Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Automation and Machine Learning
  4. Vol 6, Issue 2, 2025

Small Target Detection Algorithm for UAV Aerial Photography Based on YOLOv11n

Download as PDF

DOI: 10.23977/autml.2025.060203 | Downloads: 3 | Views: 82

Author(s)

Lingsheng Liang 1, Zijian Dong 1, Zhaojin Huangfu 1, Xinrui Chen 1

Affiliation(s)

1 School of Electronic Engineering, Jiangsu Ocean University, Lianyungang, Jiangsu, 22000, China

Corresponding Author

Zijian Dong

ABSTRACT

To address the challenges of small target detection in aerial images captured by unmanned aerial vehicles (UAVs), such as complex backgrounds, dense targets, large scale variations, and mobile deployment, this paper proposes an improved algorithm, RRF-YOLOv11n, based on the YOLOv11n model. Firstly, a convolutional layer C3K2-RVB-EMA is constructed by integrating RepViTBlock and an efficient multi-scale attention module (EMA), enhancing the model's feature extraction capability for multi-scale targets in complex backgrounds, especially for significantly deformed small targets. Secondly, to deal with the situation where small targets are more numerous in UAV aerial images, a new small target detection layer P2 (PredictionLayer2) is added and the large target detection layer P5 is removed, effectively improving the capture accuracy of small target features while reducing redundant computations in the large target detection layer. Thirdly, a Re-Calibration FPN is introduced to replace the traditional pyramid, recalibrating the boundary and semantic information in features and enhancing the weight of important features. Finally, a Focaler-DIoU loss function combining Focal Loss and DIoU is proposed, optimizing the accuracy and convergence speed of bounding box regression and solving the sample imbalance problem in small target detection. Experimental results show that RRF-YOLOv11n outperforms the original YOLOv11n model by 6.9% in the mAP50 metric on the Vis-Drone2019 dataset, reaching 41.2%, and enhances the detection accuracy of small targets in UAV aerial images. Compared with other advanced target detection algorithms, this algorithm demonstrates superior performance in both detection accuracy and speed.

KEYWORDS

YOLOv11n, Small Target Detection, Recalibrated Feature Pyramid, Focal-DIoU

CITE THIS PAPER

Lingsheng Liang, Zijian Dong, Zhaojin Huangfu, Xinrui Chen, Small Target Detection Algorithm for UAV Aerial Photography Based on YOLOv11n. Automation and Machine Learning (2025) Vol. 6: 21-31. DOI: http://dx.doi.org/10.23977/autml.2025.060203.

REFERENCES

[1] Y. Liu, P. Sun, N. Wergeles, et al., A survey and performance evaluation of deep learning methods for small object detection[J]. Expert Systems with Applications, 2021, 172: 114602.
[2] Liu, W., Angelov, D., Erhan, D., et al. SSD: Single shot multibox detector. Computer Vision – ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I, 21-37.
[3] T.Y. Ross, G. Dollár, Focal loss for dense object detection, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 2980-2988.
[4] R. Girshick, J. Donahue, T. Darrell, et al., Rich feature hierarchies for accurate object detection and semantic segmentation, in: 27th IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, JUN 23-28, 2014, CVPR, Comp Vis Fdn; IEEE; IEEE Comp Soc, 2014, pp. 580-587.
[5] S.Q. Ren, K.M. He, R. Girshick, 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.
[6] Y. Hou, Y. Wu, X.R. Kou, et al., Improved YOLOv8 algorithm for small target detection in UAV aerial images[J]. Computer Engineering and Applications, (Online) 2025, pp. 21-37.
[7] B. Li, S.L. Li, Improved YOLOv11n algorithm for UAV small target detection[J]. Computer Engineering and Applications, 2025, 61(7): 96-104.
[8] Y.F. Peng, T. Zhao, Y.K. Chen, et al., UAV small target detection algorithm based on contextual information and feature refinement[J]. Computer Engineering and Applications, 2024, 60(5): 183-190.
[9] X. Zhao, L.L. Chen, W.C. Yang, et al., DY-YOLOv5: Aerial image object detection based on multi-attention mechanism[J]. Computer Engineering and Applications, 2024, 60(7): 183-191.
[10] Q. Zhou, G.Q. Tan, S.L. Yin, et al., Improved YOLOv5s algorithm for road object detection[J]. Chinese Journal of Liquid Crystals and Displays, 2023, 38(5): 680-690.
[11]  D. Du, P. Zhu, L. Wen, et al., VisDrone-DET2019: the vision meets drone object detection in image challenge results, in: Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision Workshops, Piscataway: IEEE, 2019, pp. 213-226.
[12] Q. Zhao, B. Liu, S. Lyu, et al., TPH-YOLOv5++: Boosting object detection on drone-captured scenarios with cross-layer asymmetric transformer[J]. Remote Sensing, 2023, 15(6): 1687.
[13] Y.W. Li, Y.P. Feng, W.Z. An, et al., Small target detection algorithm in UAV images based on improved YOLOv8[J]. Chinese Journal of High Technology Letters, 2024, 34(7): 765-775.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 4122
Visits: 192958

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.