SAFaD: A System for Automatic Fall Detection on Surveillance Imagery

被引：0

作者：

Perez-Lopez, Borja ^{[1
]}

Gomez-Donoso, Francisco ^{[1
]}

Cazorla, Miguel ^{[1
]}

机构：

[1] Univ Alicante, Inst Comp Res, POB 99, Alicante, Spain

来源：

ROBOT2022: FIFTH IBERIAN ROBOTICS CONFERENCE: ADVANCES IN ROBOTICS, VOL 2 | 2023年 / 590卷

关键词：

Fall detection; Machine learning; Image analysis; Ensemble;

D O I：

10.1007/978-3-031-21062-4_46

中图分类号：

TP24 [机器人技术];

学科分类号：

080202 ; 1405 ;

摘要：

In this work we introduce SAFaD: A System for Automatic Fall Detection on Surveillance Imagery. Our system heavily relies in an intermediate representation that allows us to accurately and optimally encode the motion of a person. An ensemble of different approaches use this volume as input to predict whether a fall event has happened. We tested out system with a state-of-the-art fall detection dataset reaching a 62.86% accuracy.

引用

页码：564 / 575

页数：12

共 13 条

[1] Motion history image: its variants and applications [J].

Ahad, Md. Atiqur Rahman ;

Tan, J. K. ;

Kim, H. ;

Ishikawa, S. .

MACHINE VISION AND APPLICATIONS, 2012, 23 (02) :255-281

[2]

[Anonymous], 2021, Facts about Falls

[3]

Chen Ziwei, 2022, Big Data: 9th CCF Conference, BigData 2021, Revised Selected Papers. Communications in Computer and Information Science (1496), P283, DOI 10.1007/978-981-16-9709-8_19

[4] The representation and recognition of human movement using temporal templates [J].

Davis, JW ;

Bobick, AF .

1997 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS, 1997, :928-934

[5]

He KM, 2017, IEEE I CONF COMP VIS, P2980, DOI [10.1109/ICCV.2017.322, 10.1109/TPAMI.2018.2844175]

[6] mmFall: Fall Detection Using 4-D mmWave Radar and a Hybrid Variational RNN AutoEncoder [J].

Jin, Feng ;

Sengupta, Arindam ;

Cao, Siyang .

IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING, 2022, 19 (02) :1245-1257

[7]

Cañas JM, 2011, STUD COMPUT INTELL, V372, P225

[8] Motion and Region Aware Adversarial Learning for Fall Detection with Thermal Imaging [J].

Mehta, Vineet ;

Dhall, Abhinav ;

Pal, Sujata ;

Khan, Shehroz S. .

2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2021, :6321-6328

[9] DeepFall: Non-Invasive Fall Detection with Deep Spatio-Temporal Convolutional Autoencoders [J].

Nogas, Jacob ;

Khan, Shehroz S. ;

Mihailidis, Alex .

JOURNAL OF HEALTHCARE INFORMATICS RESEARCH, 2020, 4 (01) :50-70

[10] Detecting Falls with Wearable Sensors Using Machine Learning Techniques [J].

Ozdemir, Ahmet Turan ;

Barshan, Billur .

SENSORS, 2014, 14 (06) :10691-10708

← 1 2 →