Assessment of the Segmentation of RGB Remote Sensing Images: A Subjective Approach
The evaluation of remote sensing imagery segmentation results plays an important role in the further image analysis and decision-making. The search for the optimal segmentation method for a particular data set and the suitability of segmentation results for the use in satellite image classification...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/24/4152 |
| _version_ | 1797544219663925248 |
|---|---|
| author | Giruta Kazakeviciute-Januskeviciene Edgaras Janusonis Romualdas Bausys Tadas Limba Mindaugas Kiskis |
| author_facet | Giruta Kazakeviciute-Januskeviciene Edgaras Janusonis Romualdas Bausys Tadas Limba Mindaugas Kiskis |
| author_sort | Giruta Kazakeviciute-Januskeviciene |
| collection | DOAJ |
| description | The evaluation of remote sensing imagery segmentation results plays an important role in the further image analysis and decision-making. The search for the optimal segmentation method for a particular data set and the suitability of segmentation results for the use in satellite image classification are examples where the proper image segmentation quality assessment can affect the quality of the final result. There is no extensive research related to the assessment of the segmentation effectiveness of the images. The designed objective quality assessment metrics that can be used to assess the quality of the obtained segmentation results usually take into account the subjective features of the human visual system (HVS). A novel approach is used in the article to estimate the effectiveness of satellite image segmentation by relating and determining the correlation between subjective and objective segmentation quality metrics. Pearson’s and Spearman’s correlation was used for satellite images after applying a k-means++ clustering algorithm based on colour information. Simultaneously, the dataset of the satellite images with ground truth (GT) based on the “DeepGlobe Land Cover Classification Challenge” dataset was constructed for testing three classes of quality metrics for satellite image segmentation. |
| first_indexed | 2024-03-10T13:57:19Z |
| format | Article |
| id | doaj.art-985292a7c57949448e006da064dd5204 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T13:57:19Z |
| publishDate | 2020-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-985292a7c57949448e006da064dd52042023-11-21T01:33:26ZengMDPI AGRemote Sensing2072-42922020-12-011224415210.3390/rs12244152Assessment of the Segmentation of RGB Remote Sensing Images: A Subjective ApproachGiruta Kazakeviciute-Januskeviciene0Edgaras Janusonis1Romualdas Bausys2Tadas Limba3Mindaugas Kiskis4Department of Graphical Systems, Vilnius Gediminas Technical University, Sauletekio al. 11, LT-10223 Vilnius, LithuaniaDepartment of Graphical Systems, Vilnius Gediminas Technical University, Sauletekio al. 11, LT-10223 Vilnius, LithuaniaDepartment of Graphical Systems, Vilnius Gediminas Technical University, Sauletekio al. 11, LT-10223 Vilnius, LithuaniaFaculty of Public Governance and Business, Mykolas Romeris University, Ateities str. 20, LT-08303 Vilnius, LithuaniaFaculty of Public Governance and Business, Mykolas Romeris University, Ateities str. 20, LT-08303 Vilnius, LithuaniaThe evaluation of remote sensing imagery segmentation results plays an important role in the further image analysis and decision-making. The search for the optimal segmentation method for a particular data set and the suitability of segmentation results for the use in satellite image classification are examples where the proper image segmentation quality assessment can affect the quality of the final result. There is no extensive research related to the assessment of the segmentation effectiveness of the images. The designed objective quality assessment metrics that can be used to assess the quality of the obtained segmentation results usually take into account the subjective features of the human visual system (HVS). A novel approach is used in the article to estimate the effectiveness of satellite image segmentation by relating and determining the correlation between subjective and objective segmentation quality metrics. Pearson’s and Spearman’s correlation was used for satellite images after applying a k-means++ clustering algorithm based on colour information. Simultaneously, the dataset of the satellite images with ground truth (GT) based on the “DeepGlobe Land Cover Classification Challenge” dataset was constructed for testing three classes of quality metrics for satellite image segmentation.https://www.mdpi.com/2072-4292/12/24/4152satellite image segmentationsegmentation quality assessmentcorrelation analysisobjective quality metricssubjective evaluation |
| spellingShingle | Giruta Kazakeviciute-Januskeviciene Edgaras Janusonis Romualdas Bausys Tadas Limba Mindaugas Kiskis Assessment of the Segmentation of RGB Remote Sensing Images: A Subjective Approach Remote Sensing satellite image segmentation segmentation quality assessment correlation analysis objective quality metrics subjective evaluation |
| title | Assessment of the Segmentation of RGB Remote Sensing Images: A Subjective Approach |
| title_full | Assessment of the Segmentation of RGB Remote Sensing Images: A Subjective Approach |
| title_fullStr | Assessment of the Segmentation of RGB Remote Sensing Images: A Subjective Approach |
| title_full_unstemmed | Assessment of the Segmentation of RGB Remote Sensing Images: A Subjective Approach |
| title_short | Assessment of the Segmentation of RGB Remote Sensing Images: A Subjective Approach |
| title_sort | assessment of the segmentation of rgb remote sensing images a subjective approach |
| topic | satellite image segmentation segmentation quality assessment correlation analysis objective quality metrics subjective evaluation |
| url | https://www.mdpi.com/2072-4292/12/24/4152 |
| work_keys_str_mv | AT girutakazakeviciutejanuskeviciene assessmentofthesegmentationofrgbremotesensingimagesasubjectiveapproach AT edgarasjanusonis assessmentofthesegmentationofrgbremotesensingimagesasubjectiveapproach AT romualdasbausys assessmentofthesegmentationofrgbremotesensingimagesasubjectiveapproach AT tadaslimba assessmentofthesegmentationofrgbremotesensingimagesasubjectiveapproach AT mindaugaskiskis assessmentofthesegmentationofrgbremotesensingimagesasubjectiveapproach |