COMPARATIVE BENCHMARKING OF YOLO11 FOR UAV-BASED HUMAN DETECTION IN SIMULATED DISASTER SCENARIOS
DOI:
https://doi.org/10.33480/jitk.v12i1.8002Keywords:
Computer Vision, Human Detection, Machine Learning, UAV, YOLOAbstract
Search and Rescue (SAR) operations require rapid and reliable identification of survivors in disaster-affected areas. This study presents an empirical benchmark of YOLO11m for UAV-oriented human detection in simulated disaster scenarios. The model was trained and evaluated using the synthetically generated C2A: Human Detection in Disaster Scenarios dataset and compared with YOLOv8m, YOLOv9m, and YOLOv10m under consistent training configurations. The experiments were conducted at a resolution of 640 × 640 pixels using mixed-precision training on dual NVIDIA T4 GPUs. YOLO11m achieved an mAP@50 of 0.850, an mAP@50–95 of 0.612, a Precision of 0.880, a Recall of 0.799, and a peak F1-score of 0.830 at a confidence threshold of 0.376. The model also recorded an average inference latency of 5.5 ms per image in the test environment. Compared with the evaluated medium-scale YOLO variants, YOLO11m achieved the highest mAP@50–95 while maintaining moderate parameter and computational requirements. These results indicate that YOLO11m provides a promising accuracy–efficiency baseline for UAV-based SAR research. However, because the evaluation relies on synthetic data and does not include onboard inference or physical UAV field trials, further validation using real-world aerial disaster imagery is required before operational deployment.
Downloads
References
[1] Q. An and C. Ochiai, “Urban morphology and disaster risk reduction: A systematic literature review,” Progress in Disaster Science, vol. 27, p. 100455, Oct. 2025, doi: 10.1016/J.PDISAS.2025.100455.
[2] D. N. Nguyen, Y. Usuda, and F. Imamura, “Gaps in and Opportunities for Disaster Risk Reduction in Urban Areas Through International Standardization of Smart Community Infrastructure,” Sustainability, vol. 16, no. 21, p. 9586, Nov. 2024, doi: 10.3390/su16219586.
[3] A. Reimuth, M. Hagenlocher, L. E. Yang, A. Katzschner, M. Harb, and M. Garschagen, “Urban growth modeling for the assessment of future climate and disaster risks: approaches, gaps and needs,” Environmental Research Letters, vol. 19, no. 1, p. 013002, Jan. 2024, doi: 10.1088/1748-9326/ad1082.
[4] T. Khan Mohd, V. Nguyen, T. Hoang, P. M. Zeyede, and B. Abdisa, “Performance and Efficiency Assessment of Drone in Search and Rescue Operation,” in Artificial Intelligence and Machine Learning, Academy and Industry Research Collaboration Center (AIRCC), Jul. 2022, pp. 1–16. doi: 10.5121/csit.2022.121201.
[5] M. Mbarak, M. H. Alam, and M. Awad, “Unmanned Aerial Vehicle Technologies, Applications, and Regulatory Frameworks: A Scoping Review,” Drones, vol. 10, no. 5, p. 365, May 2026, doi: 10.3390/drones10050365.
[6] F. Ciccone and A. Ceruti, “Real-Time Search and Rescue with Drones: A Deep Learning Approach for Small-Object Detection Based on YOLO,” Drones, vol. 9, no. 8, p. 514, Jul. 2025, doi: 10.3390/drones9080514.
[7] T. Diwan, G. Anirudh, and J. V. Tembhurne, “Object detection using YOLO: challenges, architectural successors, datasets and applications,” Multimed. Tools Appl., vol. 82, no. 6, pp. 9243–9275, Mar. 2023, doi: 10.1007/s11042-022-13644-y.
[8] M. L. Ali and Z. Zhang, “The YOLO Framework: A Comprehensive Review of Evolution, Applications, and Benchmarks in Object Detection,” Computers, vol. 13, no. 12, p. 336, Dec. 2024, doi: 10.3390/computers13120336.
[9] W. A. Ezat, M. M. Dessouky, and N. A. Ismail, “Evaluation of Deep Learning YOLOv3 Algorithm for Object Detection and Classification,” Menoufia Journal of Electronic Engineering Research, vol. 30, no. 1, pp. 52–57, Jan. 2021, doi: 10.21608/mjeer.2021.146237.
[10] G. Lavanya and S. D. Pande, “Enhancing Real-time Object Detection with YOLO Algorithm,” EAI Endorsed Transactions on Internet of Things, vol. 10, Dec. 2023, doi: 10.4108/eetiot.4541.
