Knowledge and Geo-Object Based Graph Convolutional Network for Remote Sensing Semantic Segmentation

Pixel-based semantic segmentation models fail to effectively express geographic objects and their topological relationships. Therefore, in semantic segmentation of remote sensing images, these models fail to avoid salt-and-pepper effects and cannot achieve high accuracy either. To solve these proble...

Descripción completa

Detalles Bibliográficos
Autores principales: Cui, Wei, Yao, Meng, Hao, Yuanjie, Wang, Ziwei, He, Xin, Wu, Weijie, Li, Jie, Zhao, Huilin, Xia, Cong, Wang, Jin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8199747/
https://www.ncbi.nlm.nih.gov/pubmed/34199626
http://dx.doi.org/10.3390/s21113848

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8199747/
https://www.ncbi.nlm.nih.gov/pubmed/34199626
http://dx.doi.org/10.3390/s21113848

Ejemplares similares