A High-Precision Object Detection Algorithm for UAV Aerial Images: WI-YOLO

Liu Yang

doi:10.63313/JCSFT.9014

Authors

Liu Yang School of Electronic Engineering, Tianjin University of Technology and Education, Tianjin, 300222, China Author

DOI:

https://doi.org/10.63313/JCSFT.9014

Keywords:

UAV Aerial Images, Object Detection, YOLOv11, Attention Mechanism

Abstract

To tackle the challenges of low small-target detection accuracy, intense background interference, and high model computational complexity in unmanned aerial vehicle (UAV) aerial images, this study presents an enhanced lightweight object detection algorithm, namely WI-YOLO. Built on the YOLOv11n architecture, the algorithm integrates two key improvements: first, an improved efficient multi-scale attention mechanism (iEMA) is embedded into the backbone network, which strengthens the discriminability of low-contrast targets by fusing standard deviation and local contrast features; second, a wavelet transform convolution module (WTConv) is designed to expand the receptive field and preserve multi-scale structural information via a multi-level frequency-domain decomposition and reconstruction mechanism.

Experimental evaluations on the DOTA dataset show that WI-YOLO achieves 61.5% in mAP@50 and 35.1% in mAP@50:95—marking significant gains over the baseline model. Concurrently, the model’s parameter count is reduced to 5.9 MB, and its inference speed is increased to 30.5 FPS. These results demonstrate the coordinated optimization of detection accuracy and computational efficiency, making WI-YOLO well-suited for real-time detection tasks on UAV embedded platforms.

References

[1] TIAN M ,CUI M ,CHEN Z , et al. MFR-YOLOv10: Object detection in UAV-taken images based on multilayer feature reconstruction network[J].Chinese Journal of Aero-nautics,2025,38(11):103456-103456.DOI:10.1016/J.CJA.2025.103456.

[2] Zhang J ,Gao M ,Song L , et al. REA-YOLO for small object detection in UAV aerial imag-es[J].The Journal of Supercompu-ting,2025,81(14):1332-1332.DOI:10.1007/S11227-025-07836-0.

[3] Yan Y ,Zhang L . A Review of YOLO Series Algorithms in Object Detection for UAV Aerial Images[J].International Core Journal of Engineer-ing,2025,11(9):74-92.DOI:10.6919/ICJE.202509_11(9).0009.

[4] Zhou H ,Yin W ,Sun K , et al. FO-YOLO for small object detection in drone aerial image-ry[J].The Journal of Supercompu-ting,2025,81(12):1208-1208.DOI:10.1007/S11227-025-07688-8.

[5] Bian Y ,Teng H ,Lv Q , et al. YOLO-AAHU: An adaptive multi-scale small target and occluded target detection algorithm for drone aerial photography scenarios[J].Engineering Research Express,2025,7(3):035226-035226.DOI:10.1088/2631-8695/ADEEFE.

[6] Ying Z ,Yisheng H .A Survey of SAR Image Target Detection Based on Convolutional Neural Networks[J].Remote Sensing,2022,14(24):6240-6240.

[7] Yihunie S A ,E. J B .A Survey on Deep-Learning-Based LiDAR 3D Object Detection for Au-tonomous Driving[J].Sensors,2022,22(24):9577-9577.

[8] Bao D ,Hao L .Survey of Target Detection Based on Neural Network[J].Journal of Physics: Conference Series,2021,1952(2):

[9] Kang T ,Yiquan W ,Fei Z .Recent advances in small object detection based on deep learning: A review[J].Image and Vision Computing,2020,97(prepublish):103910-103910.

[10] Zhao Z ,Zheng P ,Xu S , et al.Object Detection With Deep Learning: A Review.[J].IEEE Trans. Neural Netw. Learning Syst.,2019,30(11):3212-3232.