# Robust Semantic Segmentation By Dense Fusion Network On Blurred VHR Remote Sensing Images

## TL;DR

This paper introduces a multi-modality dense fusion network that enhances the robustness of semantic segmentation in blurred or damaged very high resolution remote sensing images, outperforming existing models.

## Contribution

It proposes a cascaded dense encoder-decoder network with SELayer fusion for improved robustness using NIR, RGB, and DSM data.

## Key findings

- Steady performance under decreasing image quality
- Effective multi-modality data fusion improves segmentation robustness
- Outperforms state-of-the-art models in challenging conditions

## Abstract

Robust semantic segmentation of VHR remote sensing images from UAV sensors is critical for earth observation, land use, land cover or mapping applications. Several factors such as shadows, weather disruption and camera shakes making this problem highly challenging, especially only using RGB images. In this paper, we propose the use of multi-modality data including NIR, RGB and DSM to increase robustness of segmentation in blurred or partially damaged VHR remote sensing images. By proposing a cascaded dense encoder-decoder network and the SELayer based fusion and assembling techniques, the proposed RobustDenseNet achieves steady performance when the image quality is decreasing, compared with the state-of-the-art semantic segmentation model.