Modeling the Trade-off of Privacy Preservation and Activity Recognition on Low-Resolution Images

Authors:
  • YWYuntao Wang
    Yuntao Wang
  • ZCZirui Cheng
    Zirui Cheng
  • XYXin Yi
    Xin Yi
  • YKYan Kong
    Yan Kong
  • XWXueyang Wang
    Xueyang Wang
  • XXXuhai Xu
    Xuhai Xu
  • YYYukang Yan
    Yukang Yan
  • CYChun Yu
    Chun Yu
  • SPShwetak Patel
    Shwetak Patel
  • YSYuanchun Shi
    Yuanchun Shi

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.
All Related Versions

This publication has 42 references indexed in Scilit: