Sensor Data Augmentation from Skeleton Pose Sequences for Improving Human Activity Recognition

TL;DR

This paper introduces a novel pose-to-sensor network that generates sensor data from skeleton poses, enhancing human activity recognition accuracy with limited labeled data through joint training and comprehensive evaluation.

Contribution

The paper presents a new pose-to-sensor generation model trained jointly with activity classification, improving HAR performance on wearable sensor data.

Findings

Significant performance improvements over baseline methods.

Effective data augmentation from skeleton poses.

Successful joint training of data generation and activity recognition.

Abstract

The proliferation of deep learning has significantly advanced various fields, yet Human Activity Recognition (HAR) has not fully capitalized on these developments, primarily due to the scarcity of labeled datasets. Despite the integration of advanced Inertial Measurement Units (IMUs) in ubiquitous wearable devices like smartwatches and fitness trackers, which offer self-labeled activity data from users, the volume of labeled data remains insufficient compared to domains where deep learning has achieved remarkable success. Addressing this gap, in this paper, we propose a novel approach to improve wearable sensor-based HAR by introducing a pose-to-sensor network model that generates sensor data directly from 3D skeleton pose sequences. our method simultaneously trains the pose-to-sensor network and a human activity classifier, optimizing both data reconstruction and activity recognition. Our contributions include the integration of simultaneous training, direct pose-to-sensor generation, and a comprehensive evaluation on the MM-Fit dataset. Experimental results demonstrate the superiority of our framework with significant performance improvements over baseline methods.