Minor Privacy Protection Through Real-time Video Processing at the Edge

TL;DR

This paper presents a lightweight, real-time edge-based system for classifying faces as minors or adults in CCTV footage, enhancing privacy protection by enabling targeted privacy measures.

Contribution

It introduces a cascaded deep learning model optimized for edge devices to accurately identify minors in video streams, balancing performance and resource constraints.

Findings

Achieves 92.1% classification accuracy

Operates in near real-time on CPU at the edge

Demonstrates superiority over existing methods

Abstract

The collection of a lot of personal information about individuals, including the minor members of a family, by closed-circuit television (CCTV) cameras creates a lot of privacy concerns. Particularly, revealing children's identifications or activities may compromise their well-being. In this paper, we investigate lightweight solutions that are affordable to edge surveillance systems, which is made feasible and accurate to identify minors such that appropriate privacy-preserving measures can be applied accordingly. State of the art deep learning architectures are modified and re-purposed in a cascaded fashion to maximize the accuracy of our model. A pipeline extracts faces from the input frames and classifies each one to be of an adult or a child. Over 20,000 labeled sample points are used for classification. We explore the timing and resources needed for such a model to be used in the Edge-Fog architecture at the edge of the network, where we can achieve near real-time performance on the CPU. Quantitative experimental results show the superiority of our proposed model with an accuracy of 92.1% in classification compared to some other face recognition based child detection approaches.