Human Fall Detection in Poor Lighting Conditions Using CNN-Based Model

Md Sabir Hossain; Md Mahfuzur Rahman

doi:10.5220/0013502200003938

Human Fall Detection in Poor Lighting Conditions Using CNN-Based Model

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Human fall detection for elderly care has become a crucial field of research as it can cause serious injuries and impact the quality of life. In this article, we present a deep learning-based approach for human fall detection in low-lighting conditions using a convolutional neural network (CNN). We trained and evaluated our model on multiple datasets, both annotated for fall detection. The proposed architecture captures and analyzes the falls-related features effectively, even in achieving a significant amount of precision, recall, and F1-scores for human fall detection. Moreover, our proposed architecture outperforms (91% accuracy) several state-of-the-art models, including ResNet50, InceptionV3, MobileNet, XceptionNet, VGG16, VGG19, and DenseNet. With a reliable human fall detection architecture, this research significantly contributes to enhancing safety measures for elderly individuals.

Original language	English
Title of host publication	Proceedings of the 11th International Conference on Information and Communication Technologies for Ageing Well and e-Health, ICT4AWE 2025
Editors	Effie Lai-Chong Law, Maria Lozano Perez, Maurice Mulvenna
Publisher	Science and Technology Publications, Lda
Pages	414-420
Number of pages	7
ISBN (Electronic)	9789897587436
DOIs	https://doi.org/10.5220/0013502200003938
State	Published - 2025
Event	11th International Conference on Information and Communication Technologies for Ageing Well and e-Health, ICT4AWE 2025 - Porto, Portugal Duration: 6 Apr 2025 → 8 Apr 2025

Publication series

Name	International Conference on Information and Communication Technologies for Ageing Well and e-Health, ICT4AWE - Proceedings
ISSN (Electronic)	2184-4984

Conference

Conference	11th International Conference on Information and Communication Technologies for Ageing Well and e-Health, ICT4AWE 2025
Country/Territory	Portugal
City	Porto
Period	6/04/25 → 8/04/25

Bibliographical note

Publisher Copyright:
Copyright © 2025 by SCITEPRESS - Science and Technology Publications, Lda.

Keywords

CNN
Deep Learning
Elderly Care
Fall Detection
Low Lighting

ASJC Scopus subject areas

Computer Networks and Communications
Computer Science Applications
Health Informatics

Access to Document

10.5220/0013502200003938

Cite this

Hossain, M. S., & Rahman, M. M. (2025). Human Fall Detection in Poor Lighting Conditions Using CNN-Based Model. In E. L.-C. Law, M. L. Perez, & M. Mulvenna (Eds.), Proceedings of the 11th International Conference on Information and Communication Technologies for Ageing Well and e-Health, ICT4AWE 2025 (pp. 414-420). (International Conference on Information and Communication Technologies for Ageing Well and e-Health, ICT4AWE - Proceedings). Science and Technology Publications, Lda. https://doi.org/10.5220/0013502200003938

Hossain, Md Sabir ; Rahman, Md Mahfuzur. / Human Fall Detection in Poor Lighting Conditions Using CNN-Based Model. Proceedings of the 11th International Conference on Information and Communication Technologies for Ageing Well and e-Health, ICT4AWE 2025. editor / Effie Lai-Chong Law ; Maria Lozano Perez ; Maurice Mulvenna. Science and Technology Publications, Lda, 2025. pp. 414-420 (International Conference on Information and Communication Technologies for Ageing Well and e-Health, ICT4AWE - Proceedings).

@inproceedings{60822122108f44eab65416dfdb30c0fe,

title = "Human Fall Detection in Poor Lighting Conditions Using CNN-Based Model",

abstract = "Human fall detection for elderly care has become a crucial field of research as it can cause serious injuries and impact the quality of life. In this article, we present a deep learning-based approach for human fall detection in low-lighting conditions using a convolutional neural network (CNN). We trained and evaluated our model on multiple datasets, both annotated for fall detection. The proposed architecture captures and analyzes the falls-related features effectively, even in achieving a significant amount of precision, recall, and F1-scores for human fall detection. Moreover, our proposed architecture outperforms (91\% accuracy) several state-of-the-art models, including ResNet50, InceptionV3, MobileNet, XceptionNet, VGG16, VGG19, and DenseNet. With a reliable human fall detection architecture, this research significantly contributes to enhancing safety measures for elderly individuals.",

keywords = "CNN, Deep Learning, Elderly Care, Fall Detection, Low Lighting",

author = "Hossain, \{Md Sabir\} and Rahman, \{Md Mahfuzur\}",

note = "Publisher Copyright: Copyright {\textcopyright} 2025 by SCITEPRESS - Science and Technology Publications, Lda.; 11th International Conference on Information and Communication Technologies for Ageing Well and e-Health, ICT4AWE 2025 ; Conference date: 06-04-2025 Through 08-04-2025",

year = "2025",

doi = "10.5220/0013502200003938",

language = "English",

series = "International Conference on Information and Communication Technologies for Ageing Well and e-Health, ICT4AWE - Proceedings",

publisher = "Science and Technology Publications, Lda",

pages = "414--420",

editor = "Law, \{Effie Lai-Chong\} and Perez, \{Maria Lozano\} and Maurice Mulvenna",

booktitle = "Proceedings of the 11th International Conference on Information and Communication Technologies for Ageing Well and e-Health, ICT4AWE 2025",

