Multiclass-semantic-segmentation-in-satallite-images-using U-Net

Introduction

Tensorflow (Keras) code for "Multiclass semantic segmentation in satallite images. This project is only for learning purposes. State-of-the-art U-Net is implemented.

Dataset

The dataset consists of aerial imagery of Dubai obtained by MBRSC satellites and annotated with pixel-wise semantic segmentation in 6 classes. The total volume of the dataset is 72 images grouped into 6 larger tiles. The classes are: Building, Land (unpaved area), Road, Vegetation, Water, and Unlabeled.

Dataset link: https://www.kaggle.com/humansintheloop/semantic-segmentation-of-aerial-imagery

Implementation

Python: 3.9.12 Tensorflow-gpu: 2.6.0 Keras: 2.8

Results