EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Unmanned Aerial Vehicle Indoor Low-Computation Navigation Method Based on Vision and Deep Learning

Tzu-Ling Hsieh, Zih-Syuan Jhan, Nai-Jui Yeh, Chang-Yu Chen, Cheng-Ta Chuang

Sensors · 28.12.2023 · 24 (1) · 190

DOI: 10.3390/s24010190 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 28.12.2023. Verfasst von Tzu-Ling Hsieh und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Intelligent Automation Engineering, National Taipei University of Technology, Taipei 10608, Taiwan. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science and Technology Council, MOST Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recently, unmanned aerial vehicles (UAVs) have found extensive indoor applications. In numerous indoor UAV scenarios, navigation paths remain consistent. While many indoor positioning methods offer excellent precision, they often demand significant costs and computational resources. Furthermore, such high functionality can be superfluous for these applications. To address this issue, we present a cost-effective, computationally efficient solution for path following and obstacle avoidance. The UAV employs a down-looking camera for path following and a front-looking camera for obstacle avoidance. This paper refines the carrot casing algorithm for line tracking and introduces our novel line-fitting path-following algorithm (LFPF). Both algorithms competently manage indoor path-following tasks within a constrained field of view. However, the LFPF is superior at adapting to light variations and maintaining a consistent flight speed, maintaining its error margin within ±40 cm in real flight scenarios. For obstacle avoidance, we utilize depth images and YOLOv4-tiny to detect obstacles, subsequently implementing suitable avoidance strategies based on the type and proximity of these obstacles. Real-world tests indicated minimal computational demands, enabling the Nvidia Jetson Nano, an entry-level computing platform, to operate at 23 FPS.

Schlagwörter

Stichwörter der Autor:innen

indoorobstacle avoidancepath followingunmanned aerial vehicles (UAV)

Autor:innen und Institutionen

  • Department of Intelligent Automation Engineering, National Taipei University of Technology, Taipei 10608, Taiwan.

Förderung

  • National Science and Technology Council
  • MOST Foundation

Zitieren

APA

Hsieh, T. L., Jhan, Z. S., Yeh, N. J., Chen, C. Y., & Chuang, C. T. (2023). An Unmanned Aerial Vehicle Indoor Low-Computation Navigation Method Based on Vision and Deep Learning. Sensors, 24(1), 190. https://doi.org/10.3390/s24010190

Vancouver

Hsieh TL, Jhan ZS, Yeh NJ, Chen CY, Chuang CT. An Unmanned Aerial Vehicle Indoor Low-Computation Navigation Method Based on Vision and Deep Learning. Sensors. 2023;24(1):190. doi:10.3390/s24010190

BibTeX
@article{Hsieh2023,
  author = {Hsieh, Tzu-Ling and Jhan, Zih-Syuan and Yeh, Nai-Jui and Chen, Chang-Yu and Chuang, Cheng-Ta},
  title = {An Unmanned Aerial Vehicle Indoor Low-Computation Navigation Method Based on Vision and Deep Learning},
  journal = {Sensors},
  year = {2023},
  volume = {24},
  number = {1},
  pages = {190},
  doi = {10.3390/s24010190}
}
Kostenlos starten →