Deep Learning for Skeleton-Based Human Activity Segmentation: An Autoencoder Approach

Author:

Hossen Md Amran1ORCID,Naim Abdul Ghani2,Abas Pg Emeroylariffion1ORCID

Affiliation:

1. Faculty of Integrated Technologies, Universiti Brunei Darussalam, Gadong BE1410, Brunei

2. School of Digital Science, Universiti Brunei Darussalam, Gadong BE1410, Brunei

Abstract

Automatic segmentation is essential for enhancing human activity recognition, especially given the limitations of publicly available datasets that often lack diversity in daily activities. This study introduces a novel segmentation method that utilizes skeleton data for a more accurate and efficient analysis of human actions. By employing an autoencoder, this method extracts representative features and reconstructs the dataset, using the discrepancies between the original and reconstructed data to establish a segmentation threshold. This innovative approach allows for the automatic segmentation of activity datasets into distinct segments. Rigorous evaluations against ground truth across three publicly available datasets demonstrate the method’s effectiveness, achieving impressive average annotation error, precision, recall, and F1-score values of 3.6, 90%, 87%, and 88%, respectively. This illustrates the robustness of the proposed method in accurately identifying change points and segmenting continuous skeleton-based activities as compared to two other state-of-the-art techniques: one based on deep learning and another using the classical time-series segmentation algorithm. Additionally, the dynamic thresholding mechanism enhances the adaptability of the segmentation process to different activity dynamics improving overall segmentation accuracy. This performance highlights the potential of the proposed method to significantly advance the field of human activity recognition by improving the accuracy and efficiency of identifying and categorizing human movements.

Funder

Universiti Brunei Darussalam

Publisher

MDPI AG

Reference40 articles.

1. A Comprehensive Survey of RGB-Based and Skeleton-Based Human Action Recognition;Wang;IEEE Access,2023

2. Evaluation of 2D and 3D posture for human activity recognition;Hossen;AIP Conf. Proc.,2023

3. A comparative study of supervised and unsupervised approaches in human activity analysis based on skeleton data;Hossen;Int. J. Comput. Digit. Syst.,2023

4. A Comparative Review of Recent Kinect-Based Action Recognition Algorithms;Wang;IEEE Trans. Image Process.,2020

5. Human action recognition from various data modalities: A review;Sun;IEEE Trans. Pattern Anal. Mach. Intell.,2022

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3