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

被引:2
|
作者
Wang, Yuntao [1 ]
Cheng, Zirui [2 ]
Yi, Xin [3 ,4 ]
Kong, Yan [3 ]
Wang, Xueyang [3 ]
Xu, Xuhai [5 ]
Yan, Yukang [2 ]
Yu, Chun [2 ]
Patel, Shwetak [6 ]
Shi, Yuanchun [2 ,7 ]
机构
[1] Tsinghua Univ, Dept Comp Sci & Technol, Minist Educ, Key Lab Pervas Comp, Beijing, Peoples R China
[2] Tsinghua Univ, Dept Comp Sci & Technol, Beijing, Peoples R China
[3] Tsinghua Univ, Inst Network Sci & Cyberspace, Beijing, Peoples R China
[4] Zhongguancun Lab, Beijing, Peoples R China
[5] Univ Washington, Informat Sch, Seattle, WA 98195 USA
[6] Univ Washington, Paul G Allen Sch Comp Sci & Engn, Seattle, WA 98195 USA
[7] Qinghai Univ, Xining, Qinghai, Peoples R China
来源
PROCEEDINGS OF THE 2023 CHI CONFERENCE ON HUMAN FACTORS IN COMPUTING SYSTEMS (CHI 2023) | 2023年
关键词
Privacy; visual privacy; privacy preserving; activities of daily living; ADLs; low-resolution image;
D O I
10.1145/3544548.3581425
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
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.
引用
收藏
页数:15
相关论文
共 50 条
  • [31] The privacy-explainability trade-off: unraveling the impacts of differential privacy and federated learning on attribution methods
    Saifullah, Saifullah
    Mercier, Dominique
    Lucieri, Adriano
    Dengel, Andreas
    Ahmed, Sheraz
    FRONTIERS IN ARTIFICIAL INTELLIGENCE, 2024, 7
  • [32] Modified Crack Detection of Sewer Conduit with Low-Resolution Images
    Son, Byung Jik
    Cho, Taejun
    APPLIED SCIENCES-BASEL, 2021, 11 (05): : 1 - 16
  • [33] Face Swapping for Low-Resolution and Occluded Images In-the-Wild
    Park, Jaehyun
    Kang, Wonjun
    Koo, Hyung Il
    Cho, Nam Ik
    IEEE ACCESS, 2024, 12 : 91383 - 91395
  • [34] Evaluating the trade-off between privacy, public health safety, and digital security in a pandemic
    Akinsanmi, Titi
    Salami, Aishat
    DATA & POLICY, 2021, 3
  • [35] Workspace satisfaction: The privacy-communication trade-off in open-plan offices
    Kim, Jungsoo
    de Dear, Richard
    JOURNAL OF ENVIRONMENTAL PSYCHOLOGY, 2013, 36 : 18 - 26
  • [36] Secure Distributed Storage: Optimal Trade-Off Between Storage Rate and Privacy Leakage
    Chou, Remi A.
    Kliewer, Jorg
    IEEE TRANSACTIONS ON INFORMATION THEORY, 2024, 70 (05) : 3658 - 3668
  • [38] Multi-resolution Fusion Network for Human Pose Estimation in Low-resolution Images
    Kim, Boeun
    Choo, YeonSeung
    Jeong, Hea In
    Kim, Chung-Il
    Shin, Saim
    Kim, Jungho
    KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS, 2022, 16 (07): : 2328 - 2344
  • [39] Visual field movement detection model based on low-resolution images
    Li, Guangli
    Liu, Lei
    Zhang, Tongbo
    Yu, Hang
    Xu, Yue
    Lu, Shuai
    INTERNATIONAL JOURNAL OF EMBEDDED SYSTEMS, 2020, 12 (01) : 93 - 105
  • [40] Towards Optimization of Privacy-Utility Trade-Off Using Similarity and Diversity Based Clustering
    Majeed, Abdul
    Khan, Safiullah
    Hwang, Seong Oun
    IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING, 2024, 12 (01) : 368 - 385