PrivacEye: Privacy-Preserving First-Person Vision Using Image Features and Eye Movement Analysis

01/13/2018
by   Julian Steil, et al.
0

As first-person cameras in head-mounted displays become increasingly prevalent, so does the problem of infringing user and bystander privacy. To address this challenge, we present PrivacEye, a proof-of-concept system that detects privacysensitive everyday situations and automatically enables and disables the first-person camera using a mechanical shutter. To close the shutter, PrivacEye detects sensitive situations from first-person camera videos using an end-to-end deep-learning model. To open the shutter without visual input, PrivacEye uses a separate, smaller eye camera to detect changes in users' eye movements to gauge changes in the "privacy level" of the current situation. We evaluate PrivacEye on a dataset of first-person videos recorded in the daily life of 17 participants that they annotated with privacy sensitivity levels. We discuss the strengths and weaknesses of our proof-of-concept system based on a quantitative technical evaluation as well as qualitative insights from semi-structured interviews.

READ FULL TEXT

page 1

page 4

page 6

research
11/28/2016

Easy-setup eye movement recording system for human-computer interaction

Tracking the movement of human eyes is expected to yield natural and con...
research
10/21/2020

Towards Real-time Drowsiness Detection for Elderly Care

The primary focus of this paper is to produce a proof of concept for ext...
research
04/03/2020

Privacy-Preserving Eye Videos using Rubber Sheet Model

Video-based eye trackers estimate gaze based on eye images/videos. As se...
research
12/14/2019

Follow Pedro! An Infrared-based Person-Follower using Nonlinear Optimization

We used ROS2 as a platform to conduct AI research for developing a Follo...
research
07/04/2022

Detection of ADHD based on Eye Movements during Natural Viewing

Attention-deficit/hyperactivity disorder (ADHD) is a neurodevelopmental ...
research
03/30/2018

Learning to Anonymize Faces for Privacy Preserving Action Detection

There is an increasing concern in computer vision devices invading the p...
research
11/16/2016

Am I a Baller? Basketball Performance Assessment from First-Person Videos

This paper presents a method to assess a basketball player's performance...

Please sign up or login with your details

Forgot password? Click here to reset