Optimal block search mechanism using deep recurrent neural network for enabling the code-efficiency in HEVC
Journal of Engineering, Design and Technology
ISSN: 1726-0531
Article publication date: 18 October 2021
Abstract
Purpose
High-efficiency video coding (HEVC) is the latest video coding standard that has better coding efficiency than the H.264/advanced video coding (AVC) standard. The purpose of this paper is to design and develop an effective block search mechanism for the video compression-HEVC standard such that the developed compression standard is applied for the communication applications.
Design/methodology/approach
In the proposed method, an rate-distortion (RD) trade-off, named regressive RD trade-off is used based on the conditional autoregressive value at risk (CaViar) model. The motion estimation (ME) is based on the new block search mechanism, which is developed with the modification in the Ordered Tree-based Hex-Octagon (OrTHO)-search algorithm along with the chronological Salp swarm algorithm (SSA) based on deep recurrent neural network (deepRNN) for optimally deciding the shape of search, search length of the tree and dimension. The chronological SSA is developed by integrating the chronological concept in SSA, which is used for training the deep RNN for ME.
Findings
The competing methods used for the comparative analysis of the proposed OrTHO-search based RD + chronological-salp swarm algorithm (RD + C-SSA) based deep RNN are support vector machine (SVM), fast encoding framework, wavefront-based high parallel (WHP) and OrTHO-search based RD method. The proposed video compression method obtained a maximum peak signal-to-noise ratio (PSNR) of 42.9180 dB and a maximum structural similarity index measure (SSIM) of 0.9827.
Originality/value
In this research, an effective block search mechanism was developed with the modification in the OrTHO-search algorithm along with the chronological SSA based on deepRNN for the video compression-HEVC standard.
Keywords
Acknowledgements
Authors would like to express my very great appreciation to the co-author of this manuscript for his valuable and constructive suggestions during the planning and development of this research work.
Retraction notice: The publisher of the Journal of Engineering, Design and Technology wishes to retract the following article by Anilkumar Chandrashekhar Korishetti and Virendra S. Malemath (2021), ‘Optimal block search mechanism using deep recurrent neural network for enabling the code-efficiency in HEVC’, published in the Journal of Engineering, Design and Technology, Vol. ahead-of-print, No. ahead-of-print, https://doi.org/10.1108/JEDT-11-2020-0468. Concerns were raised regarding the identity of the authors and the originality of the research; the authors were asked to provide details of their collaboration on this article and the data used to create it, but were unable to offer sufficient description of either; as a result the findings of the paper cannot be relied upon and the standard of the article does not meet that expected by the journal. The publisher of the journal sincerely apologises to the readers.
Citation
Korishetti, A.C. and Malemath, V.S. (2021), "Optimal block search mechanism using deep recurrent neural network for enabling the code-efficiency in HEVC", Journal of Engineering, Design and Technology, Vol. ahead-of-print No. ahead-of-print. https://doi.org/10.1108/JEDT-11-2020-0468
Publisher
:Emerald Publishing Limited
Copyright © 2021, Emerald Publishing Limited