University of Central Florida Research Foundation Inc

Ishan Rajendrakumar Dave

Mubarak Shah

Chen Chen

This invention relates to a self-supervised privacy preservation action recognition system leveraging a learnable transformation anonymization function. The system is designed to process videos by removing spatial cues to protect privacy while retaining critical information for action recognition. The anonymization function, based on an encoder-decoder model, undergoes iterative training on a dataset to optimize the balance between obscuring privacy-sensitive information and preserving capability of recognizing actions. This training involves freezing and adjusting the weights of an action recognition branch and a self-supervised privacy removal branch to refine the model's effectiveness. The outcome is an anonymized video with minimized privacy information leakage, suitable for action analysis without privacy labels. Additional functionalities include frame sampling for enhanced privacy evaluation, data augmentation for model robustness, and a minimax optimization protocol ensuring optimal action recognition accuracy alongside privacy preservation.

Growing community of inventors

Orlando, FL, United States of America

Ishan Rajendrakumar Dave