PrivacEye: Privacy-Preserving Head-Mounted Eye Tracking Using Egocentric Scene Image and Eye Movement Features

TL;DR

PrivacEye is a privacy-preserving eye-tracking system that automatically controls a camera shutter based on detected privacy-sensitive situations using scene and eye movement features.

Contribution

It introduces a novel method combining scene analysis and eye movement features to detect privacy-sensitive contexts and control camera activation in real-time.

Findings

Effective privacy protection in daily life scenarios

High accuracy in detecting privacy-sensitive situations

Successful automatic camera shutter control

Abstract

Eyewear devices, such as augmented reality displays, increasingly integrate eye tracking but the first-person camera required to map a user's gaze to the visual scene can pose a significant threat to user and bystander privacy. We present PrivacEye, a method to detect privacy-sensitive everyday situations and automatically enable and disable the eye tracker's first-person camera using a mechanical shutter. To close the shutter in privacy-sensitive situations, the method uses a deep representation of the first-person video combined with rich features that encode users' eye movements. To open the shutter without visual input, PrivacEye detects changes in users' eye movements alone to gauge changes in the "privacy level" of the current situation. We evaluate our method on a first-person video dataset recorded in daily life situations of 17 participants, annotated by themselves for privacy sensitivity, and show that our method is effective in preserving privacy in this challenging setting.