Dubai-Satellite-Imagery-Multiclass-Segmentation

Note: Use Jupyter NbViewer to load the code if GitHub doesn't render

Please copy the links of the .ipynb files and paste it in NbViewer if GitHub fails to load it in the browser.

Dataset

Humans in the Loop has published an open access dataset annotated for a joint project with the Mohammed Bin Rashid Space Center in Dubai, the UAE. The dataset consists of aerial imagery of Dubai obtained by MBRSC satellites and annotated with pixel-wise semantic segmentation in 6 classes. The images were segmented by the trainees of the Roia Foundation in Syria.

The images are densely labeled and contain the following 6 classes:

Name	R	G	B	Color
Building	60	16	152	#3b1098
Land	132	41	246	#8529f6
Road	110	193	228	#6ec1e4
Vegetation	254	221	58	#fedd3a
Water	226	169	41	#e2aa29
Unlabeled	155	155	155	#9b9b9b

Benchmark Models

• Standard U-Net
• U-Net with Resnet Backbone
• DeepLabV3+

Transfer Learning from InceptionResNetV2 to U-Net CNN

• Data Augmentation
• Model Training and Evaluation

Software & Libraries

• Python >=3.*
• NumPy
• Pandas
• Matplotlib
• IPython
• Open-CV
• Tensorflow
• Keras
• Patchify
• Segmentation Models
• Albumentations