期刊
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
卷 15, 期 -, 页码 4349-4370出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSTARS.2022.3177025
关键词
Terrain factors; Data models; Training; Satellites; Remote sensing; Semantics; Image segmentation; Catastrophic forgetting; continual learning; deep learning (DL); domain adaptation; ecoregions; landslides; semantic segmentation
类别
资金
- Google AI Impact Challenge [1904-57775]
This paper investigates pixel-wise labeling of landslide areas in remotely-sensed images using deep learning, focusing on large-scale heterogeneous landslide data collection. The study introduces a mechanism for incremental training of semantic segmentation models, known as task-specific model updates (TSMU), which can be utilized for creating new landslide inventories or developing hazard maps following landslide events.
Recent small-scale studies for pixel-wise labeling of potential landslide areas in remotely-sensed images using deep learning (DL) showed potential but were based on data from very small, homogeneous regions with unproven model transferability. In this paper we consider a more realistic and practical setting for large-scale heterogeneous landslide data collection and DL-based labeling. In this setting, remotely sensed images are collected sequentially in temporal batches, where each batch focuses on images from a particular ecoregion, but different batches can focus on different ecoregions with distinct landscape characteristics. For such a scenario, we study the following questions: (1) How well do DL models trained in homogeneous regions perform when they are transferred to different ecoregions? (2) Does increasing the spatial coverage in the data improve model performance in a given ecoregion? and (3) Can a landslide pixel labeling model be incrementally updated with new data, but without access to the old data and without losing performance on the old data? We address these questions by developing a mechanism for incremental training of semantic segmentation models. We call the resulting extension task-specific model updates (TSMU). A national compilation of landslide inventories by the U.S. Geological Survey (USGS) was used to develop a global database for this study. Our results indicate that the TSMU framework can be used to aid in the creation of new landslide inventories or expanding existing datasets, and also to rapidly develop hazard maps for situational awareness following a widespread landslide event.
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