.png){kind=icon}
.png){kind=icon}
Return
BGR-net: A boundary-guided refinement network for multi-class cloud detection
.png){kind=icon}
PRE
AI
DOI：10.1016/j.rsase.2026.102024.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Proposed BGR-Net, a hybrid CNN-Transformer model for multi-class cloud detection. • Introduced Adaptive Gating Fusion to enhance discriminative features. • Achieved superior mIoU (68.37%) and F1-score (81.21%) on Himawari-9 imagery. • Significantly reduced computational overhead (GFLOPs) for real-time monitoring. • Demonstrated robust detection of thin clouds and fragmented cloud boundaries.
Keywords:
BGR-Net
cloud detection
CNN-Transformer hybrid
adaptive gating fusion
boundary-guided refinement
Journal
R
IF:
0
Papers:
261
Citations:
0