EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Real-Time Object Detection for Autonomous Solar Farm Inspection via UAVs

Javier Rodriguez-Vazquez iD, Inés Prieto-Centeno iD, Miguel Fernandez-Cortizas iD, David Perez-Saura iD, Martin Molina iD, Pascual Campoy iD

Sensors · 25.01.2024 · 24 (3) · 777

DOI: 10.3390/s24030777 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 25.01.2024. Verfasst von Javier Rodriguez-Vazquez und 5 weiteren Autor:innen. Beteiligte Einrichtung: Computer Vision and Aerial Robotics Group, Universidad Politécnica de Madrid (CVAR-UPM), 28040 Madrid, Spain. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Comunidad de Madrid, Ministerio de Ciencia e Innovación, Madrid Government.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Robotic missions for solar farm inspection demand agile and precise object detection strategies. This paper introduces an innovative keypoint-based object detection framework specifically designed for real-time solar farm inspections with UAVs. Moving away from conventional bounding box or segmentation methods, our technique focuses on detecting the vertices of solar panels, which provides a richer granularity than traditional approaches. Drawing inspiration from CenterNet, our architecture is optimized for embedded platforms like the NVIDIA AGX Jetson Orin, achieving close to 60 FPS at a resolution of 1024 ×1376 pixels, thus outperforming the camera’s operational frequency. Such a real-time capability is essential for efficient robotic operations in time-critical industrial asset inspection environments. The design of our model emphasizes reduced computational demand, positioning it as a practical solution for real-world deployment. Additionally, the integration of active learning strategies promises a considerable reduction in annotation efforts and strengthens the model’s operational feasibility. In summary, our research emphasizes the advantages of keypoint-based object detection, offering a practical and effective approach for real-time solar farm inspections with UAVs.

Schlagwörter

Stichwörter der Autor:innen

active learningautonomous navigationembedded platformskeypoint detectionneural networksonboard processinguncertainty estimation

Autor:innen und Institutionen

  • Computer Vision and Aerial Robotics Group, Universidad Politécnica de Madrid (CVAR-UPM), 28040 Madrid, Spain.
  • Centre for Automation and Robotics C.A.R. (UPM-CSIC), Calle Jose Gutierrez Abascal 2, 28006 Madrid, Spain.
  • Department of Artificial Intelligence, Universidad Politécnica de Madrid (UPM), 28031 Madrid, Spain.

ORCID-Profile: Javier Rodriguez-Vazquez, Inés Prieto-Centeno, Miguel Fernandez-Cortizas, David Perez-Saura, Martin Molina, Pascual Campoy

Förderung

  • Comunidad de Madrid
  • Ministerio de Ciencia e Innovación
  • Madrid Government
  • Spanish Ministry of Science and Innovation
  • RATEC

Zitieren

APA

Rodriguez-Vazquez, J., Prieto-Centeno, I., Fernandez-Cortizas, M., Perez-Saura, D., Molina, M., & Campoy, P. (2024). Real-Time Object Detection for Autonomous Solar Farm Inspection via UAVs. Sensors, 24(3), 777. https://doi.org/10.3390/s24030777

Vancouver

Rodriguez-Vazquez J, Prieto-Centeno I, Fernandez-Cortizas M, Perez-Saura D, Molina M, Campoy P. Real-Time Object Detection for Autonomous Solar Farm Inspection via UAVs. Sensors. 2024;24(3):777. doi:10.3390/s24030777

BibTeX
@article{RodriguezVazquez2024,
  author = {Rodriguez-Vazquez, Javier and Prieto-Centeno, Inés and Fernandez-Cortizas, Miguel and Perez-Saura, David and Molina, Martin and Campoy, Pascual},
  title = {Real-Time Object Detection for Autonomous Solar Farm Inspection via UAVs},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {3},
  pages = {777},
  doi = {10.3390/s24030777}
}
Kostenlos starten →