0.4

The package can now be imported via pip

pip install git+https://github.com/strath-ai/SatelliteCloudGenerator

0.3

Major Changes 🔥

• 🏭 Introducing CloudGenerator() which encapsulates a specific configuration, and generation probabilities (cloud_p and shadow_p). It is compatible as PyTorch module (you can plug it into augmentation pipelines, like torchvision or albumentations)

my_gen=CloudGenerator(WIDE_CONFIG,cloud_p=1.0,shadow_p=0.5)
my_gen(my_image) # will act just like add_cloud_and_shadow() but will preserve the same configuration!

---

• 🌈 Channel-Specific Cloud Magnitude allows for channels to have slightly different cloud strengths (since this strength is generally dependent on carrier wavelength) by setting channel_magnitude_shift` to a non-zero value:

---

• 😷 Segmentation Mask Functionality allows you to call the segmentation_mask(cloud_mask,shadow_mask) method, which will return a segmentation mask for your generated clouds and shadows!

...you can even set a range thin_range to something like (0.05,0.5) to also differentiate between thin and thick clouds

and this is an example content of each label:

---

I hope these features prove useful! 🚀

0.2

Major Changes 🔥

• min_lvl and max_lvl redefined (to refer to cloud strength)
• Introduction of shadow functionality with add_cloud_and_shadow
• Introduction of locality_index argument that can control the sparsity of the cloud shape
• Datasets of cloud and shadow masks can be easily generated using the 02-Dataset-Generation.ipynb notebook

Minor Changes 🪛

• Prevent NaN in cloud_hue
• Fixed Perlin generation for small images and non-standard aspect ratios

First Release

Updated DOI, Colab links and citation details.

Pre-Release

Pre-release for setting up Zenodo DOI