Métrica de avaliação objetiva de vídeo usando a informação espacial, a temporal e a disparidade.

Abstract

Digital videos are subject to several types of distortions, which may occur during the processes of acquisition, processing, compression, storage and transmission of videos, resulting in loss of visual quality. Video quality assessment is important to set system parameters and propose the reduction of degradation, to improve the systems quality. The most appropriate way to assess the visual quality of a video sequence is subjective assessment. However, objective assessment is quicker and cheaper in comparison with the subjective solutions. The development of objective metrics has increased significantly, because of the need to quantify appropriately the visual quality perceived by the Human Visual System (HVS). The production of 3D videos is increasing, as well as the need to evaluate them. A problem identified in the evaluation process is related to the methods used for 2D videos, which are not suitable for measuring the quality of 3D videos, since typical depth and distortions of the stereoscopy are not considered. This study proposes new metrics for assessment of 2D and 3D videos. The proposed metric uses spatial and temporal information and disparity to evaluate videos more closely to the subjective assessment. In order to obtain the metric for 3D videos, measurements have been proposed for 2D videos, which uses spatial information (PW-SSIM – Perceptual Weighted Video Quality Approach) and temporal information (TPW-SSIM – Temporal Perceptual Weighted Video Quality Approach). Based on these metrics, the DPW–SSIM (Disparity Perceptual Weighted Video Quality Approach) and the DTPW-SSIM metrics (Disparity Temporal Perceptual Weighted Video Quality Approach metrics) have been proposed to assess 3D videos. For the evaluation of two dimensional videos the B-SSIM metric obtained the best result for blurry images. For MPEG-2 encoded videos, transmitted by wireless and IP systems, the metric with the best result was the TPW-SSIM. Regarding the three dimensional videos, the metrics that included disparity exceeded the metrics that did not include it, and the best results were obtained for the DPW-SSIM and PW-SSIM metrics.