Object-based Video Coding for Arbitrary Shape by Visual Saliency and Temporal Correlation
Object-based Video Coding for Arbitrary Shape by Visual Saliency and Temporal Correlation
复制标题
DOI：
--
复制
发表时间：
2016-03
期刊：
影响因子：
--
通讯作者：
Kazuya Ogasawara;Tomo Miyazaki;Yoshihiro Sugaya;S. Omachi
中科院分区：
文献类型：
--
作者：
Kazuya Ogasawara;Tomo Miyazaki;Yoshihiro Sugaya;S. Omachi
本文提出了一种基于对象的视频编码方法。提出了一种适用于任意形状目标的视频编码方法。该方法基于视觉显著性和艾姆斯间的时间相关性来提取目标。随后，我们通过改变提取的对象和背景区域的编码质量来压缩视频。实验结果表明，该方法可以在保持目标对象质量的同时降低比特率。关键词-任意形状;视觉显著性;基于对象
This paper addresses a problem of object-based vid eo coding. We propose a video coding method for arbitr ary shapes of objects. The proposed method extracts objects on the basis of visual saliency and temporal correlation between fr ames. Subsequently, we compress the video by changing cod ing quality for the extracted objects and background regions. The experimental results show that the proposed method can reduce bit rate while preserving target object quality. Keywords-arbitrary shape; visual saliency; object-based