FiGO: Fine-Grained Query Optimization in Video Analytics
FiGO: Fine-Grained Query Optimization in Video Analytics
复制标题
DOI：
10.1145/3514221.3517857
复制
发表时间：
2022-06
期刊：
影响因子：
--
通讯作者：
Jiashen Cao;Karan Sarkar;Ramyad Hadidi;Joy Arulraj;Hyesoon Kim
中科院分区：
文献类型：
--
作者：
Jiashen Cao;Karan Sarkar;Ramyad Hadidi;Joy Arulraj;Hyesoon Kim
视频数据库管理系统（VDBMS）支持使用计算密集型深度学习模型大规模自动分析视频。为了减少这些模型的计算开销，研究人员提出了两种技术：（1）利用专门的轻量级模型来过滤掉不相关的帧或直接回答查询，以及（2）使用复杂度不断增加的级联模型来回答查询。对于这两种技术，查询优化器为整个视频生成粗粒度的查询计划。这些技术受到四个限制：（1）在难以检测的谓词上较低的查询准确性，（2）对于频繁出现的对象较低的过滤效率，（3）由于非平凡模型级联配置而导致的较低准确性，以及（4）由于对整个视频的粗粒度规划而错过优化机会。在本文中，我们提出FiGO来解决这些限制。FiGO的设计围绕着三种技术。首先，它使用一系列模型来支持一系列吞吐量-准确性权衡。其次，它采用细粒度的方法来进行查询优化。它使用给定集合中的不同模型处理视频的不同块，以满足用户的准确性要求。最后，它使用一种轻量级的技术来修剪模型集成，以降低查询优化时间。我们的经验表明，这些技术使FiGO在处理四个视频数据集的视频查询时，平均性能优于最先进的系统3.3倍。
Video database management systems (VDBMSs) enable automated analysis of videos at scale using computationally-intensive deep learning models. To reduce the computational overhead of these models, researchers have proposed two techniques: (1) leveraging a specialized, lightweight model to filter out irrelevant frames or to directly answer the query, and (2) using a cascade of models of increasing complexity to answer the query. For both techniques, the query optimizer generates a coarse-grained query plan for the entire video. These techniques suffer from four limitations: (1) lower query accuracy over hard-to-detect predicates, (2) lower filtering efficacy with frequently-occurring objects, (3) lower accuracy due to nontrivial model cascade configuration, and (4) missed optimization opportunities due to coarse-grained planning for the entire video. In this paper, we present FiGO to tackle these limitations. The design of FiGO is centered around three techniques. First, it uses an ensemble of models to support a range of throughput-accuracy tradeoffs. Second, it adopts a fine-grained approach to query optimization. It processes different chunks of the video using different models in the given ensemble to meet the user's accuracy requirement. Lastly, it uses a lightweight technique to prune the model ensemble to lower the query optimization time. We empirically show that these techniques enable FiGO to outperform the state-of-the-art systems for processing queries over videos by 3.3x on average across four video datasets.