Enhanced U-Net++ for Improved Semantic Segmentation in Landslide Detection
Open Access
Abstract
Landslide detection and segmentation are critical for disaster risk assessment and management. However, achieving accurate segmentation remains challenging due to the complex nature of landslide terrains and the limited availability of high-quality labeled datasets. This paper proposes an enhanced U-Net++ model for semantic segmentation of landslides in the Wenchuan region using the CAS Landslide Dataset. The proposed model integrates multi-scale feature extraction and attention mechanisms to enhance segmentation accuracy and robustness. The experimental results demonstrate that ASK-UNet++ outperforms traditional methods, achieving a mean intersection over union (mIoU) of 97.53%, a Dice coefficient of 98.27%, and an overall accuracy of 96.04%. These findings highlight the potential of the proposed approach for improving landslide monitoring and disaster response strategies.Keywords
This publication has 26 references indexed in Scilit:
- A fast and robust method for detecting trend turning points in InSAR displacement time seriesComputers & Geosciences, 2024
- Landslide assessment through integrated geoelectrical and seismic methods: A case study in Thungsong site, southern ThailandHeliyon, 2024
- CAS Landslide Dataset: A Large-Scale and Multisensor Dataset for Deep Learning-Based Landslide DetectionScientific Data, 2024
- Landslide4Sense: Reference Benchmark Data and Deep Learning Models for Landslide DetectionIEEE Transactions on Geoscience and Remote Sensing, 2022
- Deep learning in environmental remote sensing: Achievements and challengesRemote Sensing of Environment, 2020
- The Varnes classification of landslide types, an updateLandslides, 2013
- Formation mechanism and stability analysis of the Houba expansive soil landslideEngineering Geology, 2013
- Three-dimensional geophysical anatomy of an active landslide in Lias Group mudrocks, Cleveland Basin, UKGeomorphology, 2011
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- A method for producing digital probabilistic seismic landslide hazard mapsEngineering Geology, 2000