首页> 外文会议>SIBGRAPI Conference on Graphics, Patterns and Images >Transmitting What Matters: Task-Oriented Video Composition and Compression
【24h】

Transmitting What Matters: Task-Oriented Video Composition and Compression

机译:传输重要内容:面向任务的视频合成和压缩

获取原文

摘要

We present a simple yet effective framework - Transmitting What Matters (TWM) - to generate compressed videos containing only relevant objects targeted to specific computer vision tasks, such as faces for the task of face expression recognition, license plates for the task of optical character recognition, among others. TWM takes advantage of the final desired computer vision task to compose video frames only with the necessary data. The video frames are compressed and can be stored or transmitted to powerful servers where extensive and time-consuming tasks can be performed. We experimentally present the trade-offs between distortion and bitrate for a wide range of compression levels, and the impact generated by compression artifacts on the accuracy of the desired vision task. We show that, for one selected computer vision task, it is possible to dramatically reduce the amount of required data to be stored or transmitted, without compromising accuracy.
机译:我们提出了一个简单而有效的框架-传输重要内容(TWM)-生成仅包含针对特定计算机视觉任务的相关对象的压缩视频,例如用于面部表情识别的人脸,用于光学字符识别的牌照等等。 TWM利用了最终所需的计算机视觉任务来仅将视频帧与必要的数据组合在一起。视频帧经过压缩,可以存储或传输到功能强大的服务器,在其中可以执行大量且耗时的任务。我们实验性地提出了在宽范围的压缩级别下失真和比特率之间的权衡,以及压缩伪像所产生的对所需视觉任务准确性的影响。我们表明,对于一项选定的计算机视觉任务,可以在不影响准确性的情况下显着减少要存储或传输的所需数据量。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号