Advancing low‐light object detection with you only look once models: An empirical study and performance evaluation

Abstract Low‐light object detection is needed for ensuring security, enabling surveillance, and enhancing safety in diverse applications, including autonomous vehicles, surveillance systems, and search and rescue operations. A comprehensive study on low‐light object detection is presented using stat...

Full description

Saved in:
Bibliographic Details
Main Authors: Samier Uddin Ahammad Shovo, Md. Golam Rabbani Abir, Md. Mohsin Kabir, M. F. Mridha
Format: Article
Language:English
Published: Wiley 2024-12-01
Series:Cognitive Computation and Systems
Subjects:
Online Access:https://doi.org/10.1049/ccs2.12114
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846107304788754432
author Samier Uddin Ahammad Shovo
Md. Golam Rabbani Abir
Md. Mohsin Kabir
M. F. Mridha
author_facet Samier Uddin Ahammad Shovo
Md. Golam Rabbani Abir
Md. Mohsin Kabir
M. F. Mridha
author_sort Samier Uddin Ahammad Shovo
collection DOAJ
description Abstract Low‐light object detection is needed for ensuring security, enabling surveillance, and enhancing safety in diverse applications, including autonomous vehicles, surveillance systems, and search and rescue operations. A comprehensive study on low‐light object detection is presented using state‐of‐the‐art you only look once (YOLO) models, including YOLOv3, YOLOv5, YOLOv6, and YOLOv8, aiming to enhance detection performance under challenging low‐light conditions. The ExDark dataset is a dataset that consists of adequate low‐light images, modified to simulate realistic low‐light scenarios, and employed for evaluation. The deep learning algorithm optimises YOLO's architecture for low‐light detection by adapting the network structure and training strategies while preserving the algorithm's integrity. The experimental results show that YOLOv8 consistently outperforms baseline models, achieving significant improvements in accuracy and robustness in low‐light scenarios. The deep learning algorithm that acquired the best score, YOLOv8s, had a mean average precision score of 0.5513. This work contributes to the field of low‐light object detection, offering promising solutions for real‐world applications like nighttime surveillance and autonomous navigation in low‐light conditions, addressing the growing demand for advanced low‐light object detection.
format Article
id doaj-art-b601bccf83014560a4c3a22cc1e4358e
institution Kabale University
issn 2517-7567
language English
publishDate 2024-12-01
publisher Wiley
record_format Article
series Cognitive Computation and Systems
spelling doaj-art-b601bccf83014560a4c3a22cc1e4358e2024-12-26T15:31:31ZengWileyCognitive Computation and Systems2517-75672024-12-016411913410.1049/ccs2.12114Advancing low‐light object detection with you only look once models: An empirical study and performance evaluationSamier Uddin Ahammad Shovo0Md. Golam Rabbani Abir1Md. Mohsin Kabir2M. F. Mridha3Department of Computer Science and Engineering Bangladesh University of Business and Technology Dhaka BangladeshDepartment of Computer Science and Engineering Bangladesh University of Business and Technology Dhaka BangladeshDepartment of Computer Science and Engineering Bangladesh University of Business and Technology Dhaka BangladeshDepartment of Computer Science American International University‐Bangladesh Dhaka BangladeshAbstract Low‐light object detection is needed for ensuring security, enabling surveillance, and enhancing safety in diverse applications, including autonomous vehicles, surveillance systems, and search and rescue operations. A comprehensive study on low‐light object detection is presented using state‐of‐the‐art you only look once (YOLO) models, including YOLOv3, YOLOv5, YOLOv6, and YOLOv8, aiming to enhance detection performance under challenging low‐light conditions. The ExDark dataset is a dataset that consists of adequate low‐light images, modified to simulate realistic low‐light scenarios, and employed for evaluation. The deep learning algorithm optimises YOLO's architecture for low‐light detection by adapting the network structure and training strategies while preserving the algorithm's integrity. The experimental results show that YOLOv8 consistently outperforms baseline models, achieving significant improvements in accuracy and robustness in low‐light scenarios. The deep learning algorithm that acquired the best score, YOLOv8s, had a mean average precision score of 0.5513. This work contributes to the field of low‐light object detection, offering promising solutions for real‐world applications like nighttime surveillance and autonomous navigation in low‐light conditions, addressing the growing demand for advanced low‐light object detection.https://doi.org/10.1049/ccs2.12114artificial neural networksmachine learningmachine vision
spellingShingle Samier Uddin Ahammad Shovo
Md. Golam Rabbani Abir
Md. Mohsin Kabir
M. F. Mridha
Advancing low‐light object detection with you only look once models: An empirical study and performance evaluation
Cognitive Computation and Systems
artificial neural networks
machine learning
machine vision
title Advancing low‐light object detection with you only look once models: An empirical study and performance evaluation
title_full Advancing low‐light object detection with you only look once models: An empirical study and performance evaluation
title_fullStr Advancing low‐light object detection with you only look once models: An empirical study and performance evaluation
title_full_unstemmed Advancing low‐light object detection with you only look once models: An empirical study and performance evaluation
title_short Advancing low‐light object detection with you only look once models: An empirical study and performance evaluation
title_sort advancing low light object detection with you only look once models an empirical study and performance evaluation
topic artificial neural networks
machine learning
machine vision
url https://doi.org/10.1049/ccs2.12114
work_keys_str_mv AT samieruddinahammadshovo advancinglowlightobjectdetectionwithyouonlylookoncemodelsanempiricalstudyandperformanceevaluation
AT mdgolamrabbaniabir advancinglowlightobjectdetectionwithyouonlylookoncemodelsanempiricalstudyandperformanceevaluation
AT mdmohsinkabir advancinglowlightobjectdetectionwithyouonlylookoncemodelsanempiricalstudyandperformanceevaluation
AT mfmridha advancinglowlightobjectdetectionwithyouonlylookoncemodelsanempiricalstudyandperformanceevaluation