Boggart: Towards General-Purpose Acceleration of Retrospective Video Analytics
Boggart: Towards General-Purpose Acceleration of Retrospective Video Analytics
复制标题
DOI：
--
复制
发表时间：
2021-06
期刊：
影响因子：
--
通讯作者：
Neil Agarwal;R. Netravali
中科院分区：
文献类型：
--
作者：
Neil Agarwal;R. Netravali
商业回顾性视频分析平台越来越多地采用通用接口来支持不同应用程序所需的自定义查询和卷积神经网络（CNN）。然而，现有的优化是针对 CNN 由平台（而非用户）确定的设置而设计的，当违反该条件时，无法满足以下至少一个关键平台目标：可靠的准确性、低延迟和最少的浪费工作。我们推出了 Boggart，这是一个能够同时满足所有三个目标的系统，同时支持当今平台所寻求的通用性。在发出查询之前，Boggart 仔细地采用传统的计算机视觉算法来生成不精确的索引，但在不同的 CNN/查询中基本上是全面的。对于每个发出的查询，Boggart 采用新技术来快速表征其索引的不精确性，并以限制准确性下降的方式少量运行 CNN（并将结果传播到其他帧）。我们的结果强调，博格特改进的通用性是以低成本实现的，其速度与先前的特定于模型的方法相匹配（并且通常超过）。
Commercial retrospective video analytics platforms have increasingly adopted general interfaces to support the custom queries and convolutional neural networks (CNNs) that different applications require. However, existing optimizations were designed for settings where CNNs were platform- (not user-) determined, and fail to meet at least one of the following key platform goals when that condition is violated: reliable accuracy, low latency, and minimal wasted work. We present Boggart, a system that simultaneously meets all three goals while supporting the generality that today's platforms seek. Prior to queries being issued, Boggart carefully employs traditional computer vision algorithms to generate indices that are imprecise, but are fundamentally comprehensive across different CNNs/queries. For each issued query, Boggart employs new techniques to quickly characterize the imprecision of its index, and sparingly run CNNs (and propagate the results to other frames) in a way that bounds accuracy drops. Our results highlight that Boggart's improved generality comes at low cost, with speedups that match (and most often, exceed) prior, model-specific approaches.