Segmentation and classification of SAR imagery on flood zones in Colombia, a computing tool for disaster prevention
In order to prevent natural flood disasters it important to identify the flood areas. In Colombia, there is space to develop automatic tools able to detect and study flood areas. For this reason, in this work we propose a computational tool in MATLAB, able to detect and classify Colombia’s flood zon...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | info:eu-repo/semantics/publishedVersion |
| Language: | spa |
| Published: |
Universidad Antonio Nariño
2021
|
| Subjects: | |
| Online Access: | http://revistas.uan.edu.co/index.php/ingeuan/article/view/365 http://repositorio.uan.edu.co/handle/123456789/3936 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1812648024539660288 |
|---|---|
| author | Avendaño Pérez, Jonathan Parra Plazas, Jaime Alberto Bayona, Jhon Fredy |
| author_facet | Avendaño Pérez, Jonathan Parra Plazas, Jaime Alberto Bayona, Jhon Fredy |
| author_sort | Avendaño Pérez, Jonathan |
| collection | DSpace |
| description | In order to prevent natural flood disasters it important to identify the flood areas. In Colombia, there is space to develop automatic tools able to detect and study flood areas. For this reason, in this work we propose a computational tool in MATLAB, able to detect and classify Colombia’s flood zones in SAR imager. In particular, we used different classifiers, and according to the performance we selected the best. The training database was generated with the results of Fuzzy Clustering, K -means and Region -Growing segmentations on flood zones in SAR imagery. We used two different classifiers: the first one is a Bayes classifier, while the second one is a Support Vector Machine (SVM). In order to evaluate the performance, we used indices such as the overall accuracy, user accuracy and Kappa index. According to the results, the SVM classifier presents better accuracy. However, the Bayes classifier had better results classifying pixels corresponding to populations even with little training data. |
| format | info:eu-repo/semantics/publishedVersion |
| id | repositorio.uan.edu.co-123456789-3936 |
| institution | Repositorio Digital UAN |
| language | spa |
| publishDate | 2021 |
| publisher | Universidad Antonio Nariño |
| record_format | dspace |
| spelling | repositorio.uan.edu.co-123456789-39362024-10-09T23:08:56Z Segmentation and classification of SAR imagery on flood zones in Colombia, a computing tool for disaster prevention Segmentación y clasificación de imágenes SAR en zonas de inundación en Colombia, una herramienta computacional para prevención de desastres Avendaño Pérez, Jonathan Parra Plazas, Jaime Alberto Bayona, Jhon Fredy SAR Classification Segmentation flood areas imagery SAR Clasificación Segmentación imágenes de zonas de inundación In order to prevent natural flood disasters it important to identify the flood areas. In Colombia, there is space to develop automatic tools able to detect and study flood areas. For this reason, in this work we propose a computational tool in MATLAB, able to detect and classify Colombia’s flood zones in SAR imager. In particular, we used different classifiers, and according to the performance we selected the best. The training database was generated with the results of Fuzzy Clustering, K -means and Region -Growing segmentations on flood zones in SAR imagery. We used two different classifiers: the first one is a Bayes classifier, while the second one is a Support Vector Machine (SVM). In order to evaluate the performance, we used indices such as the overall accuracy, user accuracy and Kappa index. According to the results, the SVM classifier presents better accuracy. However, the Bayes classifier had better results classifying pixels corresponding to populations even with little training data. La detección de zonas de inundación es fundamental para la prevención de desastres, por este motivo en este trabajo se presenta una herramienta computacional desarrollada en MATLAB que ofrece una alternativa a las existentes en el mercado para la clasificación supervisada de imágenes SAR (Synthetic Aperture Radar) de zonas de inundación. En particular se usaron diferentes métodos de clasificación para seleccionar de acuerdo al desempeño el mejor para el estudio de zonas de inundación en Colombia.Los datos de entrenamiento fueron generados con los resultados de las segmentaciones Fuzzy-Clustering, K-means y Region-Growing sobre imágenes SAR de zonas de inundación. Los métodos de clasificación implementados fueron un clasificador basado en el método Bayesiano y un clasificador basado en máquinas de vectores de soporte (SVM). Para evaluar el desempeño de los clasificadores se utilizaron índices como la exactitud total, la exactitud dependiendo del usuario, el índice Kappay R’. De acuerdo a los resultados el clasificador basado en máquinas de soporte presenta mayor exactitud; sin embargo, el clasificador bayesiano se desempeña mejor clasificando pixeles que corresponden a poblaciones, aun con pocos datos de entrenamiento. 2021-06-16T13:53:08Z 2021-06-16T13:53:08Z 2014-09-08 info:eu-repo/semantics/publishedVersion http://purl.org/coar/resource_type/c_6501 info:eu-repo/semantics/article http://purl.org/coar/version/c_970fb48d4fbd8a85 http://revistas.uan.edu.co/index.php/ingeuan/article/view/365 http://repositorio.uan.edu.co/handle/123456789/3936 spa http://revistas.uan.edu.co/index.php/ingeuan/article/view/365/305 Acceso abierto Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) https://creativecommons.org/licenses/by-nc-sa/4.0/ info:eu-repo/semantics/openAccess http://purl.org/coar/access_right/c_abf2 application/pdf Universidad Antonio Nariño 2346-1446 2145-0935 INGE@UAN - TENDENCIAS EN LA INGENIERÍA; Vol. 4 Núm. 8 (2014) |
| spellingShingle | SAR Classification Segmentation flood areas imagery SAR Clasificación Segmentación imágenes de zonas de inundación Avendaño Pérez, Jonathan Parra Plazas, Jaime Alberto Bayona, Jhon Fredy Segmentation and classification of SAR imagery on flood zones in Colombia, a computing tool for disaster prevention |
| title | Segmentation and classification of SAR imagery on flood zones in Colombia, a computing tool for disaster prevention |
| title_full | Segmentation and classification of SAR imagery on flood zones in Colombia, a computing tool for disaster prevention |
| title_fullStr | Segmentation and classification of SAR imagery on flood zones in Colombia, a computing tool for disaster prevention |
| title_full_unstemmed | Segmentation and classification of SAR imagery on flood zones in Colombia, a computing tool for disaster prevention |
| title_short | Segmentation and classification of SAR imagery on flood zones in Colombia, a computing tool for disaster prevention |
| title_sort | segmentation and classification of sar imagery on flood zones in colombia a computing tool for disaster prevention |
| topic | SAR Classification Segmentation flood areas imagery SAR Clasificación Segmentación imágenes de zonas de inundación |
| url | http://revistas.uan.edu.co/index.php/ingeuan/article/view/365 http://repositorio.uan.edu.co/handle/123456789/3936 |
| work_keys_str_mv | AT avendanoperezjonathan segmentationandclassificationofsarimageryonfloodzonesincolombiaacomputingtoolfordisasterprevention AT parraplazasjaimealberto segmentationandclassificationofsarimageryonfloodzonesincolombiaacomputingtoolfordisasterprevention AT bayonajhonfredy segmentationandclassificationofsarimageryonfloodzonesincolombiaacomputingtoolfordisasterprevention AT avendanoperezjonathan segmentacionyclasificaciondeimagenessarenzonasdeinundacionencolombiaunaherramientacomputacionalparaprevenciondedesastres AT parraplazasjaimealberto segmentacionyclasificaciondeimagenessarenzonasdeinundacionencolombiaunaherramientacomputacionalparaprevenciondedesastres AT bayonajhonfredy segmentacionyclasificaciondeimagenessarenzonasdeinundacionencolombiaunaherramientacomputacionalparaprevenciondedesastres |
