UAV small target detection algorithm based on reconstruction of YOLOv11

doi:10.3785/j.issn.1008-973X.2026.02.008

Journal of ZheJiang University (Engineering Science)

2026, Vol. 60

Issue (2): 303-312 DOI: 10.3785/j.issn.1008-973X.2026.02.008

UAV small target detection algorithm based on reconstruction of YOLOv11

Yuyu MENG(

),Chuile KONG,Jiuyuan HUO*(

),Zeyu WU

School of Electronics and Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China

Download:

HTML

PDF(3266KB) HTML
Export: BibTeX | EndNote (RIS)

Abstract

A small target detection algorithm (DLSRF-Net) for multi-scale complex scenarios from UAV viewpoint was proposed by reconstructing the YOLOv11, to address the insufficient feature extraction and poor detection performance of existing algorithms in small target detection under UAV viewpoint due to small target sizes, complex backgrounds, and multi-scale information in the scenarios. The adaptive depthwise separative receptive field attention convolution module (DWRFAConv) was proposed to improve the model’s ability to extract the receptive field features of small targets and reduce the model load. The multi-branch lightweight multi-scale linear attention mechanism was designed to enhance the model’s attention to small targets. The RSCDI module was designed as the upsampling layer and fully connected layer of the model to solve the problem of feature information loss, suppress the useless information, and improve the model’s detection accuracy. The model sizes were classified into two categories based on parameter count and computational complexity, and experimental validation was carried out on the VisDrone2021 dataset. The results showed that the proposed algorithm achieved the optimal performance under both model size categories, and the generalization ability of the proposed algorithm was verified on the DOTA and the SSDD datasets.

Key words： small target detection complex scenario YOLOv11 multi-scale linear attention RSCDI

Received: 04 April 2025 Published: 03 February 2026

CLC:

TP 391.4

Fund: 国家自然科学基金资助项目（62262038）；甘肃省重点研发计划资助项目（25YFGA045）.

Corresponding Authors: Jiuyuan HUO E-mail: 529267338@qq.com;huojy@mail.lzjtu.cn

	Service
	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Yuyu MENG
	Chuile KONG
	Jiuyuan HUO
	Zeyu WU

Cite this article:

Yuyu MENG,Chuile KONG,Jiuyuan HUO,Zeyu WU. UAV small target detection algorithm based on reconstruction of YOLOv11. Journal of ZheJiang University (Engineering Science), 2026, 60(2): 303-312.

URL:

https://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2026.02.008 OR https://www.zjujournals.com/eng/Y2026/V60/I2/303

重构YOLOv11的无人机小目标检测算法

无人机视角下目标偏小、背景复杂、场景包含多尺度信息，现有算法在小目标检测中特征提取不充分、检测效果不佳，为此提出面向多尺度复杂场景、无人机视角下基于重构YOLOv11的小目标检测算法DLSRF-Net. 提出自适应深度可分离感受野注意力卷积模块(DSRFAConv)，提升模型对小目标感受野特征的提取能力并降低模型负载；设计多分支轻量化多尺度线性注意力机制，提升模型对小目标的关注度；设计RSCDI模块作为模型的上采样层和全连接层，解决特征信息丢失问题并抑制无用信息，提升模型的检测精度. 按照参数量和计算量将模型尺寸分为2类，并在VisDrone2021数据集上进行实验验证，结果表明，所提算法在2类模型尺寸下均取得了最优性能. 在DOTA和SSDD数据集上验证了所提算法的泛化能力.

关键词： 小目标检测, 复杂场景, YOLOv11, 多尺度线性注意力, RSCDI

Fig.1 Overall structure of UAV small target detection algorithm based on reconstruction of YOLOv11

Fig.2 Overall process of receptive-field attention convolution for dynamically extracting receptive-field spatial features

Fig.3 Structure of adaptive depthwise separative receptive field attention convolution module

Fig.4 Structure of multi-branch lightweight multi-scale linear attention module

Fig.5 Structure of receptive-field semantic cross-level depthwise-separable feature fusion module

Tab.1 Ablation experimental results of proposed modules on VisDrone dataset

Tab.2 Performance comparison of different algorithms on VisDrone2021 dataset

Fig.6 Comparison of mAP₅₀ and mAP_50-90 of different models under N category

Fig.7 Comparison of mAP₅₀ and mAP_50-90 of different models under M category

Fig.8 Comparison of detection precision of proposed model and baseline under model sizes for various targets in VisDrone2021 dataset

Fig.9 Comparison of heatmap generation results of benchmark model and proposed model

Tab.3 Experimental results of model generalization on DOTA and SSDD datasets


[1]	钟博, 王鹏飞, 王乙乔, 等基于深度学习的EEG数据分析技术综述[J]. 浙江大学学报: 工学版, 2024, 58 (5): 879- 890 ZHONG Bo, WANG Pengfei, WANG Yiqiao, et al Survey of deep learning based EEG data analysis technology[J]. Journal of Zhejiang University: Engineering Science, 2024, 58 (5): 879- 890

[2]	刘亮. 高起点发展低空经济 [N]. 经济日报, 2025-03-30(7).

[3]	孙卫国, 吕人力, 李凌威, 等. 低空经济面临的机遇、挑战与城市空中交通规划展望 [J]. 城市交通, 2025, 23(2): 13–19. SUN Weiguo, LYU Renli, LI Lingwei, et al. Opportunities and challenges for low-altitude economy and future prospects of urban air mobility planning [J]. Urban Transport of China, 2025, 23(2): 13–19.

