Edge Computing Optimization for Real-Time Facial Recognition in Smart Surveillance Systems

Views: 0
Downloads: 0
DOI https://doi.org/10.55923/aksara.v1i1.5
Wahyu Anggraini 1
1Department of Forestry and Environmental Science, IPB University
1 wahyu.anggraini@ipb.ac.id

Downloads

Streaming high-resolution video directly to cloud servers strains bandwidth and induces unacceptable latency for security alert systems. This paper develops a quantized MobileNet pipeline deployed directly on edge devices, reducing edge-to-decision latency below 45 milliseconds while preserving 94.2% top-1 verification accuracy.
Issue Vol. 1 No. 1 (2022)
Section Articles
Pages 50-62
Published 2022-06-30

Most read articles by the same author(s)

No other articles found by this author.