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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zolfaghari, Parham, Rey, Vitor Fortes, Ray, Lala, Kim, Hyun, Suh, Sungho, Lukowicz, Paul
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911930852048896
author Zolfaghari, Parham
Rey, Vitor Fortes
Ray, Lala
Kim, Hyun
Suh, Sungho
Lukowicz, Paul
author_facet Zolfaghari, Parham
Rey, Vitor Fortes
Ray, Lala
Kim, Hyun
Suh, Sungho
Lukowicz, Paul
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_16886
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Sensor Data Augmentation from Skeleton Pose Sequences for Improving Human Activity Recognition
Zolfaghari, Parham
Rey, Vitor Fortes
Ray, Lala
Kim, Hyun
Suh, Sungho
Lukowicz, Paul
Signal Processing
Computer Vision and Pattern Recognition
Machine Learning
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.
title Sensor Data Augmentation from Skeleton Pose Sequences for Improving Human Activity Recognition
topic Signal Processing
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2406.16886