A Two-Tiered Bidirectional Atrous Spatial Pyramid Pooling-Based Semantic Segmentation Model for Landslide Classification Using Remote Sensing Images

Effective landslide representation from great spatial resolution images is significant in numerous applications. Many research works and techniques have been advertised. Still, these methods are very challenging to relate in real time since they depend on remotely sensing landslides from a solitary...

Full description

Saved in:
Bibliographic Details
Main Authors: G. NaliniPriya, E. Laxmi Lydia, Reem Alshenaifi, Radhika Kavuri, Mohamad Khairi Ishak
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10771765/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846129652226064384
author G. NaliniPriya
E. Laxmi Lydia
Reem Alshenaifi
Radhika Kavuri
Mohamad Khairi Ishak
author_facet G. NaliniPriya
E. Laxmi Lydia
Reem Alshenaifi
Radhika Kavuri
Mohamad Khairi Ishak
author_sort G. NaliniPriya
collection DOAJ
description Effective landslide representation from great spatial resolution images is significant in numerous applications. Many research works and techniques have been advertised. Still, these methods are very challenging to relate in real time since they depend on remotely sensing landslides from a solitary sensor with an exact spatial resolution. Precisely identifying landslides over a vast region with intricate background entities is difficult. Machine Learning (ML) and Deep Learning (DL) have attained extraordinary performance in classifying images utilizing remotely sensed images from numerous platforms. Moreover, techniques built within DL architectures tend to implement encoder-decoder network structures, where constant convolutions effortlessly strain out numerous landslide features. This study develops a Bidirectional Atrous Spatial Pyramid Pooling-Based Semantic Segmentation and Classification Model (BASPP-SSCM) technique for landslide Remote Sensing Images. The main goal of the BASPP-SSCM technique is to segment and classify the landslide areas. In the preprocessing stage, the BASPP-SSCM model employs an adaptive Wiener filtering (AWF) technique to eliminate the noise. Next, for the semantic segmentation method, the BASPP-SSCM technique utilizes the DeepLabV3 method with the backbone of the ConvNeXtLarge model for determining the landslide region. Furthermore, the CapsNet model is utilized for the feature extraction process. Besides, the Rigdelet neural network (RNN) technique is employed for the landslide classification process. At last, the pelican optimization algorithm (POA) methodology is implemented to fine-tune the parameters involved in the RNN model. A wide range of investigations is performed to highlight the superiority of the BASPP-SSCM method using a benchmark dataset. The performance validation of the BASPP-SSCM method underscored a superior accuracy value of 98.23% of other existing approaches.
format Article
id doaj-art-f90a84c2ad384e28a048b43685d056c2
institution Kabale University
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-f90a84c2ad384e28a048b43685d056c22024-12-10T00:02:33ZengIEEEIEEE Access2169-35362024-01-011218131618133110.1109/ACCESS.2024.350888110771765A Two-Tiered Bidirectional Atrous Spatial Pyramid Pooling-Based Semantic Segmentation Model for Landslide Classification Using Remote Sensing ImagesG. NaliniPriya0E. Laxmi Lydia1https://orcid.org/0000-0003-1751-481XReem Alshenaifi2https://orcid.org/0009-0001-8749-2583Radhika Kavuri3Mohamad Khairi Ishak4https://orcid.org/0000-0002-3554-0061Department of Information Technology, Saveetha Engineering College, Chennai, IndiaDepartment of Information Technology, Velagapudi Ramakrishna Siddhartha Engineering College, Siddhartha Academy of Higher Education (Deemed to be University), Vijayawada, IndiaDepartment of Information Technology, College of Computer and Information Sciences, Majmaah University, Al Majma’ah, Saudi ArabiaAI and DS Department, Chaitanya Bharathi Institute of Technology, Gandipet, Hyderabad, IndiaDepartment of Electrical and Computer Engineering, College of Engineering and Information Technology, Ajman University, Ajman, United Arab EmiratesEffective landslide representation from great spatial resolution images is significant in numerous applications. Many research works and techniques have been advertised. Still, these methods are very challenging to relate in real time since they depend on remotely sensing landslides from a solitary sensor with an exact spatial resolution. Precisely identifying landslides over a vast region with intricate background entities is difficult. Machine Learning (ML) and Deep Learning (DL) have attained