Superpixel-Based Roughness Measure for Multispectral Satellite Image Segmentation
The new generation of artificial satellites is providing a huge amount of Earth observation images whose exploitation can report invaluable benefits, both economical and environmental. However, only a small fraction of this data volume has been analyzed, mainly due to the large human resources neede...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2015-11-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2072-4292/7/11/14620 |
| _version_ | 1818498738413371392 |
|---|---|
| author | César Antonio Ortiz Toro Consuelo Gonzalo Martín Ángel García Pedrero Ernestina Menasalvas Ruiz |
| author_facet | César Antonio Ortiz Toro Consuelo Gonzalo Martín Ángel García Pedrero Ernestina Menasalvas Ruiz |
| author_sort | César Antonio Ortiz Toro |
| collection | DOAJ |
| description | The new generation of artificial satellites is providing a huge amount of Earth observation images whose exploitation can report invaluable benefits, both economical and environmental. However, only a small fraction of this data volume has been analyzed, mainly due to the large human resources needed for that task. In this sense, the development of unsupervised methodologies for the analysis of these images is a priority. In this work, a new unsupervised segmentation algorithm for satellite images is proposed. This algorithm is based on the rough-set theory, and it is inspired by a previous segmentation algorithm defined in the RGB color domain. The main contributions of the new algorithm are: (i) extending the original algorithm to four spectral bands; (ii) the concept of the superpixel is used in order to define the neighborhood similarity of a pixel adapted to the local characteristics of each image; (iii) and two new region merged strategies are proposed and evaluated in order to establish the final number of regions in the segmented image. The experimental results show that the proposed approach improves the results provided by the original method when both are applied to satellite images with different spectral and spatial resolutions. |
| first_indexed | 2024-12-10T20:19:37Z |
| format | Article |
| id | doaj.art-c6f573f6c6014a5fa4a27b609023a04d |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-12-10T20:19:37Z |
| publishDate | 2015-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-c6f573f6c6014a5fa4a27b609023a04d2022-12-22T01:35:06ZengMDPI AGRemote Sensing2072-42922015-11-01711146201464510.3390/rs71114620rs71114620Superpixel-Based Roughness Measure for Multispectral Satellite Image SegmentationCésar Antonio Ortiz Toro0Consuelo Gonzalo Martín1Ángel García Pedrero2Ernestina Menasalvas Ruiz3Centro de Tecnología Biomédica, Universidad Politécnica de Madrid, Campus de Montegancedo, Pozuelo de Alarcón 28233, SpainCentro de Tecnología Biomédica, Universidad Politécnica de Madrid, Campus de Montegancedo, Pozuelo de Alarcón 28233, SpainCentro de Tecnología Biomédica, Universidad Politécnica de Madrid, Campus de Montegancedo, Pozuelo de Alarcón 28233, SpainCentro de Tecnología Biomédica, Universidad Politécnica de Madrid, Campus de Montegancedo, Pozuelo de Alarcón 28233, SpainThe new generation of artificial satellites is providing a huge amount of Earth observation images whose exploitation can report invaluable benefits, both economical and environmental. However, only a small fraction of this data volume has been analyzed, mainly due to the large human resources needed for that task. In this sense, the development of unsupervised methodologies for the analysis of these images is a priority. In this work, a new unsupervised segmentation algorithm for satellite images is proposed. This algorithm is based on the rough-set theory, and it is inspired by a previous segmentation algorithm defined in the RGB color domain. The main contributions of the new algorithm are: (i) extending the original algorithm to four spectral bands; (ii) the concept of the superpixel is used in order to define the neighborhood similarity of a pixel adapted to the local characteristics of each image; (iii) and two new region merged strategies are proposed and evaluated in order to establish the final number of regions in the segmented image. The experimental results show that the proposed approach improves the results provided by the original method when both are applied to satellite images with different spectral and spatial resolutions.http://www.mdpi.com/2072-4292/7/11/14620unsupervised segmentationhistonrough-setregion merging |
| spellingShingle | César Antonio Ortiz Toro Consuelo Gonzalo Martín Ángel García Pedrero Ernestina Menasalvas Ruiz Superpixel-Based Roughness Measure for Multispectral Satellite Image Segmentation Remote Sensing unsupervised segmentation histon rough-set region merging |
| title | Superpixel-Based Roughness Measure for Multispectral Satellite Image Segmentation |
| title_full | Superpixel-Based Roughness Measure for Multispectral Satellite Image Segmentation |
| title_fullStr | Superpixel-Based Roughness Measure for Multispectral Satellite Image Segmentation |
| title_full_unstemmed | Superpixel-Based Roughness Measure for Multispectral Satellite Image Segmentation |
| title_short | Superpixel-Based Roughness Measure for Multispectral Satellite Image Segmentation |
| title_sort | superpixel based roughness measure for multispectral satellite image segmentation |
| topic | unsupervised segmentation histon rough-set region merging |
| url | http://www.mdpi.com/2072-4292/7/11/14620 |
| work_keys_str_mv | AT cesarantonioortiztoro superpixelbasedroughnessmeasureformultispectralsatelliteimagesegmentation AT consuelogonzalomartin superpixelbasedroughnessmeasureformultispectralsatelliteimagesegmentation AT angelgarciapedrero superpixelbasedroughnessmeasureformultispectralsatelliteimagesegmentation AT ernestinamenasalvasruiz superpixelbasedroughnessmeasureformultispectralsatelliteimagesegmentation |