中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 地理科学与资源研究所
  3. 中国科学院地理科学与资源研究所
  4. 资源与环境信息系统国家重点实验室
  5. 外文论文
Hierarchical perception guided deep learning framework for landslide detection with multi-source remotely sensed data

文献类型：期刊论文

作者Zhong, Chencheng2,3,6; Chen, Jifa1,2,3,6; Chen, Gang1; Yang, Lu5; Tao, Lizhi2,3,6; Zou, Haibo2,3,6; Ge, Yong2,3,4; Lin, Hui2,3,6
刊名INTERNATIONAL JOURNAL OF DIGITAL EARTH
出版日期2026-07-01
卷号19期号:1页码:2632415
关键词Landslide detection hierarchical perception deep learning wavelet transform multi-source remote sensing
ISSN号1753-8947
DOI10.1080/17538947.2026.2632415
产权排序6
文献子类Article
英文摘要Rapid and accurate landslide detection from remotely sensed data is fundamental but significant work for large-scale geological disaster prevention and reduction. Vision transformers (ViT) have emerged as dominant solutions alongside CNN in landslide modeling, but they face challenges in terms of global and local information interactions, while the homogeneity between landslide areas and surrounding environments is difficult to distinguish solely from spectral images. This paper proposes a hierarchical perception-guided deep learning framework to detect landslides with multi-source remotely sensed data. Following the encoder-decoder structure, we introduce a hybrid encoding backbone with the wavelet transform to model the spectral and terrain features. It is formulated with dual-branch configurations, where the CNN-based local perception module has lightweight network blocks, and the ViT-based global one comprises efficient multi-stage fusion blocks. We then explore developing the fusion mechanism with a cross-attention paradigm to promote interactive learning between heterogeneous global and local landslide representations. Furthermore, a U-shaped multi-scale feature decoding module with a comprehensive objective function is proposed to produce high-quality landslide segmentations. Extensive experiments on two benchmark landslide detection datasets demonstrate its competitive performance by (98.70%, 78.37%, 73.48%) and (99.68%, 80.55%, 76.10%) in terms of Acc, F1-score, and mIoU, respectively.
URL标识查看原文
WOS关键词WAVELET TRANSFORM
WOS研究方向Physical Geography ; Remote Sensing
语种英语
WOS记录号WOS:001694507500001
出版者TAYLOR & FRANCIS LTD
源URL[http://ir.igsnrr.ac.cn/handle/311030/220876]  
专题资源与环境信息系统国家重点实验室_外文论文
通讯作者Chen, Jifa
作者单位1.China Univ Geosci, Coll Marine Sci & Technol, Wuhan, Peoples R China;
2.Jiangxi Normal Univ, Sch Geog & Environm, Nanchang 330022, Peoples R China;
3.Jiangxi Normal Univ, Key Lab Poyang Lake Wetland & Watershed Res, Minist Educ, Nanchang 330022, Peoples R China;
4.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Beijing, Peoples R China
5.Jiangxi Commun Investment Grp Co Ltd, Nanchang, Peoples R China;
6.Early Warning & Assessment, Jiangxi Prov Key Lab Nat Disaster Monitoring, Nanchang, Peoples R China;
推荐引用方式
GB/T 7714		 Zhong, Chencheng,Chen, Jifa,Chen, Gang,et al. Hierarchical perception guided deep learning framework for landslide detection with multi-source remotely sensed data[J]. INTERNATIONAL JOURNAL OF DIGITAL EARTH,2026,19(1):2632415.
APA Zhong, Chencheng.,Chen, Jifa.,Chen, Gang.,Yang, Lu.,Tao, Lizhi.,...&Lin, Hui.(2026).Hierarchical perception guided deep learning framework for landslide detection with multi-source remotely sensed data.INTERNATIONAL JOURNAL OF DIGITAL EARTH,19(1),2632415.
MLA Zhong, Chencheng,et al."Hierarchical perception guided deep learning framework for landslide detection with multi-source remotely sensed data".INTERNATIONAL JOURNAL OF DIGITAL EARTH 19.1(2026):2632415.

入库方式： OAI收割

来源：地理科学与资源研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。