Human Health Indicator Prediction from Gait Video

TL;DR

This paper introduces a novel deep learning approach using gait videos to predict human health indicators like BMI, age, height, and weight, addressing data scarcity and robustness issues in surveillance and monitoring contexts.

Contribution

It proposes a transfer learning paradigm from pose estimation to health indicator prediction and introduces the GLANCE module for improved feature extraction.

Findings

Achieves state-of-the-art results on MoVi dataset

GLANCE module improves pose estimation accuracy on 3DPW

Demonstrates robustness of gait-based health prediction

Abstract

Body Mass Index (BMI), age, height and weight are important indicators of human health conditions, which can provide useful information for plenty of practical purposes, such as health care, monitoring and re-identification. Most existing methods of health indicator prediction mainly use front-view body or face images. These inputs are hard to be obtained in daily life and often lead to the lack of robustness for the models, considering their strict requirements on view and pose. In this paper, we propose to employ gait videos to predict health indicators, which are more prevalent in surveillance and home monitoring scenarios. However, the study of health indicator prediction from gait videos using deep learning was hindered due to the small amount of open-sourced data. To address this issue, we analyse the similarity and relationship between pose estimation and health indicator prediction tasks, and then propose a paradigm enabling deep learning for small health indicator datasets by pre-training on the pose estimation task. Furthermore, to better suit the health indicator prediction task, we bring forward Global-Local Aware aNd Centrosymmetric Encoder (GLANCE) module. It first extracts local and global features by progressive convolutions and then fuses multi-level features by a centrosymmetric double-path hourglass structure in two different ways. Experiments demonstrate that the proposed paradigm achieves state-of-the-art results for predicting health indicators on MoVi, and that the GLANCE module is also beneficial for pose estimation on 3DPW.