[4]	GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Columbus: IEEE, 2014: 580–587.

[5]	GIRSHICK R. Fast R-CNN [C]// Proceedings of the IEEE International Conference on Computer Vision. Santiago: IEEE, 2015: 1440–1448.

[6]	REN S, HE K, GIRSHICK R, et al Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39 (6): 1137- 1149 doi: 10.1109/TPAMI.2016.2577031

[7]	LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector [C]// 14th European Conference on Computer Vision. Amsterdam: Springer, 2016: 21–37.

[8]	PULIPALUPULA M, PATLOLA S, NAYAKI M, et al. Object detection using you only look once (YOLO) algorithm in convolution neural network (CNN) [C]// Proceedings of the IEEE 8th International Conference for Convergence in Technology (I2CT). Lonavla: IEEE, 2023: 1–4.

[9]	宋耀莲, 王粲, 李大焱, 等基于改进YOLOv5s的无人机小目标检测算法[J]. 浙江大学学报: 工学版, 2024, 58 (12): 2417- 2426 SONG Yaolian, WANG Can, LI Dayan, et al UAV small target detection algorithm based on improved YOLOv5s[J]. Journal of Zhejiang University: Engineering Science, 2024, 58 (12): 2417- 2426

[10]	韩俊, 袁小平, 王准, 等基于YOLOv5s的无人机密集小目标检测算法[J]. 浙江大学学报: 工学版, 2023, 57 (6): 1224- 1233 HAN Jun, YUAN Xiaoping, WANG Zhun, et al UAV dense small target detection algorithm based on YOLOv5s[J]. Journal of Zhejiang University: Engineering Science, 2023, 57 (6): 1224- 1233

[11]	杨智能, 钟小勇, 李华耀, 等. 改进YOLOv8n的航拍小目标检测算法 [J]. 电光与控制, 2025, 32(7): 27–32. YANG Zhineng, ZHONG Xiaoyong, LI Huayao, et al. Aerial small target detection based on improved YOLOv8n algorithm [J]. Electronics Optics & Control, 2025, 32(7): 27–32.

[12]	向征, 张佳浩基于SM-YOLOv8n的无人机航拍目标检测[J]. 海军航空大学学报, 2025, 40 (2): 321- 328 XIANG Zheng, ZHANG Jiahao UAV aerial target detection based on SM-YOLOv8n[J]. Journal of Naval Aviation University, 2025, 40 (2): 321- 328

[13]	SUN Y, LAN Z, SUN Y, et al Ldstd: low-altitude drone aerial small target detector[J]. The Journal of Supercomputing, 2025, 81 (2): 414 doi: 10.1007/s11227-025-06950-3

[14]	LIU J, WEN B, XIAO J, et al Design of UAV target detection network based on deep feature fusion and optimization with small targets in complex contexts[J]. Neurocomputing, 2025, 639: 130207 doi: 10.1016/j.neucom.2025.130207

[15]	YANG W, HE Q, LI Z A lightweight multidimensional feature network for small object detection on UAVs[J]. Pattern Analysis and Applications, 2025, 28 (1): 29 doi: 10.1007/s10044-024-01389-3

[16]	KHANAM R, HUSSAIN M. YOLOv11: an overview of the key architectural enhancements [EB/OL]. (2024–10–23) [2025–05–20]. https://www.arxiv.org/abs/2410.17725.

[17]	ZHANG X, LIU C, YANG D, et al. RFAConv: innovating spatial attention and standard convolutional operation [EB/OL]. (2024–03–28) [2025–05–20]. https://arxiv.org/abs/2304.03198.

[18]	CHOLLET F. Xception: deep learning with depthwise separable convolutions [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 1800–1807.

[19]	CAI H, LI J, HU M, et al. EfficientViT: multi-scale linear attention for high-resolution dense prediction [EB/OL]. (2024–02–06) [2025–05–20]. https://arxiv.org/abs/2205.14756.

[20]	CAO Y, HE Z, WANG L, et al. VisDrone-DET2021: the vision meets drone object detection challenge results [C]// Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops. Montreal: IEEE, 2021: 2847–2854.

[21]	PENG Y, CHEN D Z, SONKA M. U-Net V2: rethinking the skip connections of U-Net for medical image segmentation [C]// Proceedings of the IEEE 22nd International Symposium on Biomedical Imaging. Houston: IEEE, 2025: 1–5.

[1]	Yahong ZHAI,Yaling CHEN,Longyan XU,Yu GONG. Improved YOLOv8s lightweight small target detection algorithm of UAV aerial image[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(8): 1708-1717.

[2]	Junyin WANG,Bin WEN,Yanjun SHEN,Jun ZHANG,Zihao WANG. Surface defect detection method for aluminum profiles based on improved YOLOv7-tiny[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(3): 523-534.

[3]	Huijuan ZHANG,Kunpeng LI,Miaoxin JI,Zhenjiang LIU,Jianjuan LIU,Chi ZHANG. UAV detection algorithm based on spatial correlation enhancement[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(3): 468-479.

[4]	Henghui MO,linjing WEI. Improved YOLOv7 based apple target detection in complex environment[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(12): 2447-2458.

[5]	Jun HAN,Xiao-ping YUAN,Zhun WANG,Ye CHEN. UAV dense small target detection algorithm based on YOLOv5s[J]. Journal of ZheJiang University (Engineering Science), 2023, 57(6): 1224-1233.

Viewed

Full text

Abstract

Cited

Shared

Discussed