A DeepLabV3+ and HED based segmentation network with an attention loss labels temporary railway construction works and residential areas in satellite images, reaching about 80 percent overall accuracy.
Holistically - Nested Edge Detection[J]
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DV3+HED+: A DCNNs-based Framework to Monitor Temporary Works and ESAs in Railway Construction Project Using VHR Satellite Images
A DeepLabV3+ and HED based segmentation network with an attention loss labels temporary railway construction works and residential areas in satellite images, reaching about 80 percent overall accuracy.