Privacy-Preserving Human Activity Recognition from Extreme Low Resolution

TL;DR

This paper proposes a novel inverse super resolution method that generates multiple low-resolution training videos from high-resolution videos to enable privacy-preserving human activity recognition at extreme low resolutions.

Contribution

The paper introduces inverse super resolution, a new paradigm that learns optimal image transformations to improve activity recognition from extremely low-resolution videos.

Findings

Inverse super resolution improves activity recognition accuracy at low resolutions.

The method effectively utilizes high-resolution videos to generate training data.

Experimental results confirm the approach's effectiveness in privacy-preserving scenarios.

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.