Nonlinear Nonlocal Algorithm for Video Filtering

• Autorzy: El Ouafdi Ahmed Fouad , El Houari Hassan

Identyfikatory

DOI

10.12913/22998624/142969

• Języki publikacji: EN

Abstrakty

EN

Video sequences are frequently contaminated by noise throughout the acquisition process, resulting in considerable degradation of video display quality. In this paper, we present a novel method of video filtering. The proposed filter is developed from an optimization problem in which a Bayesian term and a noisy video sequence prior distribution are combined. The method begins by segmenting the video sequence into space-time blocks and then substituting each noisy block by a weighted average of non-local neighbor blocks. Gradient-based weights are used to dynamically adjust the edge preservation and smoothness of the reference block. The obtained formulation enables nonlinear filtering and, hence, preserving key features such as edges and corners while using the intrinsic Bayesian filtering framework. Experiments on different video sequences with varying degrees of noise show that the proposed method performs better than state-of-the-art video filtering approaches.

Słowa kluczowe

EN

video filter; noise reduction; nonlocal filter; Bayesian filtering; nonlinear filter

PL

filtr wideo; redukcja szumów; filtr nielokalny; filtrowanie bayesowskie; filtr nieliniowy

• Wydawca: Lublin University of Technology ; Polish Society of Ecological Engineering (PTIE), Branch of PTIE in Lublin
• Czasopismo: Advances in Science and Technology. Research Journal
• Rocznik: 2021
• Tom: Vol. 15, no 4
• Strony: 243--252
• Opis fizyczny: Bibliogr. 30 poz., fig., tab.

Twórcy

autor

El Ouafdi Ahmed Fouad

• Labsiv Laboratory, Department of Computer Sciences, Faculty of Sciences, Ibn Zohr University, Agadir, Morocco

