inria-00072437, version 1

Real-Time Video Quality Assessment in Packet Networks: A Neural Network Model

Samir Mohamed ¹, Gerardo Rubino () ^a, 1, Francisco Cervantes ², Hossam Afifi ³

N° RR-4186 (2001)

• a –  INRIA
• 1:  ARMOR (INRIA - IRISA)
• 
  CNRS : UMR6074 – INRIA – Institut National des Sciences Appliquées (INSA) - Rennes – Ecole Nationale Supérieure des Télécommunications de Bretagne – Université de Rennes 1 France
• 2:  Instituto Tecnológico Autónomo de México (ITAM)
• http://www.itam.mx/es/
  ITAM Río Hondo No. 1, Col. Progreso Tizapán, México, D.F., México, 01080 Mexico
• 3:  Institut National des Télécommunications (INT)
• http://www.it-sudparis.eu/fr_accueil.html
  INT Institut National des Télécommunications 9 rue Charles Fourier 91011 Évry cedex FRANCE France

Bibliographic reference

• Type of document: Research reports
• Domain: Computer Science/Other
• Title: Real-Time Video Quality Assessment in Packet Networks: A Neural Network Model
• Abstract: There is a great demand to assess video quality transmitted in real time over packet networks, and to make this assessment in real time too. Quality assessment is achieved using two types of methods: objective or subjective. Subjective methods give more reliable results than objective methods; the latter do not always correlate well with human perception. Unfortunately, subjective methods are not suitable to real-time applications and are very difficult to carry out. In this paper, we show how Artificial Neural Networks (ANN) can be used to mimic the way by which a group of human subjects assess video quality when this video is distorted by certain quality-affecting parameters (e.g. packet loss rate, loss distribution, bit rate, frame rate, encoded frame type, etc.). Our method can be used to measure in real time the subjective video quality with very good precision. In order to illustrate its applicability, we chose to assess the quality of video flows transmitted over IP networks and we carried out subjective quality tests for video distorted by variations of those parameters.
• Full text language: English
• Report type: Research Report
• Publication date: 2001
• Keywords: PACKET VIDEO / NEURAL NETWORKS / REAL-TIME VIDEO TRANSMISSION / VIDEO QUALITY ASSESSMENT / VIDEO SIGNAL CHARACTERIZATION
• Writing date: 2001
• Internal note: RR-4186

Attached file list to this document: 

• inria-00072437, version 1
• http://hal.inria.fr/inria-00072437
• oai:hal.inria.fr:inria-00072437
• From: Rapport De Recherche Inria <>
• Submitted on: Wednesday, 24 May 2006 09:57:48
• Updated on: Thursday, 4 January 2007 15:52:26