中文版 | English
Title

A Fall Detection Network by 2D/3D Spatio-temporal Joint Models with Tensor Compression on Edge

Author
Corresponding AuthorHao,Yu
Publication Years
2022-04-30
DOI
Source Title
ISSN
1539-9087
EISSN
1558-3465
Volume21Issue:6
Abstract

Falling is ranked highly among the threats in elderly healthcare, which promotes the development of automatic fall detection systems with extensive concern. With the fast development of the Internet of Things (IoT) and Artificial Intelligence (AI), camera vision-based solutions have drawn much attention for single-frame prediction and video understanding on fall detection in the elderly by using Convolutional Neural Network (CNN) and 3D-CNN, respectively. However, these methods hardly supervise the intermediate features with good accurate and efficient performance on edge devices, which makes the system difficult to be applied in practice. This work introduces a fast and lightweight video fall detection network based on a spatio-temporal joint-point model to overcome these hurdles. Instead of detecting fall motion by the traditional CNNs, we propose a Long Short-Term Memory (LSTM) model based on time-series joint- point features extracted from a pose extractor. We also introduce the increasingly mature RGB-D camera and propose 3D pose estimation network to further improve the accuracy of the system. We propose to apply tensor train decomposition on the model to reduce storage and computational consumption so the deployment on edge devices can to realized. Experiments are conducted to verify the proposed framework. For fall detection task, the proposed video fall detection framework achieves a high sensitivity of 98.46% on Multiple Cameras Fall, 100% on UR Fall, and 98.01% on NTU RGB-D 120. For pose estimation task, our 2D model attains 73.3 mAP in the COCO keypoint challenge, which outperforms the OpenPose by 8%. Our 3D model attains 78.6% mAP on NTU RGB-D dataset with 3.6x faster speed than OpenPose.

Keywords
URL[Source Record]
Indexed By
Language
English
SUSTech Authorship
First
Funding Project
National Natural Science Foundation of China (NSFC)[6203000189] ; Shenzhen Science and Technology Program[KQTD2020020113051096] ; Innovative Team Program of Education Department of Guangdong Province[2018KCXTD028]
WOS Research Area
Computer Science
WOS Subject
Computer Science, Hardware & Architecture ; Computer Science, Software Engineering
WOS Accession No
WOS:000895635900017
Publisher
Data Source
人工提交
Citation statistics
Cited Times [WOS]:0
Document TypeJournal Article
Identifierhttp://kc.sustech.edu.cn/handle/2SGJ60CL/415766
DepartmentSUSTech Institute of Microelectronics
Affiliation
Southern University of Science and Technology
First Author AffilicationSouthern University of Science and Technology
Corresponding Author AffilicationSouthern University of Science and Technology
First Author's First AffilicationSouthern University of Science and Technology
Recommended Citation
GB/T 7714
Shuwei,Li,Changhai,Man,Ao,Shen,et al. A Fall Detection Network by 2D/3D Spatio-temporal Joint Models with Tensor Compression on Edge[J]. ACM Transactions on Embedded Computing Systems,2022,21(6).
APA
Shuwei,Li.,Changhai,Man.,Ao,Shen.,Ziyi,Guan.,Wei,Mao.,...&Hao,Yu.(2022).A Fall Detection Network by 2D/3D Spatio-temporal Joint Models with Tensor Compression on Edge.ACM Transactions on Embedded Computing Systems,21(6).
MLA
Shuwei,Li,et al."A Fall Detection Network by 2D/3D Spatio-temporal Joint Models with Tensor Compression on Edge".ACM Transactions on Embedded Computing Systems 21.6(2022).
Files in This Item:
File Name/Size DocType Version Access License
J105.A Fall Detectio(7063KB) Restricted Access--
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Export to Excel
Export to Csv
Altmetrics Score
Google Scholar
Similar articles in Google Scholar
[Shuwei,Li]'s Articles
[Changhai,Man]'s Articles
[Ao,Shen]'s Articles
Baidu Scholar
Similar articles in Baidu Scholar
[Shuwei,Li]'s Articles
[Changhai,Man]'s Articles
[Ao,Shen]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Shuwei,Li]'s Articles
[Changhai,Man]'s Articles
[Ao,Shen]'s Articles
Terms of Use
No data!
Social Bookmark/Share
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.