Weighted-MSE based on Saliency map for assessing video quality of H.264 video streams

Hugo Boujut (1) , Jenny Benois-Pineau (1) , Ofer Hadar (2) , Toufik Ahmed (1) , Patrick Bonnet (3)

1 LaBRI - Laboratoire Bordelais de Recherche en Informatique
2 CSE - Department of Communication Systems Engineering [Be'er Sheva]
3 Audemat - WorldCast Systems Group

Human vision system is very complex and has been studied for many years specifically for purposes of efficient encoding of visual, e.g. video content from digital TV. There have been physiological and psychological evidences which indicate that viewers do not pay equal attention to all exposed visual information, but only focus on certain areas known as focus of attention (FOA) or saliency regions. In this work, we propose a novel based objective quality assessment metric, for assessing the perceptual quality of decoded video sequences affected by transmission errors and packed loses. The proposed method weights the Mean Square Error (MSE), Weighted-MSE (WMSE), according to the calculated saliency map at each pixel. Our method was validated trough subjective quality experiments.

Mots clés: Video Quality Assessment; Full-Reference; Saliency Maps; Supervised Learning; H.264; HDTV

Domaines: Multimédia [cs.MM]; Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Hugo Boujut, Jenny Benois-Pineau, Ofer Hadar, Toufik Ahmed, Patrick Bonnet. Weighted-MSE based on Saliency map for assessing video quality of H.264 video streams. IS&T / SPIE Electronic Imaging, Jan 2011, San Francisco, United States. pp.78670X. ⟨hal-00575199v2⟩