Optimizing long-range UAV detection on YOLOv8: Breaking-point distance analysis and combining adaptive tiling with AdamW optimizer

6 views

Authors

  • Nguyen Van Ngon Institute of Technology, General Department of Defense Industry
  • Do Thi Nhan Institute of Technology, General Department of Defense Industry
  • Chu Hai Long Institute of Technology, General Department of Defense Industry
  • Pham Thanh Dong (Corresponding Author) Faculty of Aerospace Engineering, Le Quy Don Technical University

DOI:

https://doi.org/10.54939/1859-1043.j.mst.109.2026.154-163

Keywords:

UAV; Small object detection; YOLOv8; Image tiling; AdamW; Breaking point; Computer vision.

Abstract

The rapid proliferation of unmanned aerial vehicles (UAVs) has imposed stringent requirements on surveillance and early warning systems. In long-range detection scenarios, the apparent size of UAVs in images decreases significantly, leading to severe spatial information loss and degraded performance of convolutional neural network (CNN)-based detection models. This paper proposes a continuous quantitative analysis framework to model the relationship between observation distance and UAV detection performance by progressively reducing the input image resolution. Based on experimental regression analysis, a system-level breaking point is identified, representing a distance threshold at which detection performance begins to degrade sharply and exhibits nonlinear behavior. Furthermore, a solution integrating adaptive image tiling with the AdamW optimizer is proposed to ensure training stability and enhance performance in long-range scenarios. Experimental results on the YOLOv8s model show that the proposed approach improves mAP@0.5 in long-range detection by up to +24.9% while eliminating numerical instability during training on tiled data. Regression analysis identifies the system-level breaking point at Dc ≈ 2.5, providing a quantitative basis for activating adaptive image processing in real-world deployments on resource-constrained platforms.

References

[1]. G. Jocher, A. Chaurasia, J. Kwon, “Ultralytics YOLOv8”, GitHub Repository, (2023).

[2]. Loshchilov, F. Hutter, “Decoupled Weight Decay Regularization”, International Conference on Learning Representations (ICLR), (2019).

[3]. F. Akyon et al., “Slicing Aided Hyper Inference and Fine-tuning for Small Object Detection”, IEEE International Conference on Image Processing (ICIP), pp. 966–970, (2022). DOI: https://doi.org/10.1109/ICIP46576.2022.9897990

[4]. Y. Liu et al., “Deep Learning for Small Object Detection: A Survey”, IEEE Transactions on Pattern Analysis and Machine Intelligence, (2020).

[5]. J. Redmon et al., “You Only Look Once: Unified, Real-Time Object Detection”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779–788, (2016). DOI: https://doi.org/10.1109/CVPR.2016.91

[6]. S. Ren, K. He, R. Girshick, J. Sun, “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks”, Advances in Neural Information Processing Systems (NeurIPS), (2015).

[7]. Z. Ge et al., “YOLOX: Exceeding YOLO Series in 2021”, arXiv:2107.08430, (2021).

[8]. G. Jocher et al., “YOLOv5 by Ultralytics”, GitHub Repository, (2020).

[9]. Wang et al., “YOLOv10: Real-Time End-to-End Object Detection”, arXiv:2405.14458, (2024).

[10]. N. Carion et al., “End-to-End Object Detection with Transformers”, European Conference on Computer Vision (ECCV), pp. 213–229, (2020). DOI: https://doi.org/10.1007/978-3-030-58452-8_13

[11]. Z. Liu et al., “Swin Transformer: Hierarchical Vision Transformer using Shifted Windows”, IEEE/CVF International Conference on Computer Vision (ICCV), pp. 10012–10022, (2021). DOI: https://doi.org/10.1109/ICCV48922.2021.00986

[12]. J. Wang et al., “A Normalized Gaussian Wasserstein Distance for Tiny Object Detection”, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1886–1895, (2022).

[13]. R. Sapa, J. Kim, S. Lee, “SPD-Conv: Building Efficient CNNs for Small Object Detection”, arXiv:2208.03635, (2022).

[14]. T.-Y. Lin et al., “Feature Pyramid Networks for Object Detection”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2117–2125, (2017).

[15]. M. Kisantal et al., “Augmentation for Small Object Detection”, arXiv:1902.07296, (2019). DOI: https://doi.org/10.5121/csit.2019.91713

[16]. P. Zhu et al., “Vision Meets Drones: A Challenge”, arXiv:2001.06303, (2020).

[17]. D. Du et al., “The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking”, European Conference on Computer Vision (ECCV), pp. 370–386, (2018).

[18]. X. Yu et al., “Scale Match for Tiny Person Detection”, IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 1257–1266, (2020).

[19]. H. Zhang et al., “Context-Aware Learning for Small Object Detection”, IEEE Transactions on Circuits and Systems for Video Technology, vol. 32, no. 6, pp. 3671–3684, (2022). DOI: https://doi.org/10.1109/TCSVT.2022.3183641

[20]. C. Chen et al., “Optimization for Small Object Detection in UAV Images based on Improved YOLOv7”, Drones, vol. 7, no. 2, p. 87, (2023).

Downloads

Published

25-02-2026

How to Cite

[1]
Nguyen Van Ngon, Do Thi Nhan, Chu Hai Long, and T. Đồng Phạm, “Optimizing long-range UAV detection on YOLOv8: Breaking-point distance analysis and combining adaptive tiling with AdamW optimizer”, J. Mil. Sci. Technol., vol. 109, no. 109, pp. 154–163, Feb. 2026.

Issue

Section

Mechanics & Mechanical Engineering