Multiscale Two-Stream Fusion Network for Benggang Classification in Multi-Source Images

Benggangs, a type of soil erosion widely distributed in the hilly and mountainous regions of South China, pose significant challenges to land management and ecological conservation. Accurate identification and assessment of their location and scale are essential for effective Benggang control. With...

Full description

Saved in:
Bibliographic Details
Main Authors: Xuli Rao, Chen Feng, Jinshi Lin, Zhide Chen, Xiang Ji, Yanhe Huang, Renguang Chen
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/9/2924
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850136486176882688
author Xuli Rao
Chen Feng
Jinshi Lin
Zhide Chen
Xiang Ji
Yanhe Huang
Renguang Chen
author_facet Xuli Rao
Chen Feng
Jinshi Lin
Zhide Chen
Xiang Ji
Yanhe Huang
Renguang Chen
author_sort Xuli Rao
collection DOAJ
description Benggangs, a type of soil erosion widely distributed in the hilly and mountainous regions of South China, pose significant challenges to land management and ecological conservation. Accurate identification and assessment of their location and scale are essential for effective Benggang control. With advancements in technology, deep learning has emerged as a critical tool for Benggang classification. However, selecting suitable feature extraction and fusion methods for multi-source image data remains a significant challenge. This study proposes a Benggang classification method based on multiscale features and a two-stream fusion network (MS-TSFN). Key features of targeted Benggang areas, such as slope, aspect, curvature, hill shade, and edge, were extracted from Digital Orthophotography Map (DOM) and Digital Surface Model (DSM) data collected by drones. The two-stream fusion network, with ResNeSt as the backbone, extracted multiscale features from multi-source images and an attention-based feature fusion block was developed to explore complementary associations among features and achieve deep fusion of information across data types. A decision fusion block was employed for global prediction to classify areas as Benggang or non-Benggang. Experimental comparisons of different data inputs and network models revealed that the proposed method outperformed current state-of-the-art approaches in extracting spatial features and textures of Benggangs. The best results were obtained using a combination of DOM data, Canny edge detection, and DSM features in multi-source images. Specifically, the proposed model achieved an accuracy of 92.76%, a precision of 85.00%, a recall of 77.27%, and an F1-score of 0.8059, demonstrating its adaptability and high identification accuracy under complex terrain conditions.
format Article
id doaj-art-5625504ca7004ca588c2e911f35ed201
institution OA Journals
issn 1424-8220
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-5625504ca7004ca588c2e911f35ed2012025-08-20T02:31:08ZengMDPI AGSensors1424-82202025-05-01259292410.3390/s25092924Multiscale Two-Stream Fusion Network for Benggang Classification in Multi-Source ImagesXuli Rao0Chen Feng1Jinshi Lin2Zhide Chen3Xiang Ji4Yanhe Huang5Renguang Chen6Jinshan Soil and Water Conservation Research Center, Fujian Agriculture and Forestry University, Fuzhou 350002, ChinaSchool of Information Engineering, Fuzhou Polytechnic, Fuzhou 350108, ChinaJinshan Soil and Water Conservation Research Center, Fujian Agriculture and Forestry University, Fuzhou 350002, ChinaCollege of Computer and Cyber Security, Fujian Normal University, Fuzhou 350117, ChinaJinshan Soil and Water Conservation Research Center, Fujian Agriculture and Forestry University, Fuzhou 350002, ChinaJinshan Soil and Water Conservation Research Center, Fujian Agriculture and Forestry University, Fuzhou 350002, ChinaCollege of Computer and Cyber Security, Fujian Normal University, Fuzhou 350117, ChinaBenggangs, a type of soil erosion widely distributed in the hilly and mountainous regions of South China, pose significant challenges to land management and ecological conservation. Accurate identification and assessment of their location and scale are essential for effective Benggang control. With advancements in technology, deep learning has emerged as a critical tool for Benggang classification. However, selecting suitable feature extraction and fusion methods for multi-source image data remains a significant challenge. This study proposes a Benggang classification method based on multiscale features and a two-stream fusion network (MS-TSFN). Key features of targeted Benggang areas, such as slope, aspect, curvature, hill shade, and edge, were extracted from Digital Orthophotography Map (DOM) and Digital Surface Model (DSM) data collected by drones. The two-stream fusion network, with ResNeSt as the backbone, extracted multiscale features from multi-source images and an attention-based feature fusion block was developed to explore complementary associations among features and achieve deep fusion of information across data types. A decision fusion block was employed for global prediction to classify areas as Benggang or non-Benggang. Experimental comparisons of different data inputs and network models revealed that the proposed method outperformed current state-of-the-art approaches in extracting spatial features and textures of Benggangs. The best results were obtained using a combination of DOM data, Canny edge detection, and DSM features in multi-source images. Specifically, the proposed model achieved an accuracy of 92.76%, a precision of 85.00%, a recall of 77.27%, and an F1-score of 0.8059, demonstrating its adaptability and high identification accuracy under complex terrain conditions.https://www.mdpi.com/1424-8220/25/9/2924Benggang classificationmultiscale featurestwo-stream fusion networkmulti-source image fusionattention mechanism
spellingShingle Xuli Rao
Chen Feng
Jinshi Lin
Zhide Chen
Xiang Ji
Yanhe Huang
Renguang Chen
Multiscale Two-Stream Fusion Network for Benggang Classification in Multi-Source Images
Sensors
Benggang classification
multiscale features
two-stream fusion network
multi-source image fusion
attention mechanism
title Multiscale Two-Stream Fusion Network for Benggang Classification in Multi-Source Images
title_full Multiscale Two-Stream Fusion Network for Benggang Classification in Multi-Source Images
title_fullStr Multiscale Two-Stream Fusion Network for Benggang Classification in Multi-Source Images
title_full_unstemmed Multiscale Two-Stream Fusion Network for Benggang Classification in Multi-Source Images
title_short Multiscale Two-Stream Fusion Network for Benggang Classification in Multi-Source Images
title_sort multiscale two stream fusion network for benggang classification in multi source images
topic Benggang classification
multiscale features
two-stream fusion network
multi-source image fusion
attention mechanism
url https://www.mdpi.com/1424-8220/25/9/2924
work_keys_str_mv AT xulirao multiscaletwostreamfusionnetworkforbenggangclassificationinmultisourceimages
AT chenfeng multiscaletwostreamfusionnetworkforbenggangclassificationinmultisourceimages
AT jinshilin multiscaletwostreamfusionnetworkforbenggangclassificationinmultisourceimages
AT zhidechen multiscaletwostreamfusionnetworkforbenggangclassificationinmultisourceimages
AT xiangji multiscaletwostreamfusionnetworkforbenggangclassificationinmultisourceimages
AT yanhehuang multiscaletwostreamfusionnetworkforbenggangclassificationinmultisourceimages
AT renguangchen multiscaletwostreamfusionnetworkforbenggangclassificationinmultisourceimages