extraordinary performance in classifying images utilizing remotely sensed images from numerous platforms. Moreover, techniques built within DL architectures tend to implement encoder-decoder network structures, where constant convolutions effortlessly strain out numerous landslide features. This study develops a Bidirectional Atrous Spatial Pyramid Pooling-Based Semantic Segmentation and Classification Model (BASPP-SSCM) technique for landslide Remote Sensing Images. The main goal of the BASPP-SSCM technique is to segment and classify the landslide areas. In the preprocessing stage, the BASPP-SSCM model employs an adaptive Wiener filtering (AWF) technique to eliminate the noise. Next, for the semantic segmentation method, the BASPP-SSCM technique utilizes the DeepLabV3 method with the backbone of the ConvNeXtLarge model for determining the landslide region. Furthermore, the CapsNet model is utilized for the feature extraction process. Besides, the Rigdelet neural network (RNN) technique is employed for the landslide classification process. At last, the pelican optimization algorithm (POA) methodology is implemented to fine-tune the parameters involved in the RNN model. A wide range of investigations is performed to highlight the superiority of the BASPP-SSCM method using a benchmark dataset. The performance validation of the BASPP-SSCM method underscored a superior accuracy value of 98.23% of other existing approaches.https://ieeexplore.ieee.org/document/10771765/Semantic segmentationlandslide remote sensing imagespelican optimization algorithmfeature extractionatrous spatial pyramid pooling
spellingShingle G. NaliniPriya
E. Laxmi Lydia
Reem Alshenaifi
Radhika Kavuri
Mohamad Khairi Ishak
A Two-Tiered Bidirectional Atrous Spatial Pyramid Pooling-Based Semantic Segmentation Model for Landslide Classification Using Remote Sensing Images
IEEE Access
Semantic segmentation
landslide remote sensing images
pelican optimization algorithm
feature extraction
atrous spatial pyramid pooling
title A Two-Tiered Bidirectional Atrous Spatial Pyramid Pooling-Based Semantic Segmentation Model for Landslide Classification Using Remote Sensing Images
title_full A Two-Tiered Bidirectional Atrous Spatial Pyramid Pooling-Based Semantic Segmentation Model for Landslide Classification Using Remote Sensing Images
title_fullStr A Two-Tiered Bidirectional Atrous Spatial Pyramid Pooling-Based Semantic Segmentation Model for Landslide Classification Using Remote Sensing Images
title_full_unstemmed A Two-Tiered Bidirectional Atrous Spatial Pyramid Pooling-Based Semantic Segmentation Model for Landslide Classification Using Remote Sensing Images
title_short A Two-Tiered Bidirectional Atrous Spatial Pyramid Pooling-Based Semantic Segmentation Model for Landslide Classification Using Remote Sensing Images
title_sort two tiered bidirectional atrous spatial pyramid pooling based semantic segmentation model for landslide classification using remote sensing images
topic Semantic segmentation
landslide remote sensing images
pelican optimization algorithm
feature extraction
atrous spatial pyramid pooling
url https://ieeexplore.ieee.org/document/10771765/
work_keys_str_mv AT gnalinipriya atwotieredbidirectionalatrousspatialpyramidpoolingbasedsemanticsegmentationmodelforlandslideclassificationusingremotesensingimages
AT elaxmilydia atwotieredbidirectionalatrousspatialpyramidpoolingbasedsemanticsegmentationmodelforlandslideclassificationusingremotesensingimages
AT reemalshenaifi atwotieredbidirectionalatrousspatialpyramidpoolingbasedsemanticsegmentationmodelforlandslideclassificationusingremotesensingimages
AT radhikakavuri atwotieredbidirectionalatrousspatialpyramidpoolingbasedsemanticsegmentationmodelforlandslideclassificationusingremotesensingimages
AT mohamadkhairiishak atwotieredbidirectionalatrousspatialpyramidpoolingbasedsemanticsegmentationmodelforlandslideclassificationusingremotesensingimages
AT gnalinipriya twotieredbidirectionalatrousspatialpyramidpoolingbasedsemanticsegmentationmodelforlandslideclassificationusingremotesensingimages
AT elaxmilydia twotieredbidirectionalatrousspatialpyramidpoolingbasedsemanticsegmentationmodelforlandslideclassificationusingremotesensingimages
AT reemalshenaifi twotieredbidirectionalatrousspatialpyramidpoolingbasedsemanticsegmentationmodelforlandslideclassificationusingremotesensingimages
AT radhikakavuri twotieredbidirectionalatrousspatialpyramidpoolingbasedsemanticsegmentationmodelforlandslideclassificationusingremotesensingimages
AT mohamadkhairiishak twotieredbidirectionalatrousspatialpyramidpoolingbasedsemanticsegmentationmodelforlandslideclassificationusingremotesensingimages