Privacy-sensitive Objects Pixelation for Live Video Streaming
This work provides a solution for automatic personal privacy filtering during live video streaming, which is a critical problem for users and platforms concerned with privacy.
This paper addresses the urgent need for online pixelation of privacy-sensitive objects in live video streaming, which suffers from inaccurate detection in existing tracking-by-detection methods. The proposed Privacy-sensitive Objects Pixelation (PsOP) framework unifies pixelation for various objects by generating trajectories, significantly reducing the over-pixelation ratio.
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.