Fusion of multi-scale attention for aerial images small-target detection model based on PARE-YOLO
Abstract In view of the complex environments and varying object scales in drone-captured imagery, a novel PARE-YOLO algorithm based on YOLOv8 for small object detection is proposed. This model enhances feature extraction and fusion across multiple scales through a restructured neck network. Addition...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-88857-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823862306512044032 |
|---|---|
| author | Huiying Zhang Pan Xiao Feifan Yao Qinghua Zhang Yifei Gong |
| author_facet | Huiying Zhang Pan Xiao Feifan Yao Qinghua Zhang Yifei Gong |
| author_sort | Huiying Zhang |
| collection | DOAJ |
| description | Abstract In view of the complex environments and varying object scales in drone-captured imagery, a novel PARE-YOLO algorithm based on YOLOv8 for small object detection is proposed. This model enhances feature extraction and fusion across multiple scales through a restructured neck network. Additionally, it incorporates a lightweight detection head that is optimized for small objects, thereby significantly improving detection performance in cluttered and intricate backgrounds. To further enhance the extraction of small object features, the conventional C2f is replaced with a novel architecture. Moreover, the EMA-GIoU loss function is proposed to mitigate class imbalance and enhance robustness, particularly in scenarios characterized by skewed class distributions. Evaluation on the VisDrone2019 dataset indicates that PARE-YOLO achieves a 5.9% improvement in mean Average Precision (mAP) at a threshold of 0.5, compared to the original YOLOv8 model. In addition, the PARE-YOLO model exhibits significant robustness, achieving a mean Average Precision (mAP) at a threshold of 0.5 values on the HIT-UAV dataset that are 0.8%, 0.5%, and 1.2% higher than those of YOLOv8, YOLOv10, and RT-DETR. These results underscore the effectiveness of PARE-YOLO in addressing the challenges inherent in aerial scenarios. The code will be available online (https://github.com/Sunnyxiao69/PARE-YOLO). |
| format | Article |
| id | doaj-art-6b0a0545b4664891bb7630097bd30a12 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-6b0a0545b4664891bb7630097bd30a122025-02-09T12:32:35ZengNature PortfolioScientific Reports2045-23222025-02-0115111710.1038/s41598-025-88857-wFusion of multi-scale attention for aerial images small-target detection model based on PARE-YOLOHuiying Zhang0Pan Xiao1Feifan Yao2Qinghua Zhang3Yifei Gong4College of Information and Control Engineering, Jilin Institute of Chemical Technology, JilinCollege of Information and Control Engineering, Jilin Institute of Chemical Technology, JilinCollege of Information and Control Engineering, Jilin Institute of Chemical Technology, JilinCollege of Information and Control Engineering, Jilin Institute of Chemical Technology, JilinCollege of Information and Control Engineering, Jilin Institute of Chemical Technology, JilinAbstract In view of the complex environments and varying object scales in drone-captured imagery, a novel PARE-YOLO algorithm based on YOLOv8 for small object detection is proposed. This model enhances feature extraction and fusion across multiple scales through a restructured neck network. Additionally, it incorporates a lightweight detection head that is optimized for small objects, thereby significantly improving detection performance in cluttered and intricate backgrounds. To further enhance the extraction of small object features, the conventional C2f is replaced with a novel architecture. Moreover, the EMA-GIoU loss function is proposed to mitigate class imbalance and enhance robustness, particularly in scenarios characterized by skewed class distributions. Evaluation on the VisDrone2019 dataset indicates that PARE-YOLO achieves a 5.9% improvement in mean Average Precision (mAP) at a threshold of 0.5, compared to the original YOLOv8 model. In addition, the PARE-YOLO model exhibits significant robustness, achieving a mean Average Precision (mAP) at a threshold of 0.5 values on the HIT-UAV dataset that are 0.8%, 0.5%, and 1.2% higher than those of YOLOv8, YOLOv10, and RT-DETR. These results underscore the effectiveness of PARE-YOLO in addressing the challenges inherent in aerial scenarios. The code will be available online (https://github.com/Sunnyxiao69/PARE-YOLO).https://doi.org/10.1038/s41598-025-88857-wLightweight detection headAerial small object detectionYOLOEMA-GIoU |
| spellingShingle | Huiying Zhang Pan Xiao Feifan Yao Qinghua Zhang Yifei Gong Fusion of multi-scale attention for aerial images small-target detection model based on PARE-YOLO Scientific Reports Lightweight detection head Aerial small object detection YOLO EMA-GIoU |
| title | Fusion of multi-scale attention for aerial images small-target detection model based on PARE-YOLO |
| title_full | Fusion of multi-scale attention for aerial images small-target detection model based on PARE-YOLO |
| title_fullStr | Fusion of multi-scale attention for aerial images small-target detection model based on PARE-YOLO |
| title_full_unstemmed | Fusion of multi-scale attention for aerial images small-target detection model based on PARE-YOLO |
| title_short | Fusion of multi-scale attention for aerial images small-target detection model based on PARE-YOLO |
| title_sort | fusion of multi scale attention for aerial images small target detection model based on pare yolo |
| topic | Lightweight detection head Aerial small object detection YOLO EMA-GIoU |
| url | https://doi.org/10.1038/s41598-025-88857-w |
| work_keys_str_mv | AT huiyingzhang fusionofmultiscaleattentionforaerialimagessmalltargetdetectionmodelbasedonpareyolo AT panxiao fusionofmultiscaleattentionforaerialimagessmalltargetdetectionmodelbasedonpareyolo AT feifanyao fusionofmultiscaleattentionforaerialimagessmalltargetdetectionmodelbasedonpareyolo AT qinghuazhang fusionofmultiscaleattentionforaerialimagessmalltargetdetectionmodelbasedonpareyolo AT yifeigong fusionofmultiscaleattentionforaerialimagessmalltargetdetectionmodelbasedonpareyolo |