Real-Time Privacy Preservation for Robot Visual Perception

TL;DR

This paper introduces PCVS, a real-time privacy-preserving video streaming method for robots that guarantees concealment of sensitive objects using detection, blurring, and conformal prediction to meet specified privacy constraints.

Contribution

The paper presents PCVS, a novel real-time privacy-preserving framework that guarantees concealment of sensitive objects in robot video streams with theoretical bounds and practical deployment.

Findings

Achieves over 95% specification satisfaction rate

Outperforms existing privacy-preserving methods

Operates in real-time on robotic systems without compromising functionality

Abstract

Many robots (e.g., iRobot's Roomba) operate based on visual observations from live video streams, and such observations may inadvertently include privacy-sensitive objects, such as personal identifiers. Existing approaches for preserving privacy rely on deep learning models, differential privacy, or cryptography. They lack guarantees for the complete concealment of all sensitive objects. Guaranteeing concealment requires post-processing techniques and thus is inadequate for real-time video streams. We develop a method for privacy-constrained video streaming, PCVS, that conceals sensitive objects within real-time video streams. PCVS takes a logical specification constraining the existence of privacy-sensitive objects, e.g., never show faces when a person exists. It uses a detection model to evaluate the existence of these objects in each incoming frame. Then, it blurs out a subset of objects such that the existence of the remaining objects satisfies the specification. We then propose a conformal prediction approach to (i) establish a theoretical lower bound on the probability of the existence of these objects in a sequence of frames satisfying the specification and (ii) update the bound with the arrival of each subsequent frame. Quantitative evaluations show that PCVS achieves over 95 percent specification satisfaction rate in multiple datasets, significantly outperforming other methods. The satisfaction rate is consistently above the theoretical bounds across all datasets, indicating that the established bounds hold. Additionally, we deploy PCVS on robots in real-time operation and show that the robots operate normally without being compromised when PCVS conceals objects.