A Review of YOLO Series Algorithms in Object Detection for UAV Aerial Images

Yuhan Yan; Lin Zhang

doi:10.6919/ICJE.202509_11(9).0009

Authors

Yuhan Yan
Lin Zhang

DOI:

https://doi.org/10.6919/ICJE.202509_11(9).0009

Keywords:

Aerial Images; Object Detection; YOLO; Dataset.

Abstract

With the rapid development of the low-altitude economy, the demand for object detection in UAV aerial images has become increasingly urgent in fields such as traffic monitoring, agricultural plant protection, and emergency rescue. The YOLO series algorithms have become the mainstream technology in this field due to their advantages of single-stage end-to-end detection. However, the characteristics of UAV aerial scenes, such as extremely small target scales, dense distribution, complex backgrounds, and variable attitudes, pose severe challenges to the accuracy and real-time performance of the algorithms. This paper systematically sorts out the evolution of YOLO series algorithms, from the pioneering exploration of YOLOv1 to the Transformer architecture innovation of YOLOv12, and analyzes the core improvements of each version in terms of anchor box mechanism, feature fusion, and detection head design. It focuses on discussing the difficulties faced by YOLO algorithms in UAV aerial scenes, such as insufficient detection accuracy of small targets, complex scale distribution, and the contradiction between real-time performance and accuracy, and summarizes the key technical solutions for feature extraction, network lightweighting, detection head optimization, and loss function improvement. Meanwhile, it introduces the characteristics of mainstream datasets such as StanfordDrone and VisDrone2019. The research aims to provide relevant scholars with the research status and development context in the field of object detection in UAV aerial images, and offer references for subsequent algorithm optimization and application implementation.

Downloads

Download data is not yet available.

References

[1] Zhong S., Wang L. P.: A Review of Object Detection Technology in UAV Aerial Images, Laser & Optoelectronics Progress, Vol. 62 (2025) No. 10, p.71-89.

[2] Chen J. L., Wu Y. Q., Yuan Y. B.: Research Progress of YOLO Series Algorithms for Object Detection from UAV Perspective, Journal of Beijing University of Aeronautics and Astronautics, (2025) p.1-33. [Accessed 09 August 2025]. https://doi.org/10.13700/j.bh.1001-5965.2024.0420.

[3] Zhang L. L., Tong Q., Liu X. L.: A Review of Small Object Detection in UAV Images, Computer Simulation, Vol. 40 (2023) No. 12, p.1-7+32.

[4] Wang L. Y., Bai J., Li W. J., et al.: Research Progress of YOLO Series Object Detection Algorithms, Computer Engineering and Applications, Vol. 59 (2023) No. 14, p.15-29.

[5] Redmon J., Divvala S., Girshick R., et al.: You Only Look Once: Unified, Real-Time Object Detection, Proc. IEEE Conference on Computer Vision and Pattern Recognition (2016), p.779-788.

[6] Redmon J., Farhadi A.: YOLO9000: Better, Faster, Stronger, Proc. IEEE Conference on Computer Vision and Pattern Recognition (2017), p.7263-7271.

[7] Redmon J., Farhadi A.: YOLOv3: An Incremental Improvement, arXiv Preprint arXiv:1804.02767 (2018).

[8] Bochkovskiy A., Wang C. Y., Liao H. Y. M.: YOLOv4: Optimal Speed and Accuracy of Object Detection, arXiv Preprint arXiv:2004.10934 (2020).

[9] Ge Z., Liu S., Wang F., et al.: YOLOX: Exceeding YOLO Series in 2021, arXiv Preprint arXiv:2107.08430 (2021).

[10] Li C., Li L., Jiang H., et al.: YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications, arXiv Preprint arXiv:2209.02976 (2022).

[11] Wang C. Y., Bochkovskiy A., Liao H. Y. M.: YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors, Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (2023), p.7464-7475.

[12] Wang C. Y., Yeh I. H., Mark Liao H. Y.: YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information, European Conference on Computer Vision (Cham: Springer Nature Switzerland, 2024), p.1-21.

[13] Wang A., Chen H., Liu L., et al.: YOLOv10: Real-Time End-to-End Object Detection, Advances in Neural Information Processing Systems, Vol. 37 (2024), p.107984-108011.

[14] Tian Y., Ye Q., Doermann D.: YOLOv12: Attention-Centric Real-Time Object Detectors, arXiv Preprint arXiv:2502.12524 (2025).

