THIA: Accelerating Video Analytics using Early Inference and Fine-Grained Query Planning

02/16/2021
by   Jiashen Cao, et al.
0

To efficiently process visual data at scale, researchers have proposed two techniques for lowering the computational overhead associated with the underlying deep learning models. The first approach consists of leveraging a specialized, lightweight model to directly answer the query. The second approach focuses on filtering irrelevant frames using a lightweight model and processing the filtered frames using a heavyweight model. These techniques suffer from two limitations. With the first approach, the specialized model is unable to provide accurate results for hard-to-detect events. With the second approach, the system is unable to accelerate queries focusing on frequently occurring events as the filter is unable to eliminate a significant fraction of frames in the video. In this paper, we present THIA, a video analytics system for tackling these limitations. The design of THIA is centered around three techniques. First, instead of using a cascade of models, it uses a single object detection model with multiple exit points for short-circuiting the inference. This early inference technique allows it to support a range of throughput-accuracy tradeoffs. Second, it adopts a fine-grained approach to planning and processes different chunks of the video using different exit points to meet the user's requirements. Lastly, it uses a lightweight technique for directly estimating the exit point for a chunk to lower the optimization time. We empirically show that these techniques enable THIA to outperform two state-of-the-art video analytics systems by up to 6.5X, while providing accurate results even on queries focusing on hard-to-detect events.

READ FULL TEXT

page 2

page 4

research
04/06/2021

Zeus: Efficiently Localizing Actions in Videos using Reinforcement Learning

Detection and localization of actions in videos is an important problem ...
research
07/02/2022

CoVA: Exploiting Compressed-Domain Analysis to Accelerate Video Analytics

Modern retrospective analytics systems leverage cascade architecture to ...
research
06/21/2021

Boggart: Accelerating Retrospective Video Analytics via Model-Agnostic Ingest Processing

Delivering fast responses to retrospective queries on video datasets is ...
research
03/07/2017

NoScope: Optimizing Neural Network Queries over Video at Scale

Recent advances in computer vision-in the form of deep neural networks-h...
research
05/05/2023

Zelda: Video Analytics using Vision-Language Models

Advances in ML have motivated the design of video analytics systems that...
research
03/26/2021

MultiScope: Efficient Video Pre-processing for Exploratory Video Analytics

Performing analytics tasks over large-scale video datasets is increasing...
research
04/27/2021

FrameExit: Conditional Early Exiting for Efficient Video Recognition

In this paper, we propose a conditional early exiting framework for effi...

Please sign up or login with your details

Forgot password? Click here to reset