eprintid: 4025
rev_number: 7
eprint_status: archive
userid: 311
dir: disk0/00/00/40/25
datestamp: 2020-07-18 02:46:20
lastmod: 2020-07-18 02:46:20
status_changed: 2020-07-18 02:46:20
type: article
metadata_visibility: show
creators_name: Vu Huu, Tien
creators_name: Thao, Nguyen Thi Huong
creators_name: Vu van, San
creators_name: Hoang, Van Xiem
creators_id: tienvh@ptit.edu.vn
creators_id: thaotb07@gmail.com
creators_id: sanvv@ptit.edu.vn
creators_id: xiemhoang@vnu.edu.vn
title: Improving TDWZ Correlation Noise Estimation: A Deep Learning based Approach
ispublished: inpress
subjects: ECE
subjects: ElectronicsandComputerEngineering
divisions: fac_fet
abstract: Transform domain Wyner-Ziv video coding (TDWZ) has shown its benefits in compressing video applications with limited resources such as visual surveillance systems, remote sensing and wireless sensor networks. In TDWZ, the correlation noise model (CNM) plays a vital role since it directly affects to the number of bits needed to send from the encoder and thus the overall TDWZ compression performance. To achieve CNM with high accurate for TDWZ, we propose in this paper a novel CNM estimation approach in which the CNM with Laplacian distribution is adaptively estimated based on a deep learning (DL) mechanism. The proposed DL based CNM includes two hidden layers and a linear activation function to adaptively update the Laplacian parameter. Experimental results showed that the proposed TDWZ codec significantly outperforms the relevant benchmarks, notably by around 35% bitrate saving when compared to the DISCOVER codec and around 22% bitrate saving when compared to the HEVC Intra benchmark while providing a similar perceptual quality.
date: 2020-06
date_type: published
publisher: Radio and Electronics Association of Vietnam
official_url: https://www.rev-jec.org/index.php/rev-jec
id_number: http://dx.doi.org/10.21553/rev-jec.254
full_text_status: public
publication: REV Journal on Electronics and Communications
volume: 10
number: 1-2
pagerange: 1-10
refereed: TRUE
issn: 1859 - 378X
citation:   Vu Huu, Tien and Thao, Nguyen Thi Huong and Vu van, San and Hoang, Van Xiem  (2020) Improving TDWZ Correlation Noise Estimation: A Deep Learning based Approach.  REV Journal on Electronics and Communications, 10  (1-2).   pp. 1-10.  ISSN 1859 - 378X    (In Press)  
document_url: https://eprints.uet.vnu.edu.vn/eprints/id/eprint/4025/1/254_HVXiem_30_6.pdf