Exploring the Impact of Hand Pose and Shadow on Hand-washing Action Recognition

TL;DR

This study examines how hand pose and shadow variations affect handwashing action recognition performance, revealing that shadows and pose changes significantly degrade accuracy, and proposes mitigation via targeted additional training data.

Contribution

The paper introduces a synthetic data generation method to analyze environmental impacts on handwashing recognition and proposes a mitigation strategy using moderate pose variations.

Findings

Shadows cause earlier classifier breakdown points.

Pose variations drastically reduce accuracy.

Adding moderate pose data improves robustness.

Abstract

In the real world, camera-based application systems can face many challenges, including environmental factors and distribution shift. In this paper, we investigate how pose and shadow impact a classifier's performance, using the specific application of handwashing action recognition. To accomplish this, we generate synthetic data with desired variations to introduce controlled distribution shift. Using our synthetic dataset, we define a classifier's breakdown points to be where the system's performance starts to degrade sharply, and we show these are heavily impacted by pose and shadow conditions. In particular, heavier and larger shadows create earlier breakdown points. Also, it is intriguing to observe model accuracy drop to almost zero with bigger changes in pose. Moreover, we propose a simple mitigation strategy for pose-induced breakdown points by utilizing additional training data from non-canonical poses. Results show that the optimal choices of additional training poses are those with moderate deviations from the canonical poses with 50-60 degrees of rotation.