BlazeIt: Optimizing Declarative Aggregation and Limit Queries for Neural Network-Based Video Analytics

TL;DR

BlazeIt is a system that optimizes declarative queries for neural network-based video analytics, enabling efficient aggregation and limit queries with significant speedups over prior methods.

Contribution

It introduces a declarative query language and two novel optimization techniques for neural network-based video analytics, addressing computational and usability challenges.

Findings

Achieves up to 83x speedup over existing methods.

Supports approximate aggregation with error bounds using neural networks.

Provides efficient handling of limit queries in video analytics.

Abstract

Recent advances in neural networks (NNs) have enabled automatic querying of large volumes of video data with high accuracy. While these deep NNs can produce accurate annotations of an object's position and type in video, they are computationally expensive and require complex, imperative deployment code to answer queries. Prior work uses approximate filtering to reduce the cost of video analytics, but does not handle two important classes of queries, aggregation and limit queries; moreover, these approaches still require complex code to deploy. To address the computational and usability challenges of querying video at scale, we introduce BlazeIt, a system that optimizes queries of spatiotemporal information of objects in video. BlazeIt accepts queries via FrameQL, a declarative extension of SQL for video analytics that enables video-specific query optimization. We introduce two new query optimization techniques in BlazeIt that are not supported by prior work. First, we develop methods of using NNs as control variates to quickly answer approximate aggregation queries with error bounds. Second, we present a novel search algorithm for cardinality-limited video queries. Through these these optimizations, BlazeIt can deliver up to 83x speedups over the recent literature on video processing.