GDE-YOLO：一种用于无人机图像的轻量级高精度小目标检测器
GDE-YOLO: A Lightweight and High-Precision Small Object Detector for UAV Imagery
DOI: 10.12677/csa.2026.167248, PDF,   
作者: 李 淼：河北地质大学信息工程学院，河北 石家庄；硕良勋*：河北地质大学信息工程学院，河北 石家庄；智能传感物联网技术河北省工程研究中心，河北 石家庄；河北省地质环境智能感知与数据处理重点实验室，河北 石家庄
关键词: 无人机遥感图像；小目标检测；YOLOv11s；特征融合；VisDrone2019；UAV Remote Sensing Images； Small Object Detection； YOLOv11s； Feature Fusion； VisDrone2019
摘要: 针对无人机遥感图像中目标尺度小、背景复杂、密集遮挡导致检测精度低的问题，提出一种基于YOLOv11s改进的小目标检测算法GDE-YOLO。该算法引入C3k2_StarCross模块增强小目标边缘与多尺度特征表达，设计动态选择频率融合模块(DSFA)抑制复杂背景噪声，采用尺度动态自适应融合(SDAF)提高跨尺度特征融合与空间对齐能力，并通过动态因果跨门控检测头(DCPA_Head)提升密集目标定位精度。在VisDrone2019数据集上进行实验，结果表明，GDE-YOLO在VisDrone2019数据集上的mAP50达到44.9%，较YOLOv11s提高8.0个百分点模型参数量为5.39 M，具有较好的检测精度和应用价值。
Abstract: To address the low detection accuracy caused by small object scales, complex backgrounds, dense distributions, and occlusions in UAV remote sensing images, this paper proposes GDE-YOLO, an improved small object detection algorithm based on YOLOv11s. The proposed algorithm introduces the C3k2_StarCross module to enhance edge information and multi-scale feature representation for small objects. A Dynamic Selection Frequency Fusion Module (DSFA) is designed to suppress complex background noise. In addition, Scale Dynamic Adaptive Fusion (SDAF) is adopted to improve cross-scale feature fusion and spatial alignment. Furthermore, Dynamic Causal Prism Adapter Head (DCPA_Head) is employed to enhance localization accuracy for densely distributed objects. Experiments conducted on the VisDrone2019 dataset demonstrate that GDE-YOLO achieves an mAP50 of 44.9%, which is 8.0 percentage points higher than that of YOLOv11s. Meanwhile, the model contains only 5.39 M parameters, indicating good detection accuracy and practical application value.
文章引用：李淼, 硕良勋. GDE-YOLO：一种用于无人机图像的轻量级高精度小目标检测器[J]. 计算机科学与应用, 2026, 16(7): 140-153. https://doi.org/10.12677/csa.2026.167248

参考文献

[1] 李新晨, 李晓飞. 基于YOLOv5s的无人机拍摄场景下的目标检测[J]. 智能计算机与应用, 2025, 15(4): 151-157.
[2] 李云龙. 基于改进YOLOv11s的无人机航拍图像小目标检测模型[J]. 计算机科学与应用, 2026, 16(2): 522-531.
[3] Zhou, S., Zhou, H. and Qian, L. (2025) A Multi-Scale Small Object Detection Algorithm SMA-YOLO for UAV Remote Sensing Images. Scientific Reports, 15, Article No. 9255. [Google Scholar] [CrossRef] [PubMed]
[4] Li, H., Li, Y., Xiao, L., Zhang, Y., Cao, L. and Wu, D. (2025) RLRD-YOLO: An Improved YOLOv8 Algorithm for Small Object Detection from an Unmanned Aerial Vehicle (UAV) Perspective. Drones, 9, Article 293. [Google Scholar] [CrossRef] 
[5] 李世伟. 基于YOLOv5算法的目标检测与车牌识别系统[J]. 电子技术与软件工程, 2022(1): 138-141.
[6] Redmon, J., Divvala, S., Girshick, R. and Farhadi, A. (2016) You Only Look Once: Unified, Real-Time Object Detection. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 27-30 June 2016, 79-788. [Google Scholar] [CrossRef] 
[7] Redmon, J. and Farhadi, A. (2018) YOLOv3: An Incremental Improvement.
