Privacy Risks of Robot Vision: A User Study on Image Modalities and Resolution

TL;DR

This study explores user privacy perceptions related to robot vision, revealing that depth and semantic segmentation images are viewed as safer, and lower resolutions are perceived as more privacy-preserving.

Contribution

It provides empirical insights into how different image modalities and resolutions influence user privacy concerns in robotic applications.

Findings

Depth images are seen as privacy-safe.

Semantic segmentation images are also considered privacy-safe.

Lower resolutions like 16x16 are perceived as fully privacy-preserving.

Abstract

User privacy is a crucial concern in robotic applications, especially when mobile service robots are deployed in personal or sensitive environments. However, many robotic downstream tasks require the use of cameras, which may raise privacy risks. To better understand user perceptions of privacy in relation to visual data, we conducted a user study investigating how different image modalities and image resolutions affect users' privacy concerns. The results show that depth images are broadly viewed as privacy-safe, and a similarly high proportion of respondents feel the same about semantic segmentation images. Additionally, the majority of participants consider 32*32 resolution RGB images to be almost sufficiently privacy-preserving, while most believe that 16*16 resolution can fully guarantee privacy protection.