Realtime face identification (FID) from a video feed is highly computation-intensive, and may exhaust computation resources if performed on a device with a limited amount of resources (e.g., a mobile device). In general, FID performs better when images are sampled at a higher rate, minimizing false negatives. However, performing it at an overwhelmingly high rate exposes the system to the risk of a queue overflow that hampers the system's reliability. This paper proposes a novel, queue-aware FID framework that adapts the sampling rate to maximize the FID performance while avoiding a queue overflow by implementing the Lyapunov optimization. A preliminary evaluation via a trace-based simulation confirms the effectiveness of the framework.
@article{arxiv.2109.01212,
title = {A Reliable, Self-Adaptive Face Identification Framework via Lyapunov Optimization},
author = {Dohyeon Kim and Joongheon Kim and Jae young Bang},
journal= {arXiv preprint arXiv:2109.01212},
year = {2021}
}
Comments
This paper was presented at ACM Symposium on Operating Systems Principles (SOSP) Workshop on AI Systems (AISys), Shanghai, China, October 2017