A Comparative Performance Analysis of Popular Deep Learning Models and Segment Anything Model (SAM) for River Water Segmentation in Close-Range Remote Sensing Imagery
Accurate segmentation of river water in close-range Remote Sensing (RS) images is vital for efficient environmental monitoring and management. However, this task poses significant difficulties due to the dynamic nature of water, which exhibits varying colors and textures reflecting the sky and surro...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10493013/ |
| _version_ | 1797206098682314752 |
|---|---|
| author | Armin Moghimi Mario Welzel Turgay Celik Torsten Schlurmann |
| author_facet | Armin Moghimi Mario Welzel Turgay Celik Torsten Schlurmann |
| author_sort | Armin Moghimi |
| collection | DOAJ |
| description | Accurate segmentation of river water in close-range Remote Sensing (RS) images is vital for efficient environmental monitoring and management. However, this task poses significant difficulties due to the dynamic nature of water, which exhibits varying colors and textures reflecting the sky and surrounding structures along the riverbanks. This study addresses these complexities by evaluating and comparing several well-known deep-learning (DL) techniques on four river scene datasets. To achieve this, we fine-tuned the recently introduced “Segment Anything Model” (SAM) along with popular DL segmentation models such as U-Net, DeepLabV3+, LinkNet, PSPNet, and PAN, all using ResNet50 pre-trained on ImageNet as a backbone. Experimental results highlight the diverse performances of these models in river water segmentation. Notably, fine-tuned SAM demonstrates superior performance, followed by U-Net(ResNet50), despite their higher computational costs. In contrast, PSPNet(ResNet50), while less effective, proves to be the most efficient in terms of execution time. In addition to these findings, we introduce a novel river water segmentation dataset, LuFI-RiverSnap. <inline-formula> <tex-math notation="LaTeX">${v}1$ </tex-math></inline-formula> (<monospace>Dataset link</monospace>), characterized by a more diverse range of scenes and accurate masks compared to existing datasets. To facilitate reproducible research in remote sensing and computer vision, we release the implementations of the fine-tuned SAM model (<monospace>Code link</monospace>). The findings from this research, coupled with the presented dataset and the accuracy achieved by fine-tuned SAM segmentation, can support tracking river changes, understanding river water level trends, and exploring river ecosystem dynamics. These can also provide valuable insights for practitioners and researchers seeking models tailored to specific image characteristics with practical means in disaster risk reduction, such as rapid assessments of inundations during floods or automatic extractions of gauge data in watersheds. |
| first_indexed | 2024-04-24T09:01:37Z |
| format | Article |
| id | doaj.art-33d0f9bdb73d413994e8e91fefba0e17 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-24T09:01:37Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-33d0f9bdb73d413994e8e91fefba0e172024-04-15T23:00:42ZengIEEEIEEE Access2169-35362024-01-0112520675208510.1109/ACCESS.2024.338542510493013A Comparative Performance Analysis of Popular Deep Learning Models and Segment Anything Model (SAM) for River Water Segmentation in Close-Range Remote Sensing ImageryArmin Moghimi0https://orcid.org/0000-0002-0455-4882Mario Welzel1https://orcid.org/0000-0002-0768-9782Turgay Celik2https://orcid.org/0000-0001-6925-6010Torsten Schlurmann3https://orcid.org/0000-0002-4691-7629Ludwig-Franzius-Institute for Hydraulic, Estuarine and Coastal Engineering, Leibniz University Hannover, Hanover, GermanyLudwig-Franzius-Institute for Hydraulic, Estuarine and Coastal Engineering, Leibniz University Hannover, Hanover, GermanySchool of Electrical and Information Engineering, University of the Witwatersrand Johannesburg, Johannesburg, South AfricaLudwig-Franzius-Institute for Hydraulic, Estuarine and Coastal Engineering, Leibniz University Hannover, Hanover, GermanyAccurate segmentation of river water in close-range Remote Sensing (RS) images is vital for efficient environmental monitoring and management. However, this task poses significant difficulties due to the dynamic nature of water, which exhibits varying colors and textures reflecting the sky and surrounding structures along the riverbanks. This study addresses these complexities by evaluating and comparing several well-known deep-learning (DL) techniques on four river scene datasets. To achieve this, we