Landslide Segmentation in High-Resolution Remote Sensing Images: The Van–UPerAttnSeg Framework with Multi-Scale Feature Enhancement

Among geological disasters, landslides are a common and extremely destructive disaster. Their rapid identification is crucial for disaster analysis and response. However, traditional methods of landslide recognition mainly rely on visual interpretation and manual recognition of remote sensing images...

Full description

Saved in:
Bibliographic Details
Main Authors: Chang Li, Quan Zou, Guoqing Li, Wenyang Yu
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/7/1265
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850188295382761472
author Chang Li
Quan Zou
Guoqing Li
Wenyang Yu
author_facet Chang Li
Quan Zou
Guoqing Li
Wenyang Yu
author_sort Chang Li
collection DOAJ
description Among geological disasters, landslides are a common and extremely destructive disaster. Their rapid identification is crucial for disaster analysis and response. However, traditional methods of landslide recognition mainly rely on visual interpretation and manual recognition of remote sensing images, which are time-consuming and susceptible to subjective factors, thereby limiting the accuracy and efficiency of recognition. To overcome these limitations, for high-resolution remote sensing images, this method first uses online equalization sampling and enhancement strategy to sample high-resolution remote sensing images to ensure data balance and diversity. Then, it adopts an encoder–decoder structure, where the encoder is a visual attention network (Van) that focuses on extracting discriminative features of different scales from landslide images. The decoder consists of a pyramid pooling module (PPM) and feature pyramid network (FPN), combined with a convolutional block attention module (CBAM) module. Through this structure, the model can effectively integrate features of different scales, achieving precise positioning and recognition of landslide areas. In addition, this study introduces a sliding window algorithm based on Gaussian fusion as a post-processing method, which optimizes the prediction of landslide edge in high-resolution remote sensing images and ensures the context reasoning ability of the model. In the validation set, this method achieved a significant landslide recognition effect with a Dice score of 84.75%, demonstrating high accuracy and efficiency. This result demonstrates the importance and effectiveness of the research method in improving the accuracy and efficiency of landslide recognition, providing strong technical support for analysis and response to geological disasters.
format Article
id doaj-art-dfd8b40f12c94be9804c60a30964a22d
institution OA Journals
issn 2072-4292
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-dfd8b40f12c94be9804c60a30964a22d2025-08-20T02:15:54ZengMDPI AGRemote Sensing2072-42922025-04-01177126510.3390/rs17071265Landslide Segmentation in High-Resolution Remote Sensing Images: The Van–UPerAttnSeg Framework with Multi-Scale Feature EnhancementChang Li0Quan Zou1Guoqing Li2Wenyang Yu3College of Computer and Information Science College of Software, Southwest University, Chongqing 400715, ChinaCollege of Computer and Information Science College of Software, Southwest University, Chongqing 400715, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAmong geological disasters, landslides are a common and extremely destructive disaster. Their rapid identification is crucial for disaster analysis and response. However, traditional methods of landslide recognition mainly rely on visual interpretation and manual recognition of remote sensing images, which are time-consuming and susceptible to subjective factors, thereby limiting the accuracy and efficiency of recognition. To overcome these limitations, for high-resolution remote sensing images, this method first uses online equalization sampling and enhancement strategy to sample high-resolution remote sensing images to ensure data balance and diversity. Then, it adopts an encoder–decoder structure, where the encoder is a visual attention network (Van) that focuses on extracting discriminative features of different scales from landslide images. The decoder consists of a pyramid pooling module (PPM) and feature pyramid network (FPN), combined with a convolutional block attention module (CBAM) module. Through this structure, the model can effectively integrate features of different scales, achieving precise positioning and recognition of landslide areas. In addition, this study introduces a sliding window algorithm based on Gaussian fusion as a post-processing method, which optimizes the prediction of landslide edge in high-resolution remote sensing images and ensures the context reasoning ability of the model. In the validation set, this method achieved a significant landslide recognition effect with a Dice score of 84.75%, demonstrating high accuracy and efficiency. This result demonstrates the importance and effectiveness of the research method in improving the accuracy and efficiency of landslide recognition, providing strong technical support for analysis and response to geological disasters.https://www.mdpi.com/2072-4292/17/7/1265geological disasterlandslide recognitiondeep learningmulti-scale feature fusion
spellingShingle Chang Li
Quan Zou
Guoqing Li
Wenyang Yu
Landslide Segmentation in High-Resolution Remote Sensing Images: The Van–UPerAttnSeg Framework with Multi-Scale Feature Enhancement
Remote Sensing
geological disaster
landslide recognition
deep learning
multi-scale feature fusion
title Landslide Segmentation in High-Resolution Remote Sensing Images: The Van–UPerAttnSeg Framework with Multi-Scale Feature Enhancement
title_full Landslide Segmentation in High-Resolution Remote Sensing Images: The Van–UPerAttnSeg Framework with Multi-Scale Feature Enhancement
title_fullStr Landslide Segmentation in High-Resolution Remote Sensing Images: The Van–UPerAttnSeg Framework with Multi-Scale Feature Enhancement
title_full_unstemmed Landslide Segmentation in High-Resolution Remote Sensing Images: The Van–UPerAttnSeg Framework with Multi-Scale Feature Enhancement
title_short Landslide Segmentation in High-Resolution Remote Sensing Images: The Van–UPerAttnSeg Framework with Multi-Scale Feature Enhancement
title_sort landslide segmentation in high resolution remote sensing images the van uperattnseg framework with multi scale feature enhancement
topic geological disaster
landslide recognition
deep learning
multi-scale feature fusion
url https://www.mdpi.com/2072-4292/17/7/1265
work_keys_str_mv AT changli landslidesegmentationinhighresolutionremotesensingimagesthevanuperattnsegframeworkwithmultiscalefeatureenhancement
AT quanzou landslidesegmentationinhighresolutionremotesensingimagesthevanuperattnsegframeworkwithmultiscalefeatureenhancement
AT guoqingli landslidesegmentationinhighresolutionremotesensingimagesthevanuperattnsegframeworkwithmultiscalefeatureenhancement
AT wenyangyu landslidesegmentationinhighresolutionremotesensingimagesthevanuperattnsegframeworkwithmultiscalefeatureenhancement