Reducto: On-Camera Filtering for Resource-Efficient Real-Time Video Analytics
Reducto: On-Camera Filtering for Resource-Efficient Real-Time Video Analytics
复制标题
DOI：
10.1145/3387514.3405874
复制
发表时间：
2020-07
期刊：
影响因子：
--
通讯作者：
Yuanqi Li;Arthi Padmanabhan;Pengzhan Zhao;Yufei Wang;G. Xu;R. Netravali
中科院分区：
文献类型：
--
作者：
Yuanqi Li;Arthi Padmanabhan;Pengzhan Zhao;Yufei Wang;G. Xu;R. Netravali
为了应对实时视频分析管道的高资源（网络和计算）需求，最近的系统依赖于框架过滤。但是，过滤通常是通过在Edge/后端服务器上运行的神经网络进行的。本文研究了相机过滤，该滤镜将过滤到管道的开头。不幸的是，我们发现商品摄像机的计算资源有限，仅允许基于低级视频功能通过框架差异进行过滤。使用错误时，此类技术可能会导致查询准确性的不可接受的下降。为了克服这一点，我们构建了Readucto，该系统可以根据特征类型，过滤阈值，查询准确性和视频内容之间的时间变化相关性动态调整过滤决策。各种视频和查询的实验表明，还原可实现显着（51-97％的帧）过滤效果，同时始终达到所需的准确性。
To cope with the high resource (network and compute) demands of real-time video analytics pipelines, recent systems have relied on frame filtering. However, filtering has typically been done with neural networks running on edge/backend servers that are expensive to operate. This paper investigates on-camera filtering, which moves filtering to the beginning of the pipeline. Unfortunately, we find that commodity cameras have limited compute resources that only permit filtering via frame differencing based on low-level video features. Used incorrectly, such techniques can lead to unacceptable drops in query accuracy. To overcome this, we built Reducto, a system that dynamically adapts filtering decisions according to the time-varying correlation between feature type, filtering threshold, query accuracy, and video content. Experiments with a variety of videos and queries show that Reducto achieves significant (51-97% of frames) filtering benefits, while consistently meeting the desired accuracy.