Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

6-2023

Abstract

Sustaining high fidelity and high throughput of perception tasks over vision sensor streams on edge devices remains a formidable challenge, especially given the continuing increase in image sizes (e.g., generated by 4K cameras) and complexity of DNN models. One promising approach involves criticality-aware processing, where the computation is directed selectively to "critical" portions of individual image frames. We introduce MOSAIC, a novel system for such criticality-aware concurrent processing of multiple vision sensing streams that provides a multiplicative increase in the achievable throughput with negligible loss in perception fidelity. MOSAIC determines critical regions from images received from multiple vision sensors and spatially bin-packs these regions using a novel multi-scale Mosaic Across Scales (MoS) tiling strategy into a single `canvas frame', sized such that the edge device can retain sufficiently high processing throughput. Experimental studies using benchmark datasets for two tasks, Automatic License Plate Recognition and Drone-based Pedestrian Detection, shows that MOSAIC, executing on a Jetson TX2 edge device, can provide dramatic gains in the throughput vs. fidelity tradeoff. For instance, for drone-based pedestrian detection, for a batch size of 4, MOSAIC can pack input frames from 6 cameras to achieve (a) 4.75X (475%) higher throughput (23 FPS per camera, cumulatively 138FPS) with ≤ 1% accuracy loss, compared to a First Come First Serve (FCFS) processing paradigm.

Keywords

Edge AI, Machine Perception, Canvas-based Processing

Discipline

Artificial Intelligence and Robotics | Data Science | Graphics and Human Computer Interfaces

Research Areas

Software and Cyber-Physical Systems

Publication

MMSys '23: Proceedings of the 14th ACM Multimedia Systems Conference, Vancouver, Canada, June 7-10

First Page

278

Last Page

288

ISBN

9798400701481

Identifier

10.1145/3587819.3590986

Publisher

ACM

City or Country

New York

Embargo Period

6-25-2023

Copyright Owner and License

Authors

Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Additional URL

https://doi.org/10.1145/3587819.3590986

Share

COinS