Convolutional Neural Network Architecture for Road Segmentation

Convolutional Neural Network Architecture for Road Segmentation

image analysis

deep learning

PyTorch

segmentation

Key-words

Resources

Overview

This project was done in the context of the course 'Machine Learning' at EPFL, given by M. Jaggi and N. Flammarion. It consisted in implementing various convolutional neural network architectures and comparing their performance on a road segmentation task : road / non-road pixel classification for satellite images. CNNs were combined with a deterministic non-trainable convolutional step.

Approach

We use the neural network framework from Keras to build our models. Datasets of satellite images (with labels) were provided beforehand by the course administrators.