English

A Reliable, Self-Adaptive Face Identification Framework via Lyapunov Optimization

Distributed, Parallel, and Cluster Computing 2021-09-06 v1 Computer Vision and Pattern Recognition

Abstract

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.

Keywords

Cite

@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

R2 v1 2026-06-24T05:38:40.608Z