Privacy-sensitive Objects Pixelation for Live Video Streaming

TL;DR

This paper introduces PsOP, a novel online pixelation framework for privacy-sensitive objects in live video streaming, addressing detection inaccuracies and reducing over-pixelation through a unified trajectory-based approach.

Contribution

The paper presents a new PsOP framework that combines pre-trained detection, embedding networks, and PIAP clustering for improved privacy object pixelation in live streams.

Findings

Significantly reduces over-pixelation ratio in privacy-sensitive object pixelation.

Unifies pixelation of different object types through trajectory generation.

Enhances pixelation accuracy in live video streaming scenarios.

Abstract

With the prevailing of live video streaming, establishing an online pixelation method for privacy-sensitive objects is an urgency. Caused by the inaccurate detection of privacy-sensitive objects, simply migrating the tracking-by-detection structure into the online form will incur problems in target initialization, drifting, and over-pixelation. To cope with the inevitable but impacting detection issue, we propose a novel Privacy-sensitive Objects Pixelation (PsOP) framework for automatic personal privacy filtering during live video streaming. Leveraging pre-trained detection networks, our PsOP is extendable to any potential privacy-sensitive objects pixelation. Employing the embedding networks and the proposed Positioned Incremental Affinity Propagation (PIAP) clustering algorithm as the backbone, our PsOP unifies the pixelation of discriminating and indiscriminating pixelation objects through trajectories generation. In addition to the pixelation accuracy boosting, experiments on the streaming video data we built show that the proposed PsOP can significantly reduce the over-pixelation ratio in privacy-sensitive object pixelation.