This is a cloud detection validation dataset for Sentinel-2A images

MCDNet: Multilevel cloud detection network for remote sensing images based on dual-perspective change-guided and multi-scale feature fusion

This data set includes Landsat 8 images and their manually extracted pixel-level ground truths for cloud detection.

A semantic segmentation CNN for cloud detection

Pretrained DeepLabv3 and DeepLabv3+ for Pascal VOC & Cityscapes

Models and examples built with TensorFlow

Amazing Semantic Segmentation on Tensorflow && Keras (include FCN, UNet, SegNet, PSPNet, PAN, RefineNet, DeepLabV3, DeepLabV3+, DenseASPP, BiSegNet)

Semantic Segmentation on PyTorch (include FCN, PSPNet, Deeplabv3, Deeplabv3+, DANet, DenseASPP, BiSeNet, EncNet, DUNet, ICNet, ENet, OCNet, CCNet, PSANet, CGNet, ESPNet, LEDNet, DFANet)

The software called Fmask (Function of mask) is used for automated clouds, cloud shadows, and snow masking for Landsats 4-8 and Sentinel 2 images.

Sentinel-2 Cloud and Shadow Detection using Machine Learning

Cloud detection from Sentinel-2 satellite imagery with machine learning.

Include the fmask-algorithms for cloud detection in GRASS GIS

RS-Net is a cloud detection algorithm for satellite imagery