ROCKY SHORELINE EXTRACTION USING A DEEP LEARNING MODEL AND OBJECT-BASED IMAGE ANALYSIS
<p>In the context of the increasing anthropogenic influence on the coastal areas that are subject to high climate variability, the main challenge is to understand its current dynamics and to predict its future evolution. Therefore, monitoring of the shoreline kinematics is a key factor for the...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2021-06-01
|
| Series: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLIII-B3-2021/23/2021/isprs-archives-XLIII-B3-2021-23-2021.pdf |
| _version_ | 1818742145862860800 |
|---|---|
| author | S. Bengoufa S. Bengoufa S. Bengoufa S. Niculescu M. K. Mihoubi R. Belkessa K. Abbad |
| author_facet | S. Bengoufa S. Bengoufa S. Bengoufa S. Niculescu M. K. Mihoubi R. Belkessa K. Abbad |
| author_sort | S. Bengoufa |
| collection | DOAJ |
| description | <p>In the context of the increasing anthropogenic influence on the coastal areas that are subject to high climate variability, the main challenge is to understand its current dynamics and to predict its future evolution. Therefore, monitoring of the shoreline kinematics is a key factor for the coastal erosion assessment and an essential feature for the sustainable management of these naturally vulnerable areas.</p><p>This work focuses on the detection and extraction of the shoreline, basing on a specific remote sensing methodology using Very High Resolution (VHR) optical images. Indeed, an integrated approach based on a Deep Learning model, which is the Convolutional Neural Network (CNN) and Object Based Image Analysis (OBIA) has been developed. This study aims to evaluate the methodological contribution of this integrated approach for the (semi)-automatic extraction of the rocky shoreline, for which the botanical indicator has been chosen. Therefore the upper limit of black marine lichen has been detected and extracted as the target shoreline. It is the first indication of a (semi)-automatic detection of such a complex type of shoreline.</p><p>The classification results derived from the combined CNN model and OBIA methods had achieved a high overall accuracy of 0.94. The extracted shoreline have been compared to a shoreline of reference derived from a traditional method that is a manual digitizing. The distances between the two shorelines has been calculated in order to assess the accuracy of the extraction method. This comparison revealed that 76% of the extracted shoreline lies within 1 m, and 35% lies within 0.5 m of reference one. Therefore, the CNN model integrated to OBIA was successfully shown to be a good method for shoreline extraction and could offer an immediate insight regarding rocky shoreline position, providing an alternative to its monitoring.</p> |
| first_indexed | 2024-12-18T02:07:52Z |
| format | Article |
| id | doaj.art-30c44d894b594a1d98e6262fd21185ef |
| institution | Directory Open Access Journal |
| issn | 1682-1750 2194-9034 |
| language | English |
| last_indexed | 2024-12-18T02:07:52Z |
| publishDate | 2021-06-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj.art-30c44d894b594a1d98e6262fd21185ef2022-12-21T21:24:32ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342021-06-01XLIII-B3-2021232910.5194/isprs-archives-XLIII-B3-2021-23-2021ROCKY SHORELINE EXTRACTION USING A DEEP LEARNING MODEL AND OBJECT-BASED IMAGE ANALYSISS. Bengoufa0S. Bengoufa1S. Bengoufa2S. Niculescu3M. K. Mihoubi4R. Belkessa5K. Abbad6University of Western Brittany, CNRS, LETG Brest UMR 6554 CNRS, Technopôle Brest-Iroise, Plouzané-Brest, 29280, FranceEcole Nationale Supérieure des Sciences de la Mer et de l’Aménagement du Littoral (ENSSMAL), 16320 Algiers, AlgeriaEcole National Supérieure de l’Hydraulique, Laboratoire de Mobilisation et de Valorisation des Ressources en Eau (MVRE), 09000 BLIDA, AlgeriaUniversity of Western Brittany, CNRS, LETG Brest UMR 6554 CNRS, Technopôle Brest-Iroise, Plouzané-Brest, 29280, FranceEcole National Supérieure de