[11] M. Nikouei et al., “Small object detection: A comprehensive survey on challenges, techniques and real-world applications,” Intelligent Systems with Applications, vol. 27, p. 200561, Sep. 2025, doi: 10.1016/j.iswa.2025.200561.
[12] C. Chen et al., “YOLO-Based UAV Technology: A Review of the Research and Its Applications,” Drones, vol. 7, no. 3, p. 190, Mar. 2023, doi: 10.3390/drones7030190.
[13] B. Valarmathi et al., “Human Detection and Action Recognition for Search and Rescue in Disasters Using YOLOv3 Algorithm,” Journal of Electrical and Computer Engineering, vol. 2023, pp. 1–19, Mar. 2023, doi: 10.1155/2023/5419384.
[14] A. J. Mantau, I. W. Widayat, J.-S. Leu, and M. Köppen, “A Human-Detection Method Based on YOLOv5 and Transfer Learning Using Thermal Image Data from UAV Perspective for Surveillance System,” Drones, vol. 6, no. 10, p. 290, Oct. 2022, doi: 10.3390/drones6100290.
[15] S. Dumenčić, L. Lanča, K. Jakac, and S. Ivić, “Experimental Validation of UAV Search and Detection System in Real Wilderness Environment,” Drones, vol. 9, no. 7, p. 473, Jul. 2025, doi: 10.3390/drones9070473.
[16] N. Bachir and Q. A. Memon, “Benchmarking YOLOv5 models for improved human detection in search and rescue missions,” Journal of Electronic Science and Technology, vol. 22, no. 1, p. 100243, Mar. 2024, doi: 10.1016/j.jnlest.2024.100243.
[17] S. Wu, X. Lu, and C. Guo, “YOLOv5_mamba: unmanned aerial vehicle object detection based on bidirectional dense feedback network and adaptive gate feature fusion,” Sci. Rep., vol. 14, no. 1, p. 22396, Sep. 2024, doi: 10.1038/s41598-024-73241-x.
[18] R. A. Nihal, B. Yen, K. Itoyama, and K. Nakadai, “UAV-Enhanced Combination to Application: Comprehensive Analysis and Benchmarking of a Human Detection Dataset for Disaster Scenarios,” 2025, pp. 145–162. doi: 10.1007/978-3-031-78341-8_10.
[19] R. A. Nihal, B. Yen, K. Itoyama, and K. Nakadai, “UAV-Enhanced Combination to Application: Comprehensive Analysis and Benchmarking of a Human Detection Dataset for Disaster Scenarios,” Aug. 2024, Accessed: Nov. 05, 2025. [Online]. Available: https://arxiv.org/abs/2408.04922
[20] W. Wang, L. Yang, and N. Noguchi, “Development of a grape-harvesting robot using a multi-step detection method based on AI and a position-estimation algorithm,” Smart Agricultural Technology, vol. 9, p. 100574, Dec. 2024, doi: 10.1016/j.atech.2024.100574.
[21] E. I. Capaldi, “A low-cost wireless extension for object detection and data logging for educational robotics using the ESP-NOW protocol,” PeerJ Comput. Sci., vol. 10, p. e1826, Feb. 2024, doi: 10.7717/peerj-cs.1826.
[22] Z. Zhao, L. Alzubaidi, J. Zhang, Y. Duan, and Y. Gu, “A comparison review of transfer learning and self-supervised learning: Definitions, applications, advantages and limitations,” Expert Syst. Appl., vol. 242, p. 122807, May 2024, doi: 10.1016/j.eswa.2023.122807.
[23] N. Bodla, B. Singh, R. Chellappa, and L. S. Davis, “Soft-NMS -- Improving Object Detection With One Line of Code,” Aug. 2017, Accessed: Nov. 05, 2025. [Online]. Available: https://arxiv.org/abs/1704.04503
[24] G. Li, L. Wen, Z. Huang, R. Xia, and Y. Pang, “Data augmentation and shadow image classification for shadow detection,” IET Image Process., vol. 16, no. 3, pp. 717–728, Feb. 2022, doi: 10.1049/ipr2.12377.
[25] Y.-F. Lu, J.-W. Gao, Q. Yu, Y. Li, Y.-S. Lv, and H. Qiao, “A Cross-Scale and Illumination Invariance-Based Model for Robust Object Detection in Traffic Surveillance Scenarios,” IEEE Transactions on Intelligent Transportation Systems, vol. 24, no. 7, pp. 6989–6999, Jul. 2023, doi: 10.1109/TITS.2023.3264573.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 A. Ahmad Fadil, Jumadi Mabe Parenreng, Muhammad Fardan, Ana Sulistiana Alwi
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
-a.jpg)
-b.jpg)
