LLD-YOLO: A Low-Light Object Detection Algorithm Based on Dynamic Weighted Fusion of Shallow and Deep Features

Object detection in low-light scenarios has a wide range of applications, but existing algorithms often struggle to preserve the scarce low-level features in dark environments and exhibit limitations in localization accuracy for blurred edges and occluded objects, leading to suboptimal performance....

Full description

Saved in:
Bibliographic Details
Main Authors: Wenhao Cai, Yajun Chen, Xiaoyang Qiu, Meiqi Niu, Jianying Li
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10955203/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850177447443562496
author Wenhao Cai
Yajun Chen
Xiaoyang Qiu
Meiqi Niu
Jianying Li
author_facet Wenhao Cai
Yajun Chen
Xiaoyang Qiu
Meiqi Niu
Jianying Li
author_sort Wenhao Cai
collection DOAJ
description Object detection in low-light scenarios has a wide range of applications, but existing algorithms often struggle to preserve the scarce low-level features in dark environments and exhibit limitations in localization accuracy for blurred edges and occluded objects, leading to suboptimal performance. To address these challenges, we propose an improved neck structure, SRB-FPN, to achieve fine-grained cross-level semantic alignment and feature fusion, while also optimizing the regression loss function to develop LLD-YOLO, a detector specifically designed for low-light conditions. To enhance the representation of key feature units and dynamically optimize the fusion weights between shallow and deep features, we introduce the SDFBF module. To improve the diversity of receptive fields and strengthen the network’s multi-scale feature capture capability, we incorporate the DBB-C2f module. Furthermore, we integrate the hard-sample focusing property of Focaler IoU with the geometric perception advantages of MPDIoU, proposing Focal MPDIoU Loss to refine the localization of difficult samples and precisely capture bounding box variations. Ultimately, LLD-YOLO achieves an mAP50 of 70.0% on the ExDark dataset, outperforming the baseline by 2.7 percentage points. Extensive experiments on three public datasets, ExDark, NOD, and RTTS, further validate the superior performance of the proposed method in low-light conditions and its strong adaptability to foggy environments.
format Article
id doaj-art-dc2aae3f3ca84375a0c799a8fce99f81
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-dc2aae3f3ca84375a0c799a8fce99f812025-08-20T02:18:58ZengIEEEIEEE Access2169-35362025-01-0113699676997910.1109/ACCESS.2025.355857410955203LLD-YOLO: A Low-Light Object Detection Algorithm Based on Dynamic Weighted Fusion of Shallow and Deep FeaturesWenhao Cai0https://orcid.org/0009-0009-5792-1373Yajun Chen1https://orcid.org/0009-0006-2494-1878Xiaoyang Qiu2https://orcid.org/0009-0002-5446-2887Meiqi Niu3Jianying Li4https://orcid.org/0009-0000-7690-7563School of Electronic Information Engineering, China West Normal University, Nanchong, ChinaSchool of Electronic Information Engineering, China West Normal University, Nanchong, ChinaSchool of Electronic Information Engineering, China West Normal University, Nanchong, ChinaSchool of Electronic Information Engineering, China West Normal University, Nanchong, ChinaSchool of Electronic Information Engineering, China West Normal University, Nanchong, ChinaObject detection in low-light scenarios has a wide range of applications, but existing algorithms often struggle to preserve the scarce low-level features in dark environments and exhibit limitations in localization accuracy for blurred edges and occluded objects, leading to suboptimal performance. To address these challenges, we propose an improved neck structure, SRB-FPN, to achieve fine-grained cross-level semantic alignment and feature fusion, while also optimizing the regression loss function to develop LLD-YOLO, a detector specifically designed for low-light conditions. To enhance the representation of key feature units and dynamically optimize the fusion weights between shallow and deep features, we introduce the SDFBF module. To improve the diversity of receptive fields and strengthen the network’s multi-scale feature capture capability, we incorporate the DBB-C2f module. Furthermore, we integrate the hard-sample focusing property of Focaler IoU with the geometric perception advantages of MPDIoU, proposing Focal MPDIoU Loss to refine the localization of difficult samples and precisely capture bounding box variations. Ultimately, LLD-YOLO achieves an mAP50 of 70.0% on the ExDark dataset, outperforming the baseline by 2.7 percentage points. Extensive experiments on three public datasets, ExDark, NOD, and RTTS, further validate the superior performance of the proposed method in low-light conditions and its strong adaptability to foggy environments.https://ieeexplore.ieee.org/document/10955203/Keywords object detectionlow-light scenariosYOLOdynamic feature fusion
spellingShingle Wenhao Cai
Yajun Chen
Xiaoyang Qiu
Meiqi Niu
Jianying Li
LLD-YOLO: A Low-Light Object Detection Algorithm Based on Dynamic Weighted Fusion of Shallow and Deep Features
IEEE Access
Keywords object detection
low-light scenarios
YOLO
dynamic feature fusion
title LLD-YOLO: A Low-Light Object Detection Algorithm Based on Dynamic Weighted Fusion of Shallow and Deep Features
title_full LLD-YOLO: A Low-Light Object Detection Algorithm Based on Dynamic Weighted Fusion of Shallow and Deep Features
title_fullStr LLD-YOLO: A Low-Light Object Detection Algorithm Based on Dynamic Weighted Fusion of Shallow and Deep Features
title_full_unstemmed LLD-YOLO: A Low-Light Object Detection Algorithm Based on Dynamic Weighted Fusion of Shallow and Deep Features
title_short LLD-YOLO: A Low-Light Object Detection Algorithm Based on Dynamic Weighted Fusion of Shallow and Deep Features
title_sort lld yolo a low light object detection algorithm based on dynamic weighted fusion of shallow and deep features
topic Keywords object detection
low-light scenarios
YOLO
dynamic feature fusion
url https://ieeexplore.ieee.org/document/10955203/
work_keys_str_mv AT wenhaocai lldyoloalowlightobjectdetectionalgorithmbasedondynamicweightedfusionofshallowanddeepfeatures
AT yajunchen lldyoloalowlightobjectdetectionalgorithmbasedondynamicweightedfusionofshallowanddeepfeatures
AT xiaoyangqiu lldyoloalowlightobjectdetectionalgorithmbasedondynamicweightedfusionofshallowanddeepfeatures
AT meiqiniu lldyoloalowlightobjectdetectionalgorithmbasedondynamicweightedfusionofshallowanddeepfeatures
AT jianyingli lldyoloalowlightobjectdetectionalgorithmbasedondynamicweightedfusionofshallowanddeepfeatures