• https://orcid.org/0000-0003-1173-2170

autor

El Houari Hassan

• LaGuardia Community College, CUNY, New York, USA

Bibliografia

• 1. Yahya A.A. Tan, J. Li L. Video noise reduction method using adaptive spatial-temporal filtering, Discrete Dyn. Nat. Soc. 2015; 10. doi:10.1155/2015/351763
• 2. Chatati S.M. Christopher S. A review on video noise reduction methods. International Conference on Recent Advances in Energy-efficient Computing and Communication (ICRAECC). 2019:1– 6. doi:10.1109/ICRAECC43874.2019.8995148.
• 3. Yan L., Yanfeng Q.Novel adaptive temporal filter based on motion compensation for video noise reduction, International Symposium on Communications and Information Technologies. 2006:1031- 1034. doi:10.1109/ISCIT.2006.339934.
• 4. Rakhshanfar M., Amer A. Motion blur resistant method for temporal video noise reduction, IEEE International Conference on Image Processing (ICIP). 2014: 2694 -2698. doi:10.1109/ICIP.2014.7025545.
• 5. Zuo C., Liu Y., Tan X., Wang W., Zhang, M. Video noise reduction based on a spatiotemporal kalmanbilateral mixture model, Sci. World J. 2013:438147. doi:10.1155/2013/438147.
• 6. Hong-Zhi W., Ling C., Shu-Liang X. Improved video noise reduction algorithm based on spatial-temporal combination. International Conference on Image and Graphics. 2013: 64–67. doi:10.1109/ICIG.2013.19.
• 7. Mikula K., Preusser T., Rumpf M. Morphological image sequence processing, Comput. Vis. Sci.2004, 6 (4): 197-209. doi : 10.1007/s00791004-0129-0
• 8. Perona P. Malik J. Scale-space and edge detection using anisotropic diffusion, IEEE Trans. Pattern Anal. Mach. Intell.1990, 12 (7):629–639. doi:10.1109/34.56205
• 9. Lee S. H., Kang M. G. Space-time video filtering algorithm based on 3-d anisotropic diffusion equation. International Conference on Image Processing. ICIP98, 1998, 2: 447–450. doi:10.1109/ICIP.1998.723418
• 10. Jahne J.B. Computer Vision and Applications: A Guide for Students and Practitioners, 2007, Elsevier.
• 11. Bovik A.C. Handbook of Image and Video Processing (Communications, Networking and Multimedia), 2005, Academic Press, Inc., USA.
• 12. Scharr H., Spies H. Accurate optical flow in noisy image sequences using flow adapted anisotropic diffusion, Signal Pross. 2005, 20(6): 537–553. doi:10.1016/j.image.2005.03.005
• 13. Hadj Fredj A., Malek J, Gpu-based anisotropic diffusion algorithm for video image noise reduction, Microprocessors and Microsystems. 2017,53: 190–201. doi: 10.1016/j.micpro.2017.08.003
• 14. Zhang K, Zuo W., Chen Y., Meng D., Zhang L. Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising, IEEE Trans. Image Process. 2017; 26 (7): 3142–3155, doi:10.1109/TIP.2017.2662206
• 15. Gorjizadeh S., Sadegh P., Siavash A. Noisy image segmentation using a self -organizing map network. Adv. Sci. Technol. Res. J. 2015; 9(26):118–123.
• 16. Davy A., Ehret T., Morel J.-M., Arias, P. Facciolo, G. Video noise reduction by combining patch search and cnns, Comput. Vis. Sci. 2021; 63: 73–88. doi:10.1007/s10851-020-00995-0
• 17. Monteil J, Beghdadi A. A new interpretation and improvement of the nonlinear anisotropic diffusion for image enhancement, IEEE Trans. Pattern Anal. Mach. Intell. 1999; 21 (9): 940-946, doi: 10.1109/34.790435
• 18. Oksendal B. Stochastic Differential Equations: An Introduction with Applications. 2005; Springer.
• 19. Risken H. The Fokker-Planck Equation: Methods of Solutions and Applications, Springer Series in Synergetics, 1996; Springer.
• 20. Lebrun M., Buades A., More J.-M. A nonlocal bayesian image noise reduction algorithm, Siam J. Imaging Sci. 2013; 6 (3):1665–1688, doi: 10.5201/ipol.2013.16.
• 21. Dabov K., Foi A., Katkovnik V., Egiazarian K.Image processing: Algorithms and systems,
• neural networks, and machine learning, in: Image noise reduction with block-matching and 3D filtering. 2006; 6064: 354 – 365, doi:10.1109/ICIP.2014.7025545
• 22. Kostadin D., Foi A., Egiazarian K. Video noise reduction by sparse 3d transform-domain collaborative filtering, 15th European Signal Processing Conference. 2007: 145–149.
• 23. Maggioni M., Boracchi G., Foi A., Egiazarian K. Video noise reduction deblocking and enhancement through separable 4-d nonlocal spatiotemporal transforms, IEEE Tran. Image Proc. 2015; 21 (9): 39523966. doi: 10.1109/TIP.2012.2199324
• 24. Maggioni, F. VB4D open source (2021. [Online].). URL http://www.cs.tut.fi/ ∼ foi/GCF-BM3D/
• 25. Zlokolica V., Philips W. Motion- and detail-adaptive noise reduction of video, in: E. R. Dougherty, J. T. Astola, K. O. Egiazarian (Eds.), Image Processing: Algorithms and Systems III, Vol. 5298, International Society for Optics and Photonics, SPIE, 2004: 403412, doi:10.1117/12.520847
• 26. Maggioni M., Sanchez-Monge E.,´Foi, A. Joint removal of random and fixed-pattern noise through spatiotemporal video filtering, IEEE Trans. Image Process. 2014; 23 (10): 4282–4296. doi:10.1109/TIP.2014.2345261.
• 27. Hsia S.-C., Hsu W.-C., Tsai C.-L. High-efficiency tv video noise reduction through adaptive spatialtemporal frame filtering, J. Real Time Image Proc. 2015; 10(3): 561–572. doi: 10.1155/2013/438147.
• 28. Almahdi R., Hardie R. C. Recursive non-local means filter for video noise reduction, J. Image Video Proc. 2017, 29. doi:10.1186/s13640017-0177-2.
• 29. Arias P., Morel J.-M. Video noise reduction via empirical Bayesian estimation of space-time patches, J. Math. Imaging Vis. 2018 ; 60: 70– 93. doi :10.1007/s10851-017-0742-4
• 30. Uttenweiler D., Weber C., Jahne B., Fink R. H. A. Spatiotemporal¨ anisotropic diffusion filtering to improve signal-to-noise ratios and object restoration in fluorescence microscopic image sequences. J. Biomed. Opt. 2005 ; 8 (1): 40–47. doi: 10.1117/1.1527627

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).