EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

UAV-Based Person Detection with Frame and Event Sensors: A Model–Platform Case Study on Jetson Orin Nano and BrainChip AKD1000 Neuromorphic Hardware

Fernando Palacios iD, Ana Redondo Rodriguez iD, Hélder Rodríguez, Salvador Domínguez-Durante, Daniel Sanz-Merodio iD, Miguel López iD

Sensors · 06.11.2026 · 26 (21) · 7034

DOI: 10.3390/s26217034 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 06.11.2026. Verfasst von Fernando Palacios und 5 weiteren Autor:innen. Beteiligte Einrichtung: ARQUIMEA Robotics, Arquimea Research Center, 38320 La Laguna, Spain. Die Arbeit nennt 75 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Detecting people from unmanned aerial vehicles (UAVs) in coastal environments is challenging because targets are often small, distant, and observed against complex backgrounds. This case study presents an application-driven system-level comparison of frame- and event-based sensing vision systems. We developed a purpose-built multimodal UAV dataset of beach users, bathers, and surfers using frame and event-based cameras. Frame images and events were evaluated using feasible standard and converted spiking YOLOv2-derived configurations on a Jetson Orin Nano and a BrainChip AKD1000 neuromorphic processor. The experimental setup serves as a challenging stress test to expose limitations and relative behavior across configurations. The evaluation covers end-to-end processing performance and energy and sensor power. Frame-based YOLOv2 achieved the highest detection performance, with an F1-score of 0.215 and an mAP50 of 0.212. The best spiking configuration, sYOLOv2 with event input, achieved an F1-score of 0.172 and an mAP50 of 0.114. Frame-based YOLOv2 on the Jetson GPU also achieved the lowest end-to-end processing energy cost (2886.6 mJ per sample) and highest throughput (2.011 samples/s). At the component level, the event camera reduced operating power by 82.1% relative to the frame camera, while the AKD1000 consumed approximately 1.3 W during backend execution. However, these component-level savings did not yield an end-to-end energy advantage because of host-processing overhead and lower throughput. The results highlight the need to assess sensing and complete-pipeline costs when evaluating the efficiency of neuromorphic embedded vision systems.

Schlagwörter

Stichwörter der Autor:innen

aerial systems: applicationsneuromorphic computingobject detectionperformance evaluation and benchmarkingspiking neural network (SNN)

Autor:innen und Institutionen

  • ARQUIMEA Robotics, Arquimea Research Center, 38320 La Laguna, Spain.

ORCID-Profile: Fernando Palacios, Ana Redondo Rodriguez, Daniel Sanz-Merodio, Miguel López

Förderung

  • European Union

Zitieren

APA

Palacios, F., Rodriguez, A. R., Rodríguez, H., Domínguez-Durante, S., Sanz-Merodio, D., & López, M. (2026). UAV-Based Person Detection with Frame and Event Sensors: A Model–Platform Case Study on Jetson Orin Nano and BrainChip AKD1000 Neuromorphic Hardware. Sensors, 26(21), 7034. https://doi.org/10.3390/s26217034

Vancouver

Palacios F, Rodriguez AR, Rodríguez H, Domínguez-Durante S, Sanz-Merodio D, López M. UAV-Based Person Detection with Frame and Event Sensors: A Model–Platform Case Study on Jetson Orin Nano and BrainChip AKD1000 Neuromorphic Hardware. Sensors. 2026;26(21):7034. doi:10.3390/s26217034

BibTeX
@article{Palacios2026,
  author = {Palacios, Fernando and Rodriguez, Ana Redondo and Rodríguez, Hélder and Domínguez-Durante, Salvador and Sanz-Merodio, Daniel and López, Miguel},
  title = {UAV-Based Person Detection with Frame and Event Sensors: A Model–Platform Case Study on Jetson Orin Nano and BrainChip AKD1000 Neuromorphic Hardware},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {21},
  pages = {7034},
  doi = {10.3390/s26217034}
}
Kostenlos starten →