Aerial Small Object Detection with Boundary-Aware and Semantic-Guided Feature Pyramid
Main Article Content
Abstract
Aerial small object detection in UAV imagery faces multiple challenges, including highly imbalanced scale distribution, low object resolution, complex background textures, and constrained computational resources. To address these issues, this paper proposes Aerial-YOLO, an aerial object detection algorithm that integrates boundary-aware enhancement and a semantic-guided feature pyramid. First, a boundary-aware and scale-adaptive collaborative enhancement module is constructed in the backbone network. By introducing directional structural reinforcement and adaptive multi-scale convolution mechanisms, the proposed module strengthens object contours and scale-discriminative features, thereby improving localization stability in dense scenes. Second, a lightweight semantic-guided feature pyramid network is designed, whose core component is an Adaptive Cross-scale Injection Gate module. Through unidirectional semantic guidance and sparse fusion strategies, high-level semantic information selectively enhances low-level fine-grained details, improving multi-scale representation capability while reducing computational overhead. In addition, a structural detail reconstruction module is embedded between the backbone and the neck, where directional enhancement and frequency-domain reweighting mechanisms are employed to amplify high-frequency responses of small objects and alleviate interference from complex backgrounds. Experimental results on the VisDrone2019 dataset demonstrate that Aerial-YOLO significantly improves small object detection performance while maintaining real-time inference capability. Further evaluations on the TinyPerson dataset verify the strong generalization ability and robustness of the proposed method.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
R. Patel, “Application and future prospects of geographic information system (GIS) in intelligent transportation,” Transactions on Computational and Scientific Methods, vol. 5, no. 3, 2025.
W. Hua and Q. Chen, “A survey of small object detection based on deep learning in aerial images,” Artificial Intelligence Review, vol. 58, no. 6, p. 162, 2025.
S. Lu, Y. Guo, J. Long, et al., “Dense small target detection algorithm for UAV aerial imagery,” Image and Vision Computing, vol. 156, p. 105485, 2025.
E. Edozie, A. N. Shuaibu, U. K. John, et al., “Comprehensive review of recent developments in visual object detection based on deep learning,” Artificial Intelligence Review, vol. 58, no. 9, p. 277, 2025.
M. Trigka and E. Dritsas, “A comprehensive survey of machine learning techniques and models for object detection,” Sensors, vol. 25, no. 1, p. 214, 2025.
D. Nguyen and V.-D. Hoang, “A Lightweight Multi-Scale Attention Model for Small Object Detection in UAV Imagery,” IEEE Access, 2026.
Y. Wang, S. Li, Y. Zhang, et al., “Lightweight concrete crack segmentation network for drone image with complex backgrounds using multi-scale feature fusion and optimized architecture,” Construction and Building Materials, vol. 495, p. 143667, 2025.
S. Zhou, C. Rong, and H. Wang, “A lightweight YOLOv8-based small object detection algorithm for UAV scenes,” Signal Processing, vol. 42, no. 1, pp. 72–82, 2026.
S. Zhang, F. Xiao, and C. Ge, “Lightweight aerial image detection algorithm based on improved RT-DETR,” Electronic Measurement Technology, vol. 48, no. 22, pp. 187–197, 2025.
G. Wang, X. Li, and Y. Liu, “UAV target recognition algorithm based on residual separable convolution and multi-scale fusion,” Electronics Optics & Control, vol. 32, no. 12, pp. 43–49, 112, 2025.
X. Liao and X. Tang, “A lightweight UAV aerial target detection model based on YOLOv10n,” Infrared Technology, vol. 47, no. 11, pp. 1427– 1434, 2025.
G. Chang, S. Zhao, S. Hou, et al., “Improved YOLOv8n-based UAV aerial small object detection algorithm,” Science Technology and Engineering, vol. 25, no. 31, pp. 13500–13508, 2025.
T. Jing, Y. Cao, X. Chen, et al., “Improved YOLOv11 for UAV aerial small object detection,” Computer Engineering and Applications, vol. 62, no. 2, pp. 138–148, 2026.
H. Tao, L. Zhang, Z. Sun, et al., “Multi-strategy improvement of coal gangue recognition method of YOLOv11,” Sensors, vol. 25, no. 7, p. 1983, 2025.
K. Zhou and S. Jiang, “Forest fire detection algorithm based on improved YOLOv11n,” Sensors, vol. 25, no. 10, p. 2989, 2025.
J. Zhang and X. L. Peng, “YOLOv11-LC: accurate detection of benign and malignant endometrial lesions using LCA-enhanced YOLOv11 with CMA-C3k2,” Signal, Image and Video Processing, vol. 20, no. 1, p. 15, 2026.
L. Shang, Y. Qiao, H. Lei, et al., “WSADet: A wavelet scale-aware UAV object detector for complex conditions,” Pattern Recognition, p. 112965, 2025.
M. Kisieliute and I. Daugela, “MuRDE-FPN: Precise UAV Localization Using Enhanced Feature Pyramid Network,” Drones, vol. 10, no. 3, p. 162, 2026.
M. Hu, Y. Li, L. Fang, et al., “A2-FPN: Attention aggregation based feature pyramid network for instance segmentation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021.
J. Chen and J. Liu, “MSAF-YOLO: A high-performance small object detection network for aerial images,” Infrared Technology, pp. 1–9.
D. Zhu, Y. Wei, F. Wang, et al., “UAV ground small object detection algorithm based on multiple attention mechanisms,” Laser & Optoelectronics Progress, vol. 63, no. 4, pp. 452–466, 2026.
Y. Yang, W. Wei, S. Zheng, et al., “IF-DETR: An improved RT-DETR aerial image detection algorithm,” Electronic Measurement Technology, pp. 1–12.
M. Li and C. She, “UAV aerial small object detection algorithm based on cross-scale feature fusion,” Electronic Measurement Technology, pp. 1– 10.