EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Optical Flow-Based Obstacle Detection for Mid-Air Collision Avoidance

Daniel Vera-Yanez iD, António Pereira iD, Nuno Rodrigues iD, José Pascual Molina iD, Arturo S García iD, Antonio Fernández-Caballero iD

Sensors · 09.05.2024 · 24 (10) · 3016

DOI: 10.3390/s24103016 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 09.05.2024. Verfasst von Daniel Vera-Yanez und 5 weiteren Autor:innen. Beteiligte Einrichtung: Instituto de Investigación en Informática de Albacete, Universidad de Castilla-La Mancha, 02071 Albacete, Spain. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Agencia Estatal de Investigación, Spanish MCIN, Universidad de Castilla-La Mancha.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The sky may seem big enough for two flying vehicles to collide, but the facts show that mid-air collisions still occur occasionally and are a significant concern. Pilots learn manual tactics to avoid collisions, such as see-and-avoid, but these rules have limitations. Automated solutions have reduced collisions, but these technologies are not mandatory in all countries or airspaces, and they are expensive. These problems have prompted researchers to continue the search for low-cost solutions. One attractive solution is to use computer vision to detect obstacles in the air due to its reduced cost and weight. A well-trained deep learning solution is appealing because object detection is fast in most cases, but it relies entirely on the training data set. The algorithm chosen for this study is optical flow. The optical flow vectors can help us to separate the motion caused by camera motion from the motion caused by incoming objects without relying on training data. This paper describes the development of an optical flow-based airborne obstacle detection algorithm to avoid mid-air collisions. The approach uses the visual information from a monocular camera and detects the obstacles using morphological filters, optical flow, focus of expansion, and a data clustering algorithm. The proposal was evaluated using realistic vision data obtained with a self-developed simulator. The simulator provides different environments, trajectories, and altitudes of flying objects. The results showed that the optical flow-based algorithm detected all incoming obstacles along their trajectories in the experiments. The results showed an F-score greater than 75% and a good balance between precision and recall.

Schlagwörter

Stichwörter der Autor:innen

DBSCANcomputer visionmid-air collisionobstacle detectionoptical flow

Autor:innen und Institutionen

  • Instituto de Investigación en Informática de Albacete, Universidad de Castilla-La Mancha, 02071 Albacete, Spain.
  • Computer Science and Communications Research Centre, School of Technology and Management, Polytechnic Institute of Leiria, 2411-901 Leiria, Portugal.
  • Institute of New Technologies-Leiria Office, INOV INESC InovaÇÃO, 2411-901 Leiria, Portugal.
  • Departamento de Sistemas Informáticos, Universidad de Castilla-La Mancha, 02071 Albacete, Spain.

ORCID-Profile: Daniel Vera-Yanez, António Pereira, Nuno Rodrigues, José Pascual Molina, Arturo S García, Antonio Fernández-Caballero

Förderung

  • Agencia Estatal de Investigación
  • Spanish MCIN
  • Universidad de Castilla-La Mancha
  • Portuguese FCT-Fundação para a Ciência e a Tecnologia
  • DBoidS—Digital twin Boids fire prevention System

Zitieren

APA

Vera-Yanez, D., Pereira, A., Rodrigues, N., Molina, J. P., García, A. S., & Fernández-Caballero, A. (2024). Optical Flow-Based Obstacle Detection for Mid-Air Collision Avoidance. Sensors, 24(10), 3016. https://doi.org/10.3390/s24103016

Vancouver

Vera-Yanez D, Pereira A, Rodrigues N, Molina JP, García AS, Fernández-Caballero A. Optical Flow-Based Obstacle Detection for Mid-Air Collision Avoidance. Sensors. 2024;24(10):3016. doi:10.3390/s24103016

BibTeX
@article{VeraYanez2024,
  author = {Vera-Yanez, Daniel and Pereira, António and Rodrigues, Nuno and Molina, José Pascual and García, Arturo S and Fernández-Caballero, Antonio},
  title = {Optical Flow-Based Obstacle Detection for Mid-Air Collision Avoidance},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {10},
  pages = {3016},
  doi = {10.3390/s24103016}
}
Kostenlos starten →