[15] Yang Z. F., Yuan J. Z., Xu C., et al.: A Review of Research Progress on Object Detection Based on YOLO Series, Proc. 28th Annual Conference on Network New Technology and Application 2024 of China Computer Users Association Network Application Branch (Beijing Union University Beijing Key Laboratory of Information Service Engineering; Beijing Union University College of Robotics Brain and Cognitive Intelligence Beijing Laboratory; Beijing Open University, 2024), p.263-267. DOI:10.26914/c.cnkihy.2024.047826.

[16] Xing S. S., Zhao W. L.: A Review of UAV Object Detection in Complex Scenes Based on YOLO Series Algorithms, Application Research of Computers, Vol. 37 (2020) No. S2, p.28-30.

[17] Liu P., Zhang X. H., Zhang Z. L., et al.: A Review of Object Detection from RCNN to YOLO, Proc. 16th National Conference on Signal and Intelligent Information Processing and Application (Tianjin University of Technology and Education School of Information Technology Engineering; Tianjin Sino-German University of Applied Sciences School of Intelligent Manufacturing; Tianjin Huahong Technology Co., Ltd., 2022), p.16-23. DOI:10.26914/c.cnkihy.2022.053359.

[18] Cao Y. Y., Liu Y. C., Gao X. Y., et al.: LightTassel-YOLO: A Real-Time Detection Method for Maize Tassels Based on UAV Remote Sensing, Smart Agriculture (Chinese & English), (2025) p.1-15. [Accessed 09 August 2025]. https://link.cnki.net/urlid/10.1681.S.20250804.0915.002.

[19] Li J. P., Meng X. L., Hu L. L., et al.: Small Target Crack Detection in Bridges Based on Improved YOLOv8, Journal of Tsinghua University (Natural Science Edition), Vol. 65 (2025) No. 07, p.1260-1271. DOI:10.16511/j.cnki.qhdxxb.2025.26.023.

[20] Shi T., Cui J., Li S.: Algorithm for Real-Time UAV Vehicle Detection by Optimizing and Improving YOLOv8, Computer Engineering and Applications, Vol. 60 (2024) No. 09, p.79-89.

[21] Fan Y. Y., Liu Y. S., Wang Q. S.: Infrared Small Target Personnel Detection Algorithm for Underground Unmanned Vehicles, Transducer and Microsystem Technologies, Vol. 44 (2025) No. 08, p.133-137+142. DOI:10.13873/J.1000-9787(2025)08-0133-05.

[22] Shen C., Zhao J.: Aerial Small Target Detection Algorithm Based on Multi-Feature Cross-Layer Fusion, Journal of Ordnance Equipment Engineering, Vol. 46 (2025) No. 04, p.243-251.

[23] Xu H. Z., Gu X. N.: Optimization Research on Traffic Small Target Image Detection Algorithm from UAV Perspective, Computer Engineering and Applications, Vol. 60 (2024) No. 21, p.194-204.

[24] Bao Z.: The UAV Target Detection Algorithm Based on Improved YOLO V8, Proc. International Conference on Image Processing, Machine Learning and Pattern Recognition (2024), p.264-269.

[25] Wang Z., Zhang X., Li J., et al.: A YOLO-Based Target Detection Model for Offshore Unmanned Aerial Vehicle Data, Sustainability, Vol. 13 (2021) No. 23, p.12980.

[26] Song L., Yu H., Yang Y., et al.: YOLO-VG: An Efficient Real-Time Recyclable Waste Detection Network, Journal of Real-Time Image Processing, Vol. 22 (2025) No. 2, p.79.

[27] Feng X. X., Ren A. H., Qi H.: Lightweight Highway Vehicle Detection Algorithm Based on YOLOv8n, Transducer and Microsystem Technologies, Vol. 44 (2025) No. 07, p.155-158+163. DOI:10.13873/J.1000-9787(2025)07-0155-04.

[28] Wang H., Liu Y.: YOLO-LiRa: Lightweight Detection Algorithm for Small Aerial Targets, Measurement Science and Technology, Vol. 36 (2025) No. 6, p.066009.

[29] Lyu Y., Zhang T., Li X., et al.: LightUAV-YOLO: A Lightweight Object Detection Model for Unmanned Aerial Vehicle Image, J. Supercomput., Vol. 81 (2025) No. 1, p.105.

[30] Shi R., Li T., Yamaguchi Y.: An Attribution-Based Pruning Method for Real-Time Mango Detection with YOLO Network, Computers and Electronics in Agriculture, Vol. 169 (2020), p.105214.

