基于区域划分的立体视频整帧丢失错误隐藏新算法

Region classification-based error concealment algorithm for full frame loss in stereoscopic video

针对立体视频传输中右视点整帧丢失,提出了一种基于区域划分的立体视频整帧丢失错误隐藏新算法。首先通过丢失帧视点内和视点间相邻帧的运动信息,估计丢失帧的运动区域与静止区域;然后利用视点间的全局视差,将丢失帧运动区域进一步划分为遮挡边界区域和非遮挡边界区域,并对遮挡边界区域和非遮挡边界区域分别采用运动补偿预测和视差补偿预测进行恢复,而对静止区域则直接采用帧拷贝的方法恢复丢失信息。实验结果表明,本文算法有效提高了所恢复的立体视频丢失帧图像的主客观质量。

A region classification-based error concealment algorithm for full frame loss in stereoscopic video transmission is proposed in this paper.Motion regions and motionless regions in the lost frame of the right view are estimated according to the motion information of the adjacent correctly decoded frames in the left and right views,and the motion regions are further classified into obscured and non-obscured boundary regions by using the global disparity among the two views.Motion-compensated prediction and disparity-compensated prediction are used to restore the motion obscured and non-obscured boundary regions,while the motionless regions are simply copied from the previous frame of the lost frame.Experimental results show that the proposed algorithm is efficient in improving the subjective and objective quality of the concealed lost frames.