Semantic segmentation and description for video transcoding
Semantic segmentation and description for video transcoding
复制标题
视频转码的语义分割和描述
DOI：
10.1109/icme.2003.1221382
复制
发表时间：
2003
期刊：
影响因子：
--
通讯作者：
T. Ebrahimi
中科院分区：
文献类型：
--
作者：
A. Cavallaro;Olivier Steiger;T. Ebrahimi
我们提出了一个自动的基于内容的视频转码算法，这是基于人类如何感知视觉信息。转码器支持多个视频对象及其描述。首先通过语义分割将视频分解为有意义的对象。然后，代码转换器调整其行为，以不同方式对相关（前景）和非相关对象进行编码。基于对象和基于帧的编码器都与语义分割相结合。实验结果表明，在转码之前使用语义和描述降低了带宽要求，并且使得能够使视频表示适应有限的网络和终端设备能力，仍然保留必要的信息。
We present an automatic content-based video transcoding algorithm, which is based on how humans perceive visual information. The transcoder support multiple video objects and their description. First the video is decomposed into meaningful objects through semantic segmentation. Then the transcoder adapts its behavior to code relevant (foreground) and non-relevant objects differently. Both objects-based and frame-based encoders are combined with semantic segmentation. Experimental results show that the use of semantics and description prior to transcoding reduces the bandwidth requirements and makes it possible to adapt the video representation to limited network and terminal device capabilities still retaining the essential information.