Towards Automatic Sizing for PPE with a Point Cloud Based Variational Autoencoder

TL;DR

This paper introduces an unsupervised machine learning approach using a PointNet-inspired variational autoencoder to identify representative human models from 3D point cloud data, aiding PPE design and fitting.

Contribution

It presents a novel VAE-based method for automatic sizing model generation from human point clouds, improving PPE fitting processes.

Findings

Successfully identified representative human models from point cloud data.

Generated a set of idealized sizing exemplars for PPE design.

Demonstrated application on facial scans for mask design reference.

Abstract

Sizing and fitting of Personal Protective Equipment (PPE) is a critical part of the product creation process; however, traditional methods to do this type of work can be labor intensive and based on limited or non-representative anthropomorphic data. In the case of PPE, a poor fit can jeopardize an individual's health and safety. In this paper we present an unsupervised machine learning algorithm that can identify a representative set of exemplars, individuals that can be utilized by designers as idealized sizing models. The algorithm is based around a Variational Autoencoder (VAE) with a Point-Net inspired encoder and decoder architecture trained on Human point-cloud data obtained from the CEASAR dataset. The learned latent space is then clustered to identify a specified number of sizing groups. We demonstrate this technique on scans of human faces to provide designers of masks and facial coverings a reference set of individuals to test existing mask styles.