Modeling the Trade-off of Privacy Preservation and Activity Recognition on Low-Resolution Images
Authors:
- Yuntao WangYWYuntao Wang
- Zirui ChengZCZirui Cheng
- Xin YiXYXin Yi
- Yan KongYKYan Kong
- Xueyang WangXWXueyang Wang
- Xuhai XuXXXuhai Xu
- Yukang YanYYYukang Yan
- Chun YuCYChun Yu
- Shwetak PatelSPShwetak Patel
- Yuanchun ShiYSYuanchun Shi
Preprint
Abstract
A computer vision system using low-resolution image sensors can provide intelligent services (e.g., activity recognition) but preserve unnecessary visual privacy information from the hardware level. However, preserving visual privacy and enabling accurate machine recognition have adversarial needs on image resolution. Modeling the trade-off of privacy preservation and machine recognition performance can guide future privacy-preserving computer vision systems using low-resolution image sensors. In this paper, using the at-home activity of daily livings (ADLs) as the scenario, we first obtained the most important visual privacy features through a user survey. Then we quantified and analyzed the effects of image resolution on human and machine recognition performance in activity recognition and privacy awareness tasks. We also investigated how modern image super-resolution techniques influence these effects. Based on the results, we proposed a method for modeling the trade-off of privacy preservation and activity recognition on low-resolution images.Keywords
All Related Versions
This publication has 42 references indexed in Scilit:
- Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study2018
- Connecting Pixels to Privacy and Utility: Automatic Redaction of Private Information in Images2018
- Repacking ‘Privacy’ for a Networked WorldComputer Supported Cooperative Work (CSCW), 2017
- Deep Residual Learning for Image Recognition2016
- Privacy-conscious human detection using low-resolution video2015
- Visual privacy protection methods: A surveyExpert Systems with Applications, 2015
- W3-privacy: understanding what, when, and where inference channels in multi-camera surveillance videoMultimedia Tools and Applications, 2012
- ImageNet: A large-scale hierarchical image database2009
- Face De-identification2009
- Assessment of Older People: Self-Maintaining and Instrumental Activities of Daily LivingThe Gerontologist, 1969