期刊
COMPUTERS & GEOSCIENCES
卷 155, 期 -, 页码 -出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.cageo.2021.104860
关键词
Landslide susceptibility prediction; Deep learning; Computer vision; Remote sensing; Semantic segmentation
资金
- China Geological Survey [DD20190637]
The study defines landslide susceptibility as a semantic segmentation problem on optical remote sensing images and evaluates six different semantic segmentation models. The results indicate that certain models are more suitable for this problem scenario and the predictive accuracy of models can be further improved by adjusting network architectures.
The visual characteristics of landslide susceptibility have not yet been fully explored. Professional or trained technicians have to take much time and effort to interpret remote sensing images and locate landslides accordingly. Although conventional machine learning methods based on hand-crafted features for landslide susceptibility prediction (LSP) have acquired remarkable performance, they have certain requirements for prior knowledge. Aiming to learn complex and inherent visual patterns of landslides through minimal manual intervention and achieve fine-grained prediction, in this paper, we define LSP as a semantic segmentation problem on optical remote sensing images. Six widely used semantic segmentation models including Fully Convolutional Network, U-Net, Pyramid Scene Parsing Network, Global Convolutional Network (GCN), DeepLab v3 and DeepLab v3+ are introduced and evaluated for LSP. As the lack of landslide datasets, an open labeled landslide dataset of remote sensing imagery is created for research. The results show that GCN and DeepLab v3 are more applicable for this problem scenario, and the best Mean Intersection-over-Union and Pixel Accuracy of models are 54.2% and 74.0% respectively, which could be further improved by more targeted network architectures. In conclusion, semantic segmentation methods are demonstrated to be effctive for predicting new potential landslides based on remote sensing images.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据