EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Building Segmentation from Remote Sensing Data using Enhanced U-Net

Gefei Kong, Chaoquan Zhang, Yi Zhao, Hongchao Fan

Nordic Machine Intelligence · 2023

DOI: 10.5617/nmi.10157 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Nordic Machine Intelligence, 2023. Verfasst von Gefei Kong und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this paper, a simple boundary-enhanced network and a new multi-task loss function are proposed for building segmentation from multiple remote sensing sources. The experimental results on MapAI-challenge dataset demonstrates that our network can segment buildings from remote sensing data, especially on the image & laser multi-source dataset. The mean score of IoU and BIoU is 0.8995 for task 1 and 0.9155 for task 2 on the MapAI validation dataset and 0.5239 for task 1, and 0.7038 for task 2 on the MapAI test dataset.

Zitieren

APA

Kong, G., Zhang, C., Zhao, Y., & Fan, H. (2023). Building Segmentation from Remote Sensing Data using Enhanced U-Net. Nordic Machine Intelligence. https://doi.org/10.5617/nmi.10157

Vancouver

Kong G, Zhang C, Zhao Y, Fan H. Building Segmentation from Remote Sensing Data using Enhanced U-Net. Nordic Machine Intelligence. 2023. doi:10.5617/nmi.10157

BibTeX
@article{Kong2023,
  author = {Kong, Gefei and Zhang, Chaoquan and Zhao, Yi and Fan, Hongchao},
  title = {Building Segmentation from Remote Sensing Data using Enhanced U-Net},
  journal = {Nordic Machine Intelligence},
  year = {2023},
  doi = {10.5617/nmi.10157}
}
Kostenlos starten →