AccMPEG: Optimizing Video Encoding for Video Analytics
AccMPEG: Optimizing Video Encoding for Video Analytics
复制标题
DOI：
10.48550/arxiv.2204.12534
复制
发表时间：
2022-04
期刊：
影响因子：
--
通讯作者：
Kuntai Du;Qizheng Zhang;Anton Arapin;Haodong Wang;Zhengxu Xia;Junchen Jiang
中科院分区：
文献类型：
--
作者：
Kuntai Du;Qizheng Zhang;Anton Arapin;Haodong Wang;Zhengxu Xia;Junchen Jiang
新的视频编码和流媒体系统的延迟满足三个关键是了解每个（16 x16）宏块的编码质量对服务器端DNN精度的影响程度，我们称之为精度梯度。我们的见解是，这些宏块级精度梯度可以通过一个廉价的模型来提供视频帧，从而以足够的精度推断出来。AccMPEG提供了一套技术，在给定新的服务器端DNN的情况下，可以快速创建一个廉价的模型，以近实时地推断任何新帧的精度梯度。我们对AccMPEG在两种边缘设备（一个Intel Xeon银4100 CPU或NVIDIA Jetson Nano）和三个视觉任务（六个最近预训练的DNN）上的广泛评估表明，与最先进的基线相比，AccMPEG（具有相同的摄像机端计算资源）可以将端到端推理延迟减少10-43%，而不会影响准确性。
latency of a new video encoding and streaming system meets the three The key is to learn how much the encoding quality at each (16x16) macroblock can influence the server-side DNN accuracy, which we call accuracy gradient . Our insight is that these macroblock-level accuracy gradient can be inferred with sufficient precision by feeding the video frames through a cheap model. AccMPEG provides a suite of techniques that, given a new server-side DNN, can quickly create a cheap model to infer the accuracy gradient on any new frame in near realtime. Our extensive evaluation of AccMPEG on two types of edge devices (one Intel Xeon Silver 4100 CPU or NVIDIA Jetson Nano) and three vision tasks (six recent pre-trained DNNs) shows that AccMPEG (with the same camera-side compute resources) can reduce the end-to-end inference delay by 10-43% without hurting accuracy compared to the state-of-the-art baselines.