Balancing Latency and Accuracy on Deep Video Analytics at the Edge

Loading...
Thumbnail Image

Access rights

openAccess
acceptedVersion

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Date

2022-02

Major/Subject

Mcode

Degree programme

Language

en

Pages

8

Series

2022 IEEE 19th Annual Consumer Communications & Networking Conference, pp. 299-306, IEEE Consumer Communications and Networking Conference

Abstract

Real-time deep video analytic at the edge is an enabling technology for emerging applications, such as vulnerable road user detection for autonomous driving, which requires highly accurate results of model inference within a low latency. In this paper, we investigate the accuracy-latency trade-off in the design and implementation of real-time deep video analytic at the edge. Without loss of generality, we select the widely used YOLO-based object detection and WebRTC-based video streaming for case study. Here, the latency consists of both networking latency caused by video streaming and the processing latency for video encoding/decoding and model inference. We conduct extensive measurements to figure out how the dynamically changing settings of video streaming affect the achieved latency, the quality of video, and further the accuracy of model inference. Based on the findings, we propose a mechanism for adapting video streaming settings (i.e. bitrate, resolution) online to optimize the accuracy of video analytic within latency constraints. The mechanism has proved, through a simulated setup, to be efficient in searching the optimal settings.

Description

| openaire: EC/H2020/825496/EU//5G-MOBIX

Keywords

video streaming, deep learning inference, object detection

Other note

Citation

Li, X, Cho, B & Xiao, Y 2022, Balancing Latency and Accuracy on Deep Video Analytics at the Edge . in 2022 IEEE 19th Annual Consumer Communications & Networking Conference . IEEE Consumer Communications and Networking Conference, IEEE, pp. 299-306, IEEE Consumer Communications and Networking Conference, Las Vegas, Nevada, United States, 08/01/2022 . https://doi.org/10.1109/CCNC49033.2022.9700636