Table 1 Three public semantic segmentation datasets of ultra-high-resolution remote sensing images are used in this paper.

From: Spatially adaptive interaction network for semantic segmentation of high-resolution remote sensing images

Dataset

Max size

Number of classes

% of 4K UHR image

#Image

DeepGlobe71

6 M pixels (\(2448\times 2448\))

7

100

803

Vaihingen

28 M pixels (\(2494\times 2064\))

6

100

33

Potsdam

103 M pixels (\(6000\times 6000\))

6

100

38

Back to article page