# Algorithms for Semantic Segmentation of Multispectral Remote Sensing Imagery using Deep Learning

## TL;DR

This paper adapts deep learning models for semantic segmentation of multispectral remote sensing images, using synthetic data for training to address label scarcity, and introduces a new high-resolution dataset for evaluation.

## Contribution

It presents a novel approach of using synthetic MSI data for initializing deep neural networks, improving overfitting issues and establishing a new benchmark with the RIT-18 dataset.

## Key findings

- Models initialized with synthetic MSI data outperform traditional methods.
- The RIT-18 dataset provides a new benchmark for MSI semantic segmentation.
- Synthetic data reduces overfitting in deep learning models.

## Abstract

Deep convolutional neural networks (DCNNs) have been used to achieve state-of-the-art performance on many computer vision tasks (e.g., object recognition, object detection, semantic segmentation) thanks to a large repository of annotated image data. Large labeled datasets for other sensor modalities, e.g., multispectral imagery (MSI), are not available due to the large cost and manpower required. In this paper, we adapt state-of-the-art DCNN frameworks in computer vision for semantic segmentation for MSI imagery. To overcome label scarcity for MSI data, we substitute real MSI for generated synthetic MSI in order to initialize a DCNN framework. We evaluate our network initialization scheme on the new RIT-18 dataset that we present in this paper. This dataset contains very-high resolution MSI collected by an unmanned aircraft system. The models initialized with synthetic imagery were less prone to over-fitting and provide a state-of-the-art baseline for future work.