EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Learning-Based Multiple Droplet Contamination Detector for Vision Systems Using a You Only Look Once Algorithm

Youngkwang Kim, Woochan Kim, Jungwoo Yoon, Sangkug Chung, Daegeun Kim

Information · 28.02.2024 · 15 (3) · 134

DOI: 10.3390/info15030134 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Information, online erschienen am 28.02.2024. Verfasst von Youngkwang Kim und 4 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: 2024 Research Fund of Myongji University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents a practical contamination detection system for camera lenses using image analysis with deep learning. The proposed system can detect contamination in camera digital images through contamination learning utilizing deep learning, and it aims to prevent performance degradation of intelligent vision systems due to lens contamination in cameras. This system is based on the object detection algorithm YOLO (v5n, v5s, v5m, v5l, and v5x), which is trained with 4000 images captured under different lighting and background conditions. The trained models showed that the average precision improves as the algorithm size increases, especially for YOLOv5x, which showed excellent efficiency in detecting droplet contamination within 23 ms. They also achieved an average precision (mAP@0.5) of 87.46%, recall (mAP@0.5:0.95) of 51.90%, precision of 90.28%, recall of 81.47%, and F1 score of 85.64%. As a proof of concept, we demonstrated the identification and removal of contamination on camera lenses by integrating a contamination detection system and a transparent heater-based cleaning system. The proposed system is anticipated to be applied to autonomous driving systems, public safety surveillance cameras, environmental monitoring drones, etc., to increase operational safety and reliability.

Förderung

  • 2024 Research Fund of Myongji University

Zitieren

APA

Kim, Y., Kim, W., Yoon, J., Chung, S., & Kim, D. (2024). Deep Learning-Based Multiple Droplet Contamination Detector for Vision Systems Using a You Only Look Once Algorithm. Information, 15(3), 134. https://doi.org/10.3390/info15030134

Vancouver

Kim Y, Kim W, Yoon J, Chung S, Kim D. Deep Learning-Based Multiple Droplet Contamination Detector for Vision Systems Using a You Only Look Once Algorithm. Information. 2024;15(3):134. doi:10.3390/info15030134

BibTeX
@article{Kim2024,
  author = {Kim, Youngkwang and Kim, Woochan and Yoon, Jungwoo and Chung, Sangkug and Kim, Daegeun},
  title = {Deep Learning-Based Multiple Droplet Contamination Detector for Vision Systems Using a You Only Look Once Algorithm},
  journal = {Information},
  year = {2024},
  volume = {15},
  number = {3},
  pages = {134},
  doi = {10.3390/info15030134}
}
Kostenlos starten →