Selective Content Removal for Egocentric Wearable Camera in Nutritional Studies

Abstract

Research and innovation on wearable sensor technology has grown exponentially over this decade. The privacy-related concerns have grown in tandem. Automatic Ingestion Monitor v2 (AIM-2) is an egocentric camera and sensor that aids monitoring of individual diet and eating behavior by capturing still images throughout the day and using sensor data to detect eating. The images may be used to recognize foods being eaten, eating environment, and other behaviors and daily activities. At the same time, captured images may carry privacy concerning content such as (1) people in social eating and/or bystanders (i.e., bystander privacy); (2) sensitive documents that may appear on a computer screen in the view of AIM-2 (i.e., context privacy). Managing privacy concerns by discarding images potentially containing private content is not practical as many activities are performed socially or with the use of computing devices. Therefore, we propose an automatic, image redaction-based privacy protection by selective content removal based on semantic segmentation using a deep learning neural network. We prioritize removal of humans and display screens. A free-living dataset containing 1 day of data from 15 participants was used to develop and validate the proposed method. We used 331,614 augmented data from 9 participates and publicly available data for training. The proposed method was validated on data of 6 participants and reported bystander privacy removal with precision of 0.87 and recall of 0.94 and reported context privacy removal by precision and recall of 0.97 and 0.98. The results of the study showed that selective content removal using deep learning neural network is a much more desirable approach to address privacy concerns for an egocentric wearable camera.

Safeguarding National Security Interests Utilizing Location-Aware Camera Devices

“…[2020] describe a low-cost distributed storage system architecture for video data to fend off geo-range attacks. In their work on discussing solutions to privacy concerns in wear-able cameras [8], M. A. Hassan et al [2020] discuss how privacy concerns may creep into the usage of egocentric wearable cameras.…”

“…In their work on discussing solutions to privacy concerns in wear-able cameras [8], M. A. Hassan et al [2020] discuss how privacy concerns may creep into the usage of egocentric wearable cameras. They propose using deep learning neural networks to apply image redaction by selective removal to address the privacy concerns of bystanders or other parties.…”

Interdisciplinary perspectives on privacy awareness in lifelogging technology development

“…Egocentric vision has greatly enhanced the vulnerability of bystanders (Ferdous et al 2017 ). Recent research has worked on preserving visual privacy of the third parties that did not give consent: Dimiccoli et al ( 2018 ) analyzed how image degradation might preserve the privacy of persons appearing in the image while activities can still be recognized; Hassan and Sazonov ( 2020 ) proposed an image redaction approach for privacy protection by selective content removal using a semantic segmentation-based deep learning.…”