Recoverable Anonymization for Pose Estimation: A Privacy-Enhancing Approach
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909304693456896 |
|---|---|
| author | Huang, Wenjun Ni, Yang Rezvani, Arghavan Jeong, SungHeon Chen, Hanning Liu, Yezi Wen, Fei Imani, Mohsen |
| author_facet | Huang, Wenjun Ni, Yang Rezvani, Arghavan Jeong, SungHeon Chen, Hanning Liu, Yezi Wen, Fei Imani, Mohsen |
| contents | Human pose estimation (HPE) is crucial for various applications. However, deploying HPE algorithms in surveillance contexts raises significant privacy concerns due to the potential leakage of sensitive personal information (SPI) such as facial features, and ethnicity. Existing privacy-enhancing methods often compromise either privacy or performance, or they require costly additional modalities. We propose a novel privacy-enhancing system that generates privacy-enhanced portraits while maintaining high HPE performance. Our key innovations include the reversible recovery of SPI for authorized personnel and the preservation of contextual information. By jointly optimizing a privacy-enhancing module, a privacy recovery module, and a pose estimator, our system ensures robust privacy protection, efficient SPI recovery, and high-performance HPE. Experimental results demonstrate the system's robust performance in privacy enhancement, SPI recovery, and HPE. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_02715 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Recoverable Anonymization for Pose Estimation: A Privacy-Enhancing Approach Huang, Wenjun Ni, Yang Rezvani, Arghavan Jeong, SungHeon Chen, Hanning Liu, Yezi Wen, Fei Imani, Mohsen Computer Vision and Pattern Recognition Cryptography and Security Machine Learning Human pose estimation (HPE) is crucial for various applications. However, deploying HPE algorithms in surveillance contexts raises significant privacy concerns due to the potential leakage of sensitive personal information (SPI) such as facial features, and ethnicity. Existing privacy-enhancing methods often compromise either privacy or performance, or they require costly additional modalities. We propose a novel privacy-enhancing system that generates privacy-enhanced portraits while maintaining high HPE performance. Our key innovations include the reversible recovery of SPI for authorized personnel and the preservation of contextual information. By jointly optimizing a privacy-enhancing module, a privacy recovery module, and a pose estimator, our system ensures robust privacy protection, efficient SPI recovery, and high-performance HPE. Experimental results demonstrate the system's robust performance in privacy enhancement, SPI recovery, and HPE. |
| title | Recoverable Anonymization for Pose Estimation: A Privacy-Enhancing Approach |
| topic | Computer Vision and Pattern Recognition Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2409.02715 |