovskiy, E, Chambolle, A, Cremers, D (2014) Convex relaxation of vectorial problems with coupled regularization. SIAM J. Imaging Sci. 7: pp. 294-336 CrossRef
  18. Berkels, B, R盲tz, A, Rumpf, M, Voigt, A (2007) Extracting Grain boundaries and macroscopic deformations from images on atomic scale. J. Sci. Comput. 35: pp. 1-23 CrossRef
  19. Chambolle, A, Pock, T (2011) A first-order primal-dual algorithm for convex problems with applications to imaging. J. Math. Imaging Vis. 40: pp. 120-145 CrossRef
  20. Chambolle, A (2004) An algorithm for total variation minimization and applications. J. Math. Imaging Vis. 20: pp. 89-97 CrossRef
  21. S谩nchez P茅rez, J., Meinhardt-Llopis, E., Facciolo, G.: TV-L1 Optical Flow Estimation. Image Processing On Line (IPOL), pp. 137鈥?50 (2013)
  22. Baker, S, Scharstein, D, Lewis, JP, Roth, S, Black, MJ, Szeliski, R (2010) A database and evaluation methodology for optical flow. Int. J. Comput. Vis. 92: pp. 1-31 CrossRef
  23. Butler, DJ, Wulff, J, Stanley, GB, Black, MJ A naturalistic open source movie for optical flow evaluation. In: Fitzgibbon, A, Lazebnik, S, Perona, P, Sato, Y, Schmid, C eds. (2012) Computer Vision 鈥?ECCV 2012. Springer, Heidelberg, pp. 611-625 CrossRef
  24. Bredies, K Recovering piecewise smooth multichannel images by minimization of convex functionals with total generalized variation penalty. In: Bruhn, A, Pock, T, Tai, X-C eds. (2014) Efficient Algorithms for Global Optimization Methods in Computer Vision. Springer, Heidelberg, pp. 44-77 CrossRef
  
• 作者单位：Computer Vision -- ACCV 2014
• 丛书名：978-3-319-16813-5
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349

文摘

This paper proposes a new regularization term for optical flow related problems. The proposed regularizer properly handles rotation movements and it also produces good smoothness conditions on the flow field while preserving discontinuities. We also present a dual formulation of the new term that turns the minimization problem into a saddle-point problem that can be solved using a primal-dual algorithm. The performance of the new regularizer has been compared against the Total Variation (TV) in three different problems: optical flow estimation, optical flow inpainting, and optical flow completion from sparse samples. In the three situations the new regularizer improves the results obtained with the TV as a smoothing term.