Deep Learning Approach Protecting Privacy in Camera-Based Critical Applications

TL;DR

This paper introduces a deep learning method that enhances privacy in camera systems by differentiating between salient and non-salient objects, reducing unnecessary data capture in critical applications.

Contribution

A novel deep learning approach that automatically identifies and suppresses non-salient objects to protect privacy without predefined object categories.

Findings

Effective in distinguishing salient from non-salient objects

Reduces privacy risks by minimizing unnecessary data capture

Applicable to various camera-based critical applications

Abstract

Many critical applications rely on cameras to capture video footage for analytical purposes. This has led to concerns about these cameras accidentally capturing more information than is necessary. In this paper, we propose a deep learning approach towards protecting privacy in camera-based systems. Instead of specifying specific objects (e.g. faces) are privacy sensitive, our technique distinguishes between salient (visually prominent) and non-salient objects based on the intuition that the latter is unlikely to be needed by the application.