Improved model MASW YOLO for small target detection in UAV images based on YOLOv8

Abstract The present paper proposes an algorithmic model, MASW-YOLO, that improves YOLOv8n. This model aims to address the problems of small targets, missed detection, and misdetection of UAV viewpoint feature detection targets. The backbone network structure is enhanced by incorporating a multi-sca...

Full description

Saved in:
Bibliographic Details
Main Authors: Xianghe Meng, Fei Yuan, Dexiang Zhang
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-10428-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849343908591435776
author Xianghe Meng
Fei Yuan
Dexiang Zhang
author_facet Xianghe Meng
Fei Yuan
Dexiang Zhang
author_sort Xianghe Meng
collection DOAJ
description Abstract The present paper proposes an algorithmic model, MASW-YOLO, that improves YOLOv8n. This model aims to address the problems of small targets, missed detection, and misdetection of UAV viewpoint feature detection targets. The backbone network structure is enhanced by incorporating a multi-scale convolutional MSCA attention mechanism, which introduces a deep convolution process to aggregate local information. This method aims to increase small-target detection accuracy. Concurrently, the neck network structure is reconstructed, with the fusion effect of multi-scale weakening of non-adjacent levels addressed by using an AFPN progressive pyramid network to replace the PANFPN structure of the base model. The MSCA and AFPN form a multiscale feature synergy mechanism, whereby the response values of MSCA become inputs to AFPN, and the multiscale integration of AFPN further amplifies the advantages of MSCA. The use of flexible non-maximum suppression Soft-NMS is chosen to replace the non-maximum suppression NMS to improve the model’s detection of occlusion and dense targets. The loss function of the model is optimised through the implementation of Wise-IoU, which serves as a replacement for the loss function of the baseline model, thereby enhancing the accuracy of bounding box regression, especially perform better when the target deformation or scale change is large. Experiments conducted on the VisDrone2019 dataset demonstrate that the average detection accuracy of the MASW-YOLO algorithm is 38.3%, which is augmented by 7.9% through the utilisation of the original YOLOv8n network. Furthermore, the number of network parameters is reduced by 19.6%.
format Article
id doaj-art-c152ac7e3a6e47cbac9c52ca6266e41b
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-c152ac7e3a6e47cbac9c52ca6266e41b2025-08-20T03:42:49ZengNature PortfolioScientific Reports2045-23222025-07-0115111810.1038/s41598-025-10428-wImproved model MASW YOLO for small target detection in UAV images based on YOLOv8Xianghe Meng0Fei Yuan1Dexiang Zhang2College of Electrical Engineering and Automation, Anhui UniversityInstitute of Information Engineering, Chinese Academy of SciencesCollege of Electrical Engineering and Automation, Anhui UniversityAbstract The present paper proposes an algorithmic model, MASW-YOLO, that improves YOLOv8n. This model aims to address the problems of small targets, missed detection, and misdetection of UAV viewpoint feature detection targets. The backbone network structure is enhanced by incorporating a multi-scale convolutional MSCA attention mechanism, which introduces a deep convolution process to aggregate local information. This method aims to increase small-target detection accuracy. Concurrently, the neck network structure is reconstructed, with the fusion effect of multi-scale weakening of non-adjacent levels addressed by using an AFPN progressive pyramid network to replace the PANFPN structure of the base model. The MSCA and AFPN form a multiscale feature synergy mechanism, whereby the response values of MSCA become inputs to AFPN, and the multiscale integration of AFPN further amplifies the advantages of MSCA. The use of flexible non-maximum suppression Soft-NMS is chosen to replace the non-maximum suppression NMS to improve the model’s detection of occlusion and dense targets. The loss function of the model is optimised through the implementation of Wise-IoU, which serves as a replacement for the loss function of the baseline model, thereby enhancing the accuracy of bounding box regression, especially perform better when the target deformation or scale change is large. Experiments conducted on the VisDrone2019 dataset demonstrate that the average detection accuracy of the MASW-YOLO algorithm is 38.3%, which is augmented by 7.9% through the utilisation of the original YOLOv8n network. Furthermore, the number of network parameters is reduced by 19.6%.https://doi.org/10.1038/s41598-025-10428-wDeep learningYOLOv8nMSCA attentionAFPNSoft-NMSWise-IoU
spellingShingle Xianghe Meng
Fei Yuan
Dexiang Zhang
Improved model MASW YOLO for small target detection in UAV images based on YOLOv8
Scientific Reports
Deep learning
YOLOv8n
MSCA attention
AFPN
Soft-NMS
Wise-IoU
title Improved model MASW YOLO for small target detection in UAV images based on YOLOv8
title_full Improved model MASW YOLO for small target detection in UAV images based on YOLOv8
title_fullStr Improved model MASW YOLO for small target detection in UAV images based on YOLOv8
title_full_unstemmed Improved model MASW YOLO for small target detection in UAV images based on YOLOv8
title_short Improved model MASW YOLO for small target detection in UAV images based on YOLOv8
title_sort improved model masw yolo for small target detection in uav images based on yolov8
topic Deep learning
YOLOv8n
MSCA attention
AFPN
Soft-NMS
Wise-IoU
url https://doi.org/10.1038/s41598-025-10428-w
work_keys_str_mv AT xianghemeng improvedmodelmaswyoloforsmalltargetdetectioninuavimagesbasedonyolov8
AT feiyuan improvedmodelmaswyoloforsmalltargetdetectioninuavimagesbasedonyolov8
AT dexiangzhang improvedmodelmaswyoloforsmalltargetdetectioninuavimagesbasedonyolov8