[8] Wang, C.Y., Yeh, I.H. and Liao, H.Y.M. (2024) YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information. In: Lecture Notes in Computer Science, Springer, 1-21. [Google Scholar] [CrossRef] 
[9] Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., et al. (2024) YOLOv10: Real-Time End-to-End Object Detection. Advances in Neural Information Processing Systems, 37, 107984-108011.
[10] Ren, S., He, K., Girshick, R. and Sun, J. (2017) Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 1137-1149. [Google Scholar] [CrossRef] [PubMed]
[11] Zhou, S., Yang, L., Liu, H., Zhou, C., Liu, J., Zhao, S., et al. (2025) A Lightweight Drone Detection Method Integrated into a Linear Attention Mechanism Based on Improved YOLOv11. Remote Sensing, 17, Article 705. [Google Scholar] [CrossRef] 
[12] Zhu, X., Lyu, S., Wang, X. and Zhao, Q. (2021) TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-Captured Scenarios. 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Montreal, 11-17 October 2021, 2778-2788. [Google Scholar] [CrossRef] 
[13] Zhao, Q., Liu, B., Lyu, S., Wang, C. and Zhang, H. (2023) TPH-YOLOv5++: Boosting Object Detection on Drone-Captured Scenarios with Cross-Layer Asymmetric Transformer. Remote Sensing, 15, Article 1687. [Google Scholar] [CrossRef] 
[14] He, A., Li, X., Wu, X., Su, C., Chen, J., Xu, S., et al. (2024) ALSS-YOLO: An Adaptive Lightweight Channel Split and Shuffling Network for TIR Wildlife Detection in UAV Imagery. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 17, 17308-17326. [Google Scholar] [CrossRef] 
[15] Wan, Z., Lan, Y., Xu, Z., Shang, K. and Zhang, F. (2025) DAU-YOLO: A Lightweight and Effective Method for Small Object Detection in UAV Images. Remote Sensing, 17, Article 1768. [Google Scholar] [CrossRef] 
[16] Hou, T., Leng, C., Wang, J., Pei, Z., Peng, J., Cheng, I., et al. (2025) MFEL-YOLO for Small Object Detection in UAV Aerial Images. Expert Systems with Applications, 291, Article 128459. [Google Scholar] [CrossRef] 
[17] Zhang, Y., Ye, M., Zhu, G., Liu, Y., Guo, P. and Yan, J. (2024) FFCA-YOLO for Small Object Detection in Remote Sensing Images. IEEE Transactions on Geoscience and Remote Sensing, 62, 1-15. [Google Scholar] [CrossRef] 
[18] Fan, K., Li, Q., Li, Q., Zhong, G., Chu, Y., Le, Z., et al. (2024) YOLO-Remote: An Object Detection Algorithm for Remote Sensing Targets. IEEE Access, 12, 155654-155665. [Google Scholar] [CrossRef] 
[19] He, Z., She, R., Tan, B., Li, J. and Lei, X. (2026) SSCW-YOLO: A Lightweight and High-Precision Model for Small Object Detection in UAV Scenarios. Drones, 10, Article 41. [Google Scholar] [CrossRef] 
[20] Munir, A., Siddiqui, A.J., Hossain, M.S. and El-Maleh, A. (2025) YOLO-RAW: Advancing UAV Detection with Robustness to Adverse Weather Conditions. IEEE Transactions on Intelligent Transportation Systems, 26, 7857-7873. [Google Scholar] [CrossRef] 
[21] 蒲小莉, 赖惠成, 高古学. BF-YOLO: 基于YOLOv8改进的小目标检测算法[J]. 计算机工程与科学, 2025, 47(8): 1425-1434.
[22] Wei, L., Afzal, I. and Guo, J. (2025) CF-YOLO: A Cross-Layer Feature Fusion YOLO Framework for Small Object Detection. Journal of Electronic Imaging, 34, Article 053006. [Google Scholar] [CrossRef] 
[23] Wang, C., Han, Y., Yang, C., Wu, M., Chen, Z., Yun, L., et al. (2025) CF-YOLO for Small Target Detection in Drone Imagery Based on YOLOv11 Algorithm. Scientific Reports, 15, Article No. 16741. [Google Scholar] [CrossRef] [PubMed]