Robust Human Identity Anonymization using Pose Estimation

TL;DR

This paper introduces a pose estimation-based method for human identity anonymization that improves head localization accuracy and reduces missed detections compared to traditional face detection systems, enhancing privacy protection.

Contribution

The paper presents a novel skeleton-based approach for anonymization, outperforming face detection methods and incorporating a confidence fusion technique for further enhancement.

Findings

Reduces missed face detections in anonymization tasks

Improves privacy protection for pedestrians

Outperforms traditional face detection approaches

Abstract

Many outdoor autonomous mobile platforms require more human identity anonymized data to power their data-driven algorithms. The human identity anonymization should be robust so that less manual intervention is needed, which remains a challenge for current face detection and anonymization systems. In this paper, we propose to use the skeleton generated from the state-of-the-art human pose estimation model to help localize human heads. We develop criteria to evaluate the performance and compare it with the face detection approach. We demonstrate that the proposed algorithm can reduce missed faces and thus better protect the identity information for the pedestrians. We also develop a confidence-based fusion method to further improve the performance.