Predicting Spatio-Temporal Entropic Differences for Robust No Reference Video Quality Assessment

Mitra, Shankhanil and Soundararajan, Rajiv and Channappayya, Sumohana S. (2021) Predicting Spatio-Temporal Entropic Differences for Robust No Reference Video Quality Assessment. IEEE Signal Processing Letters, 28. pp. 170-174. ISSN 1070-9908

Text
IEEE_Signal.pdf - Published Version
Restricted to Registered users only
Download (654kB) | Request a copy

Abstract

We consider the problem of robust no reference (NR) video quality assessment (VQA) where the algorithms need to have good generalization performance when they are trained and tested on different datasets. We specifically address this question in the context of predicting video quality for compression and transmission applications. Motivated by the success of the spatio-temporal entropic differences video quality predictor in this context, we design a framework using convolutional neural networks to predict spatial and temporal entropic differences without the need for a reference or human opinion score. This approach enables our model to capture both spatial and temporal distortions effectively and allows for robust generalization. We evaluate our algorithms on a variety of datasets and show superior cross database performance when compared to state of the art NR VQA algorithms. © 1994-2012 IEEE.

[error in script]

IITH Creators:

IITH Creators	ORCiD
Channappayya, Sumohana S.	https://orcid.org/0000-0002-5880-4023

Item Type:

Article

Additional Information:

Manuscript received November 22, 2020; revised December 29, 2020; accepted December 30, 2020. Date of publication January 6, 2021; date of current version January 27, 2021. This work was supported in part by the Ministry of Education, Government of India. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Matteo Naccari. (Corresponding author: Shankhanil Mitra.) Shankhanil Mitra and Rajiv Soundararajan are with the Department of Electrical Communication Engineering, Indian Institute of Science, Bangalore 560012, India (e-mail: shankhanilm@iisc.ac.in; rajivs@iisc.ac.in).

Uncontrolled Keywords:

Convolutional neural network (CNN); no-reference Video Quality Assessment (NR VQA); spatio-temporal reduced reference entropic difference (ST-RRED)

Subjects:

Electrical Engineering

Divisions:

Department of Electrical Engineering

Depositing User:

. LibTrainee 2021

Date Deposited:

17 Sep 2022 06:39

Last Modified:

17 Sep 2022 06:39