1. JEECS
  2. All Volumes and Issues
  3. Volume 12, Number 1, 2026
  4. Impact of Architectural Scaling in YOLO11 Models on Object Detection Accuracy and Inference Performance in UAV Systems

Impact of Architectural Scaling in YOLO11 Models on Object Detection Accuracy and Inference Performance in UAV Systems

JEECS.
2026;
Volume 12, Number 1
: pp. 107 – 119
https://doi.org/10.23939/jeecs2026.01.107
Received: March 31, 2026
Revised: May 05, 2026
Accepted: May 12, 2026
Published: May 28, 2026

M. Shepliakov, A. Lozynskyy. (2026). Impact of architectural scaling in YOLO11 models on object detection accuracy and inference performance in UAV systems. Energy Engineering and Control Systems, Vol. 12, No. 1, pp. 107 – 119. https://doi.org/10.23939/jeecs2026.01.107

Authors:
  1. Maksym Shepliakov
  2. Andriy Lozynskyy
1
Lviv Polytechnic National University
ORCID: 0009-0009-9025-6125
2
Lviv Polytechnic National University
ORCID: 0000-0003-1351-7183

This paper investigates the impact of architectural scaling in YOLO-family neural object detectors on object detection performance in unmanned aerial vehicle (UAV) systems under CPU-only inference conditions without hardware acceleration. Standard nano and small model configurations are analyzed, along with an intermediate model obtained through controlled width scaling of the network. Experimental evaluation is conducted on an embedded Raspberry Pi 5 platform under fixed hardware and software conditions using ONNX Runtime, ensuring fair comparability of the models. Performance is assessed using detection accuracy metrics ([email protected]; [email protected]:0.95), average inference latency and the coefficient of variation of latency, as well as an integrated efficiency metric. The results demonstrate that increasing model complexity leads to a nonlinear improvement in detection accuracy, accompanied by a growth in inference latency, which limits the applicability of such models in real-time scenarios.

