VPPlus: Exploring the Potentials of Video Processing for Live Video Analytics at the Edge
VPPlus: Exploring the Potentials of Video Processing for Live Video Analytics at the Edge
复制标题
DOI：
10.1109/iwqos54832.2022.9812896
复制
发表时间：
2022-06
期刊：
影响因子：
--
通讯作者：
Junpeng Guo;Shengqing Xia;Chunyi Peng
中科院分区：
文献类型：
--
作者：
Junpeng Guo;Shengqing Xia;Chunyi Peng
边缘辅助视频分析正日益受到关注。在这项工作中，我们解决了一个重要问题，即在不牺牲视频分析的准确性和及时性的前提下，对从设备实时传输到边缘的视频内容进行压缩。我们发现，可以在更大的配置空间上调整设备端处理以实现更多的视频压缩，这一点在很大程度上被忽视了。受我们初步研究的启发，我们设计了VPPlus，以在保持分析准确性的同时，尽可能地挖掘视频压缩的潜力。VPPlus包含两个核心模块——离线剖析和在线自适应——以便自动且快速地生成适当的反馈来调整设备端处理。我们通过在两个常用数据集上的五个目标检测任务验证了VPPlus的有效性和高效性；在几乎所有情况下，VPPlus都优于现有最先进的方法。
Edge-assisted video analytics is gaining momentum. In this work, we tackle an important problem to compress video content live streamed from the device to the edge without scarifying accuracy and timeliness of its video analytics. We find that on-device processing can be tuned over a larger configuration space for more video compression, which was largely overlooked. Inspired by our pilot study, we design VPPlus to fulfill the potentials to compress the video as much as we can, while preserving analytical accuracy. VPPlus incorporates two core modules – offline profiling and online adaptation – to generate proper feedback automatically and quickly to tune on-device processing. We validate the effectiveness and efficiency of VPPlususing five object detection tasks over two popular datasets; VPPlus outperforms the state-of-art approaches in almost all the cases.