[31] Situ Z., Teng S., Liao X., et al.: Real-Time Sewer Defect Detection Based on YOLO Network, Transfer Learning, and Channel Pruning Algorithm, Journal of Civil Structural Health Monitoring, Vol. 14 (2024) No. 1, p.41-57.

[32] Chen J. H., Wang X. H.: Dense Small Target Detection Algorithm in UAV Aerial Images Based on Improved YOLOv5, Computer Engineering and Applications, Vol. 60 (2024) No. 03, p.100-108.

[33] Zhang Y. T.: Research on Nighttime Pedestrian and Vehicle Detection Based on Improved YOLO Algorithm (MS., Dalian Jiaotong University, China 2025). DOI:10.26990/d.cnki.gsltc.2025.000619.

[34] Wu S., Huang D. D., Liu Z., et al.: Improved YOLOv8n-Based Multi-Scale Object Detection Algorithm for UAV Ground Observation and Its Implementation, Computer Engineering and Applications, (2025) p.1-14. [Accessed 09 August 2025]. https://link.cnki.net/urlid/11.2127.tp.20250707.1324.022.

[35] Ren Z., Yao K., Sheng S., et al.: YOLO-SDH: Improved YOLOv5 Using Scaled Decoupled Head for Object Detection, International Journal of Machine Learning and Cybernetics, Vol. 16 (2025) No. 3, p.1643-1660.

[36] Li M., Yan N.: IPD-YOLO: Person Detection in Infrared Images from UAV Perspective Based on Improved YOLO11, Digital Signal Processing, (2025), p.105469.

[37] Song P. Y., Chen H., Gou H. B.: UAV Object Detection Algorithm Based on Improved YOLOv5s, Computer Engineering and Applications, Vol. 59 (2023) No. 01, p.108-116.

[38] Wu M. J., Yun L. J., Chen Z. Q., et al.: Small Target Detection Algorithm from UAV Perspective Based on Improved YOLOv5s, Computer Engineering and Applications, Vol. 60 (2024) No. 02, p.191-199.

[39] Zhao X., Chen Y.: YOLO-DroneMS: Multi-Scale Object Detection Network for Unmanned Aerial Vehicle (UAV) Images, Drones (2504-446X), Vol. 8 (2024) No. 11.

[40] Tang L., Jia Y., Zhang Y. N.: UAV Detection Algorithm with Bidirectional Multi-Scale Feature Fusion, Computer Engineering and Applications, Vol. 61 (2025) No. 10, p.267-278.

[41] Sun J. Y., Xu M. J., Zhang J. P., et al.: Optimized and Improved YOLOv8 Object Detection Algorithm from UAV Perspective, Computer Engineering and Applications, Vol. 61 (2025) No. 01, p.109-120.

[42] Robicquet A., Alahi A., Sadeghian A., et al.: Forecasting Social Navigation in Crowded Complex Scenes, arXiv Preprint arXiv:1601.00998 (2016).

[43] Hsieh M. R., Lin Y. L., Hsu W. H.: Drone-Based Object Counting by Spatially Regularized Regional Proposal Network, Proc. IEEE International Conference on Computer Vision (2017), p.4145-4153.

[44] Du D., Qi Y., Yu H., et al.: The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking, Proc. European Conference on Computer Vision (ECCV) (2018), p.370-386.

[45] Du D., Zhu P., Wen L., et al.: VisDrone-DET2019: The Vision Meets Drone Object Detection in Image Challenge Results, Proc. IEEE/CVF International Conference on Computer Vision Workshops (2019), p.0-0.

[46] Bozcan I., Kayacan E.: Au-Air: A Multi-Modal Unmanned Aerial Vehicle Dataset for Low Altitude Traffic Surveillance, Proc. 2020 IEEE International Conference on Robotics and Automation (ICRA) (IEEE, 2020), p.8504-8510.

[47] Wen L., Du D., Zhu P., et al.: Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark, Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (2021), p.7812-7821.

[48] Shamsoshoara A., Afghah F., Razi A., et al.: Aerial Imagery Pile Burn Detection Using Deep Learning: The FLAME Dataset, Computer Networks, Vol. 193 (2021), p.108001.

[49] Sun Y., Cao B., Zhu P., et al.: Drone-Based RGB-Infrared Cross-Modality Vehicle Detection via Uncertainty-Aware Learning, IEEE Transactions on Circuits and Systems for Video Technology, Vol. 32 (2022) No. 10, p.6700-6713.

[50] Zhang W., Liu C., Chang F., et al.: Multi-Scale and Occlusion Aware Network for Vehicle Detection and Segmentation on UAV Aerial Images, Remote Sensing, Vol. 12 (2020) No. 11, p.1760.