fine-tuned the recently introduced “Segment Anything Model” (SAM) along with popular DL segmentation models such as U-Net, DeepLabV3+, LinkNet, PSPNet, and PAN, all using ResNet50 pre-trained on ImageNet as a backbone. Experimental results highlight the diverse performances of these models in river water segmentation. Notably, fine-tuned SAM demonstrates superior performance, followed by U-Net(ResNet50), despite their higher computational costs. In contrast, PSPNet(ResNet50), while less effective, proves to be the most efficient in terms of execution time. In addition to these findings, we introduce a novel river water segmentation dataset, LuFI-RiverSnap. <inline-formula> <tex-math notation="LaTeX">${v}1$ </tex-math></inline-formula> (<monospace>Dataset link</monospace>), characterized by a more diverse range of scenes and accurate masks compared to existing datasets. To facilitate reproducible research in remote sensing and computer vision, we release the implementations of the fine-tuned SAM model (<monospace>Code link</monospace>). The findings from this research, coupled with the presented dataset and the accuracy achieved by fine-tuned SAM segmentation, can support tracking river changes, understanding river water level trends, and exploring river ecosystem dynamics. These can also provide valuable insights for practitioners and researchers seeking models tailored to specific image characteristics with practical means in disaster risk reduction, such as rapid assessments of inundations during floods or automatic extractions of gauge data in watersheds.https://ieeexplore.ieee.org/document/10493013/Deep learningsegment anything model (SAM)river water segmentationU-NetDeepLabV3+LinkNet |
| spellingShingle | Armin Moghimi Mario Welzel Turgay Celik Torsten Schlurmann A Comparative Performance Analysis of Popular Deep Learning Models and Segment Anything Model (SAM) for River Water Segmentation in Close-Range Remote Sensing Imagery IEEE Access Deep learning segment anything model (SAM) river water segmentation U-Net DeepLabV3+ LinkNet |
| title | A Comparative Performance Analysis of Popular Deep Learning Models and Segment Anything Model (SAM) for River Water Segmentation in Close-Range Remote Sensing Imagery |
| title_full | A Comparative Performance Analysis of Popular Deep Learning Models and Segment Anything Model (SAM) for River Water Segmentation in Close-Range Remote Sensing Imagery |
| title_fullStr | A Comparative Performance Analysis of Popular Deep Learning Models and Segment Anything Model (SAM) for River Water Segmentation in Close-Range Remote Sensing Imagery |
| title_full_unstemmed | A Comparative Performance Analysis of Popular Deep Learning Models and Segment Anything Model (SAM) for River Water Segmentation in Close-Range Remote Sensing Imagery |
| title_short | A Comparative Performance Analysis of Popular Deep Learning Models and Segment Anything Model (SAM) for River Water Segmentation in Close-Range Remote Sensing Imagery |
| title_sort | comparative performance analysis of popular deep learning models and segment anything model sam for river water segmentation in close range remote sensing imagery |
| topic | Deep learning segment anything model (SAM) river water segmentation U-Net DeepLabV3+ LinkNet |
| url | https://ieeexplore.ieee.org/document/10493013/ |
| work_keys_str_mv | AT arminmoghimi acomparativeperformanceanalysisofpopulardeeplearningmodelsandsegmentanythingmodelsamforriverwatersegmentationincloserangeremotesensingimagery AT mariowelzel acomparativeperformanceanalysisofpopulardeeplearningmodelsandsegmentanythingmodelsamforriverwatersegmentationincloserangeremotesensingimagery AT turgaycelik acomparativeperformanceanalysisofpopulardeeplearningmodelsandsegmentanythingmodelsamforriverwatersegmentationincloserangeremotesensingimagery AT torstenschlurmann acomparativeperformanceanalysisofpopulardeeplearningmodelsandsegmentanythingmodelsamforriverwatersegmentationincloserangeremotesensingimagery AT arminmoghimi comparativeperformanceanalysisofpopulardeeplearningmodelsandsegmentanythingmodelsamforriverwatersegmentationincloserangeremotesensingimagery AT mariowelzel comparativeperformanceanalysisofpopulardeeplearningmodelsandsegmentanythingmodelsamforriverwatersegmentationincloserangeremotesensingimagery AT turgaycelik comparativeperformanceanalysisofpopulardeeplearningmodelsandsegmentanythingmodelsamforriverwatersegmentationincloserangeremotesensingimagery AT torstenschlurmann comparativeperformanceanalysisofpopulardeeplearningmodelsandsegmentanythingmodelsamforriverwatersegmentationincloserangeremotesensingimagery |