Detection of Benggang in Remote Sensing Imagery through Integration of Segmentation Anything Model with Object-Based Classification

Benggang is a type of erosion landform that commonly occurs in the southern regions of China, posing significant threats to local farmland and human safety. Object-based classification (OBC) can be applied with high-resolution (HR) remote sensing images for detecting Benggang areas on a large spatia...

Full description

Bibliographic Details
Main Authors: Yixin Hu, Zhixin Qi, Zhexun Zhou, Yan Qin
Format: Article
Language:English
Published: MDPI AG 2024-01-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/16/2/428
_version_ 1797342586118078464
author Yixin Hu
Zhixin Qi
Zhexun Zhou
Yan Qin
author_facet Yixin Hu
Zhixin Qi
Zhexun Zhou
Yan Qin
author_sort Yixin Hu
collection DOAJ
description Benggang is a type of erosion landform that commonly occurs in the southern regions of China, posing significant threats to local farmland and human safety. Object-based classification (OBC) can be applied with high-resolution (HR) remote sensing images for detecting Benggang areas on a large spatial scale, offering essential data for aiding in the remediation efforts for these areas. Nevertheless, traditional image segmentation methods may face challenges in accurately delineating Benggang areas. Consequently, the extraction of spatial and textural features from these areas can be susceptible to inaccuracies, potentially compromising the detection accuracy of Benggang areas. To address this issue, this study proposed a novel approach that integrates Segment Anything Model (SAM) and OBC for Benggang detection. The SAM was used to segment HR remote sensing imagery to delineate the boundaries of Benggang areas. After that, the OBC was employed to identify Benggang areas based on spectral, geometrical, and textural features. In comparison to traditional pixel-based classification using the random forest classifier (RFC-PBC) and OBC based on the multi-resolution segmentation (MRS-OBC), the proposed SAM-OBC exhibited superior performance, achieving a detection accuracy of 85.46%, a false alarm rate of 2.19%, and an overall accuracy of 96.48%. The feature importance analysis conducted with random forests highlighted the GLDV Entropy, GLDV Angular Second Moment (ASM), and GLCM ASM as the most pivotal features for the identification of Benggang areas. Due to its inability to extract and utilize these textural features, the PBC yielded suboptimal results compared to both the SAM-OBC and MRS-OBC. In contrast to the MRS, the SAM demonstrated superior capabilities in the precise delineation of Benggang areas, ensuring the extraction of accurate textural and spatial features. As a result, the SAM-OBC significantly enhanced detection accuracy by 34.12% and reduced the false alarm rate by 2.06% compared to the MRS-OBC. The results indicate that the SAM-OBC performs well in Benggang detection, holding significant implications for the monitoring and remediation of Benggang areas.
first_indexed 2024-03-08T10:35:25Z
format Article
id doaj.art-6306551250eb405482a74880d852d461
institution Directory Open Access Journal
issn 2072-4292
language English
last_indexed 2024-03-08T10:35:25Z
publishDate 2024-01-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj.art-6306551250eb405482a74880d852d4612024-01-26T18:20:21ZengMDPI AGRemote Sensing2072-42922024-01-0116242810.3390/rs16020428Detection of Benggang in Remote Sensing Imagery through Integration of Segmentation Anything Model with Object-Based ClassificationYixin Hu0Zhixin Qi1Zhexun Zhou2Yan Qin3School of Geography and Planning, Sun Yat-sen University, Guangzhou 510006, ChinaSchool of Geography and Planning, Sun Yat-sen University, Guangzhou 510006, ChinaCollege of Physics and Optoelectronic Engineering, Harbin Engineering University, Harbin 150001, ChinaGuangdong Research Institute of Water Resources and Hydropower, Guangzhou 510635, ChinaBenggang is a type of erosion landform that commonly occurs in the southern regions of China, posing significant threats to local farmland and human safety. Object-based classification (OBC) can be applied with high-resolution (HR) remote sensing images for detecting Benggang areas on a large spatial scale, offering essential data for aiding in the remediation efforts for these areas. Nevertheless, traditional image segmentation methods may face challenges in accurately delineating Benggang areas. Consequently, the extraction of spatial and textural features from these areas can be susceptible to inaccuracies, potentially compromising the detection accuracy of Benggang areas. To address this issue, this study proposed a novel approach that integrates Segment Anything Model (SAM) and OBC for Benggang detection. The SAM was used to segment HR remote sensing imagery to delineate the boundaries of Benggang areas. After that, the OBC was employed to identify Benggang areas based on spectral, geometrical, and textural features. In comparison to traditional pixel-based classification using the random forest classifier (RFC-PBC) and OBC based on the multi-resolution segmentation (MRS-OBC), the proposed SAM-OBC exhibited superior performance, achieving a detection accuracy of 85.46%, a false alarm rate of 2.19%, and an overall accuracy of 96.48%. The feature importance analysis conducted with random forests highlighted the GLDV Entropy, GLDV Angular Second Moment (ASM), and GLCM ASM as the most pivotal features for the identification of Benggang areas. Due to its inability to extract and utilize these textural features, the PBC yielded suboptimal results compared to both the SAM-OBC and MRS-OBC. In contrast to the MRS, the SAM demonstrated superior capabilities in the precise delineation of Benggang areas, ensuring the extraction of accurate textural and spatial features. As a result, the SAM-OBC significantly enhanced detection accuracy by 34.12% and reduced the false alarm rate by 2.06% compared to the MRS-OBC. The results indicate that the SAM-OBC performs well in Benggang detection, holding significant implications for the monitoring and remediation of Benggang areas.https://www.mdpi.com/2072-4292/16/2/428Benggangsoil erosionremote sensing monitoringsegment anything model
spellingShingle Yixin Hu
Zhixin Qi
Zhexun Zhou
Yan Qin
Detection of Benggang in Remote Sensing Imagery through Integration of Segmentation Anything Model with Object-Based Classification
Remote Sensing
Benggang
soil erosion
remote sensing monitoring
segment anything model
title Detection of Benggang in Remote Sensing Imagery through Integration of Segmentation Anything Model with Object-Based Classification
title_full Detection of Benggang in Remote Sensing Imagery through Integration of Segmentation Anything Model with Object-Based Classification
title_fullStr Detection of Benggang in Remote Sensing Imagery through Integration of Segmentation Anything Model with Object-Based Classification
title_full_unstemmed Detection of Benggang in Remote Sensing Imagery through Integration of Segmentation Anything Model with Object-Based Classification
title_short Detection of Benggang in Remote Sensing Imagery through Integration of Segmentation Anything Model with Object-Based Classification
title_sort detection of benggang in remote sensing imagery through integration of segmentation anything model with object based classification
topic Benggang
soil erosion
remote sensing monitoring
segment anything model
url https://www.mdpi.com/2072-4292/16/2/428
work_keys_str_mv AT yixinhu detectionofbengganginremotesensingimagerythroughintegrationofsegmentationanythingmodelwithobjectbasedclassification
AT zhixinqi detectionofbengganginremotesensingimagerythroughintegrationofsegmentationanythingmodelwithobjectbasedclassification
AT zhexunzhou detectionofbengganginremotesensingimagerythroughintegrationofsegmentationanythingmodelwithobjectbasedclassification
AT yanqin detectionofbengganginremotesensingimagerythroughintegrationofsegmentationanythingmodelwithobjectbasedclassification