FAKER: Full-body Anonymization with Human Keypoint Extraction for Real-time Video Deidentification
This addresses privacy concerns in video surveillance for industries using CCTV or IP cameras, though it appears incremental as it builds on existing pose estimation and anonymization techniques.
The paper tackles the problem of full-body anonymization in videos by proposing a novel approach that uses a smaller model to achieve real-time performance, successfully removing personal identification details like skin color and clothing while accurately representing positions and movements.
In the contemporary digital era, protection of personal information has become a paramount issue. The exponential growth of the media industry has heightened concerns regarding the anonymization of individuals captured in video footage. Traditional methods, such as blurring or pixelation, are commonly employed, while recent advancements have introduced generative adversarial networks (GAN) to redraw faces in videos. In this study, we propose a novel approach that employs a significantly smaller model to achieve real-time full-body anonymization of individuals in videos. Unlike conventional techniques that often fail to effectively remove personal identification information such as skin color, clothing, accessories, and body shape while our method successfully eradicates all such details. Furthermore, by leveraging pose estimation algorithms, our approach accurately represents information regarding individuals' positions, movements, and postures. This algorithm can be seamlessly integrated into CCTV or IP camera systems installed in various industrial settings, functioning in real-time and thus facilitating the widespread adoption of full-body anonymization technology.