RMAU-NET: A Residual-Multihead-Attention U-Net Architecture for Landslide Segmentation and Detection from Remote Sensing Images

TL;DR

This paper introduces RMAU-NET, a novel deep learning architecture combining residual and multi-head attention mechanisms within a U-Net framework, for effective landslide detection and segmentation from remote sensing images, demonstrating high accuracy on multiple datasets.

Contribution

The paper presents a new neural network architecture that integrates residual connections and multi-head attention for improved landslide detection and segmentation from remote sensing images.

Findings

Achieved F1 scores of 98.23 and 93.83 on detection tasks.

Attained mIoU scores of 63.74 and 76.88 on segmentation tasks.

Proven potential for real-life landslide observation applications.

Abstract

In recent years, landslide disasters have reported frequently due to the extreme weather events of droughts, floods , storms, or the consequence of human activities such as deforestation, excessive exploitation of natural resources. However, automatically observing landslide is challenging due to the extremely large observing area and the rugged topography such as mountain or highland. This motivates us to propose an end-to-end deep-learning-based model which explores the remote sensing images for automatically observing landslide events. By considering remote sensing images as the input data, we can obtain free resource, observe large and rough terrains by time. To explore the remote sensing images, we proposed a novel neural network architecture which is for two tasks of landslide detection and landslide segmentation. We evaluated our proposed model on three different benchmark datasets of LandSlide4Sense, Bijie, and Nepal. By conducting extensive experiments, we achieve F1 scores of 98.23, 93.83 for the landslide detection task on LandSlide4Sense, Bijie datasets; mIoU scores of 63.74, 76.88 on the segmentation tasks regarding LandSlide4Sense, Nepal datasets. These experimental results prove potential to integrate our proposed model into real-life landslide observation systems.