A multi-scale small object detection algorithm SMA-YOLO for UAV remote sensing images

Abstract Detecting small objects in complex remote sensing environments presents significant challenges, including insufficient extraction of local spatial information, rigid feature fusion, and limited global feature representation. In addition, improving model performance requires a delicate balan...

Full description

Saved in:
Bibliographic Details
Main Authors: Shilong Zhou, Haijin Zhou, Lei Qian
Format: Article
Language:English
Published: Nature Portfolio 2025-03-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-92344-7
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849390370678374400
author Shilong Zhou
Haijin Zhou
Lei Qian
author_facet Shilong Zhou
Haijin Zhou
Lei Qian
author_sort Shilong Zhou
collection DOAJ
description Abstract Detecting small objects in complex remote sensing environments presents significant challenges, including insufficient extraction of local spatial information, rigid feature fusion, and limited global feature representation. In addition, improving model performance requires a delicate balance between improving accuracy and managing computational complexity. To address these challenges, we propose the SMA-YOLO algorithm. First, we introduce the Non-Semantic Sparse Attention (NSSA) mechanism in the backbone network, which efficiently extracts non-semantic features related to the task, thus improving the model’s sensitivity to small objects. In the model’s throat, we design a Bidirectional Multi-Branch Auxiliary Feature Pyramid Network (BIMA-FPN), which integrates high-level semantic information with low-level spatial details, improving small object detection while expanding multi-scale receptive fields. Finally, we incorporate a Channel-Space Feature Fusion Adaptive Head (CSFA-Head), which fully handles multi-scale features and adaptively handles consistency problems of different scales, further improving the robustness of the model in complex scenarios. Experimental results on the VisDrone2019 dataset show that SMA-YOLO achieves a 13% improvement in mAP compared to the baseline model, demonstrating exceptional adaptability in small object detection tasks for remote sensing imagery. These results provide valuable insights and new approaches to further advance research in this area.
format Article
id doaj-art-9cd4c8160dd94d70900c32e6c0078fb6
institution Kabale University
issn 2045-2322
language English
publishDate 2025-03-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-9cd4c8160dd94d70900c32e6c0078fb62025-08-20T03:41:41ZengNature PortfolioScientific Reports2045-23222025-03-0115111510.1038/s41598-025-92344-7A multi-scale small object detection algorithm SMA-YOLO for UAV remote sensing imagesShilong Zhou0Haijin Zhou1Lei Qian2Key Laboratory of Environmental Optics and Technology, Anhui Institute of Optics and Fine Mechanics, Hefei Institutes of Physical Science, Chinese Academy of SciencesKey Laboratory of Environmental Optics and Technology, Anhui Institute of Optics and Fine Mechanics, Hefei Institutes of Physical Science, Chinese Academy of SciencesKey Laboratory of Environmental Optics and Technology, Anhui Institute of Optics and Fine Mechanics, Hefei Institutes of Physical Science, Chinese Academy of SciencesAbstract Detecting small objects in complex remote sensing environments presents significant challenges, including insufficient extraction of local spatial information, rigid feature fusion, and limited global feature representation. In addition, improving model performance requires a delicate balance between improving accuracy and managing computational complexity. To address these challenges, we propose the SMA-YOLO algorithm. First, we introduce the Non-Semantic Sparse Attention (NSSA) mechanism in the backbone network, which efficiently extracts non-semantic features related to the task, thus improving the model’s sensitivity to small objects. In the model’s throat, we design a Bidirectional Multi-Branch Auxiliary Feature Pyramid Network (BIMA-FPN), which integrates high-level semantic information with low-level spatial details, improving small object detection while expanding multi-scale receptive fields. Finally, we incorporate a Channel-Space Feature Fusion Adaptive Head (CSFA-Head), which fully handles multi-scale features and adaptively handles consistency problems of different scales, further improving the robustness of the model in complex scenarios. Experimental results on the VisDrone2019 dataset show that SMA-YOLO achieves a 13% improvement in mAP compared to the baseline model, demonstrating exceptional adaptability in small object detection tasks for remote sensing imagery. These results provide valuable insights and new approaches to further advance research in this area.https://doi.org/10.1038/s41598-025-92344-7Remote sensing imagesObject detectionMulti-branch auxiliaryFeature fusion
spellingShingle Shilong Zhou
Haijin Zhou
Lei Qian
A multi-scale small object detection algorithm SMA-YOLO for UAV remote sensing images
Scientific Reports
Remote sensing images
Object detection
Multi-branch auxiliary
Feature fusion
title A multi-scale small object detection algorithm SMA-YOLO for UAV remote sensing images
title_full A multi-scale small object detection algorithm SMA-YOLO for UAV remote sensing images
title_fullStr A multi-scale small object detection algorithm SMA-YOLO for UAV remote sensing images
title_full_unstemmed A multi-scale small object detection algorithm SMA-YOLO for UAV remote sensing images
title_short A multi-scale small object detection algorithm SMA-YOLO for UAV remote sensing images
title_sort multi scale small object detection algorithm sma yolo for uav remote sensing images
topic Remote sensing images
Object detection
Multi-branch auxiliary
Feature fusion
url https://doi.org/10.1038/s41598-025-92344-7
work_keys_str_mv AT shilongzhou amultiscalesmallobjectdetectionalgorithmsmayoloforuavremotesensingimages
AT haijinzhou amultiscalesmallobjectdetectionalgorithmsmayoloforuavremotesensingimages
AT leiqian amultiscalesmallobjectdetectionalgorithmsmayoloforuavremotesensingimages
AT shilongzhou multiscalesmallobjectdetectionalgorithmsmayoloforuavremotesensingimages
AT haijinzhou multiscalesmallobjectdetectionalgorithmsmayoloforuavremotesensingimages
AT leiqian multiscalesmallobjectdetectionalgorithmsmayoloforuavremotesensingimages