Toward Efficient UAV-Based Small Object Detection: A Lightweight Network with Enhanced Feature Fusion

UAV-based small target detection is crucial in environmental monitoring, circuit detection, and related applications. However, UAV images often face challenges such as significant scale variation, dense small targets, high inter-class similarity, and intra-class diversity, which can lead to missed d...

Full description

Saved in:
Bibliographic Details
Main Authors: Xingyu Di, Kangning Cui, Rui-Feng Wang
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/13/2235
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850115538290737152
author Xingyu Di
Kangning Cui
Rui-Feng Wang
author_facet Xingyu Di
Kangning Cui
Rui-Feng Wang
author_sort Xingyu Di
collection DOAJ
description UAV-based small target detection is crucial in environmental monitoring, circuit detection, and related applications. However, UAV images often face challenges such as significant scale variation, dense small targets, high inter-class similarity, and intra-class diversity, which can lead to missed detections, thus reducing performance. To solve these problems, this study proposes a lightweight and high-precision model UAV-YOLO based on YOLOv8s. Firstly, a double separation convolution (DSC) module is designed to replace the Bottleneck structure in the C2f module with deep separable convolution and point-by-point convolution fusion, which can reduce the model parameters and calculation complexity while enhancing feature expression. Secondly, a new SPPL module is proposed, which combines spatial pyramid pooling rapid fusion (SPPF) with long-distance dependency modeling (LSKA) to improve the robustness of the model to multi-scale targets through cross-level feature association. Then, DyHead is used to replace the original detector head, and the discrimination ability of small targets in complex background is enhanced by adaptive weight allocation and cross-scale feature optimization fusion. Finally, the WIPIoU loss function is proposed, which integrates the advantages of Wise-IoU, MPDIoU and Inner-IoU, and incorporates the geometric center of bounding box, aspect ratio and overlap degree into a unified measure to improve the localization accuracy of small targets and accelerate the convergence. The experimental results on the VisDrone2019 dataset showed that compared to YOLOv8s, UAV-YOLO achieved an 8.9% improvement in the recall of mAP@0.5 and 6.8%, while the parameters and calculations were reduced by 23.4% and 40.7%, respectively. Additional evaluations of the DIOR, RSOD, and NWPU VHR-10 datasets demonstrate the generalization capability of the model.
format Article
id doaj-art-d49caae5cd314f52aa17adb1f93dbab7
institution OA Journals
issn 2072-4292
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-d49caae5cd314f52aa17adb1f93dbab72025-08-20T02:36:33ZengMDPI AGRemote Sensing2072-42922025-06-011713223510.3390/rs17132235Toward Efficient UAV-Based Small Object Detection: A Lightweight Network with Enhanced Feature FusionXingyu Di0Kangning Cui1Rui-Feng Wang2School of Communication and Artificial Intelligence, School of Integrated Circuits, Nanjing Institute of Technology, Nanjing 211167, ChinaDepartment of Mathematics, City University of Hong Kong, 83 Tat Chee Ave., Kowloon, Hong KongCollege of Engineering, China Agricultural University, 17 Qinghua East Road, Haidian, Beijing 100083, ChinaUAV-based small target detection is crucial in environmental monitoring, circuit detection, and related applications. However, UAV images often face challenges such as significant scale variation, dense small targets, high inter-class similarity, and intra-class diversity, which can lead to missed detections, thus reducing performance. To solve these problems, this study proposes a lightweight and high-precision model UAV-YOLO based on YOLOv8s. Firstly, a double separation convolution (DSC) module is designed to replace the Bottleneck structure in the C2f module with deep separable convolution and point-by-point convolution fusion, which can reduce the model parameters and calculation complexity while enhancing feature expression. Secondly, a new SPPL module is proposed, which combines spatial pyramid pooling rapid fusion (SPPF) with long-distance dependency modeling (LSKA) to improve the robustness of the model to multi-scale targets through cross-level feature association. Then, DyHead is used to replace the original detector head, and the discrimination ability of small targets in complex background is enhanced by adaptive weight allocation and cross-scale feature optimization fusion. Finally, the WIPIoU loss function is proposed, which integrates the advantages of Wise-IoU, MPDIoU and Inner-IoU, and incorporates the geometric center of bounding box, aspect ratio and overlap degree into a unified measure to improve the localization accuracy of small targets and accelerate the convergence. The experimental results on the VisDrone2019 dataset showed that compared to YOLOv8s, UAV-YOLO achieved an 8.9% improvement in the recall of mAP@0.5 and 6.8%, while the parameters and calculations were reduced by 23.4% and 40.7%, respectively. Additional evaluations of the DIOR, RSOD, and NWPU VHR-10 datasets demonstrate the generalization capability of the model.https://www.mdpi.com/2072-4292/17/13/2235YOLOsmall object detectionUAV aerial photographylightweight model
spellingShingle Xingyu Di
Kangning Cui
Rui-Feng Wang
Toward Efficient UAV-Based Small Object Detection: A Lightweight Network with Enhanced Feature Fusion
Remote Sensing
YOLO
small object detection
UAV aerial photography
lightweight model
title Toward Efficient UAV-Based Small Object Detection: A Lightweight Network with Enhanced Feature Fusion
title_full Toward Efficient UAV-Based Small Object Detection: A Lightweight Network with Enhanced Feature Fusion
title_fullStr Toward Efficient UAV-Based Small Object Detection: A Lightweight Network with Enhanced Feature Fusion
title_full_unstemmed Toward Efficient UAV-Based Small Object Detection: A Lightweight Network with Enhanced Feature Fusion
title_short Toward Efficient UAV-Based Small Object Detection: A Lightweight Network with Enhanced Feature Fusion
title_sort toward efficient uav based small object detection a lightweight network with enhanced feature fusion
topic YOLO
small object detection
UAV aerial photography
lightweight model
url https://www.mdpi.com/2072-4292/17/13/2235
work_keys_str_mv AT xingyudi towardefficientuavbasedsmallobjectdetectionalightweightnetworkwithenhancedfeaturefusion
AT kangningcui towardefficientuavbasedsmallobjectdetectionalightweightnetworkwithenhancedfeaturefusion
AT ruifengwang towardefficientuavbasedsmallobjectdetectionalightweightnetworkwithenhancedfeaturefusion