.png){kind=icon}
.png){kind=icon}
Return
SD-YOLO: A lightweight and high-performance deep model for small and dense object detection
.png){kind=icon}
PRE
AI
P
M
D
T
DOI：10.1007/s11760-025-04932-9.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Detecting small, dense, and occluded objects in UAV-based remote sensing imagery is a crucial challenge, requiring algorithms that balance high accuracy with real-time efficiency. To address this, we introduce SD-YOLO, a model enhancing YOLOv8 through three key innovations. First, its lightweight design prunes redundant low-resolution feature maps and adds a tiny detection head, which reduces parameters considerably. Second, the backbone is enhanced by replacing standard C2f blocks with our C2f-DMSC for superior multi-dimensional feature extraction, and by integrating a Transformer module to capture global context. Third, our MSCBAM attention module expands the receptive field and refines feature processing by emphasizing critical regions. To meet diverse application needs, we offer two variants: the highly efficient SD-YOLOn and the high-accuracy SD-YOLOs, created via channel scaling. Evaluations show SD-YOLOn achieves 35.8%\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$35.8\%$$\end{document}, 76.3%\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$76.3\%$$\end{document}, and 43.7%\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$43.7\%$$\end{document}mAP0.5\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\texttt {mAP}_{0.5}$$\end{document} results on VisDrone-2019, LEVIR-Ship, and DOTA, respectively, with a model size three times smaller, thus demonstrating its effectiveness for small, dense object detection in remote sensing.
Keywords:
Object detection
Remote sensing
Deep learning
Aerial imagery
Unmanned aerial vehicles
You Only Look Once
Journal
IF:
2.1
Papers:
778
Citations:
4.6K
Organization
Cited Papers