Real-Time 3D QoE Evaluation of Novel 3D Media - Novel 3D Media Technologies - page 166

utilized to represent the structural degradation of color plus depth 3D images.
Subsequently, this information together with additional data (e.g., luminance ,
contrast ) can be used to evaluate the quality of corrupted 3D video sequences.
The changes in edge map will not count for pixel level changes of the original and
processed color and depth map sequences. Therefore supplementary data is
required to measure pixel domain changes of these sequences. The edge informa-
tion of color and depth map image sequences, together with some additional
information such as luminance and contrast , is compared to obtain quality ratings
for 3D video in the proposed method.
The schematic diagram of the proposed Near NR quality evaluation method is
shown in Fig. 9.4 . At the receiver-side, edge information is extracted from both the
color and depth map images. In addition to this structural measure based on edge
information, luminance and contrast information from the original and processed
Fig. 9.2 Graphical illustration of the proposed quality metric using the Orbi sequence (50th
frame) coded using QP 30 and transmitted over a network with PLR 20 %. (a) original depth map;
(b) extracted edge information from the original depth map; (c) original color image; (d) extracted
edge information from the original color image; (e) processed depth map; (f) extracted edge
information from the processed depth map; (g) processed color image, and (h) extracted edge
information from the processed color image