Full Reference Stereoscopic Video Quality Assessment Based On Spatio-Depth Saliency And Motion Strength

Abstract

Stereoscopic video quality is a perceptual phenomena that is related to the human visual system (HVS). In this paper, we present a spatio-depth saliency and motion strength based full reference stereoscopic video quality metric (FRSVQA). Initially, we obtain a spatial distortion map on every video frame to estimate spatial quality. The spatial distortion map is then refined by the depth salient maps to estimate depth quality. We also estimate the temporal quality by refining the spatial distortion map with the inter-frame difference map at the locations specified by motion edges. The spatial, depth and temporal qualities are systematically combined and averaged over the frames to estimate the overall stereo video quality metric.