l’Hydraulique, Laboratoire de Mobilisation et de Valorisation des Ressources en Eau (MVRE), 09000 BLIDA, AlgeriaEcole Nationale Supérieure des Sciences de la Mer et de l’Aménagement du Littoral (ENSSMAL), 16320 Algiers, AlgeriaEcole Nationale Supérieure des Sciences de la Mer et de l’Aménagement du Littoral (ENSSMAL), 16320 Algiers, Algeria<p>In the context of the increasing anthropogenic influence on the coastal areas that are subject to high climate variability, the main challenge is to understand its current dynamics and to predict its future evolution. Therefore, monitoring of the shoreline kinematics is a key factor for the coastal erosion assessment and an essential feature for the sustainable management of these naturally vulnerable areas.</p><p>This work focuses on the detection and extraction of the shoreline, basing on a specific remote sensing methodology using Very High Resolution (VHR) optical images. Indeed, an integrated approach based on a Deep Learning model, which is the Convolutional Neural Network (CNN) and Object Based Image Analysis (OBIA) has been developed. This study aims to evaluate the methodological contribution of this integrated approach for the (semi)-automatic extraction of the rocky shoreline, for which the botanical indicator has been chosen. Therefore the upper limit of black marine lichen has been detected and extracted as the target shoreline. It is the first indication of a (semi)-automatic detection of such a complex type of shoreline.</p><p>The classification results derived from the combined CNN model and OBIA methods had achieved a high overall accuracy of 0.94. The extracted shoreline have been compared to a shoreline of reference derived from a traditional method that is a manual digitizing. The distances between the two shorelines has been calculated in order to assess the accuracy of the extraction method. This comparison revealed that 76% of the extracted shoreline lies within 1 m, and 35% lies within 0.5 m of reference one. Therefore, the CNN model integrated to OBIA was successfully shown to be a good method for shoreline extraction and could offer an immediate insight regarding rocky shoreline position, providing an alternative to its monitoring.</p>https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLIII-B3-2021/23/2021/isprs-archives-XLIII-B3-2021-23-2021.pdf |
| spellingShingle | S. Bengoufa S. Bengoufa S. Bengoufa S. Niculescu M. K. Mihoubi R. Belkessa K. Abbad ROCKY SHORELINE EXTRACTION USING A DEEP LEARNING MODEL AND OBJECT-BASED IMAGE ANALYSIS The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | ROCKY SHORELINE EXTRACTION USING A DEEP LEARNING MODEL AND OBJECT-BASED IMAGE ANALYSIS |
| title_full | ROCKY SHORELINE EXTRACTION USING A DEEP LEARNING MODEL AND OBJECT-BASED IMAGE ANALYSIS |
| title_fullStr | ROCKY SHORELINE EXTRACTION USING A DEEP LEARNING MODEL AND OBJECT-BASED IMAGE ANALYSIS |
| title_full_unstemmed | ROCKY SHORELINE EXTRACTION USING A DEEP LEARNING MODEL AND OBJECT-BASED IMAGE ANALYSIS |
| title_short | ROCKY SHORELINE EXTRACTION USING A DEEP LEARNING MODEL AND OBJECT-BASED IMAGE ANALYSIS |
| title_sort | rocky shoreline extraction using a deep learning model and object based image analysis |
| url | https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLIII-B3-2021/23/2021/isprs-archives-XLIII-B3-2021-23-2021.pdf |
| work_keys_str_mv | AT sbengoufa rockyshorelineextractionusingadeeplearningmodelandobjectbasedimageanalysis AT sbengoufa rockyshorelineextractionusingadeeplearningmodelandobjectbasedimageanalysis AT sbengoufa rockyshorelineextractionusingadeeplearningmodelandobjectbasedimageanalysis AT sniculescu rockyshorelineextractionusingadeeplearningmodelandobjectbasedimageanalysis AT mkmihoubi rockyshorelineextractionusingadeeplearningmodelandobjectbasedimageanalysis AT rbelkessa rockyshorelineextractionusingadeeplearningmodelandobjectbasedimageanalysis AT kabbad rockyshorelineextractionusingadeeplearningmodelandobjectbasedimageanalysis |