EUVIMEDObjevte EUVIMED
Open access · CC BY 4.0

A Performance Analysis of You Only Look Once Models for Deployment on Constrained Computational Edge Devices in Drone Applications

Lucas Rey, Ana M. Bernardos, Andrzej D. Dobrzycki, David Carramiñana, Luca Bergesio, Juan A. Besada, José Ramón Casar

Electronics · 2025-02-06 · 14 (3) · 638

DOI: 10.3390/electronics14030638 ↗

At a glance

Journal article in Electronics, published online on 2025-02-06. Written by Lucas Rey and 6 co-authors. Cited 84 times so far (Crossref); 26 references. The full text is freely available (open access, CC BY 4.0). Funded by: Horizon Europe EDF Programme, Spanish Ministry of Economic Affairs and Digital Transformation and by the EU Next Generation EU/PRTR programme, MCIN/AEI/10.13039/501100011033.

AbstraktBibliografické údajeCiteRelated studies

Abstract (original language)

Advancements in embedded systems and Artificial Intelligence (AI) have enhanced the capabilities of Unmanned Aircraft Vehicles (UAVs) in computer vision. However, the integration of AI techniques o-nboard drones is constrained by their processing capabilities. In this sense, this study evaluates the deployment of object detection models (YOLOv8n and YOLOv8s) on both resource-constrained edge devices and cloud environments. The objective is to carry out a comparative performance analysis using a representative real-time UAV image processing pipeline. Specifically, the NVIDIA Jetson Orin Nano, Orin NX, and Raspberry Pi 5 (RPI5) devices have been tested to measure their detection accuracy, inference speed, and energy consumption, and the effects of post-training quantization (PTQ). The results show that YOLOv8n surpasses YOLOv8s in its inference speed, achieving 52 FPS on the Jetson Orin NX and 65 fps with INT8 quantization. Conversely, the RPI5 failed to satisfy the real-time processing needs in spite of its suitability for low-energy consumption applications. An analysis of both the cloud-based and edge-based end-to-end processing times showed that increased communication latencies hindered real-time applications, revealing trade-offs between edge (low latency) and cloud processing (quick processing). Overall, these findings contribute to providing recommendations and optimization strategies for the deployment of AI models on UAVs.

Funding

  • Horizon Europe EDF Programme
  • Spanish Ministry of Economic Affairs and Digital Transformation and by the EU Next Generation EU/PRTR programme
  • MCIN/AEI/10.13039/501100011033

Cite

APA

Rey, L., Bernardos, A. M., Dobrzycki, A. D., Carramiñana, D., Bergesio, L., 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. https://doi.org/10.3390/electronics14030638

Vancouver

Rey L, Bernardos AM, Dobrzycki AD, Carramiñana D, Bergesio L, Besada JA, et al. A Performance Analysis of You Only Look Once Models for Deployment on Constrained Computational Edge Devices in Drone Applications. Electronics. 2025;14(3):638. doi:10.3390/electronics14030638

BibTeX
@article{Rey2025,
  author = {Rey, Lucas and Bernardos, Ana M. and Dobrzycki, Andrzej D. and Carramiñana, David and Bergesio, Luca and Besada, Juan A. and Casar, José Ramón},
  title = {A Performance Analysis of You Only Look Once Models for Deployment on Constrained Computational Edge Devices in Drone Applications},
  journal = {Electronics},
  year = {2025},
  volume = {14},
  number = {3},
  pages = {638},
  doi = {10.3390/electronics14030638}
}
Start for free →