Unmanned Aerial Vehicles
object detection
YOLOv11
neural network scaling
neural network width
CPU inference
inference latency
detection accuracy
real-time systems
  1. Fan, S., & Cao, B. (2026). The Survey of Evolutionary Deep Learning-Based UAV Intelligent Power Inspection. Drones, 10(1), 55–55. https://doi.org/10.3390/drones10010055
  2. Hou, W., Wu, H., Wu, D., Shen, Y., Liu, Z., Zhang, L., & Li, J. (2025). Small Object Detection Method for UAV Remote Sensing Images Based on αS-YOLO. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 18, 8984–8994. https://doi.org/10.1109/jstars.2025.3539873
  3. Kumar, G., Rawat, S. S., Gautam, J., & Ayodeji Olalekan Salau. (2025). UAV-based object detection model for smart surveillance using deep neural network. Measurement Sensors, 43, 101982–101982. https://doi.org/10.1016/j.measen.2025.101982
  4. Kurmashev, I., Semenyuk, V., Lupidi, A., Alyoshin, D., Kurmasheva, L., & Cantelli-Forti, A. (2025). Study of the Optimal YOLO Visual Detector Model for Enhancing UAV Detection and Classification in Optoelectronic Channels of Sensor Fusion Systems. Drones, 9(11), 732. https://doi.org/10.3390/drones9110732
  5. Ma, C., Fu, Y., Wang, D., Guo, R., Zhao, X., & Fang, J. (2023). YOLO-UAV: Object Detection Method of Unmanned Aerial Vehicle Imagery Based on Efficient Multi-Scale Feature Fusion. IEEE Access, 11, 126857–126878. https://doi.org/10.1109/access.2023.3329713
  6. Partheepan, S., Sanati, F., & Hassan, J. (2025). Evaluating YOLO Variants with Transfer Learning for Real-Time UAV Obstacle Detection in Simulated Forest Environments. IEEE Access, 13, 99266–99290. https://doi.org/10.1109/access.2025.3577251
  7. Wang, Q., Ye, G., Chen, Q., Zhang, S., & Wang, F. (2024). A UAV perspective based lightweight target detection and tracking algorithm for intelligent transportation. Complex & Intelligent Systems, 11(1). https://doi.org/10.1007/s40747-024-01687-7
  8. He, L., Zhou, Y., Liu, L., & Ma, J. (2024). Research and Application of YOLOv11-Based Object Segmentation in Intelligent Recognition at Construction Sites. Buildings, 14(12), 3777. https://doi.org/10.3390/buildings14123777
  9. Shi, W., Dai, J., Li, C., & Niu, N. (2025). YOLOv11-EMD: An Enhanced Object Detection Algorithm Assisted by Multi-Stage Transfer Learning for Industrial Steel Surface Defect Detection. Mathematics, 13(17), 2769. https://doi.org/10.3390/math13172769
  10. Ramos, L. T., & Sappa, A. D. (2025). A Decade of You Only Look Once (YOLO) for Object Detection: A Review. IEEE Access, 13, 192747–192794. https://doi.org/10.1109/access.2025.3630988
  11. Han, Y., Yan, X., Li, Y., Li, D., Liu, X., Huang, H., & Bie, D. (2025). A Lightweight Feature Enhancement Model for UAV Detection in Real-World Scenarios. Drones, 9(12), 874. https://doi.org/10.3390/drones9120874
  12. Raza, A., Hanif, F., & Mohammed, H. A. (2025). Analyzing the enhancement of CNN-YOLO and transformer based architectures for real-time animal detection in complex ecological environments. Scientific Reports, 15(1), 39142–39142. https://doi.org/10.1038/s41598-025-26645-2
  13. Jin, T., Shen, Z., & Geng, H. (2025). Optimized YOLOv11m for real-time high-speed railway catenary defect detection. Scientific Reports, 16(1). https://doi.org/10.1038/s41598-025-29172-2
  14. Ikram, S., Bajwa, I., Sujan Gyawali, Ikram, A., & Najah Alsubaie. (2025). Enhancing Object Detection in Assistive Technology for the Visually Impaired: A DETR-Based Approach. IEEE Access, 1–1. https://doi.org/10.1109/access.2025.3558370
  15. Hatem Ibrahem, Diefy, A., & Kang, H.-S. (2021). Real-Time Weakly Supervised Object Detection Using Center-of-Features Localization. IEEE Access, 9, 38742–38756. https://doi.org/10.1109/access.2021.3064372
  16. Mukaram Safaldin, Nizar Zaghden, & Mahmoud Mejdoub. (2024). An Improved YOLOv8 to Detect Moving Objects. IEEE Access, 1–1. https://doi.org/10.1109/access.2024.3393835
  17. Rahman, A. Y., & Zakaria, Z. (2025). Hybrid YOLOv8 and Fast R-CNN for Accurate Schematic Detection in Power Distribution Networks. IEEE Access, 13, 69425–69437. https://doi.org/10.1109/access.2025.3561279
  18. Ge, X., Li, X., Zhang, C., Li, J., & Gao, Y. (2024). Robust and Real-time Ship Object Detection Method Based on Enhanced CNN. IEEE Access, 1–1. https://doi.org/10.1109/access.2024.3442776
  19. Cintas, E., Ozyer, B., & Simsek, E. (2020). Vision-Based Moving UAV Tracking by Another UAV on Low-Cost Hardware and a New Ground Control Station. IEEE Access, 8, 194601–194611. https://doi.org/10.1109/access.2020.3033481