}

Hossain, MS & Rahman, MM 2025, Human Fall Detection in Poor Lighting Conditions Using CNN-Based Model. in EL-C Law, ML Perez & M Mulvenna (eds), Proceedings of the 11th International Conference on Information and Communication Technologies for Ageing Well and e-Health, ICT4AWE 2025. International Conference on Information and Communication Technologies for Ageing Well and e-Health, ICT4AWE - Proceedings, Science and Technology Publications, Lda, pp. 414-420, 11th International Conference on Information and Communication Technologies for Ageing Well and e-Health, ICT4AWE 2025, Porto, Portugal, 6/04/25. https://doi.org/10.5220/0013502200003938

Human Fall Detection in Poor Lighting Conditions Using CNN-Based Model. / Hossain, Md Sabir; Rahman, Md Mahfuzur.
Proceedings of the 11th International Conference on Information and Communication Technologies for Ageing Well and e-Health, ICT4AWE 2025. ed. / Effie Lai-Chong Law; Maria Lozano Perez; Maurice Mulvenna. Science and Technology Publications, Lda, 2025. p. 414-420 (International Conference on Information and Communication Technologies for Ageing Well and e-Health, ICT4AWE - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Human Fall Detection in Poor Lighting Conditions Using CNN-Based Model

AU - Hossain, Md Sabir

AU - Rahman, Md Mahfuzur

PY - 2025

Y1 - 2025

N2 - Human fall detection for elderly care has become a crucial field of research as it can cause serious injuries and impact the quality of life. In this article, we present a deep learning-based approach for human fall detection in low-lighting conditions using a convolutional neural network (CNN). We trained and evaluated our model on multiple datasets, both annotated for fall detection. The proposed architecture captures and analyzes the falls-related features effectively, even in achieving a significant amount of precision, recall, and F1-scores for human fall detection. Moreover, our proposed architecture outperforms (91% accuracy) several state-of-the-art models, including ResNet50, InceptionV3, MobileNet, XceptionNet, VGG16, VGG19, and DenseNet. With a reliable human fall detection architecture, this research significantly contributes to enhancing safety measures for elderly individuals.

AB - Human fall detection for elderly care has become a crucial field of research as it can cause serious injuries and impact the quality of life. In this article, we present a deep learning-based approach for human fall detection in low-lighting conditions using a convolutional neural network (CNN). We trained and evaluated our model on multiple datasets, both annotated for fall detection. The proposed architecture captures and analyzes the falls-related features effectively, even in achieving a significant amount of precision, recall, and F1-scores for human fall detection. Moreover, our proposed architecture outperforms (91% accuracy) several state-of-the-art models, including ResNet50, InceptionV3, MobileNet, XceptionNet, VGG16, VGG19, and DenseNet. With a reliable human fall detection architecture, this research significantly contributes to enhancing safety measures for elderly individuals.

KW - CNN

KW - Deep Learning

KW - Elderly Care

KW - Fall Detection

KW - Low Lighting

UR - https://www.scopus.com/pages/publications/105003534835

U2 - 10.5220/0013502200003938

DO - 10.5220/0013502200003938

M3 - Conference contribution

AN - SCOPUS:105003534835

T3 - International Conference on Information and Communication Technologies for Ageing Well and e-Health, ICT4AWE - Proceedings

SP - 414

EP - 420

BT - Proceedings of the 11th International Conference on Information and Communication Technologies for Ageing Well and e-Health, ICT4AWE 2025

A2 - Law, Effie Lai-Chong

A2 - Perez, Maria Lozano

A2 - Mulvenna, Maurice

PB - Science and Technology Publications, Lda

T2 - 11th International Conference on Information and Communication Technologies for Ageing Well and e-Health, ICT4AWE 2025

Y2 - 6 April 2025 through 8 April 2025

ER -

Hossain MS, Rahman MM. Human Fall Detection in Poor Lighting Conditions Using CNN-Based Model. In Law ELC, Perez ML, Mulvenna M, editors, Proceedings of the 11th International Conference on Information and Communication Technologies for Ageing Well and e-Health, ICT4AWE 2025. Science and Technology Publications, Lda. 2025. p. 414-420. (International Conference on Information and Communication Technologies for Ageing Well and e-Health, ICT4AWE - Proceedings). doi: 10.5220/0013502200003938

Human Fall Detection in Poor Lighting Conditions Using CNN-Based Model

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this