Е-Публикации
Технически университет - София

Abstract: This paper reviews methods and algorithms for processing noisy video sequences and presents the development of a novel algorithm designed to classify and denoise video sequences affected by specific types of noise, including Gaussian and Salt-and-Pepper noise. The proposed algorithm first classifies the type of noise present in the video sequence and then applies the appropriate filtration technique based on the classification results. The effectiveness of the algorithm is tested on at least three RGB video sequences, each with a frame rate of 30 frames per second and a minimum duration of 10 seconds. Experimental results demonstrate the algorithm's capability to accurately classify noise types and effectively denoise video sequences, highlighting its potential for improving video quality in various applications.

References

1. K. Ji, W. Lei, and W. Zhang, "Spatio-Temporal Video Denoising Based on Attention Mechanism, " International Journal of Pattern Recognition and Artificial Intelligence, vol. 37, no. 06, pp. 2355006, 2023.
2. A. Davy, T. Ehret, J. M. Morel, P. Arias, and G. Facciolo, "Non-local video denoising by CNN, " arXiv preprint arXiv:1811.12758, 2018.
3. G. Vaksman, M. Elad, and P. Milanfar, "Patch craft: Video denoising by deep modeling and patch matching, " in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 2157-2166.
4. M. Tassano, J. Delon, and T. Veit, "FastDVDnet: Towards Real-Time Video Denoising Without Explicit Motion Estimation, " in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
5. S. S. Sarkar, A. Kakad, and S. M. Satapathy, "FastRWDnet: Implementation of novel real-T ime deep video denoising utilizing optimized FastDVDnet, " Innovations in Systems and Software Engineering, pp. 1-12, 2022.
6. A. Krizhevsky and G. Hinton, "Learning multiple layers of features from tiny images, " 2009.
7. https://mixkit.co/free-stock-video/nature/

Issue