Shadow Augmentation for Handwashing Action Recognition: from Synthetic to Real Datasets

TL;DR

This paper investigates shadow augmentation techniques to improve handwashing action recognition in outdoor video analytics, demonstrating that synthetic shadow data enhances model robustness across real-world datasets.

Contribution

It introduces a shadow augmentation method based on synthetic data to mitigate shadow-induced performance degradation in action recognition systems.

Findings

Heavier and larger shadows improve model robustness.

Shadow augmentation enhances performance across different neural networks.

Method is effective on multiple datasets.

Abstract

Video analytics systems designed for deployment in outdoor conditions can be vulnerable to many environmental changes, particularly changes in shadow. Existing works have shown that shadow and its introduced distribution shift can cause system performance to degrade sharply. In this paper, we explore mitigation strategies to shadow-induced breakdown points of an action recognition system, using the specific application of handwashing action recognition for improving food safety. Using synthetic data, we explore the optimal shadow attributes to be included when training an action recognition system in order to improve performance under different shadow conditions. Experimental results indicate that heavier and larger shadow is more effective at mitigating the breakdown points. Building upon this observation, we propose a shadow augmentation method to be applied to real-world data. Results demonstrate the effectiveness of the shadow augmentation method for model training and consistency of its effectiveness across different neural network architectures and datasets.