EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Semaphore Recognition Using Deep Learning

Yan Huan, Weiqi Yan

Electronics · 12.01.2025 · 14 (2) · 286

DOI: 10.3390/electronics14020286 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 12.01.2025. Verfasst von Yan Huan und 1 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study explored the application of deep learning models for signal flag recognition, comparing YOLO11 with basic CNN, ResNet18, and DenseNet121. Experimental results demonstrated that YOLO11 outperformed the other models, achieving superior performance across all common evaluation metrics. The confusion matrix further confirmed that YOLO11 exhibited the highest classification accuracy among the tested models. Moreover, by integrating MediaPipe’s human posture data with image data to create multimodal inputs for training, it was observed that the posture data significantly enhanced the model’s performance. Leveraging MediaPipe’s posture data for annotation generation and model training enabled YOLO11 to achieve an impressive 99% accuracy on the test set. This study highlights the effectiveness of YOLO11 for flag signal recognition tasks. Furthermore, it demonstrates that when handling tasks involving human posture, MediaPipe not only enhances model performance through posture feature data but also facilitates data processing and contributes to validating prediction results in subsequent stages.

Zitieren

APA

Huan, Y., & Yan, W. (2025). Semaphore Recognition Using Deep Learning. Electronics, 14(2), 286. https://doi.org/10.3390/electronics14020286

Vancouver

Huan Y, Yan W. Semaphore Recognition Using Deep Learning. Electronics. 2025;14(2):286. doi:10.3390/electronics14020286

BibTeX
@article{Huan2025,
  author = {Huan, Yan and Yan, Weiqi},
  title = {Semaphore Recognition Using Deep Learning},
  journal = {Electronics},
  year = {2025},
  volume = {14},
  number = {2},
  pages = {286},
  doi = {10.3390/electronics14020286}
}
Kostenlos starten →