Privacy-Preserving Human Activity Recognition from Extreme Low Resolution
arXiv:1604.03196
Abstract
Privacy protection from surreptitious video recordings is an important societal challenge. We desire a computer vision system (e.g., a robot) that can recognize human activities and assist our daily life, yet ensure that it is not recording video that may invade our privacy. This paper presents a fundamental approach to address such contradicting objectives: human activity recognition while only using extreme low-resolution (e.g., 16x12) anonymized videos. We introduce the paradigm of inverse super resolution (ISR), the concept of learning the optimal set of image transformations to generate multiple low-resolution (LR) training videos from a single video. Our ISR learns different types of sub-pixel transformations optimized for the activity classification, allowing the classifier to best take advantage of existing high-resolution videos (e.g., YouTube videos) by creating multiple LR training videos tailored for the problem. We experimentally confirm that the paradigm of inverse super resolution is able to benefit activity recognition from extreme low-resolution videos.
Cited by in corpus (14)
- A Study of Face Obfuscation in ImageNet
- Musical Chair: Efficient Real-Time Recognition Using Collaborative IoT Devices
- Generative Adversarial Networks: A Survey Towards Private and Secure Applications
- Privacy Aware Offloading of Deep Neural Networks
- Training with the Invisibles: Obfuscating Images to Share Safely for Learning Visual Recognition Models
- Foreground-Aware Stylization and Consensus Pseudo-Labeling for Domain Adaptation of First-Person Hand Segmentation
- Adversarial Learning of Privacy-Preserving and Task-Oriented Representations
- Fully-Coupled Two-Stream Spatiotemporal Networks for Extremely Low Resolution Action Recognition
- Password-conditioned Anonymization and Deanonymization with Face Identity Transformers
- Privacy-preserving Object Detection
- How low can you go? Privacy-preserving people detection with an omni-directional camera
- Deep Poisoning: Towards Robust Image Data Sharing against Visual Disclosure
- Privacy-Preserving Video Classification with Convolutional Neural Networks
- An adversarial learning framework for preserving users' anonymity in face-based emotion recognition