  20. Chen, M., Zhou, F., Sun, B., Chen, L., Liu, W., Li, Z., & Wang, R. (2025). Compact DETR: A More Compact Real-Time Object Detector for Remote Sensing Object Detection. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 18, 23925–23935. https://doi.org/10.1109/jstars.2025.3607373
  21. Serghei, T.-L., & Popescu, D. (2026). DeTrAck: UAV Detection and Tracking Using Neural Networks Ensemble on Surveillance Systems. IEEE Access, 14, 1712–1728. https://doi.org/10.1109/access.2025.3649960
  22. Niu, Z., Zhang, J., Li, Z., Zhao, X., Yu, X., & Wang, Y. (2024). Automatic Detection and Predictive Geolocation of Foreign Object Debris on Airport Runway. IEEE Access, 1–1. https://doi.org/10.1109/access.2024.3460788
  23. Yu, W., & Mo, K. (2025). YOLO-GCOF: A Lightweight Low-Altitude Drone Detection Model. IEEE Access, 13, 53053–53064. https://doi.org/10.1109/access.2025.3553477
  24. Son, H.-S., Kim, D.-K., Yang, S.-H., & Choi, Y.-K. (2023). Recognition of the Shape and Location of Multiple Power Lines Based on Deep Learning with Post-Processing. IEEE Access, 11, 57895–57904. https://doi.org/10.1109/access.2023.3283613
  25. Nan, G., Zhao, Y., Fu, L., & Ye, Q. (2024). Object Detection by Channel and Spatial Exchange for Multimodal Remote Sensing Imagery. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 17, 8581–8593. https://doi.org/10.1109/jstars.2024.3388013
  26. Rey, L., Bernardos, A. M., Dobrzycki, A. D., Carramiñana, D., Luca Bergesio, Besada, J. A., & Casar, J. R. (2025). A Performance Analysis of You Only Look Once Models for Deployment on Constrained Computational Edge Devices in Drone Applications. Electronics, 14(3), 638–638. https://doi.org/10.3390/electronics14030638
  27. Tan, M., & Le, Q. V. (2020). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. ArXiv.org., September 11, 2020. https://doi.org/10.48550/arXiv.1905.11946
  28. Vaddi, S., Kim, D., Kumar, C., Shad, S., & Jannesari, A. (2021). Efficient Object Detection Model for Real-time UAV Application. Computer and Information Science, 14(1), 45. https://doi.org/10.5539/cis.v14n1p45
  29. Ultralytics. (2025). Model YAML Configuration Guide. Ultralytics.com. Available from: https://docs.ultralytics.com/guides/model-yaml-config/#configuration-structure (accessed on May 25, 2026)
  30. Silva, L. A., Sanchez San Blas, H., Peral García, D., Sales Mendes, A., & Villarubia González, G. (2020). An Architectural Multi-Agent System for a Pavement Monitoring System with Pothole Recognition in UAV Images. Sensors, 20(21), 6205. https://doi.org/10.3390/s20216205
  31. Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014). Microsoft COCO: Common Objects in Context. Computer Vision – ECCV 2014, 8693, 740–755. https://doi.org/10.1007/978-3-319-10602-1_48
  32. Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2009). The Pascal Visual Object Classes (VOC) Challenge. International Journal of Computer Vision, 88(2), 303–338. https://doi.org/10.1007/s11263-009-0275-4
  33. Rana, A., & Vaidya, P. (2026). YOLO-based deep learning framework for real-time multi-class plant health monitoring in precision agriculture. Scientific Reports, 16(1). https://doi.org/10.1038/s41598-025-29132-w
  34. Zhu, J., Rong, J., Kou, W., Zhou, Q., & Suo, P. (2025). Robust real-time recognition of drones and birds in complex scenarios: a multimodal data fusion recognize approach. Complex & Intelligent Systems, 12(1). https://doi.org/10.1007/s40747-025-02117-y
  35. Ultralytics. (n.d.). Val. Docs.ultralytics.com. Available from: https://docs.ultralytics.com/modes/val/ (accessed on May 25, 2026)
  36. Ly Thi Huyen, C., Pham Quyet, C., & Thi Nguyen, Q. (2026). Vehicle Identification and Classification Using YOLO Algorithm. IIUM Engineering Journal, 27(1), 251–262. https://doi.org/10.31436/iiumej.v27i1.3694
  37. Adhikari, B., Li, J., Michel, E. S., Dykes, J., Tseng, T.-M. P., Tagert, M. L., & Chen, D. (2025). A Comprehensive Evaluation of YOLO-based Deer Detection Performance on Edge Devices. ArXiv.org. Available from: https://arxiv.org/abs/2509.20318v2 (accessed on May 25, 2026)
  38. Sapkota, R., & Karkee, M. (2025). Ultralytics YOLO Evolution: An Overview of YOLO26, YOLO11, YOLOv8 and YOLOv5 Object Detectors for Computer Vision and Pattern Recognition. ArXiv.org. Available from: https://arxiv.org/abs/2510.09653v2 (accessed on May 25, 2026)
  39. Şimşek, F. (2026). Real-Time Object Detection with QuantizedYOLOv11 and YOLOv8 on Raspberry Pi 5 for Low-Speed ADAS. https://doi.org/10.21203/rs.3.rs-8584571/v1
  40. W. Yi and L. Wang. (2025). Robust Object Detection for Autonomous Driving in Adverse Weather Conditions with Multi-Scale Feature Enhancement. IEEE Open Journal of Intelligent Transportation Systems, vol. 6, pp. 1459-1475, https://doi.org/10.1109/OJITS.2025.3631716